| { |
| "kind": "discovery#restDescription", |
| "batchPath": "batch", |
| "documentationLink": "https://cloud.google.com/video-intelligence/docs/", |
| "id": "videointelligence:v1p3beta1", |
| "resources": { |
| "videos": { |
| "methods": { |
| "annotate": { |
| "parameterOrder": [], |
| "response": { |
| "$ref": "GoogleLongrunning_Operation" |
| }, |
| "description": "Performs asynchronous video annotation. Progress and results can be retrieved through the `google.longrunning.Operations` interface. `Operation.metadata` contains `AnnotateVideoProgress` (progress). `Operation.response` contains `AnnotateVideoResponse` (results).", |
| "httpMethod": "POST", |
| "scopes": [ |
| "https://www.googleapis.com/auth/cloud-platform" |
| ], |
| "parameters": {}, |
| "path": "v1p3beta1/videos:annotate", |
| "request": { |
| "$ref": "GoogleCloudVideointelligenceV1p3beta1_AnnotateVideoRequest" |
| }, |
| "id": "videointelligence.videos.annotate", |
| "flatPath": "v1p3beta1/videos:annotate" |
| } |
| } |
| } |
| }, |
| "description": "Detects objects, explicit content, and scene changes in videos. It also specifies the region for annotation and transcribes speech to text. Supports both asynchronous API and streaming API.", |
| "ownerName": "Google", |
| "icons": { |
| "x32": "http://www.google.com/images/icons/product/search-32.gif", |
| "x16": "http://www.google.com/images/icons/product/search-16.gif" |
| }, |
| "version_module": true, |
| "schemas": { |
| "GoogleCloudVideointelligenceV1beta2_FaceAnnotation": { |
| "description": "Deprecated. No effect.", |
| "type": "object", |
| "properties": { |
| "thumbnail": { |
| "format": "byte", |
| "description": "Thumbnail of a representative face view (in JPEG format).", |
| "type": "string" |
| }, |
| "segments": { |
| "description": "All video segments where a face was detected.", |
| "type": "array", |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1beta2_FaceSegment" |
| } |
| }, |
| "frames": { |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1beta2_FaceFrame" |
| }, |
| "description": "All video frames where a face was detected.", |
| "type": "array" |
| } |
| }, |
| "id": "GoogleCloudVideointelligenceV1beta2_FaceAnnotation" |
| }, |
| "GoogleCloudVideointelligenceV1p1beta1_WordInfo": { |
| "description": "Word-specific information for recognized words. Word information is only included in the response when certain request parameters are set, such as `enable_word_time_offsets`.", |
| "properties": { |
| "word": { |
| "type": "string", |
| "description": "The word corresponding to this set of information." |
| }, |
| "startTime": { |
| "type": "string", |
| "description": "Time offset relative to the beginning of the audio, and corresponding to the start of the spoken word. This field is only set if `enable_word_time_offsets=true` and only in the top hypothesis. This is an experimental feature and the accuracy of the time offset can vary.", |
| "format": "google-duration" |
| }, |
| "speakerTag": { |
| "readOnly": true, |
| "format": "int32", |
| "description": "Output only. A distinct integer value is assigned for every speaker within the audio. This field specifies which one of those speakers was detected to have spoken this word. Value ranges from 1 up to diarization_speaker_count, and is only set if speaker diarization is enabled.", |
| "type": "integer" |
| }, |
| "endTime": { |
| "type": "string", |
| "description": "Time offset relative to the beginning of the audio, and corresponding to the end of the spoken word. This field is only set if `enable_word_time_offsets=true` and only in the top hypothesis. This is an experimental feature and the accuracy of the time offset can vary.", |
| "format": "google-duration" |
| }, |
| "confidence": { |
| "type": "number", |
| "format": "float", |
| "description": "Output only. The confidence estimate between 0.0 and 1.0. A higher number indicates an estimated greater likelihood that the recognized words are correct. This field is set only for the top alternative. This field is not guaranteed to be accurate and users should not rely on it to be always provided. The default of 0.0 is a sentinel value indicating `confidence` was not set.", |
| "readOnly": true |
| } |
| }, |
| "id": "GoogleCloudVideointelligenceV1p1beta1_WordInfo", |
| "type": "object" |
| }, |
| "GoogleCloudVideointelligenceV1_AnnotateVideoResponse": { |
| "id": "GoogleCloudVideointelligenceV1_AnnotateVideoResponse", |
| "properties": { |
| "annotationResults": { |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1_VideoAnnotationResults" |
| }, |
| "type": "array", |
| "description": "Annotation results for all videos specified in `AnnotateVideoRequest`." |
| } |
| }, |
| "type": "object", |
| "description": "Video annotation response. Included in the `response` field of the `Operation` returned by the `GetOperation` call of the `google::longrunning::Operations` service." |
| }, |
| "GoogleCloudVideointelligenceV1p3beta1_LogoRecognitionAnnotation": { |
| "type": "object", |
| "description": "Annotation corresponding to one detected, tracked and recognized logo class.", |
| "properties": { |
| "tracks": { |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1p3beta1_Track" |
| }, |
| "description": "All logo tracks where the recognized logo appears. Each track corresponds to one logo instance appearing in consecutive frames.", |
| "type": "array" |
| }, |
| "segments": { |
| "description": "All video segments where the recognized logo appears. There might be multiple instances of the same logo class appearing in one VideoSegment.", |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1p3beta1_VideoSegment" |
| }, |
| "type": "array" |
| }, |
| "entity": { |
| "description": "Entity category information to specify the logo class that all the logo tracks within this LogoRecognitionAnnotation are recognized as.", |
| "$ref": "GoogleCloudVideointelligenceV1p3beta1_Entity" |
| } |
| }, |
| "id": "GoogleCloudVideointelligenceV1p3beta1_LogoRecognitionAnnotation" |
| }, |
| "GoogleCloudVideointelligenceV1p3beta1_ExplicitContentAnnotation": { |
| "properties": { |
| "version": { |
| "description": "Feature version.", |
| "type": "string" |
| }, |
| "frames": { |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1p3beta1_ExplicitContentFrame" |
| }, |
| "type": "array", |
| "description": "All video frames where explicit content was detected." |
| } |
| }, |
| "id": "GoogleCloudVideointelligenceV1p3beta1_ExplicitContentAnnotation", |
| "description": "Explicit content annotation (based on per-frame visual signals only). If no explicit content has been detected in a frame, no annotations are present for that frame.", |
| "type": "object" |
| }, |
| "GoogleCloudVideointelligenceV1p3beta1_TextFrame": { |
| "id": "GoogleCloudVideointelligenceV1p3beta1_TextFrame", |
| "properties": { |
| "rotatedBoundingBox": { |
| "$ref": "GoogleCloudVideointelligenceV1p3beta1_NormalizedBoundingPoly", |
| "description": "Bounding polygon of the detected text for this frame." |
| }, |
| "timeOffset": { |
| "type": "string", |
| "format": "google-duration", |
| "description": "Timestamp of this frame." |
| } |
| }, |
| "description": "Video frame level annotation results for text annotation (OCR). Contains information regarding timestamp and bounding box locations for the frames containing detected OCR text snippets.", |
| "type": "object" |
| }, |
| "GoogleCloudVideointelligenceV1p3beta1_PersonDetectionAnnotation": { |
| "properties": { |
| "tracks": { |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1p3beta1_Track" |
| }, |
| "description": "The detected tracks of a person.", |
| "type": "array" |
| }, |
| "version": { |
| "description": "Feature version.", |
| "type": "string" |
| } |
| }, |
| "id": "GoogleCloudVideointelligenceV1p3beta1_PersonDetectionAnnotation", |
| "type": "object", |
| "description": "Person detection annotation per video." |
| }, |
| "GoogleCloudVideointelligenceV1p3beta1_CelebrityRecognitionAnnotation": { |
| "type": "object", |
| "properties": { |
| "version": { |
| "description": "Feature version.", |
| "type": "string" |
| }, |
| "celebrityTracks": { |
| "type": "array", |
| "description": "The tracks detected from the input video, including recognized celebrities and other detected faces in the video.", |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1p3beta1_CelebrityTrack" |
| } |
| } |
| }, |
| "description": "Celebrity recognition annotation per video.", |
| "id": "GoogleCloudVideointelligenceV1p3beta1_CelebrityRecognitionAnnotation" |
| }, |
| "GoogleCloudVideointelligenceV1_FaceDetectionAnnotation": { |
| "id": "GoogleCloudVideointelligenceV1_FaceDetectionAnnotation", |
| "properties": { |
| "version": { |
| "type": "string", |
| "description": "Feature version." |
| } |
| }, |
| "type": "object", |
| "description": "Face detection annotation." |
| }, |
| "GoogleCloudVideointelligenceV1p1beta1_ExplicitContentFrame": { |
| "id": "GoogleCloudVideointelligenceV1p1beta1_ExplicitContentFrame", |
| "type": "object", |
| "description": "Video frame level annotation results for explicit content.", |
| "properties": { |
| "pornographyLikelihood": { |
| "enum": [ |
| "LIKELIHOOD_UNSPECIFIED", |
| "VERY_UNLIKELY", |
| "UNLIKELY", |
| "POSSIBLE", |
| "LIKELY", |
| "VERY_LIKELY" |
| ], |
| "enumDescriptions": [ |
| "Unspecified likelihood.", |
| "Very unlikely.", |
| "Unlikely.", |
| "Possible.", |
| "Likely.", |
| "Very likely." |
| ], |
| "description": "Likelihood of the pornography content..", |
| "type": "string" |
| }, |
| "timeOffset": { |
| "type": "string", |
| "format": "google-duration", |
| "description": "Time-offset, relative to the beginning of the video, corresponding to the video frame for this location." |
| } |
| } |
| }, |
| "GoogleCloudVideointelligenceV1p1beta1_VideoAnnotationProgress": { |
| "description": "Annotation progress for a single video.", |
| "type": "object", |
| "properties": { |
| "segment": { |
| "description": "Specifies which segment is being tracked if the request contains more than one segment.", |
| "$ref": "GoogleCloudVideointelligenceV1p1beta1_VideoSegment" |
| }, |
| "startTime": { |
| "type": "string", |
| "format": "google-datetime", |
| "description": "Time when the request was received." |
| }, |
| "inputUri": { |
| "description": "Video file location in [Cloud Storage](https://cloud.google.com/storage/).", |
| "type": "string" |
| }, |
| "feature": { |
| "enum": [ |
| "FEATURE_UNSPECIFIED", |
| "LABEL_DETECTION", |
| "SHOT_CHANGE_DETECTION", |
| "EXPLICIT_CONTENT_DETECTION", |
| "FACE_DETECTION", |
| "SPEECH_TRANSCRIPTION", |
| "TEXT_DETECTION", |
| "OBJECT_TRACKING", |
| "LOGO_RECOGNITION", |
| "PERSON_DETECTION" |
| ], |
| "type": "string", |
| "enumDescriptions": [ |
| "Unspecified.", |
| "Label detection. Detect objects, such as dog or flower.", |
| "Shot change detection.", |
| "Explicit content detection.", |
| "Human face detection.", |
| "Speech transcription.", |
| "OCR text detection and tracking.", |
| "Object detection and tracking.", |
| "Logo detection, tracking, and recognition.", |
| "Person detection." |
| ], |
| "description": "Specifies which feature is being tracked if the request contains more than one feature." |
| }, |
| "updateTime": { |
| "format": "google-datetime", |
| "type": "string", |
| "description": "Time of the most recent update." |
| }, |
| "progressPercent": { |
| "description": "Approximate percentage processed thus far. Guaranteed to be 100 when fully processed.", |
| "format": "int32", |
| "type": "integer" |
| } |
| }, |
| "id": "GoogleCloudVideointelligenceV1p1beta1_VideoAnnotationProgress" |
| }, |
| "GoogleCloudVideointelligenceV1p3beta1_AnnotateVideoRequest": { |
| "description": "Video annotation request.", |
| "type": "object", |
| "id": "GoogleCloudVideointelligenceV1p3beta1_AnnotateVideoRequest", |
| "properties": { |
| "inputContent": { |
| "description": "The video data bytes. If unset, the input video(s) should be specified via the `input_uri`. If set, `input_uri` must be unset.", |
| "type": "string", |
| "format": "byte" |
| }, |
| "features": { |
| "items": { |
| "enum": [ |
| "FEATURE_UNSPECIFIED", |
| "LABEL_DETECTION", |
| "SHOT_CHANGE_DETECTION", |
| "EXPLICIT_CONTENT_DETECTION", |
| "FACE_DETECTION", |
| "SPEECH_TRANSCRIPTION", |
| "TEXT_DETECTION", |
| "OBJECT_TRACKING", |
| "LOGO_RECOGNITION", |
| "CELEBRITY_RECOGNITION", |
| "PERSON_DETECTION" |
| ], |
| "type": "string", |
| "enumDescriptions": [ |
| "Unspecified.", |
| "Label detection. Detect objects, such as dog or flower.", |
| "Shot change detection.", |
| "Explicit content detection.", |
| "Human face detection.", |
| "Speech transcription.", |
| "OCR text detection and tracking.", |
| "Object detection and tracking.", |
| "Logo detection, tracking, and recognition.", |
| "Celebrity recognition.", |
| "Person detection." |
| ] |
| }, |
| "description": "Required. Requested video annotation features.", |
| "type": "array" |
| }, |
| "locationId": { |
| "description": "Optional. Cloud region where annotation should take place. Supported cloud regions are: `us-east1`, `us-west1`, `europe-west1`, `asia-east1`. If no region is specified, the region will be determined based on video file location.", |
| "type": "string" |
| }, |
| "videoContext": { |
| "$ref": "GoogleCloudVideointelligenceV1p3beta1_VideoContext", |
| "description": "Additional video context and/or feature-specific parameters." |
| }, |
| "outputUri": { |
| "description": "Optional. Location where the output (in JSON format) should be stored. Currently, only [Cloud Storage](https://cloud.google.com/storage/) URIs are supported. These must be specified in the following format: `gs://bucket-id/object-id` (other URI formats return google.rpc.Code.INVALID_ARGUMENT). For more information, see [Request URIs](https://cloud.google.com/storage/docs/request-endpoints).", |
| "type": "string" |
| }, |
| "inputUri": { |
| "type": "string", |
| "description": "Input video location. Currently, only [Cloud Storage](https://cloud.google.com/storage/) URIs are supported. URIs must be specified in the following format: `gs://bucket-id/object-id` (other URI formats return google.rpc.Code.INVALID_ARGUMENT). For more information, see [Request URIs](https://cloud.google.com/storage/docs/request-endpoints). To identify multiple videos, a video URI may include wildcards in the `object-id`. Supported wildcards: '*' to match 0 or more characters; '?' to match 1 character. If unset, the input video should be embedded in the request as `input_content`. If set, `input_content` must be unset." |
| } |
| } |
| }, |
| "GoogleCloudVideointelligenceV1p2beta1_Track": { |
| "description": "A track of an object instance.", |
| "properties": { |
| "attributes": { |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1p2beta1_DetectedAttribute" |
| }, |
| "type": "array", |
| "description": "Optional. Attributes in the track level." |
| }, |
| "segment": { |
| "description": "Video segment of a track.", |
| "$ref": "GoogleCloudVideointelligenceV1p2beta1_VideoSegment" |
| }, |
| "confidence": { |
| "type": "number", |
| "description": "Optional. The confidence score of the tracked object.", |
| "format": "float" |
| }, |
| "timestampedObjects": { |
| "description": "The object with timestamp and attributes per frame in the track.", |
| "type": "array", |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1p2beta1_TimestampedObject" |
| } |
| } |
| }, |
| "type": "object", |
| "id": "GoogleCloudVideointelligenceV1p2beta1_Track" |
| }, |
| "GoogleCloudVideointelligenceV1p1beta1_Entity": { |
| "type": "object", |
| "id": "GoogleCloudVideointelligenceV1p1beta1_Entity", |
| "properties": { |
| "description": { |
| "type": "string", |
| "description": "Textual description, e.g., `Fixed-gear bicycle`." |
| }, |
| "languageCode": { |
| "type": "string", |
| "description": "Language code for `description` in BCP-47 format." |
| }, |
| "entityId": { |
| "description": "Opaque entity ID. Some IDs may be available in [Google Knowledge Graph Search API](https://developers.google.com/knowledge-graph/).", |
| "type": "string" |
| } |
| }, |
| "description": "Detected entity from video analysis." |
| }, |
| "GoogleCloudVideointelligenceV1p2beta1_DetectedLandmark": { |
| "id": "GoogleCloudVideointelligenceV1p2beta1_DetectedLandmark", |
| "type": "object", |
| "properties": { |
| "confidence": { |
| "type": "number", |
| "format": "float", |
| "description": "The confidence score of the detected landmark. Range [0, 1]." |
| }, |
| "point": { |
| "description": "The 2D point of the detected landmark using the normalized image coordindate system. The normalized coordinates have the range from 0 to 1.", |
| "$ref": "GoogleCloudVideointelligenceV1p2beta1_NormalizedVertex" |
| }, |
| "name": { |
| "type": "string", |
| "description": "The name of this landmark, for example, left_hand, right_shoulder." |
| } |
| }, |
| "description": "A generic detected landmark represented by name in string format and a 2D location." |
| }, |
| "GoogleCloudVideointelligenceV1p1beta1_AnnotateVideoProgress": { |
| "type": "object", |
| "id": "GoogleCloudVideointelligenceV1p1beta1_AnnotateVideoProgress", |
| "description": "Video annotation progress. Included in the `metadata` field of the `Operation` returned by the `GetOperation` call of the `google::longrunning::Operations` service.", |
| "properties": { |
| "annotationProgress": { |
| "description": "Progress metadata for all videos specified in `AnnotateVideoRequest`.", |
| "type": "array", |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1p1beta1_VideoAnnotationProgress" |
| } |
| } |
| } |
| }, |
| "GoogleCloudVideointelligenceV1beta2_AnnotateVideoResponse": { |
| "properties": { |
| "annotationResults": { |
| "type": "array", |
| "description": "Annotation results for all videos specified in `AnnotateVideoRequest`.", |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1beta2_VideoAnnotationResults" |
| } |
| } |
| }, |
| "type": "object", |
| "description": "Video annotation response. Included in the `response` field of the `Operation` returned by the `GetOperation` call of the `google::longrunning::Operations` service.", |
| "id": "GoogleCloudVideointelligenceV1beta2_AnnotateVideoResponse" |
| }, |
| "GoogleCloudVideointelligenceV1p3beta1_ObjectTrackingAnnotation": { |
| "description": "Annotations corresponding to one tracked object.", |
| "type": "object", |
| "id": "GoogleCloudVideointelligenceV1p3beta1_ObjectTrackingAnnotation", |
| "properties": { |
| "confidence": { |
| "type": "number", |
| "format": "float", |
| "description": "Object category's labeling confidence of this track." |
| }, |
| "trackId": { |
| "type": "string", |
| "format": "int64", |
| "description": "Streaming mode ONLY. In streaming mode, we do not know the end time of a tracked object before it is completed. Hence, there is no VideoSegment info returned. Instead, we provide a unique identifiable integer track_id so that the customers can correlate the results of the ongoing ObjectTrackAnnotation of the same track_id over time." |
| }, |
| "version": { |
| "type": "string", |
| "description": "Feature version." |
| }, |
| "entity": { |
| "$ref": "GoogleCloudVideointelligenceV1p3beta1_Entity", |
| "description": "Entity to specify the object category that this track is labeled as." |
| }, |
| "segment": { |
| "$ref": "GoogleCloudVideointelligenceV1p3beta1_VideoSegment", |
| "description": "Non-streaming batch mode ONLY. Each object track corresponds to one video segment where it appears." |
| }, |
| "frames": { |
| "type": "array", |
| "description": "Information corresponding to all frames where this object track appears. Non-streaming batch mode: it may be one or multiple ObjectTrackingFrame messages in frames. Streaming mode: it can only be one ObjectTrackingFrame message in frames.", |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1p3beta1_ObjectTrackingFrame" |
| } |
| } |
| } |
| }, |
| "GoogleCloudVideointelligenceV1p3beta1_TextSegment": { |
| "description": "Video segment level annotation results for text detection.", |
| "type": "object", |
| "properties": { |
| "frames": { |
| "type": "array", |
| "description": "Information related to the frames where OCR detected text appears.", |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1p3beta1_TextFrame" |
| } |
| }, |
| "confidence": { |
| "format": "float", |
| "description": "Confidence for the track of detected text. It is calculated as the highest over all frames where OCR detected text appears.", |
| "type": "number" |
| }, |
| "segment": { |
| "$ref": "GoogleCloudVideointelligenceV1p3beta1_VideoSegment", |
| "description": "Video segment where a text snippet was detected." |
| } |
| }, |
| "id": "GoogleCloudVideointelligenceV1p3beta1_TextSegment" |
| }, |
| "GoogleCloudVideointelligenceV1p1beta1_VideoSegment": { |
| "properties": { |
| "startTimeOffset": { |
| "format": "google-duration", |
| "type": "string", |
| "description": "Time-offset, relative to the beginning of the video, corresponding to the start of the segment (inclusive)." |
| }, |
| "endTimeOffset": { |
| "format": "google-duration", |
| "type": "string", |
| "description": "Time-offset, relative to the beginning of the video, corresponding to the end of the segment (inclusive)." |
| } |
| }, |
| "id": "GoogleCloudVideointelligenceV1p1beta1_VideoSegment", |
| "type": "object", |
| "description": "Video segment." |
| }, |
| "GoogleCloudVideointelligenceV1p3beta1_Celebrity": { |
| "description": "Celebrity definition.", |
| "type": "object", |
| "properties": { |
| "displayName": { |
| "type": "string", |
| "description": "The celebrity name." |
| }, |
| "description": { |
| "description": "Textual description of additional information about the celebrity, if applicable.", |
| "type": "string" |
| }, |
| "name": { |
| "description": "The resource name of the celebrity. Have the format `video-intelligence/kg-mid` indicates a celebrity from preloaded gallery. kg-mid is the id in Google knowledge graph, which is unique for the celebrity.", |
| "type": "string" |
| } |
| }, |
| "id": "GoogleCloudVideointelligenceV1p3beta1_Celebrity" |
| }, |
| "GoogleLongrunning_Operation": { |
| "id": "GoogleLongrunning_Operation", |
| "properties": { |
| "response": { |
| "description": "The normal response of the operation in case of success. If the original method returns no data on success, such as `Delete`, the response is `google.protobuf.Empty`. If the original method is standard `Get`/`Create`/`Update`, the response should be the resource. For other methods, the response should have the type `XxxResponse`, where `Xxx` is the original method name. For example, if the original method name is `TakeSnapshot()`, the inferred response type is `TakeSnapshotResponse`.", |
| "additionalProperties": { |
| "description": "Properties of the object. Contains field @type with type URL.", |
| "type": "any" |
| }, |
| "type": "object" |
| }, |
| "metadata": { |
| "description": "Service-specific metadata associated with the operation. It typically contains progress information and common metadata such as create time. Some services might not provide such metadata. Any method that returns a long-running operation should document the metadata type, if any.", |
| "type": "object", |
| "additionalProperties": { |
| "description": "Properties of the object. Contains field @type with type URL.", |
| "type": "any" |
| } |
| }, |
| "error": { |
| "description": "The error result of the operation in case of failure or cancellation.", |
| "$ref": "GoogleRpc_Status" |
| }, |
| "name": { |
| "description": "The server-assigned name, which is only unique within the same service that originally returns it. If you use the default HTTP mapping, the `name` should be a resource name ending with `operations/{unique_id}`.", |
| "type": "string" |
| }, |
| "done": { |
| "description": "If the value is `false`, it means the operation is still in progress. If `true`, the operation is completed, and either `error` or `response` is available.", |
| "type": "boolean" |
| } |
| }, |
| "type": "object", |
| "description": "This resource represents a long-running operation that is the result of a network API call." |
| }, |
| "GoogleCloudVideointelligenceV1p3beta1_SpeechRecognitionAlternative": { |
| "properties": { |
| "words": { |
| "description": "Output only. A list of word-specific information for each recognized word. Note: When `enable_speaker_diarization` is set to true, you will see all the words from the beginning of the audio.", |
| "readOnly": true, |
| "type": "array", |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1p3beta1_WordInfo" |
| } |
| }, |
| "transcript": { |
| "description": "Transcript text representing the words that the user spoke.", |
| "type": "string" |
| }, |
| "confidence": { |
| "type": "number", |
| "description": "Output only. The confidence estimate between 0.0 and 1.0. A higher number indicates an estimated greater likelihood that the recognized words are correct. This field is set only for the top alternative. This field is not guaranteed to be accurate and users should not rely on it to be always provided. The default of 0.0 is a sentinel value indicating `confidence` was not set.", |
| "readOnly": true, |
| "format": "float" |
| } |
| }, |
| "id": "GoogleCloudVideointelligenceV1p3beta1_SpeechRecognitionAlternative", |
| "type": "object", |
| "description": "Alternative hypotheses (a.k.a. n-best list)." |
| }, |
| "GoogleCloudVideointelligenceV1_LabelAnnotation": { |
| "description": "Label annotation.", |
| "properties": { |
| "categoryEntities": { |
| "description": "Common categories for the detected entity. For example, when the label is `Terrier`, the category is likely `dog`. And in some cases there might be more than one categories e.g., `Terrier` could also be a `pet`.", |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1_Entity" |
| }, |
| "type": "array" |
| }, |
| "entity": { |
| "$ref": "GoogleCloudVideointelligenceV1_Entity", |
| "description": "Detected entity." |
| }, |
| "segments": { |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1_LabelSegment" |
| }, |
| "description": "All video segments where a label was detected.", |
| "type": "array" |
| }, |
| "frames": { |
| "description": "All video frames where a label was detected.", |
| "type": "array", |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1_LabelFrame" |
| } |
| }, |
| "version": { |
| "description": "Feature version.", |
| "type": "string" |
| } |
| }, |
| "type": "object", |
| "id": "GoogleCloudVideointelligenceV1_LabelAnnotation" |
| }, |
| "GoogleCloudVideointelligenceV1beta2_DetectedAttribute": { |
| "id": "GoogleCloudVideointelligenceV1beta2_DetectedAttribute", |
| "properties": { |
| "value": { |
| "description": "Text value of the detection result. For example, the value for \"HairColor\" can be \"black\", \"blonde\", etc.", |
| "type": "string" |
| }, |
| "confidence": { |
| "format": "float", |
| "type": "number", |
| "description": "Detected attribute confidence. Range [0, 1]." |
| }, |
| "name": { |
| "type": "string", |
| "description": "The name of the attribute, for example, glasses, dark_glasses, mouth_open. A full list of supported type names will be provided in the document." |
| } |
| }, |
| "type": "object", |
| "description": "A generic detected attribute represented by name in string format." |
| }, |
| "GoogleCloudVideointelligenceV1p3beta1_NormalizedBoundingPoly": { |
| "type": "object", |
| "properties": { |
| "vertices": { |
| "description": "Normalized vertices of the bounding polygon.", |
| "type": "array", |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1p3beta1_NormalizedVertex" |
| } |
| } |
| }, |
| "id": "GoogleCloudVideointelligenceV1p3beta1_NormalizedBoundingPoly", |
| "description": "Normalized bounding polygon for text (that might not be aligned with axis). Contains list of the corner points in clockwise order starting from top-left corner. For example, for a rectangular bounding box: When the text is horizontal it might look like: 0----1 | | 3----2 When it's clockwise rotated 180 degrees around the top-left corner it becomes: 2----3 | | 1----0 and the vertex order will still be (0, 1, 2, 3). Note that values can be less than 0, or greater than 1 due to trignometric calculations for location of the box." |
| }, |
| "GoogleCloudVideointelligenceV1beta2_VideoSegment": { |
| "id": "GoogleCloudVideointelligenceV1beta2_VideoSegment", |
| "type": "object", |
| "description": "Video segment.", |
| "properties": { |
| "startTimeOffset": { |
| "description": "Time-offset, relative to the beginning of the video, corresponding to the start of the segment (inclusive).", |
| "format": "google-duration", |
| "type": "string" |
| }, |
| "endTimeOffset": { |
| "format": "google-duration", |
| "type": "string", |
| "description": "Time-offset, relative to the beginning of the video, corresponding to the end of the segment (inclusive)." |
| } |
| } |
| }, |
| "GoogleCloudVideointelligenceV1beta2_LogoRecognitionAnnotation": { |
| "properties": { |
| "entity": { |
| "$ref": "GoogleCloudVideointelligenceV1beta2_Entity", |
| "description": "Entity category information to specify the logo class that all the logo tracks within this LogoRecognitionAnnotation are recognized as." |
| }, |
| "tracks": { |
| "type": "array", |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1beta2_Track" |
| }, |
| "description": "All logo tracks where the recognized logo appears. Each track corresponds to one logo instance appearing in consecutive frames." |
| }, |
| "segments": { |
| "description": "All video segments where the recognized logo appears. There might be multiple instances of the same logo class appearing in one VideoSegment.", |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1beta2_VideoSegment" |
| }, |
| "type": "array" |
| } |
| }, |
| "description": "Annotation corresponding to one detected, tracked and recognized logo class.", |
| "type": "object", |
| "id": "GoogleCloudVideointelligenceV1beta2_LogoRecognitionAnnotation" |
| }, |
| "GoogleCloudVideointelligenceV1p3beta1_FaceDetectionConfig": { |
| "id": "GoogleCloudVideointelligenceV1p3beta1_FaceDetectionConfig", |
| "description": "Config for FACE_DETECTION.", |
| "type": "object", |
| "properties": { |
| "includeAttributes": { |
| "description": "Whether to enable face attributes detection, such as glasses, dark_glasses, mouth_open etc. Ignored if 'include_bounding_boxes' is set to false.", |
| "type": "boolean" |
| }, |
| "includeBoundingBoxes": { |
| "description": "Whether bounding boxes are included in the face annotation output.", |
| "type": "boolean" |
| }, |
| "model": { |
| "description": "Model to use for face detection. Supported values: \"builtin/stable\" (the default if unset) and \"builtin/latest\".", |
| "type": "string" |
| } |
| } |
| }, |
| "GoogleCloudVideointelligenceV1p2beta1_ObjectTrackingAnnotation": { |
| "properties": { |
| "frames": { |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1p2beta1_ObjectTrackingFrame" |
| }, |
| "type": "array", |
| "description": "Information corresponding to all frames where this object track appears. Non-streaming batch mode: it may be one or multiple ObjectTrackingFrame messages in frames. Streaming mode: it can only be one ObjectTrackingFrame message in frames." |
| }, |
| "version": { |
| "description": "Feature version.", |
| "type": "string" |
| }, |
| "confidence": { |
| "description": "Object category's labeling confidence of this track.", |
| "format": "float", |
| "type": "number" |
| }, |
| "segment": { |
| "description": "Non-streaming batch mode ONLY. Each object track corresponds to one video segment where it appears.", |
| "$ref": "GoogleCloudVideointelligenceV1p2beta1_VideoSegment" |
| }, |
| "entity": { |
| "description": "Entity to specify the object category that this track is labeled as.", |
| "$ref": "GoogleCloudVideointelligenceV1p2beta1_Entity" |
| }, |
| "trackId": { |
| "description": "Streaming mode ONLY. In streaming mode, we do not know the end time of a tracked object before it is completed. Hence, there is no VideoSegment info returned. Instead, we provide a unique identifiable integer track_id so that the customers can correlate the results of the ongoing ObjectTrackAnnotation of the same track_id over time.", |
| "format": "int64", |
| "type": "string" |
| } |
| }, |
| "description": "Annotations corresponding to one tracked object.", |
| "id": "GoogleCloudVideointelligenceV1p2beta1_ObjectTrackingAnnotation", |
| "type": "object" |
| }, |
| "GoogleCloudVideointelligenceV1beta2_AnnotateVideoProgress": { |
| "type": "object", |
| "properties": { |
| "annotationProgress": { |
| "description": "Progress metadata for all videos specified in `AnnotateVideoRequest`.", |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1beta2_VideoAnnotationProgress" |
| }, |
| "type": "array" |
| } |
| }, |
| "id": "GoogleCloudVideointelligenceV1beta2_AnnotateVideoProgress", |
| "description": "Video annotation progress. Included in the `metadata` field of the `Operation` returned by the `GetOperation` call of the `google::longrunning::Operations` service." |
| }, |
| "GoogleCloudVideointelligenceV1p1beta1_FaceFrame": { |
| "properties": { |
| "normalizedBoundingBoxes": { |
| "type": "array", |
| "description": "Normalized Bounding boxes in a frame. There can be more than one boxes if the same face is detected in multiple locations within the current frame.", |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1p1beta1_NormalizedBoundingBox" |
| } |
| }, |
| "timeOffset": { |
| "type": "string", |
| "format": "google-duration", |
| "description": "Time-offset, relative to the beginning of the video, corresponding to the video frame for this location." |
| } |
| }, |
| "id": "GoogleCloudVideointelligenceV1p1beta1_FaceFrame", |
| "description": "Deprecated. No effect.", |
| "type": "object" |
| }, |
| "GoogleCloudVideointelligenceV1_VideoAnnotationResults": { |
| "id": "GoogleCloudVideointelligenceV1_VideoAnnotationResults", |
| "description": "Annotation results for a single video.", |
| "properties": { |
| "error": { |
| "$ref": "GoogleRpc_Status", |
| "description": "If set, indicates an error. Note that for a single `AnnotateVideoRequest` some videos may succeed and some may fail." |
| }, |
| "faceDetectionAnnotations": { |
| "description": "Face detection annotations.", |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1_FaceDetectionAnnotation" |
| }, |
| "type": "array" |
| }, |
| "speechTranscriptions": { |
| "description": "Speech transcription.", |
| "type": "array", |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1_SpeechTranscription" |
| } |
| }, |
| "objectAnnotations": { |
| "type": "array", |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1_ObjectTrackingAnnotation" |
| }, |
| "description": "Annotations for list of objects detected and tracked in video." |
| }, |
| "explicitAnnotation": { |
| "description": "Explicit content annotation.", |
| "$ref": "GoogleCloudVideointelligenceV1_ExplicitContentAnnotation" |
| }, |
| "textAnnotations": { |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1_TextAnnotation" |
| }, |
| "type": "array", |
| "description": "OCR text detection and tracking. Annotations for list of detected text snippets. Each will have list of frame information associated with it." |
| }, |
| "segmentPresenceLabelAnnotations": { |
| "type": "array", |
| "description": "Presence label annotations on video level or user-specified segment level. There is exactly one element for each unique label. Compared to the existing topical `segment_label_annotations`, this field presents more fine-grained, segment-level labels detected in video content and is made available only when the client sets `LabelDetectionConfig.model` to \"builtin/latest\" in the request.", |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1_LabelAnnotation" |
| } |
| }, |
| "segment": { |
| "description": "Video segment on which the annotation is run.", |
| "$ref": "GoogleCloudVideointelligenceV1_VideoSegment" |
| }, |
| "frameLabelAnnotations": { |
| "description": "Label annotations on frame level. There is exactly one element for each unique label.", |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1_LabelAnnotation" |
| }, |
| "type": "array" |
| }, |
| "inputUri": { |
| "description": "Video file location in [Cloud Storage](https://cloud.google.com/storage/).", |
| "type": "string" |
| }, |
| "segmentLabelAnnotations": { |
| "type": "array", |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1_LabelAnnotation" |
| }, |
| "description": "Topical label annotations on video level or user-specified segment level. There is exactly one element for each unique label." |
| }, |
| "personDetectionAnnotations": { |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1_PersonDetectionAnnotation" |
| }, |
| "type": "array", |
| "description": "Person detection annotations." |
| }, |
| "shotAnnotations": { |
| "description": "Shot annotations. Each shot is represented as a video segment.", |
| "type": "array", |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1_VideoSegment" |
| } |
| }, |
| "faceAnnotations": { |
| "description": "Deprecated. Please use `face_detection_annotations` instead.", |
| "type": "array", |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1_FaceAnnotation" |
| } |
| }, |
| "logoRecognitionAnnotations": { |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1_LogoRecognitionAnnotation" |
| }, |
| "type": "array", |
| "description": "Annotations for list of logos detected, tracked and recognized in video." |
| }, |
| "shotLabelAnnotations": { |
| "description": "Topical label annotations on shot level. There is exactly one element for each unique label.", |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1_LabelAnnotation" |
| }, |
| "type": "array" |
| }, |
| "shotPresenceLabelAnnotations": { |
| "description": "Presence label annotations on shot level. There is exactly one element for each unique label. Compared to the existing topical `shot_label_annotations`, this field presents more fine-grained, shot-level labels detected in video content and is made available only when the client sets `LabelDetectionConfig.model` to \"builtin/latest\" in the request.", |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1_LabelAnnotation" |
| }, |
| "type": "array" |
| } |
| }, |
| "type": "object" |
| }, |
| "GoogleCloudVideointelligenceV1p3beta1_DetectedLandmark": { |
| "properties": { |
| "name": { |
| "description": "The name of this landmark, for example, left_hand, right_shoulder.", |
| "type": "string" |
| }, |
| "point": { |
| "$ref": "GoogleCloudVideointelligenceV1p3beta1_NormalizedVertex", |
| "description": "The 2D point of the detected landmark using the normalized image coordindate system. The normalized coordinates have the range from 0 to 1." |
| }, |
| "confidence": { |
| "format": "float", |
| "description": "The confidence score of the detected landmark. Range [0, 1].", |
| "type": "number" |
| } |
| }, |
| "type": "object", |
| "description": "A generic detected landmark represented by name in string format and a 2D location.", |
| "id": "GoogleCloudVideointelligenceV1p3beta1_DetectedLandmark" |
| }, |
| "GoogleCloudVideointelligenceV1beta2_Track": { |
| "id": "GoogleCloudVideointelligenceV1beta2_Track", |
| "properties": { |
| "attributes": { |
| "type": "array", |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1beta2_DetectedAttribute" |
| }, |
| "description": "Optional. Attributes in the track level." |
| }, |
| "confidence": { |
| "description": "Optional. The confidence score of the tracked object.", |
| "type": "number", |
| "format": "float" |
| }, |
| "timestampedObjects": { |
| "description": "The object with timestamp and attributes per frame in the track.", |
| "type": "array", |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1beta2_TimestampedObject" |
| } |
| }, |
| "segment": { |
| "description": "Video segment of a track.", |
| "$ref": "GoogleCloudVideointelligenceV1beta2_VideoSegment" |
| } |
| }, |
| "description": "A track of an object instance.", |
| "type": "object" |
| }, |
| "GoogleCloudVideointelligenceV1_ObjectTrackingAnnotation": { |
| "type": "object", |
| "properties": { |
| "trackId": { |
| "type": "string", |
| "format": "int64", |
| "description": "Streaming mode ONLY. In streaming mode, we do not know the end time of a tracked object before it is completed. Hence, there is no VideoSegment info returned. Instead, we provide a unique identifiable integer track_id so that the customers can correlate the results of the ongoing ObjectTrackAnnotation of the same track_id over time." |
| }, |
| "entity": { |
| "description": "Entity to specify the object category that this track is labeled as.", |
| "$ref": "GoogleCloudVideointelligenceV1_Entity" |
| }, |
| "segment": { |
| "$ref": "GoogleCloudVideointelligenceV1_VideoSegment", |
| "description": "Non-streaming batch mode ONLY. Each object track corresponds to one video segment where it appears." |
| }, |
| "confidence": { |
| "type": "number", |
| "description": "Object category's labeling confidence of this track.", |
| "format": "float" |
| }, |
| "frames": { |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1_ObjectTrackingFrame" |
| }, |
| "description": "Information corresponding to all frames where this object track appears. Non-streaming batch mode: it may be one or multiple ObjectTrackingFrame messages in frames. Streaming mode: it can only be one ObjectTrackingFrame message in frames.", |
| "type": "array" |
| }, |
| "version": { |
| "description": "Feature version.", |
| "type": "string" |
| } |
| }, |
| "id": "GoogleCloudVideointelligenceV1_ObjectTrackingAnnotation", |
| "description": "Annotations corresponding to one tracked object." |
| }, |
| "GoogleCloudVideointelligenceV1p1beta1_TextAnnotation": { |
| "type": "object", |
| "id": "GoogleCloudVideointelligenceV1p1beta1_TextAnnotation", |
| "description": "Annotations related to one detected OCR text snippet. This will contain the corresponding text, confidence value, and frame level information for each detection.", |
| "properties": { |
| "version": { |
| "description": "Feature version.", |
| "type": "string" |
| }, |
| "segments": { |
| "type": "array", |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1p1beta1_TextSegment" |
| }, |
| "description": "All video segments where OCR detected text appears." |
| }, |
| "text": { |
| "type": "string", |
| "description": "The detected text." |
| } |
| } |
| }, |
| "GoogleCloudVideointelligenceV1p2beta1_TimestampedObject": { |
| "properties": { |
| "attributes": { |
| "type": "array", |
| "description": "Optional. The attributes of the object in the bounding box.", |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1p2beta1_DetectedAttribute" |
| } |
| }, |
| "normalizedBoundingBox": { |
| "description": "Normalized Bounding box in a frame, where the object is located.", |
| "$ref": "GoogleCloudVideointelligenceV1p2beta1_NormalizedBoundingBox" |
| }, |
| "timeOffset": { |
| "type": "string", |
| "format": "google-duration", |
| "description": "Time-offset, relative to the beginning of the video, corresponding to the video frame for this object." |
| }, |
| "landmarks": { |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1p2beta1_DetectedLandmark" |
| }, |
| "type": "array", |
| "description": "Optional. The detected landmarks." |
| } |
| }, |
| "type": "object", |
| "description": "For tracking related features. An object at time_offset with attributes, and located with normalized_bounding_box.", |
| "id": "GoogleCloudVideointelligenceV1p2beta1_TimestampedObject" |
| }, |
| "GoogleCloudVideointelligenceV1beta2_NormalizedBoundingBox": { |
| "properties": { |
| "right": { |
| "format": "float", |
| "type": "number", |
| "description": "Right X coordinate." |
| }, |
| "bottom": { |
| "format": "float", |
| "type": "number", |
| "description": "Bottom Y coordinate." |
| }, |
| "top": { |
| "type": "number", |
| "description": "Top Y coordinate.", |
| "format": "float" |
| }, |
| "left": { |
| "format": "float", |
| "type": "number", |
| "description": "Left X coordinate." |
| } |
| }, |
| "description": "Normalized bounding box. The normalized vertex coordinates are relative to the original image. Range: [0, 1].", |
| "id": "GoogleCloudVideointelligenceV1beta2_NormalizedBoundingBox", |
| "type": "object" |
| }, |
| "GoogleCloudVideointelligenceV1_LogoRecognitionAnnotation": { |
| "properties": { |
| "entity": { |
| "$ref": "GoogleCloudVideointelligenceV1_Entity", |
| "description": "Entity category information to specify the logo class that all the logo tracks within this LogoRecognitionAnnotation are recognized as." |
| }, |
| "tracks": { |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1_Track" |
| }, |
| "type": "array", |
| "description": "All logo tracks where the recognized logo appears. Each track corresponds to one logo instance appearing in consecutive frames." |
| }, |
| "segments": { |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1_VideoSegment" |
| }, |
| "type": "array", |
| "description": "All video segments where the recognized logo appears. There might be multiple instances of the same logo class appearing in one VideoSegment." |
| } |
| }, |
| "description": "Annotation corresponding to one detected, tracked and recognized logo class.", |
| "id": "GoogleCloudVideointelligenceV1_LogoRecognitionAnnotation", |
| "type": "object" |
| }, |
| "GoogleCloudVideointelligenceV1beta2_TextSegment": { |
| "description": "Video segment level annotation results for text detection.", |
| "type": "object", |
| "properties": { |
| "segment": { |
| "$ref": "GoogleCloudVideointelligenceV1beta2_VideoSegment", |
| "description": "Video segment where a text snippet was detected." |
| }, |
| "frames": { |
| "description": "Information related to the frames where OCR detected text appears.", |
| "type": "array", |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1beta2_TextFrame" |
| } |
| }, |
| "confidence": { |
| "type": "number", |
| "description": "Confidence for the track of detected text. It is calculated as the highest over all frames where OCR detected text appears.", |
| "format": "float" |
| } |
| }, |
| "id": "GoogleCloudVideointelligenceV1beta2_TextSegment" |
| }, |
| "GoogleCloudVideointelligenceV1_ExplicitContentFrame": { |
| "type": "object", |
| "description": "Video frame level annotation results for explicit content.", |
| "id": "GoogleCloudVideointelligenceV1_ExplicitContentFrame", |
| "properties": { |
| "timeOffset": { |
| "format": "google-duration", |
| "type": "string", |
| "description": "Time-offset, relative to the beginning of the video, corresponding to the video frame for this location." |
| }, |
| "pornographyLikelihood": { |
| "type": "string", |
| "description": "Likelihood of the pornography content..", |
| "enumDescriptions": [ |
| "Unspecified likelihood.", |
| "Very unlikely.", |
| "Unlikely.", |
| "Possible.", |
| "Likely.", |
| "Very likely." |
| ], |
| "enum": [ |
| "LIKELIHOOD_UNSPECIFIED", |
| "VERY_UNLIKELY", |
| "UNLIKELY", |
| "POSSIBLE", |
| "LIKELY", |
| "VERY_LIKELY" |
| ] |
| } |
| } |
| }, |
| "GoogleCloudVideointelligenceV1p1beta1_TimestampedObject": { |
| "description": "For tracking related features. An object at time_offset with attributes, and located with normalized_bounding_box.", |
| "type": "object", |
| "properties": { |
| "normalizedBoundingBox": { |
| "$ref": "GoogleCloudVideointelligenceV1p1beta1_NormalizedBoundingBox", |
| "description": "Normalized Bounding box in a frame, where the object is located." |
| }, |
| "attributes": { |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1p1beta1_DetectedAttribute" |
| }, |
| "type": "array", |
| "description": "Optional. The attributes of the object in the bounding box." |
| }, |
| "timeOffset": { |
| "format": "google-duration", |
| "description": "Time-offset, relative to the beginning of the video, corresponding to the video frame for this object.", |
| "type": "string" |
| }, |
| "landmarks": { |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1p1beta1_DetectedLandmark" |
| }, |
| "description": "Optional. The detected landmarks.", |
| "type": "array" |
| } |
| }, |
| "id": "GoogleCloudVideointelligenceV1p1beta1_TimestampedObject" |
| }, |
| "GoogleCloudVideointelligenceV1p3beta1_LabelDetectionConfig": { |
| "description": "Config for LABEL_DETECTION.", |
| "properties": { |
| "stationaryCamera": { |
| "description": "Whether the video has been shot from a stationary (i.e., non-moving) camera. When set to true, might improve detection accuracy for moving objects. Should be used with `SHOT_AND_FRAME_MODE` enabled.", |
| "type": "boolean" |
| }, |
| "frameConfidenceThreshold": { |
| "type": "number", |
| "format": "float", |
| "description": "The confidence threshold we perform filtering on the labels from frame-level detection. If not set, it is set to 0.4 by default. The valid range for this threshold is [0.1, 0.9]. Any value set outside of this range will be clipped. Note: For best results, follow the default threshold. We will update the default threshold everytime when we release a new model." |
| }, |
| "model": { |
| "type": "string", |
| "description": "Model to use for label detection. Supported values: \"builtin/stable\" (the default if unset) and \"builtin/latest\"." |
| }, |
| "videoConfidenceThreshold": { |
| "description": "The confidence threshold we perform filtering on the labels from video-level and shot-level detections. If not set, it's set to 0.3 by default. The valid range for this threshold is [0.1, 0.9]. Any value set outside of this range will be clipped. Note: For best results, follow the default threshold. We will update the default threshold everytime when we release a new model.", |
| "format": "float", |
| "type": "number" |
| }, |
| "labelDetectionMode": { |
| "enumDescriptions": [ |
| "Unspecified.", |
| "Detect shot-level labels.", |
| "Detect frame-level labels.", |
| "Detect both shot-level and frame-level labels." |
| ], |
| "type": "string", |
| "description": "What labels should be detected with LABEL_DETECTION, in addition to video-level labels or segment-level labels. If unspecified, defaults to `SHOT_MODE`.", |
| "enum": [ |
| "LABEL_DETECTION_MODE_UNSPECIFIED", |
| "SHOT_MODE", |
| "FRAME_MODE", |
| "SHOT_AND_FRAME_MODE" |
| ] |
| } |
| }, |
| "type": "object", |
| "id": "GoogleCloudVideointelligenceV1p3beta1_LabelDetectionConfig" |
| }, |
| "GoogleCloudVideointelligenceV1_FaceSegment": { |
| "description": "Video segment level annotation results for face detection.", |
| "properties": { |
| "segment": { |
| "$ref": "GoogleCloudVideointelligenceV1_VideoSegment", |
| "description": "Video segment where a face was detected." |
| } |
| }, |
| "type": "object", |
| "id": "GoogleCloudVideointelligenceV1_FaceSegment" |
| }, |
| "GoogleCloudVideointelligenceV1p3beta1_CelebrityTrack": { |
| "description": "The annotation result of a celebrity face track. RecognizedCelebrity field could be empty if the face track does not have any matched celebrities.", |
| "id": "GoogleCloudVideointelligenceV1p3beta1_CelebrityTrack", |
| "properties": { |
| "celebrities": { |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1p3beta1_RecognizedCelebrity" |
| }, |
| "type": "array", |
| "description": "Top N match of the celebrities for the face in this track." |
| }, |
| "faceTrack": { |
| "description": "A track of a person's face.", |
| "$ref": "GoogleCloudVideointelligenceV1p3beta1_Track" |
| } |
| }, |
| "type": "object" |
| }, |
| "GoogleCloudVideointelligenceV1_NormalizedBoundingBox": { |
| "description": "Normalized bounding box. The normalized vertex coordinates are relative to the original image. Range: [0, 1].", |
| "properties": { |
| "top": { |
| "description": "Top Y coordinate.", |
| "format": "float", |
| "type": "number" |
| }, |
| "bottom": { |
| "description": "Bottom Y coordinate.", |
| "type": "number", |
| "format": "float" |
| }, |
| "left": { |
| "type": "number", |
| "description": "Left X coordinate.", |
| "format": "float" |
| }, |
| "right": { |
| "type": "number", |
| "description": "Right X coordinate.", |
| "format": "float" |
| } |
| }, |
| "type": "object", |
| "id": "GoogleCloudVideointelligenceV1_NormalizedBoundingBox" |
| }, |
| "GoogleCloudVideointelligenceV1beta2_FaceFrame": { |
| "description": "Deprecated. No effect.", |
| "properties": { |
| "timeOffset": { |
| "description": "Time-offset, relative to the beginning of the video, corresponding to the video frame for this location.", |
| "format": "google-duration", |
| "type": "string" |
| }, |
| "normalizedBoundingBoxes": { |
| "type": "array", |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1beta2_NormalizedBoundingBox" |
| }, |
| "description": "Normalized Bounding boxes in a frame. There can be more than one boxes if the same face is detected in multiple locations within the current frame." |
| } |
| }, |
| "type": "object", |
| "id": "GoogleCloudVideointelligenceV1beta2_FaceFrame" |
| }, |
| "GoogleCloudVideointelligenceV1p3beta1_FaceSegment": { |
| "description": "Video segment level annotation results for face detection.", |
| "properties": { |
| "segment": { |
| "description": "Video segment where a face was detected.", |
| "$ref": "GoogleCloudVideointelligenceV1p3beta1_VideoSegment" |
| } |
| }, |
| "id": "GoogleCloudVideointelligenceV1p3beta1_FaceSegment", |
| "type": "object" |
| }, |
| "GoogleCloudVideointelligenceV1_FaceFrame": { |
| "type": "object", |
| "id": "GoogleCloudVideointelligenceV1_FaceFrame", |
| "properties": { |
| "normalizedBoundingBoxes": { |
| "description": "Normalized Bounding boxes in a frame. There can be more than one boxes if the same face is detected in multiple locations within the current frame.", |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1_NormalizedBoundingBox" |
| }, |
| "type": "array" |
| }, |
| "timeOffset": { |
| "type": "string", |
| "description": "Time-offset, relative to the beginning of the video, corresponding to the video frame for this location.", |
| "format": "google-duration" |
| } |
| }, |
| "description": "Deprecated. No effect." |
| }, |
| "GoogleCloudVideointelligenceV1p1beta1_PersonDetectionAnnotation": { |
| "type": "object", |
| "id": "GoogleCloudVideointelligenceV1p1beta1_PersonDetectionAnnotation", |
| "properties": { |
| "tracks": { |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1p1beta1_Track" |
| }, |
| "type": "array", |
| "description": "The detected tracks of a person." |
| }, |
| "version": { |
| "description": "Feature version.", |
| "type": "string" |
| } |
| }, |
| "description": "Person detection annotation per video." |
| }, |
| "GoogleCloudVideointelligenceV1p2beta1_FaceFrame": { |
| "description": "Deprecated. No effect.", |
| "type": "object", |
| "id": "GoogleCloudVideointelligenceV1p2beta1_FaceFrame", |
| "properties": { |
| "normalizedBoundingBoxes": { |
| "description": "Normalized Bounding boxes in a frame. There can be more than one boxes if the same face is detected in multiple locations within the current frame.", |
| "type": "array", |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1p2beta1_NormalizedBoundingBox" |
| } |
| }, |
| "timeOffset": { |
| "format": "google-duration", |
| "description": "Time-offset, relative to the beginning of the video, corresponding to the video frame for this location.", |
| "type": "string" |
| } |
| } |
| }, |
| "GoogleCloudVideointelligenceV1_AnnotateVideoProgress": { |
| "type": "object", |
| "id": "GoogleCloudVideointelligenceV1_AnnotateVideoProgress", |
| "description": "Video annotation progress. Included in the `metadata` field of the `Operation` returned by the `GetOperation` call of the `google::longrunning::Operations` service.", |
| "properties": { |
| "annotationProgress": { |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1_VideoAnnotationProgress" |
| }, |
| "type": "array", |
| "description": "Progress metadata for all videos specified in `AnnotateVideoRequest`." |
| } |
| } |
| }, |
| "GoogleCloudVideointelligenceV1p1beta1_VideoAnnotationResults": { |
| "type": "object", |
| "id": "GoogleCloudVideointelligenceV1p1beta1_VideoAnnotationResults", |
| "properties": { |
| "segmentLabelAnnotations": { |
| "description": "Topical label annotations on video level or user-specified segment level. There is exactly one element for each unique label.", |
| "type": "array", |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1p1beta1_LabelAnnotation" |
| } |
| }, |
| "faceAnnotations": { |
| "description": "Deprecated. Please use `face_detection_annotations` instead.", |
| "type": "array", |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1p1beta1_FaceAnnotation" |
| } |
| }, |
| "shotLabelAnnotations": { |
| "type": "array", |
| "description": "Topical label annotations on shot level. There is exactly one element for each unique label.", |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1p1beta1_LabelAnnotation" |
| } |
| }, |
| "shotPresenceLabelAnnotations": { |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1p1beta1_LabelAnnotation" |
| }, |
| "description": "Presence label annotations on shot level. There is exactly one element for each unique label. Compared to the existing topical `shot_label_annotations`, this field presents more fine-grained, shot-level labels detected in video content and is made available only when the client sets `LabelDetectionConfig.model` to \"builtin/latest\" in the request.", |
| "type": "array" |
| }, |
| "speechTranscriptions": { |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1p1beta1_SpeechTranscription" |
| }, |
| "description": "Speech transcription.", |
| "type": "array" |
| }, |
| "textAnnotations": { |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1p1beta1_TextAnnotation" |
| }, |
| "type": "array", |
| "description": "OCR text detection and tracking. Annotations for list of detected text snippets. Each will have list of frame information associated with it." |
| }, |
| "error": { |
| "description": "If set, indicates an error. Note that for a single `AnnotateVideoRequest` some videos may succeed and some may fail.", |
| "$ref": "GoogleRpc_Status" |
| }, |
| "explicitAnnotation": { |
| "$ref": "GoogleCloudVideointelligenceV1p1beta1_ExplicitContentAnnotation", |
| "description": "Explicit content annotation." |
| }, |
| "segmentPresenceLabelAnnotations": { |
| "type": "array", |
| "description": "Presence label annotations on video level or user-specified segment level. There is exactly one element for each unique label. Compared to the existing topical `segment_label_annotations`, this field presents more fine-grained, segment-level labels detected in video content and is made available only when the client sets `LabelDetectionConfig.model` to \"builtin/latest\" in the request.", |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1p1beta1_LabelAnnotation" |
| } |
| }, |
| "personDetectionAnnotations": { |
| "type": "array", |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1p1beta1_PersonDetectionAnnotation" |
| }, |
| "description": "Person detection annotations." |
| }, |
| "objectAnnotations": { |
| "type": "array", |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1p1beta1_ObjectTrackingAnnotation" |
| }, |
| "description": "Annotations for list of objects detected and tracked in video." |
| }, |
| "shotAnnotations": { |
| "type": "array", |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1p1beta1_VideoSegment" |
| }, |
| "description": "Shot annotations. Each shot is represented as a video segment." |
| }, |
| "faceDetectionAnnotations": { |
| "description": "Face detection annotations.", |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1p1beta1_FaceDetectionAnnotation" |
| }, |
| "type": "array" |
| }, |
| "segment": { |
| "description": "Video segment on which the annotation is run.", |
| "$ref": "GoogleCloudVideointelligenceV1p1beta1_VideoSegment" |
| }, |
| "frameLabelAnnotations": { |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1p1beta1_LabelAnnotation" |
| }, |
| "type": "array", |
| "description": "Label annotations on frame level. There is exactly one element for each unique label." |
| }, |
| "inputUri": { |
| "description": "Video file location in [Cloud Storage](https://cloud.google.com/storage/).", |
| "type": "string" |
| }, |
| "logoRecognitionAnnotations": { |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1p1beta1_LogoRecognitionAnnotation" |
| }, |
| "description": "Annotations for list of logos detected, tracked and recognized in video.", |
| "type": "array" |
| } |
| }, |
| "description": "Annotation results for a single video." |
| }, |
| "GoogleCloudVideointelligenceV1p2beta1_NormalizedBoundingBox": { |
| "type": "object", |
| "id": "GoogleCloudVideointelligenceV1p2beta1_NormalizedBoundingBox", |
| "description": "Normalized bounding box. The normalized vertex coordinates are relative to the original image. Range: [0, 1].", |
| "properties": { |
| "left": { |
| "format": "float", |
| "description": "Left X coordinate.", |
| "type": "number" |
| }, |
| "right": { |
| "description": "Right X coordinate.", |
| "type": "number", |
| "format": "float" |
| }, |
| "top": { |
| "description": "Top Y coordinate.", |
| "format": "float", |
| "type": "number" |
| }, |
| "bottom": { |
| "description": "Bottom Y coordinate.", |
| "format": "float", |
| "type": "number" |
| } |
| } |
| }, |
| "GoogleCloudVideointelligenceV1p2beta1_AnnotateVideoResponse": { |
| "description": "Video annotation response. Included in the `response` field of the `Operation` returned by the `GetOperation` call of the `google::longrunning::Operations` service.", |
| "id": "GoogleCloudVideointelligenceV1p2beta1_AnnotateVideoResponse", |
| "properties": { |
| "annotationResults": { |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1p2beta1_VideoAnnotationResults" |
| }, |
| "description": "Annotation results for all videos specified in `AnnotateVideoRequest`.", |
| "type": "array" |
| } |
| }, |
| "type": "object" |
| }, |
| "GoogleCloudVideointelligenceV1p3beta1_LabelFrame": { |
| "properties": { |
| "timeOffset": { |
| "type": "string", |
| "description": "Time-offset, relative to the beginning of the video, corresponding to the video frame for this location.", |
| "format": "google-duration" |
| }, |
| "confidence": { |
| "type": "number", |
| "description": "Confidence that the label is accurate. Range: [0, 1].", |
| "format": "float" |
| } |
| }, |
| "type": "object", |
| "id": "GoogleCloudVideointelligenceV1p3beta1_LabelFrame", |
| "description": "Video frame level annotation results for label detection." |
| }, |
| "GoogleCloudVideointelligenceV1p2beta1_VideoAnnotationProgress": { |
| "description": "Annotation progress for a single video.", |
| "type": "object", |
| "id": "GoogleCloudVideointelligenceV1p2beta1_VideoAnnotationProgress", |
| "properties": { |
| "updateTime": { |
| "description": "Time of the most recent update.", |
| "format": "google-datetime", |
| "type": "string" |
| }, |
| "inputUri": { |
| "type": "string", |
| "description": "Video file location in [Cloud Storage](https://cloud.google.com/storage/)." |
| }, |
| "feature": { |
| "enum": [ |
| "FEATURE_UNSPECIFIED", |
| "LABEL_DETECTION", |
| "SHOT_CHANGE_DETECTION", |
| "EXPLICIT_CONTENT_DETECTION", |
| "FACE_DETECTION", |
| "SPEECH_TRANSCRIPTION", |
| "TEXT_DETECTION", |
| "OBJECT_TRACKING", |
| "LOGO_RECOGNITION", |
| "PERSON_DETECTION" |
| ], |
| "enumDescriptions": [ |
| "Unspecified.", |
| "Label detection. Detect objects, such as dog or flower.", |
| "Shot change detection.", |
| "Explicit content detection.", |
| "Human face detection.", |
| "Speech transcription.", |
| "OCR text detection and tracking.", |
| "Object detection and tracking.", |
| "Logo detection, tracking, and recognition.", |
| "Person detection." |
| ], |
| "description": "Specifies which feature is being tracked if the request contains more than one feature.", |
| "type": "string" |
| }, |
| "startTime": { |
| "type": "string", |
| "format": "google-datetime", |
| "description": "Time when the request was received." |
| }, |
| "progressPercent": { |
| "type": "integer", |
| "format": "int32", |
| "description": "Approximate percentage processed thus far. Guaranteed to be 100 when fully processed." |
| }, |
| "segment": { |
| "description": "Specifies which segment is being tracked if the request contains more than one segment.", |
| "$ref": "GoogleCloudVideointelligenceV1p2beta1_VideoSegment" |
| } |
| } |
| }, |
| "GoogleCloudVideointelligenceV1p2beta1_DetectedAttribute": { |
| "type": "object", |
| "properties": { |
| "confidence": { |
| "type": "number", |
| "format": "float", |
| "description": "Detected attribute confidence. Range [0, 1]." |
| }, |
| "value": { |
| "type": "string", |
| "description": "Text value of the detection result. For example, the value for \"HairColor\" can be \"black\", \"blonde\", etc." |
| }, |
| "name": { |
| "description": "The name of the attribute, for example, glasses, dark_glasses, mouth_open. A full list of supported type names will be provided in the document.", |
| "type": "string" |
| } |
| }, |
| "id": "GoogleCloudVideointelligenceV1p2beta1_DetectedAttribute", |
| "description": "A generic detected attribute represented by name in string format." |
| }, |
| "GoogleCloudVideointelligenceV1p3beta1_SpeechTranscription": { |
| "properties": { |
| "alternatives": { |
| "description": "May contain one or more recognition hypotheses (up to the maximum specified in `max_alternatives`). These alternatives are ordered in terms of accuracy, with the top (first) alternative being the most probable, as ranked by the recognizer.", |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1p3beta1_SpeechRecognitionAlternative" |
| }, |
| "type": "array" |
| }, |
| "languageCode": { |
| "description": "Output only. The [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tag of the language in this result. This language code was detected to have the most likelihood of being spoken in the audio.", |
| "type": "string", |
| "readOnly": true |
| } |
| }, |
| "id": "GoogleCloudVideointelligenceV1p3beta1_SpeechTranscription", |
| "description": "A speech recognition result corresponding to a portion of the audio.", |
| "type": "object" |
| }, |
| "GoogleCloudVideointelligenceV1p3beta1_ObjectTrackingFrame": { |
| "properties": { |
| "timeOffset": { |
| "format": "google-duration", |
| "type": "string", |
| "description": "The timestamp of the frame in microseconds." |
| }, |
| "normalizedBoundingBox": { |
| "description": "The normalized bounding box location of this object track for the frame.", |
| "$ref": "GoogleCloudVideointelligenceV1p3beta1_NormalizedBoundingBox" |
| } |
| }, |
| "id": "GoogleCloudVideointelligenceV1p3beta1_ObjectTrackingFrame", |
| "type": "object", |
| "description": "Video frame level annotations for object detection and tracking. This field stores per frame location, time offset, and confidence." |
| }, |
| "GoogleCloudVideointelligenceV1beta2_Entity": { |
| "type": "object", |
| "id": "GoogleCloudVideointelligenceV1beta2_Entity", |
| "properties": { |
| "description": { |
| "type": "string", |
| "description": "Textual description, e.g., `Fixed-gear bicycle`." |
| }, |
| "languageCode": { |
| "description": "Language code for `description` in BCP-47 format.", |
| "type": "string" |
| }, |
| "entityId": { |
| "description": "Opaque entity ID. Some IDs may be available in [Google Knowledge Graph Search API](https://developers.google.com/knowledge-graph/).", |
| "type": "string" |
| } |
| }, |
| "description": "Detected entity from video analysis." |
| }, |
| "GoogleCloudVideointelligenceV1p3beta1_SpeechContext": { |
| "id": "GoogleCloudVideointelligenceV1p3beta1_SpeechContext", |
| "properties": { |
| "phrases": { |
| "items": { |
| "type": "string" |
| }, |
| "description": "Optional. A list of strings containing words and phrases \"hints\" so that the speech recognition is more likely to recognize them. This can be used to improve the accuracy for specific words and phrases, for example, if specific commands are typically spoken by the user. This can also be used to add additional words to the vocabulary of the recognizer. See [usage limits](https://cloud.google.com/speech/limits#content).", |
| "type": "array" |
| } |
| }, |
| "description": "Provides \"hints\" to the speech recognizer to favor specific words and phrases in the results.", |
| "type": "object" |
| }, |
| "GoogleCloudVideointelligenceV1p1beta1_FaceDetectionAnnotation": { |
| "type": "object", |
| "properties": { |
| "version": { |
| "description": "Feature version.", |
| "type": "string" |
| } |
| }, |
| "id": "GoogleCloudVideointelligenceV1p1beta1_FaceDetectionAnnotation", |
| "description": "Face detection annotation." |
| }, |
| "GoogleCloudVideointelligenceV1p3beta1_AnnotateVideoProgress": { |
| "id": "GoogleCloudVideointelligenceV1p3beta1_AnnotateVideoProgress", |
| "properties": { |
| "annotationProgress": { |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1p3beta1_VideoAnnotationProgress" |
| }, |
| "type": "array", |
| "description": "Progress metadata for all videos specified in `AnnotateVideoRequest`." |
| } |
| }, |
| "type": "object", |
| "description": "Video annotation progress. Included in the `metadata` field of the `Operation` returned by the `GetOperation` call of the `google::longrunning::Operations` service." |
| }, |
| "GoogleCloudVideointelligenceV1p3beta1_ObjectTrackingConfig": { |
| "properties": { |
| "model": { |
| "type": "string", |
| "description": "Model to use for object tracking. Supported values: \"builtin/stable\" (the default if unset) and \"builtin/latest\"." |
| } |
| }, |
| "type": "object", |
| "id": "GoogleCloudVideointelligenceV1p3beta1_ObjectTrackingConfig", |
| "description": "Config for OBJECT_TRACKING." |
| }, |
| "GoogleCloudVideointelligenceV1p1beta1_TextSegment": { |
| "properties": { |
| "confidence": { |
| "format": "float", |
| "description": "Confidence for the track of detected text. It is calculated as the highest over all frames where OCR detected text appears.", |
| "type": "number" |
| }, |
| "frames": { |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1p1beta1_TextFrame" |
| }, |
| "type": "array", |
| "description": "Information related to the frames where OCR detected text appears." |
| }, |
| "segment": { |
| "$ref": "GoogleCloudVideointelligenceV1p1beta1_VideoSegment", |
| "description": "Video segment where a text snippet was detected." |
| } |
| }, |
| "description": "Video segment level annotation results for text detection.", |
| "id": "GoogleCloudVideointelligenceV1p1beta1_TextSegment", |
| "type": "object" |
| }, |
| "GoogleCloudVideointelligenceV1_SpeechRecognitionAlternative": { |
| "type": "object", |
| "id": "GoogleCloudVideointelligenceV1_SpeechRecognitionAlternative", |
| "properties": { |
| "words": { |
| "readOnly": true, |
| "type": "array", |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1_WordInfo" |
| }, |
| "description": "Output only. A list of word-specific information for each recognized word. Note: When `enable_speaker_diarization` is set to true, you will see all the words from the beginning of the audio." |
| }, |
| "confidence": { |
| "readOnly": true, |
| "format": "float", |
| "description": "Output only. The confidence estimate between 0.0 and 1.0. A higher number indicates an estimated greater likelihood that the recognized words are correct. This field is set only for the top alternative. This field is not guaranteed to be accurate and users should not rely on it to be always provided. The default of 0.0 is a sentinel value indicating `confidence` was not set.", |
| "type": "number" |
| }, |
| "transcript": { |
| "description": "Transcript text representing the words that the user spoke.", |
| "type": "string" |
| } |
| }, |
| "description": "Alternative hypotheses (a.k.a. n-best list)." |
| }, |
| "GoogleCloudVideointelligenceV1p3beta1_TimestampedObject": { |
| "properties": { |
| "timeOffset": { |
| "type": "string", |
| "format": "google-duration", |
| "description": "Time-offset, relative to the beginning of the video, corresponding to the video frame for this object." |
| }, |
| "landmarks": { |
| "description": "Optional. The detected landmarks.", |
| "type": "array", |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1p3beta1_DetectedLandmark" |
| } |
| }, |
| "normalizedBoundingBox": { |
| "$ref": "GoogleCloudVideointelligenceV1p3beta1_NormalizedBoundingBox", |
| "description": "Normalized Bounding box in a frame, where the object is located." |
| }, |
| "attributes": { |
| "type": "array", |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1p3beta1_DetectedAttribute" |
| }, |
| "description": "Optional. The attributes of the object in the bounding box." |
| } |
| }, |
| "id": "GoogleCloudVideointelligenceV1p3beta1_TimestampedObject", |
| "description": "For tracking related features. An object at time_offset with attributes, and located with normalized_bounding_box.", |
| "type": "object" |
| }, |
| "GoogleCloudVideointelligenceV1beta2_SpeechRecognitionAlternative": { |
| "description": "Alternative hypotheses (a.k.a. n-best list).", |
| "type": "object", |
| "id": "GoogleCloudVideointelligenceV1beta2_SpeechRecognitionAlternative", |
| "properties": { |
| "transcript": { |
| "type": "string", |
| "description": "Transcript text representing the words that the user spoke." |
| }, |
| "confidence": { |
| "readOnly": true, |
| "description": "Output only. The confidence estimate between 0.0 and 1.0. A higher number indicates an estimated greater likelihood that the recognized words are correct. This field is set only for the top alternative. This field is not guaranteed to be accurate and users should not rely on it to be always provided. The default of 0.0 is a sentinel value indicating `confidence` was not set.", |
| "format": "float", |
| "type": "number" |
| }, |
| "words": { |
| "type": "array", |
| "description": "Output only. A list of word-specific information for each recognized word. Note: When `enable_speaker_diarization` is set to true, you will see all the words from the beginning of the audio.", |
| "readOnly": true, |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1beta2_WordInfo" |
| } |
| } |
| } |
| }, |
| "GoogleCloudVideointelligenceV1p3beta1_VideoAnnotationProgress": { |
| "id": "GoogleCloudVideointelligenceV1p3beta1_VideoAnnotationProgress", |
| "type": "object", |
| "properties": { |
| "updateTime": { |
| "description": "Time of the most recent update.", |
| "format": "google-datetime", |
| "type": "string" |
| }, |
| "inputUri": { |
| "description": "Video file location in [Cloud Storage](https://cloud.google.com/storage/).", |
| "type": "string" |
| }, |
| "feature": { |
| "enumDescriptions": [ |
| "Unspecified.", |
| "Label detection. Detect objects, such as dog or flower.", |
| "Shot change detection.", |
| "Explicit content detection.", |
| "Human face detection.", |
| "Speech transcription.", |
| "OCR text detection and tracking.", |
| "Object detection and tracking.", |
| "Logo detection, tracking, and recognition.", |
| "Celebrity recognition.", |
| "Person detection." |
| ], |
| "description": "Specifies which feature is being tracked if the request contains more than one feature.", |
| "enum": [ |
| "FEATURE_UNSPECIFIED", |
| "LABEL_DETECTION", |
| "SHOT_CHANGE_DETECTION", |
| "EXPLICIT_CONTENT_DETECTION", |
| "FACE_DETECTION", |
| "SPEECH_TRANSCRIPTION", |
| "TEXT_DETECTION", |
| "OBJECT_TRACKING", |
| "LOGO_RECOGNITION", |
| "CELEBRITY_RECOGNITION", |
| "PERSON_DETECTION" |
| ], |
| "type": "string" |
| }, |
| "segment": { |
| "description": "Specifies which segment is being tracked if the request contains more than one segment.", |
| "$ref": "GoogleCloudVideointelligenceV1p3beta1_VideoSegment" |
| }, |
| "startTime": { |
| "type": "string", |
| "description": "Time when the request was received.", |
| "format": "google-datetime" |
| }, |
| "progressPercent": { |
| "description": "Approximate percentage processed thus far. Guaranteed to be 100 when fully processed.", |
| "type": "integer", |
| "format": "int32" |
| } |
| }, |
| "description": "Annotation progress for a single video." |
| }, |
| "GoogleCloudVideointelligenceV1p1beta1_NormalizedBoundingBox": { |
| "properties": { |
| "bottom": { |
| "type": "number", |
| "format": "float", |
| "description": "Bottom Y coordinate." |
| }, |
| "right": { |
| "description": "Right X coordinate.", |
| "type": "number", |
| "format": "float" |
| }, |
| "top": { |
| "description": "Top Y coordinate.", |
| "format": "float", |
| "type": "number" |
| }, |
| "left": { |
| "description": "Left X coordinate.", |
| "type": "number", |
| "format": "float" |
| } |
| }, |
| "id": "GoogleCloudVideointelligenceV1p1beta1_NormalizedBoundingBox", |
| "description": "Normalized bounding box. The normalized vertex coordinates are relative to the original image. Range: [0, 1].", |
| "type": "object" |
| }, |
| "GoogleCloudVideointelligenceV1beta2_ObjectTrackingAnnotation": { |
| "description": "Annotations corresponding to one tracked object.", |
| "type": "object", |
| "properties": { |
| "frames": { |
| "description": "Information corresponding to all frames where this object track appears. Non-streaming batch mode: it may be one or multiple ObjectTrackingFrame messages in frames. Streaming mode: it can only be one ObjectTrackingFrame message in frames.", |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1beta2_ObjectTrackingFrame" |
| }, |
| "type": "array" |
| }, |
| "trackId": { |
| "type": "string", |
| "format": "int64", |
| "description": "Streaming mode ONLY. In streaming mode, we do not know the end time of a tracked object before it is completed. Hence, there is no VideoSegment info returned. Instead, we provide a unique identifiable integer track_id so that the customers can correlate the results of the ongoing ObjectTrackAnnotation of the same track_id over time." |
| }, |
| "entity": { |
| "description": "Entity to specify the object category that this track is labeled as.", |
| "$ref": "GoogleCloudVideointelligenceV1beta2_Entity" |
| }, |
| "confidence": { |
| "type": "number", |
| "format": "float", |
| "description": "Object category's labeling confidence of this track." |
| }, |
| "segment": { |
| "description": "Non-streaming batch mode ONLY. Each object track corresponds to one video segment where it appears.", |
| "$ref": "GoogleCloudVideointelligenceV1beta2_VideoSegment" |
| }, |
| "version": { |
| "description": "Feature version.", |
| "type": "string" |
| } |
| }, |
| "id": "GoogleCloudVideointelligenceV1beta2_ObjectTrackingAnnotation" |
| }, |
| "GoogleCloudVideointelligenceV1p2beta1_LabelAnnotation": { |
| "properties": { |
| "entity": { |
| "description": "Detected entity.", |
| "$ref": "GoogleCloudVideointelligenceV1p2beta1_Entity" |
| }, |
| "frames": { |
| "description": "All video frames where a label was detected.", |
| "type": "array", |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1p2beta1_LabelFrame" |
| } |
| }, |
| "segments": { |
| "description": "All video segments where a label was detected.", |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1p2beta1_LabelSegment" |
| }, |
| "type": "array" |
| }, |
| "version": { |
| "description": "Feature version.", |
| "type": "string" |
| }, |
| "categoryEntities": { |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1p2beta1_Entity" |
| }, |
| "type": "array", |
| "description": "Common categories for the detected entity. For example, when the label is `Terrier`, the category is likely `dog`. And in some cases there might be more than one categories e.g., `Terrier` could also be a `pet`." |
| } |
| }, |
| "type": "object", |
| "description": "Label annotation.", |
| "id": "GoogleCloudVideointelligenceV1p2beta1_LabelAnnotation" |
| }, |
| "GoogleCloudVideointelligenceV1_Entity": { |
| "description": "Detected entity from video analysis.", |
| "id": "GoogleCloudVideointelligenceV1_Entity", |
| "type": "object", |
| "properties": { |
| "description": { |
| "description": "Textual description, e.g., `Fixed-gear bicycle`.", |
| "type": "string" |
| }, |
| "entityId": { |
| "description": "Opaque entity ID. Some IDs may be available in [Google Knowledge Graph Search API](https://developers.google.com/knowledge-graph/).", |
| "type": "string" |
| }, |
| "languageCode": { |
| "description": "Language code for `description` in BCP-47 format.", |
| "type": "string" |
| } |
| } |
| }, |
| "GoogleCloudVideointelligenceV1beta2_LabelSegment": { |
| "id": "GoogleCloudVideointelligenceV1beta2_LabelSegment", |
| "type": "object", |
| "properties": { |
| "confidence": { |
| "format": "float", |
| "type": "number", |
| "description": "Confidence that the label is accurate. Range: [0, 1]." |
| }, |
| "segment": { |
| "description": "Video segment where a label was detected.", |
| "$ref": "GoogleCloudVideointelligenceV1beta2_VideoSegment" |
| } |
| }, |
| "description": "Video segment level annotation results for label detection." |
| }, |
| "GoogleCloudVideointelligenceV1p1beta1_ExplicitContentAnnotation": { |
| "type": "object", |
| "description": "Explicit content annotation (based on per-frame visual signals only). If no explicit content has been detected in a frame, no annotations are present for that frame.", |
| "properties": { |
| "version": { |
| "description": "Feature version.", |
| "type": "string" |
| }, |
| "frames": { |
| "type": "array", |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1p1beta1_ExplicitContentFrame" |
| }, |
| "description": "All video frames where explicit content was detected." |
| } |
| }, |
| "id": "GoogleCloudVideointelligenceV1p1beta1_ExplicitContentAnnotation" |
| }, |
| "GoogleCloudVideointelligenceV1p3beta1_ExplicitContentDetectionConfig": { |
| "type": "object", |
| "properties": { |
| "model": { |
| "description": "Model to use for explicit content detection. Supported values: \"builtin/stable\" (the default if unset) and \"builtin/latest\".", |
| "type": "string" |
| } |
| }, |
| "description": "Config for EXPLICIT_CONTENT_DETECTION.", |
| "id": "GoogleCloudVideointelligenceV1p3beta1_ExplicitContentDetectionConfig" |
| }, |
| "GoogleCloudVideointelligenceV1p1beta1_NormalizedBoundingPoly": { |
| "type": "object", |
| "properties": { |
| "vertices": { |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1p1beta1_NormalizedVertex" |
| }, |
| "description": "Normalized vertices of the bounding polygon.", |
| "type": "array" |
| } |
| }, |
| "id": "GoogleCloudVideointelligenceV1p1beta1_NormalizedBoundingPoly", |
| "description": "Normalized bounding polygon for text (that might not be aligned with axis). Contains list of the corner points in clockwise order starting from top-left corner. For example, for a rectangular bounding box: When the text is horizontal it might look like: 0----1 | | 3----2 When it's clockwise rotated 180 degrees around the top-left corner it becomes: 2----3 | | 1----0 and the vertex order will still be (0, 1, 2, 3). Note that values can be less than 0, or greater than 1 due to trignometric calculations for location of the box." |
| }, |
| "GoogleCloudVideointelligenceV1_Track": { |
| "type": "object", |
| "description": "A track of an object instance.", |
| "id": "GoogleCloudVideointelligenceV1_Track", |
| "properties": { |
| "confidence": { |
| "type": "number", |
| "format": "float", |
| "description": "Optional. The confidence score of the tracked object." |
| }, |
| "segment": { |
| "$ref": "GoogleCloudVideointelligenceV1_VideoSegment", |
| "description": "Video segment of a track." |
| }, |
| "attributes": { |
| "type": "array", |
| "description": "Optional. Attributes in the track level.", |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1_DetectedAttribute" |
| } |
| }, |
| "timestampedObjects": { |
| "type": "array", |
| "description": "The object with timestamp and attributes per frame in the track.", |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1_TimestampedObject" |
| } |
| } |
| } |
| }, |
| "GoogleCloudVideointelligenceV1beta2_ExplicitContentAnnotation": { |
| "properties": { |
| "version": { |
| "type": "string", |
| "description": "Feature version." |
| }, |
| "frames": { |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1beta2_ExplicitContentFrame" |
| }, |
| "description": "All video frames where explicit content was detected.", |
| "type": "array" |
| } |
| }, |
| "description": "Explicit content annotation (based on per-frame visual signals only). If no explicit content has been detected in a frame, no annotations are present for that frame.", |
| "id": "GoogleCloudVideointelligenceV1beta2_ExplicitContentAnnotation", |
| "type": "object" |
| }, |
| "GoogleCloudVideointelligenceV1p1beta1_FaceSegment": { |
| "properties": { |
| "segment": { |
| "description": "Video segment where a face was detected.", |
| "$ref": "GoogleCloudVideointelligenceV1p1beta1_VideoSegment" |
| } |
| }, |
| "type": "object", |
| "id": "GoogleCloudVideointelligenceV1p1beta1_FaceSegment", |
| "description": "Video segment level annotation results for face detection." |
| }, |
| "GoogleCloudVideointelligenceV1_PersonDetectionAnnotation": { |
| "type": "object", |
| "id": "GoogleCloudVideointelligenceV1_PersonDetectionAnnotation", |
| "description": "Person detection annotation per video.", |
| "properties": { |
| "tracks": { |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1_Track" |
| }, |
| "type": "array", |
| "description": "The detected tracks of a person." |
| }, |
| "version": { |
| "description": "Feature version.", |
| "type": "string" |
| } |
| } |
| }, |
| "GoogleCloudVideointelligenceV1beta2_VideoAnnotationProgress": { |
| "properties": { |
| "progressPercent": { |
| "type": "integer", |
| "format": "int32", |
| "description": "Approximate percentage processed thus far. Guaranteed to be 100 when fully processed." |
| }, |
| "feature": { |
| "description": "Specifies which feature is being tracked if the request contains more than one feature.", |
| "enum": [ |
| "FEATURE_UNSPECIFIED", |
| "LABEL_DETECTION", |
| "SHOT_CHANGE_DETECTION", |
| "EXPLICIT_CONTENT_DETECTION", |
| "FACE_DETECTION", |
| "SPEECH_TRANSCRIPTION", |
| "TEXT_DETECTION", |
| "OBJECT_TRACKING", |
| "LOGO_RECOGNITION", |
| "PERSON_DETECTION" |
| ], |
| "enumDescriptions": [ |
| "Unspecified.", |
| "Label detection. Detect objects, such as dog or flower.", |
| "Shot change detection.", |
| "Explicit content detection.", |
| "Human face detection.", |
| "Speech transcription.", |
| "OCR text detection and tracking.", |
| "Object detection and tracking.", |
| "Logo detection, tracking, and recognition.", |
| "Person detection." |
| ], |
| "type": "string" |
| }, |
| "updateTime": { |
| "description": "Time of the most recent update.", |
| "format": "google-datetime", |
| "type": "string" |
| }, |
| "startTime": { |
| "type": "string", |
| "description": "Time when the request was received.", |
| "format": "google-datetime" |
| }, |
| "segment": { |
| "$ref": "GoogleCloudVideointelligenceV1beta2_VideoSegment", |
| "description": "Specifies which segment is being tracked if the request contains more than one segment." |
| }, |
| "inputUri": { |
| "description": "Video file location in [Cloud Storage](https://cloud.google.com/storage/).", |
| "type": "string" |
| } |
| }, |
| "id": "GoogleCloudVideointelligenceV1beta2_VideoAnnotationProgress", |
| "description": "Annotation progress for a single video.", |
| "type": "object" |
| }, |
| "GoogleCloudVideointelligenceV1beta2_TextFrame": { |
| "type": "object", |
| "description": "Video frame level annotation results for text annotation (OCR). Contains information regarding timestamp and bounding box locations for the frames containing detected OCR text snippets.", |
| "id": "GoogleCloudVideointelligenceV1beta2_TextFrame", |
| "properties": { |
| "timeOffset": { |
| "description": "Timestamp of this frame.", |
| "format": "google-duration", |
| "type": "string" |
| }, |
| "rotatedBoundingBox": { |
| "description": "Bounding polygon of the detected text for this frame.", |
| "$ref": "GoogleCloudVideointelligenceV1beta2_NormalizedBoundingPoly" |
| } |
| } |
| }, |
| "GoogleCloudVideointelligenceV1_LabelSegment": { |
| "properties": { |
| "confidence": { |
| "type": "number", |
| "format": "float", |
| "description": "Confidence that the label is accurate. Range: [0, 1]." |
| }, |
| "segment": { |
| "description": "Video segment where a label was detected.", |
| "$ref": "GoogleCloudVideointelligenceV1_VideoSegment" |
| } |
| }, |
| "description": "Video segment level annotation results for label detection.", |
| "id": "GoogleCloudVideointelligenceV1_LabelSegment", |
| "type": "object" |
| }, |
| "GoogleCloudVideointelligenceV1p3beta1_FaceAnnotation": { |
| "type": "object", |
| "id": "GoogleCloudVideointelligenceV1p3beta1_FaceAnnotation", |
| "description": "Deprecated. No effect.", |
| "properties": { |
| "thumbnail": { |
| "format": "byte", |
| "description": "Thumbnail of a representative face view (in JPEG format).", |
| "type": "string" |
| }, |
| "frames": { |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1p3beta1_FaceFrame" |
| }, |
| "description": "All video frames where a face was detected.", |
| "type": "array" |
| }, |
| "segments": { |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1p3beta1_FaceSegment" |
| }, |
| "description": "All video segments where a face was detected.", |
| "type": "array" |
| } |
| } |
| }, |
| "GoogleCloudVideointelligenceV1beta2_ExplicitContentFrame": { |
| "description": "Video frame level annotation results for explicit content.", |
| "id": "GoogleCloudVideointelligenceV1beta2_ExplicitContentFrame", |
| "properties": { |
| "timeOffset": { |
| "type": "string", |
| "description": "Time-offset, relative to the beginning of the video, corresponding to the video frame for this location.", |
| "format": "google-duration" |
| }, |
| "pornographyLikelihood": { |
| "enum": [ |
| "LIKELIHOOD_UNSPECIFIED", |
| "VERY_UNLIKELY", |
| "UNLIKELY", |
| "POSSIBLE", |
| "LIKELY", |
| "VERY_LIKELY" |
| ], |
| "enumDescriptions": [ |
| "Unspecified likelihood.", |
| "Very unlikely.", |
| "Unlikely.", |
| "Possible.", |
| "Likely.", |
| "Very likely." |
| ], |
| "type": "string", |
| "description": "Likelihood of the pornography content.." |
| } |
| }, |
| "type": "object" |
| }, |
| "GoogleCloudVideointelligenceV1p1beta1_TextFrame": { |
| "type": "object", |
| "id": "GoogleCloudVideointelligenceV1p1beta1_TextFrame", |
| "description": "Video frame level annotation results for text annotation (OCR). Contains information regarding timestamp and bounding box locations for the frames containing detected OCR text snippets.", |
| "properties": { |
| "timeOffset": { |
| "type": "string", |
| "description": "Timestamp of this frame.", |
| "format": "google-duration" |
| }, |
| "rotatedBoundingBox": { |
| "$ref": "GoogleCloudVideointelligenceV1p1beta1_NormalizedBoundingPoly", |
| "description": "Bounding polygon of the detected text for this frame." |
| } |
| } |
| }, |
| "GoogleCloudVideointelligenceV1_TextAnnotation": { |
| "properties": { |
| "segments": { |
| "description": "All video segments where OCR detected text appears.", |
| "type": "array", |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1_TextSegment" |
| } |
| }, |
| "text": { |
| "description": "The detected text.", |
| "type": "string" |
| }, |
| "version": { |
| "type": "string", |
| "description": "Feature version." |
| } |
| }, |
| "type": "object", |
| "id": "GoogleCloudVideointelligenceV1_TextAnnotation", |
| "description": "Annotations related to one detected OCR text snippet. This will contain the corresponding text, confidence value, and frame level information for each detection." |
| }, |
| "GoogleCloudVideointelligenceV1p3beta1_VideoContext": { |
| "type": "object", |
| "id": "GoogleCloudVideointelligenceV1p3beta1_VideoContext", |
| "properties": { |
| "labelDetectionConfig": { |
| "$ref": "GoogleCloudVideointelligenceV1p3beta1_LabelDetectionConfig", |
| "description": "Config for LABEL_DETECTION." |
| }, |
| "speechTranscriptionConfig": { |
| "description": "Config for SPEECH_TRANSCRIPTION.", |
| "$ref": "GoogleCloudVideointelligenceV1p3beta1_SpeechTranscriptionConfig" |
| }, |
| "personDetectionConfig": { |
| "$ref": "GoogleCloudVideointelligenceV1p3beta1_PersonDetectionConfig", |
| "description": "Config for PERSON_DETECTION." |
| }, |
| "objectTrackingConfig": { |
| "description": "Config for OBJECT_TRACKING.", |
| "$ref": "GoogleCloudVideointelligenceV1p3beta1_ObjectTrackingConfig" |
| }, |
| "explicitContentDetectionConfig": { |
| "$ref": "GoogleCloudVideointelligenceV1p3beta1_ExplicitContentDetectionConfig", |
| "description": "Config for EXPLICIT_CONTENT_DETECTION." |
| }, |
| "textDetectionConfig": { |
| "description": "Config for TEXT_DETECTION.", |
| "$ref": "GoogleCloudVideointelligenceV1p3beta1_TextDetectionConfig" |
| }, |
| "faceDetectionConfig": { |
| "$ref": "GoogleCloudVideointelligenceV1p3beta1_FaceDetectionConfig", |
| "description": "Config for FACE_DETECTION." |
| }, |
| "segments": { |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1p3beta1_VideoSegment" |
| }, |
| "description": "Video segments to annotate. The segments may overlap and are not required to be contiguous or span the whole video. If unspecified, each video is treated as a single segment.", |
| "type": "array" |
| }, |
| "shotChangeDetectionConfig": { |
| "description": "Config for SHOT_CHANGE_DETECTION.", |
| "$ref": "GoogleCloudVideointelligenceV1p3beta1_ShotChangeDetectionConfig" |
| } |
| }, |
| "description": "Video context and/or feature-specific parameters." |
| }, |
| "GoogleCloudVideointelligenceV1beta2_LabelFrame": { |
| "description": "Video frame level annotation results for label detection.", |
| "type": "object", |
| "id": "GoogleCloudVideointelligenceV1beta2_LabelFrame", |
| "properties": { |
| "timeOffset": { |
| "format": "google-duration", |
| "description": "Time-offset, relative to the beginning of the video, corresponding to the video frame for this location.", |
| "type": "string" |
| }, |
| "confidence": { |
| "type": "number", |
| "format": "float", |
| "description": "Confidence that the label is accurate. Range: [0, 1]." |
| } |
| } |
| }, |
| "GoogleCloudVideointelligenceV1_ObjectTrackingFrame": { |
| "type": "object", |
| "description": "Video frame level annotations for object detection and tracking. This field stores per frame location, time offset, and confidence.", |
| "id": "GoogleCloudVideointelligenceV1_ObjectTrackingFrame", |
| "properties": { |
| "normalizedBoundingBox": { |
| "description": "The normalized bounding box location of this object track for the frame.", |
| "$ref": "GoogleCloudVideointelligenceV1_NormalizedBoundingBox" |
| }, |
| "timeOffset": { |
| "format": "google-duration", |
| "type": "string", |
| "description": "The timestamp of the frame in microseconds." |
| } |
| } |
| }, |
| "GoogleCloudVideointelligenceV1p2beta1_VideoAnnotationResults": { |
| "properties": { |
| "frameLabelAnnotations": { |
| "type": "array", |
| "description": "Label annotations on frame level. There is exactly one element for each unique label.", |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1p2beta1_LabelAnnotation" |
| } |
| }, |
| "segment": { |
| "description": "Video segment on which the annotation is run.", |
| "$ref": "GoogleCloudVideointelligenceV1p2beta1_VideoSegment" |
| }, |
| "inputUri": { |
| "type": "string", |
| "description": "Video file location in [Cloud Storage](https://cloud.google.com/storage/)." |
| }, |
| "explicitAnnotation": { |
| "$ref": "GoogleCloudVideointelligenceV1p2beta1_ExplicitContentAnnotation", |
| "description": "Explicit content annotation." |
| }, |
| "error": { |
| "$ref": "GoogleRpc_Status", |
| "description": "If set, indicates an error. Note that for a single `AnnotateVideoRequest` some videos may succeed and some may fail." |
| }, |
| "faceAnnotations": { |
| "type": "array", |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1p2beta1_FaceAnnotation" |
| }, |
| "description": "Deprecated. Please use `face_detection_annotations` instead." |
| }, |
| "personDetectionAnnotations": { |
| "type": "array", |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1p2beta1_PersonDetectionAnnotation" |
| }, |
| "description": "Person detection annotations." |
| }, |
| "shotAnnotations": { |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1p2beta1_VideoSegment" |
| }, |
| "description": "Shot annotations. Each shot is represented as a video segment.", |
| "type": "array" |
| }, |
| "shotPresenceLabelAnnotations": { |
| "type": "array", |
| "description": "Presence label annotations on shot level. There is exactly one element for each unique label. Compared to the existing topical `shot_label_annotations`, this field presents more fine-grained, shot-level labels detected in video content and is made available only when the client sets `LabelDetectionConfig.model` to \"builtin/latest\" in the request.", |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1p2beta1_LabelAnnotation" |
| } |
| }, |
| "objectAnnotations": { |
| "type": "array", |
| "description": "Annotations for list of objects detected and tracked in video.", |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1p2beta1_ObjectTrackingAnnotation" |
| } |
| }, |
| "faceDetectionAnnotations": { |
| "type": "array", |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1p2beta1_FaceDetectionAnnotation" |
| }, |
| "description": "Face detection annotations." |
| }, |
| "segmentPresenceLabelAnnotations": { |
| "description": "Presence label annotations on video level or user-specified segment level. There is exactly one element for each unique label. Compared to the existing topical `segment_label_annotations`, this field presents more fine-grained, segment-level labels detected in video content and is made available only when the client sets `LabelDetectionConfig.model` to \"builtin/latest\" in the request.", |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1p2beta1_LabelAnnotation" |
| }, |
| "type": "array" |
| }, |
| "shotLabelAnnotations": { |
| "description": "Topical label annotations on shot level. There is exactly one element for each unique label.", |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1p2beta1_LabelAnnotation" |
| }, |
| "type": "array" |
| }, |
| "speechTranscriptions": { |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1p2beta1_SpeechTranscription" |
| }, |
| "description": "Speech transcription.", |
| "type": "array" |
| }, |
| "segmentLabelAnnotations": { |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1p2beta1_LabelAnnotation" |
| }, |
| "description": "Topical label annotations on video level or user-specified segment level. There is exactly one element for each unique label.", |
| "type": "array" |
| }, |
| "logoRecognitionAnnotations": { |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1p2beta1_LogoRecognitionAnnotation" |
| }, |
| "type": "array", |
| "description": "Annotations for list of logos detected, tracked and recognized in video." |
| }, |
| "textAnnotations": { |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1p2beta1_TextAnnotation" |
| }, |
| "type": "array", |
| "description": "OCR text detection and tracking. Annotations for list of detected text snippets. Each will have list of frame information associated with it." |
| } |
| }, |
| "description": "Annotation results for a single video.", |
| "type": "object", |
| "id": "GoogleCloudVideointelligenceV1p2beta1_VideoAnnotationResults" |
| }, |
| "GoogleCloudVideointelligenceV1p3beta1_RecognizedCelebrity": { |
| "description": "The recognized celebrity with confidence score.", |
| "type": "object", |
| "id": "GoogleCloudVideointelligenceV1p3beta1_RecognizedCelebrity", |
| "properties": { |
| "celebrity": { |
| "description": "The recognized celebrity.", |
| "$ref": "GoogleCloudVideointelligenceV1p3beta1_Celebrity" |
| }, |
| "confidence": { |
| "type": "number", |
| "format": "float", |
| "description": "Recognition confidence. Range [0, 1]." |
| } |
| } |
| }, |
| "GoogleCloudVideointelligenceV1p2beta1_FaceDetectionAnnotation": { |
| "properties": { |
| "version": { |
| "description": "Feature version.", |
| "type": "string" |
| } |
| }, |
| "description": "Face detection annotation.", |
| "type": "object", |
| "id": "GoogleCloudVideointelligenceV1p2beta1_FaceDetectionAnnotation" |
| }, |
| "GoogleCloudVideointelligenceV1beta2_PersonDetectionAnnotation": { |
| "type": "object", |
| "properties": { |
| "tracks": { |
| "type": "array", |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1beta2_Track" |
| }, |
| "description": "The detected tracks of a person." |
| }, |
| "version": { |
| "type": "string", |
| "description": "Feature version." |
| } |
| }, |
| "description": "Person detection annotation per video.", |
| "id": "GoogleCloudVideointelligenceV1beta2_PersonDetectionAnnotation" |
| }, |
| "GoogleCloudVideointelligenceV1p2beta1_TextSegment": { |
| "type": "object", |
| "properties": { |
| "frames": { |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1p2beta1_TextFrame" |
| }, |
| "description": "Information related to the frames where OCR detected text appears.", |
| "type": "array" |
| }, |
| "segment": { |
| "description": "Video segment where a text snippet was detected.", |
| "$ref": "GoogleCloudVideointelligenceV1p2beta1_VideoSegment" |
| }, |
| "confidence": { |
| "type": "number", |
| "description": "Confidence for the track of detected text. It is calculated as the highest over all frames where OCR detected text appears.", |
| "format": "float" |
| } |
| }, |
| "id": "GoogleCloudVideointelligenceV1p2beta1_TextSegment", |
| "description": "Video segment level annotation results for text detection." |
| }, |
| "GoogleCloudVideointelligenceV1p3beta1_LabelSegment": { |
| "type": "object", |
| "description": "Video segment level annotation results for label detection.", |
| "id": "GoogleCloudVideointelligenceV1p3beta1_LabelSegment", |
| "properties": { |
| "segment": { |
| "$ref": "GoogleCloudVideointelligenceV1p3beta1_VideoSegment", |
| "description": "Video segment where a label was detected." |
| }, |
| "confidence": { |
| "format": "float", |
| "type": "number", |
| "description": "Confidence that the label is accurate. Range: [0, 1]." |
| } |
| } |
| }, |
| "GoogleCloudVideointelligenceV1p3beta1_WordInfo": { |
| "type": "object", |
| "id": "GoogleCloudVideointelligenceV1p3beta1_WordInfo", |
| "description": "Word-specific information for recognized words. Word information is only included in the response when certain request parameters are set, such as `enable_word_time_offsets`.", |
| "properties": { |
| "endTime": { |
| "description": "Time offset relative to the beginning of the audio, and corresponding to the end of the spoken word. This field is only set if `enable_word_time_offsets=true` and only in the top hypothesis. This is an experimental feature and the accuracy of the time offset can vary.", |
| "type": "string", |
| "format": "google-duration" |
| }, |
| "confidence": { |
| "type": "number", |
| "readOnly": true, |
| "description": "Output only. The confidence estimate between 0.0 and 1.0. A higher number indicates an estimated greater likelihood that the recognized words are correct. This field is set only for the top alternative. This field is not guaranteed to be accurate and users should not rely on it to be always provided. The default of 0.0 is a sentinel value indicating `confidence` was not set.", |
| "format": "float" |
| }, |
| "word": { |
| "description": "The word corresponding to this set of information.", |
| "type": "string" |
| }, |
| "speakerTag": { |
| "format": "int32", |
| "readOnly": true, |
| "type": "integer", |
| "description": "Output only. A distinct integer value is assigned for every speaker within the audio. This field specifies which one of those speakers was detected to have spoken this word. Value ranges from 1 up to diarization_speaker_count, and is only set if speaker diarization is enabled." |
| }, |
| "startTime": { |
| "format": "google-duration", |
| "description": "Time offset relative to the beginning of the audio, and corresponding to the start of the spoken word. This field is only set if `enable_word_time_offsets=true` and only in the top hypothesis. This is an experimental feature and the accuracy of the time offset can vary.", |
| "type": "string" |
| } |
| } |
| }, |
| "GoogleCloudVideointelligenceV1p1beta1_ObjectTrackingFrame": { |
| "type": "object", |
| "description": "Video frame level annotations for object detection and tracking. This field stores per frame location, time offset, and confidence.", |
| "properties": { |
| "normalizedBoundingBox": { |
| "$ref": "GoogleCloudVideointelligenceV1p1beta1_NormalizedBoundingBox", |
| "description": "The normalized bounding box location of this object track for the frame." |
| }, |
| "timeOffset": { |
| "type": "string", |
| "format": "google-duration", |
| "description": "The timestamp of the frame in microseconds." |
| } |
| }, |
| "id": "GoogleCloudVideointelligenceV1p1beta1_ObjectTrackingFrame" |
| }, |
| "GoogleCloudVideointelligenceV1p2beta1_FaceSegment": { |
| "description": "Video segment level annotation results for face detection.", |
| "id": "GoogleCloudVideointelligenceV1p2beta1_FaceSegment", |
| "type": "object", |
| "properties": { |
| "segment": { |
| "$ref": "GoogleCloudVideointelligenceV1p2beta1_VideoSegment", |
| "description": "Video segment where a face was detected." |
| } |
| } |
| }, |
| "GoogleCloudVideointelligenceV1p2beta1_ExplicitContentFrame": { |
| "id": "GoogleCloudVideointelligenceV1p2beta1_ExplicitContentFrame", |
| "properties": { |
| "pornographyLikelihood": { |
| "type": "string", |
| "description": "Likelihood of the pornography content..", |
| "enum": [ |
| "LIKELIHOOD_UNSPECIFIED", |
| "VERY_UNLIKELY", |
| "UNLIKELY", |
| "POSSIBLE", |
| "LIKELY", |
| "VERY_LIKELY" |
| ], |
| "enumDescriptions": [ |
| "Unspecified likelihood.", |
| "Very unlikely.", |
| "Unlikely.", |
| "Possible.", |
| "Likely.", |
| "Very likely." |
| ] |
| }, |
| "timeOffset": { |
| "description": "Time-offset, relative to the beginning of the video, corresponding to the video frame for this location.", |
| "type": "string", |
| "format": "google-duration" |
| } |
| }, |
| "description": "Video frame level annotation results for explicit content.", |
| "type": "object" |
| }, |
| "GoogleCloudVideointelligenceV1p2beta1_SpeechRecognitionAlternative": { |
| "description": "Alternative hypotheses (a.k.a. n-best list).", |
| "type": "object", |
| "properties": { |
| "transcript": { |
| "description": "Transcript text representing the words that the user spoke.", |
| "type": "string" |
| }, |
| "confidence": { |
| "description": "Output only. The confidence estimate between 0.0 and 1.0. A higher number indicates an estimated greater likelihood that the recognized words are correct. This field is set only for the top alternative. This field is not guaranteed to be accurate and users should not rely on it to be always provided. The default of 0.0 is a sentinel value indicating `confidence` was not set.", |
| "format": "float", |
| "readOnly": true, |
| "type": "number" |
| }, |
| "words": { |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1p2beta1_WordInfo" |
| }, |
| "readOnly": true, |
| "description": "Output only. A list of word-specific information for each recognized word. Note: When `enable_speaker_diarization` is set to true, you will see all the words from the beginning of the audio.", |
| "type": "array" |
| } |
| }, |
| "id": "GoogleCloudVideointelligenceV1p2beta1_SpeechRecognitionAlternative" |
| }, |
| "GoogleCloudVideointelligenceV1p1beta1_DetectedAttribute": { |
| "description": "A generic detected attribute represented by name in string format.", |
| "type": "object", |
| "properties": { |
| "value": { |
| "description": "Text value of the detection result. For example, the value for \"HairColor\" can be \"black\", \"blonde\", etc.", |
| "type": "string" |
| }, |
| "confidence": { |
| "type": "number", |
| "description": "Detected attribute confidence. Range [0, 1].", |
| "format": "float" |
| }, |
| "name": { |
| "description": "The name of the attribute, for example, glasses, dark_glasses, mouth_open. A full list of supported type names will be provided in the document.", |
| "type": "string" |
| } |
| }, |
| "id": "GoogleCloudVideointelligenceV1p1beta1_DetectedAttribute" |
| }, |
| "GoogleCloudVideointelligenceV1p3beta1_Track": { |
| "description": "A track of an object instance.", |
| "type": "object", |
| "id": "GoogleCloudVideointelligenceV1p3beta1_Track", |
| "properties": { |
| "timestampedObjects": { |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1p3beta1_TimestampedObject" |
| }, |
| "description": "The object with timestamp and attributes per frame in the track.", |
| "type": "array" |
| }, |
| "confidence": { |
| "type": "number", |
| "description": "Optional. The confidence score of the tracked object.", |
| "format": "float" |
| }, |
| "attributes": { |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1p3beta1_DetectedAttribute" |
| }, |
| "description": "Optional. Attributes in the track level.", |
| "type": "array" |
| }, |
| "segment": { |
| "description": "Video segment of a track.", |
| "$ref": "GoogleCloudVideointelligenceV1p3beta1_VideoSegment" |
| } |
| } |
| }, |
| "GoogleCloudVideointelligenceV1p2beta1_NormalizedBoundingPoly": { |
| "id": "GoogleCloudVideointelligenceV1p2beta1_NormalizedBoundingPoly", |
| "properties": { |
| "vertices": { |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1p2beta1_NormalizedVertex" |
| }, |
| "type": "array", |
| "description": "Normalized vertices of the bounding polygon." |
| } |
| }, |
| "type": "object", |
| "description": "Normalized bounding polygon for text (that might not be aligned with axis). Contains list of the corner points in clockwise order starting from top-left corner. For example, for a rectangular bounding box: When the text is horizontal it might look like: 0----1 | | 3----2 When it's clockwise rotated 180 degrees around the top-left corner it becomes: 2----3 | | 1----0 and the vertex order will still be (0, 1, 2, 3). Note that values can be less than 0, or greater than 1 due to trignometric calculations for location of the box." |
| }, |
| "GoogleCloudVideointelligenceV1beta2_TextAnnotation": { |
| "type": "object", |
| "properties": { |
| "text": { |
| "type": "string", |
| "description": "The detected text." |
| }, |
| "segments": { |
| "type": "array", |
| "description": "All video segments where OCR detected text appears.", |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1beta2_TextSegment" |
| } |
| }, |
| "version": { |
| "description": "Feature version.", |
| "type": "string" |
| } |
| }, |
| "id": "GoogleCloudVideointelligenceV1beta2_TextAnnotation", |
| "description": "Annotations related to one detected OCR text snippet. This will contain the corresponding text, confidence value, and frame level information for each detection." |
| }, |
| "GoogleCloudVideointelligenceV1_DetectedAttribute": { |
| "type": "object", |
| "description": "A generic detected attribute represented by name in string format.", |
| "properties": { |
| "value": { |
| "type": "string", |
| "description": "Text value of the detection result. For example, the value for \"HairColor\" can be \"black\", \"blonde\", etc." |
| }, |
| "confidence": { |
| "type": "number", |
| "format": "float", |
| "description": "Detected attribute confidence. Range [0, 1]." |
| }, |
| "name": { |
| "type": "string", |
| "description": "The name of the attribute, for example, glasses, dark_glasses, mouth_open. A full list of supported type names will be provided in the document." |
| } |
| }, |
| "id": "GoogleCloudVideointelligenceV1_DetectedAttribute" |
| }, |
| "GoogleCloudVideointelligenceV1p3beta1_TextAnnotation": { |
| "type": "object", |
| "id": "GoogleCloudVideointelligenceV1p3beta1_TextAnnotation", |
| "description": "Annotations related to one detected OCR text snippet. This will contain the corresponding text, confidence value, and frame level information for each detection.", |
| "properties": { |
| "text": { |
| "description": "The detected text.", |
| "type": "string" |
| }, |
| "segments": { |
| "type": "array", |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1p3beta1_TextSegment" |
| }, |
| "description": "All video segments where OCR detected text appears." |
| }, |
| "version": { |
| "type": "string", |
| "description": "Feature version." |
| } |
| } |
| }, |
| "GoogleCloudVideointelligenceV1p1beta1_LogoRecognitionAnnotation": { |
| "id": "GoogleCloudVideointelligenceV1p1beta1_LogoRecognitionAnnotation", |
| "type": "object", |
| "description": "Annotation corresponding to one detected, tracked and recognized logo class.", |
| "properties": { |
| "tracks": { |
| "type": "array", |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1p1beta1_Track" |
| }, |
| "description": "All logo tracks where the recognized logo appears. Each track corresponds to one logo instance appearing in consecutive frames." |
| }, |
| "entity": { |
| "$ref": "GoogleCloudVideointelligenceV1p1beta1_Entity", |
| "description": "Entity category information to specify the logo class that all the logo tracks within this LogoRecognitionAnnotation are recognized as." |
| }, |
| "segments": { |
| "type": "array", |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1p1beta1_VideoSegment" |
| }, |
| "description": "All video segments where the recognized logo appears. There might be multiple instances of the same logo class appearing in one VideoSegment." |
| } |
| } |
| }, |
| "GoogleCloudVideointelligenceV1p1beta1_LabelSegment": { |
| "id": "GoogleCloudVideointelligenceV1p1beta1_LabelSegment", |
| "description": "Video segment level annotation results for label detection.", |
| "properties": { |
| "confidence": { |
| "description": "Confidence that the label is accurate. Range: [0, 1].", |
| "type": "number", |
| "format": "float" |
| }, |
| "segment": { |
| "description": "Video segment where a label was detected.", |
| "$ref": "GoogleCloudVideointelligenceV1p1beta1_VideoSegment" |
| } |
| }, |
| "type": "object" |
| }, |
| "GoogleCloudVideointelligenceV1beta2_LabelAnnotation": { |
| "description": "Label annotation.", |
| "type": "object", |
| "properties": { |
| "categoryEntities": { |
| "description": "Common categories for the detected entity. For example, when the label is `Terrier`, the category is likely `dog`. And in some cases there might be more than one categories e.g., `Terrier` could also be a `pet`.", |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1beta2_Entity" |
| }, |
| "type": "array" |
| }, |
| "entity": { |
| "$ref": "GoogleCloudVideointelligenceV1beta2_Entity", |
| "description": "Detected entity." |
| }, |
| "version": { |
| "type": "string", |
| "description": "Feature version." |
| }, |
| "segments": { |
| "type": "array", |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1beta2_LabelSegment" |
| }, |
| "description": "All video segments where a label was detected." |
| }, |
| "frames": { |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1beta2_LabelFrame" |
| }, |
| "description": "All video frames where a label was detected.", |
| "type": "array" |
| } |
| }, |
| "id": "GoogleCloudVideointelligenceV1beta2_LabelAnnotation" |
| }, |
| "GoogleCloudVideointelligenceV1_LabelFrame": { |
| "id": "GoogleCloudVideointelligenceV1_LabelFrame", |
| "description": "Video frame level annotation results for label detection.", |
| "properties": { |
| "timeOffset": { |
| "format": "google-duration", |
| "type": "string", |
| "description": "Time-offset, relative to the beginning of the video, corresponding to the video frame for this location." |
| }, |
| "confidence": { |
| "format": "float", |
| "type": "number", |
| "description": "Confidence that the label is accurate. Range: [0, 1]." |
| } |
| }, |
| "type": "object" |
| }, |
| "GoogleCloudVideointelligenceV1p3beta1_VideoSegment": { |
| "id": "GoogleCloudVideointelligenceV1p3beta1_VideoSegment", |
| "properties": { |
| "startTimeOffset": { |
| "description": "Time-offset, relative to the beginning of the video, corresponding to the start of the segment (inclusive).", |
| "type": "string", |
| "format": "google-duration" |
| }, |
| "endTimeOffset": { |
| "description": "Time-offset, relative to the beginning of the video, corresponding to the end of the segment (inclusive).", |
| "format": "google-duration", |
| "type": "string" |
| } |
| }, |
| "type": "object", |
| "description": "Video segment." |
| }, |
| "GoogleRpc_Status": { |
| "type": "object", |
| "description": "The `Status` type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by [gRPC](https://github.com/grpc). Each `Status` message contains three pieces of data: error code, error message, and error details. You can find out more about this error model and how to work with it in the [API Design Guide](https://cloud.google.com/apis/design/errors).", |
| "properties": { |
| "message": { |
| "description": "A developer-facing error message, which should be in English. Any user-facing error message should be localized and sent in the google.rpc.Status.details field, or localized by the client.", |
| "type": "string" |
| }, |
| "details": { |
| "type": "array", |
| "items": { |
| "type": "object", |
| "additionalProperties": { |
| "type": "any", |
| "description": "Properties of the object. Contains field @type with type URL." |
| } |
| }, |
| "description": "A list of messages that carry the error details. There is a common set of message types for APIs to use." |
| }, |
| "code": { |
| "description": "The status code, which should be an enum value of google.rpc.Code.", |
| "type": "integer", |
| "format": "int32" |
| } |
| }, |
| "id": "GoogleRpc_Status" |
| }, |
| "GoogleCloudVideointelligenceV1p3beta1_NormalizedBoundingBox": { |
| "description": "Normalized bounding box. The normalized vertex coordinates are relative to the original image. Range: [0, 1].", |
| "type": "object", |
| "id": "GoogleCloudVideointelligenceV1p3beta1_NormalizedBoundingBox", |
| "properties": { |
| "bottom": { |
| "description": "Bottom Y coordinate.", |
| "type": "number", |
| "format": "float" |
| }, |
| "left": { |
| "type": "number", |
| "description": "Left X coordinate.", |
| "format": "float" |
| }, |
| "top": { |
| "type": "number", |
| "format": "float", |
| "description": "Top Y coordinate." |
| }, |
| "right": { |
| "type": "number", |
| "format": "float", |
| "description": "Right X coordinate." |
| } |
| } |
| }, |
| "GoogleCloudVideointelligenceV1p1beta1_SpeechRecognitionAlternative": { |
| "id": "GoogleCloudVideointelligenceV1p1beta1_SpeechRecognitionAlternative", |
| "type": "object", |
| "description": "Alternative hypotheses (a.k.a. n-best list).", |
| "properties": { |
| "confidence": { |
| "format": "float", |
| "description": "Output only. The confidence estimate between 0.0 and 1.0. A higher number indicates an estimated greater likelihood that the recognized words are correct. This field is set only for the top alternative. This field is not guaranteed to be accurate and users should not rely on it to be always provided. The default of 0.0 is a sentinel value indicating `confidence` was not set.", |
| "type": "number", |
| "readOnly": true |
| }, |
| "words": { |
| "readOnly": true, |
| "description": "Output only. A list of word-specific information for each recognized word. Note: When `enable_speaker_diarization` is set to true, you will see all the words from the beginning of the audio.", |
| "type": "array", |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1p1beta1_WordInfo" |
| } |
| }, |
| "transcript": { |
| "type": "string", |
| "description": "Transcript text representing the words that the user spoke." |
| } |
| } |
| }, |
| "GoogleCloudVideointelligenceV1p3beta1_StreamingVideoAnnotationResults": { |
| "properties": { |
| "objectAnnotations": { |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1p3beta1_ObjectTrackingAnnotation" |
| }, |
| "description": "Object tracking results.", |
| "type": "array" |
| }, |
| "explicitAnnotation": { |
| "description": "Explicit content annotation results.", |
| "$ref": "GoogleCloudVideointelligenceV1p3beta1_ExplicitContentAnnotation" |
| }, |
| "shotAnnotations": { |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1p3beta1_VideoSegment" |
| }, |
| "type": "array", |
| "description": "Shot annotation results. Each shot is represented as a video segment." |
| }, |
| "frameTimestamp": { |
| "type": "string", |
| "format": "google-duration", |
| "description": "Timestamp of the processed frame in microseconds." |
| }, |
| "labelAnnotations": { |
| "description": "Label annotation results.", |
| "type": "array", |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1p3beta1_LabelAnnotation" |
| } |
| } |
| }, |
| "id": "GoogleCloudVideointelligenceV1p3beta1_StreamingVideoAnnotationResults", |
| "type": "object", |
| "description": "Streaming annotation results corresponding to a portion of the video that is currently being processed. Only ONE type of annotation will be specified in the response." |
| }, |
| "GoogleCloudVideointelligenceV1_TimestampedObject": { |
| "id": "GoogleCloudVideointelligenceV1_TimestampedObject", |
| "properties": { |
| "landmarks": { |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1_DetectedLandmark" |
| }, |
| "type": "array", |
| "description": "Optional. The detected landmarks." |
| }, |
| "timeOffset": { |
| "description": "Time-offset, relative to the beginning of the video, corresponding to the video frame for this object.", |
| "type": "string", |
| "format": "google-duration" |
| }, |
| "attributes": { |
| "description": "Optional. The attributes of the object in the bounding box.", |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1_DetectedAttribute" |
| }, |
| "type": "array" |
| }, |
| "normalizedBoundingBox": { |
| "$ref": "GoogleCloudVideointelligenceV1_NormalizedBoundingBox", |
| "description": "Normalized Bounding box in a frame, where the object is located." |
| } |
| }, |
| "type": "object", |
| "description": "For tracking related features. An object at time_offset with attributes, and located with normalized_bounding_box." |
| }, |
| "GoogleCloudVideointelligenceV1p2beta1_TextAnnotation": { |
| "type": "object", |
| "description": "Annotations related to one detected OCR text snippet. This will contain the corresponding text, confidence value, and frame level information for each detection.", |
| "id": "GoogleCloudVideointelligenceV1p2beta1_TextAnnotation", |
| "properties": { |
| "segments": { |
| "type": "array", |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1p2beta1_TextSegment" |
| }, |
| "description": "All video segments where OCR detected text appears." |
| }, |
| "text": { |
| "type": "string", |
| "description": "The detected text." |
| }, |
| "version": { |
| "type": "string", |
| "description": "Feature version." |
| } |
| } |
| }, |
| "GoogleCloudVideointelligenceV1_ExplicitContentAnnotation": { |
| "description": "Explicit content annotation (based on per-frame visual signals only). If no explicit content has been detected in a frame, no annotations are present for that frame.", |
| "type": "object", |
| "id": "GoogleCloudVideointelligenceV1_ExplicitContentAnnotation", |
| "properties": { |
| "version": { |
| "type": "string", |
| "description": "Feature version." |
| }, |
| "frames": { |
| "description": "All video frames where explicit content was detected.", |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1_ExplicitContentFrame" |
| }, |
| "type": "array" |
| } |
| } |
| }, |
| "GoogleCloudVideointelligenceV1_VideoSegment": { |
| "description": "Video segment.", |
| "id": "GoogleCloudVideointelligenceV1_VideoSegment", |
| "properties": { |
| "startTimeOffset": { |
| "description": "Time-offset, relative to the beginning of the video, corresponding to the start of the segment (inclusive).", |
| "type": "string", |
| "format": "google-duration" |
| }, |
| "endTimeOffset": { |
| "format": "google-duration", |
| "description": "Time-offset, relative to the beginning of the video, corresponding to the end of the segment (inclusive).", |
| "type": "string" |
| } |
| }, |
| "type": "object" |
| }, |
| "GoogleCloudVideointelligenceV1beta2_SpeechTranscription": { |
| "id": "GoogleCloudVideointelligenceV1beta2_SpeechTranscription", |
| "properties": { |
| "languageCode": { |
| "readOnly": true, |
| "description": "Output only. The [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tag of the language in this result. This language code was detected to have the most likelihood of being spoken in the audio.", |
| "type": "string" |
| }, |
| "alternatives": { |
| "description": "May contain one or more recognition hypotheses (up to the maximum specified in `max_alternatives`). These alternatives are ordered in terms of accuracy, with the top (first) alternative being the most probable, as ranked by the recognizer.", |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1beta2_SpeechRecognitionAlternative" |
| }, |
| "type": "array" |
| } |
| }, |
| "description": "A speech recognition result corresponding to a portion of the audio.", |
| "type": "object" |
| }, |
| "GoogleCloudVideointelligenceV1p3beta1_TextDetectionConfig": { |
| "description": "Config for TEXT_DETECTION.", |
| "type": "object", |
| "id": "GoogleCloudVideointelligenceV1p3beta1_TextDetectionConfig", |
| "properties": { |
| "languageHints": { |
| "items": { |
| "type": "string" |
| }, |
| "type": "array", |
| "description": "Language hint can be specified if the language to be detected is known a priori. It can increase the accuracy of the detection. Language hint must be language code in BCP-47 format. Automatic language detection is performed if no hint is provided." |
| }, |
| "model": { |
| "description": "Model to use for text detection. Supported values: \"builtin/stable\" (the default if unset) and \"builtin/latest\".", |
| "type": "string" |
| } |
| } |
| }, |
| "GoogleCloudVideointelligenceV1p1beta1_LabelFrame": { |
| "id": "GoogleCloudVideointelligenceV1p1beta1_LabelFrame", |
| "type": "object", |
| "description": "Video frame level annotation results for label detection.", |
| "properties": { |
| "timeOffset": { |
| "type": "string", |
| "format": "google-duration", |
| "description": "Time-offset, relative to the beginning of the video, corresponding to the video frame for this location." |
| }, |
| "confidence": { |
| "type": "number", |
| "format": "float", |
| "description": "Confidence that the label is accurate. Range: [0, 1]." |
| } |
| } |
| }, |
| "GoogleCloudVideointelligenceV1p2beta1_ExplicitContentAnnotation": { |
| "id": "GoogleCloudVideointelligenceV1p2beta1_ExplicitContentAnnotation", |
| "properties": { |
| "version": { |
| "type": "string", |
| "description": "Feature version." |
| }, |
| "frames": { |
| "description": "All video frames where explicit content was detected.", |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1p2beta1_ExplicitContentFrame" |
| }, |
| "type": "array" |
| } |
| }, |
| "type": "object", |
| "description": "Explicit content annotation (based on per-frame visual signals only). If no explicit content has been detected in a frame, no annotations are present for that frame." |
| }, |
| "GoogleCloudVideointelligenceV1p3beta1_FaceDetectionAnnotation": { |
| "type": "object", |
| "id": "GoogleCloudVideointelligenceV1p3beta1_FaceDetectionAnnotation", |
| "description": "Face detection annotation.", |
| "properties": { |
| "version": { |
| "type": "string", |
| "description": "Feature version." |
| } |
| } |
| }, |
| "GoogleCloudVideointelligenceV1_NormalizedVertex": { |
| "description": "A vertex represents a 2D point in the image. NOTE: the normalized vertex coordinates are relative to the original image and range from 0 to 1.", |
| "type": "object", |
| "id": "GoogleCloudVideointelligenceV1_NormalizedVertex", |
| "properties": { |
| "x": { |
| "description": "X coordinate.", |
| "format": "float", |
| "type": "number" |
| }, |
| "y": { |
| "type": "number", |
| "format": "float", |
| "description": "Y coordinate." |
| } |
| } |
| }, |
| "GoogleCloudVideointelligenceV1p3beta1_FaceFrame": { |
| "id": "GoogleCloudVideointelligenceV1p3beta1_FaceFrame", |
| "type": "object", |
| "properties": { |
| "timeOffset": { |
| "type": "string", |
| "format": "google-duration", |
| "description": "Time-offset, relative to the beginning of the video, corresponding to the video frame for this location." |
| }, |
| "normalizedBoundingBoxes": { |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1p3beta1_NormalizedBoundingBox" |
| }, |
| "description": "Normalized Bounding boxes in a frame. There can be more than one boxes if the same face is detected in multiple locations within the current frame.", |
| "type": "array" |
| } |
| }, |
| "description": "Deprecated. No effect." |
| }, |
| "GoogleCloudVideointelligenceV1p2beta1_NormalizedVertex": { |
| "properties": { |
| "y": { |
| "type": "number", |
| "description": "Y coordinate.", |
| "format": "float" |
| }, |
| "x": { |
| "description": "X coordinate.", |
| "format": "float", |
| "type": "number" |
| } |
| }, |
| "description": "A vertex represents a 2D point in the image. NOTE: the normalized vertex coordinates are relative to the original image and range from 0 to 1.", |
| "id": "GoogleCloudVideointelligenceV1p2beta1_NormalizedVertex", |
| "type": "object" |
| }, |
| "GoogleCloudVideointelligenceV1p2beta1_ObjectTrackingFrame": { |
| "properties": { |
| "timeOffset": { |
| "format": "google-duration", |
| "description": "The timestamp of the frame in microseconds.", |
| "type": "string" |
| }, |
| "normalizedBoundingBox": { |
| "$ref": "GoogleCloudVideointelligenceV1p2beta1_NormalizedBoundingBox", |
| "description": "The normalized bounding box location of this object track for the frame." |
| } |
| }, |
| "description": "Video frame level annotations for object detection and tracking. This field stores per frame location, time offset, and confidence.", |
| "type": "object", |
| "id": "GoogleCloudVideointelligenceV1p2beta1_ObjectTrackingFrame" |
| }, |
| "GoogleCloudVideointelligenceV1_VideoAnnotationProgress": { |
| "id": "GoogleCloudVideointelligenceV1_VideoAnnotationProgress", |
| "properties": { |
| "startTime": { |
| "type": "string", |
| "description": "Time when the request was received.", |
| "format": "google-datetime" |
| }, |
| "inputUri": { |
| "description": "Video file location in [Cloud Storage](https://cloud.google.com/storage/).", |
| "type": "string" |
| }, |
| "updateTime": { |
| "format": "google-datetime", |
| "type": "string", |
| "description": "Time of the most recent update." |
| }, |
| "feature": { |
| "enumDescriptions": [ |
| "Unspecified.", |
| "Label detection. Detect objects, such as dog or flower.", |
| "Shot change detection.", |
| "Explicit content detection.", |
| "Human face detection.", |
| "Speech transcription.", |
| "OCR text detection and tracking.", |
| "Object detection and tracking.", |
| "Logo detection, tracking, and recognition.", |
| "Person detection." |
| ], |
| "type": "string", |
| "enum": [ |
| "FEATURE_UNSPECIFIED", |
| "LABEL_DETECTION", |
| "SHOT_CHANGE_DETECTION", |
| "EXPLICIT_CONTENT_DETECTION", |
| "FACE_DETECTION", |
| "SPEECH_TRANSCRIPTION", |
| "TEXT_DETECTION", |
| "OBJECT_TRACKING", |
| "LOGO_RECOGNITION", |
| "PERSON_DETECTION" |
| ], |
| "description": "Specifies which feature is being tracked if the request contains more than one feature." |
| }, |
| "segment": { |
| "description": "Specifies which segment is being tracked if the request contains more than one segment.", |
| "$ref": "GoogleCloudVideointelligenceV1_VideoSegment" |
| }, |
| "progressPercent": { |
| "type": "integer", |
| "format": "int32", |
| "description": "Approximate percentage processed thus far. Guaranteed to be 100 when fully processed." |
| } |
| }, |
| "description": "Annotation progress for a single video.", |
| "type": "object" |
| }, |
| "GoogleCloudVideointelligenceV1beta2_WordInfo": { |
| "id": "GoogleCloudVideointelligenceV1beta2_WordInfo", |
| "properties": { |
| "speakerTag": { |
| "format": "int32", |
| "description": "Output only. A distinct integer value is assigned for every speaker within the audio. This field specifies which one of those speakers was detected to have spoken this word. Value ranges from 1 up to diarization_speaker_count, and is only set if speaker diarization is enabled.", |
| "type": "integer", |
| "readOnly": true |
| }, |
| "endTime": { |
| "format": "google-duration", |
| "type": "string", |
| "description": "Time offset relative to the beginning of the audio, and corresponding to the end of the spoken word. This field is only set if `enable_word_time_offsets=true` and only in the top hypothesis. This is an experimental feature and the accuracy of the time offset can vary." |
| }, |
| "startTime": { |
| "format": "google-duration", |
| "type": "string", |
| "description": "Time offset relative to the beginning of the audio, and corresponding to the start of the spoken word. This field is only set if `enable_word_time_offsets=true` and only in the top hypothesis. This is an experimental feature and the accuracy of the time offset can vary." |
| }, |
| "word": { |
| "description": "The word corresponding to this set of information.", |
| "type": "string" |
| }, |
| "confidence": { |
| "format": "float", |
| "description": "Output only. The confidence estimate between 0.0 and 1.0. A higher number indicates an estimated greater likelihood that the recognized words are correct. This field is set only for the top alternative. This field is not guaranteed to be accurate and users should not rely on it to be always provided. The default of 0.0 is a sentinel value indicating `confidence` was not set.", |
| "readOnly": true, |
| "type": "number" |
| } |
| }, |
| "description": "Word-specific information for recognized words. Word information is only included in the response when certain request parameters are set, such as `enable_word_time_offsets`.", |
| "type": "object" |
| }, |
| "GoogleCloudVideointelligenceV1beta2_TimestampedObject": { |
| "id": "GoogleCloudVideointelligenceV1beta2_TimestampedObject", |
| "properties": { |
| "attributes": { |
| "type": "array", |
| "description": "Optional. The attributes of the object in the bounding box.", |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1beta2_DetectedAttribute" |
| } |
| }, |
| "normalizedBoundingBox": { |
| "description": "Normalized Bounding box in a frame, where the object is located.", |
| "$ref": "GoogleCloudVideointelligenceV1beta2_NormalizedBoundingBox" |
| }, |
| "landmarks": { |
| "description": "Optional. The detected landmarks.", |
| "type": "array", |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1beta2_DetectedLandmark" |
| } |
| }, |
| "timeOffset": { |
| "type": "string", |
| "description": "Time-offset, relative to the beginning of the video, corresponding to the video frame for this object.", |
| "format": "google-duration" |
| } |
| }, |
| "type": "object", |
| "description": "For tracking related features. An object at time_offset with attributes, and located with normalized_bounding_box." |
| }, |
| "GoogleCloudVideointelligenceV1p1beta1_NormalizedVertex": { |
| "properties": { |
| "x": { |
| "description": "X coordinate.", |
| "type": "number", |
| "format": "float" |
| }, |
| "y": { |
| "description": "Y coordinate.", |
| "format": "float", |
| "type": "number" |
| } |
| }, |
| "type": "object", |
| "id": "GoogleCloudVideointelligenceV1p1beta1_NormalizedVertex", |
| "description": "A vertex represents a 2D point in the image. NOTE: the normalized vertex coordinates are relative to the original image and range from 0 to 1." |
| }, |
| "GoogleCloudVideointelligenceV1p2beta1_PersonDetectionAnnotation": { |
| "properties": { |
| "version": { |
| "type": "string", |
| "description": "Feature version." |
| }, |
| "tracks": { |
| "type": "array", |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1p2beta1_Track" |
| }, |
| "description": "The detected tracks of a person." |
| } |
| }, |
| "id": "GoogleCloudVideointelligenceV1p2beta1_PersonDetectionAnnotation", |
| "description": "Person detection annotation per video.", |
| "type": "object" |
| }, |
| "GoogleCloudVideointelligenceV1_TextFrame": { |
| "type": "object", |
| "description": "Video frame level annotation results for text annotation (OCR). Contains information regarding timestamp and bounding box locations for the frames containing detected OCR text snippets.", |
| "id": "GoogleCloudVideointelligenceV1_TextFrame", |
| "properties": { |
| "rotatedBoundingBox": { |
| "$ref": "GoogleCloudVideointelligenceV1_NormalizedBoundingPoly", |
| "description": "Bounding polygon of the detected text for this frame." |
| }, |
| "timeOffset": { |
| "format": "google-duration", |
| "description": "Timestamp of this frame.", |
| "type": "string" |
| } |
| } |
| }, |
| "GoogleCloudVideointelligenceV1beta2_FaceDetectionAnnotation": { |
| "properties": { |
| "version": { |
| "description": "Feature version.", |
| "type": "string" |
| } |
| }, |
| "type": "object", |
| "description": "Face detection annotation.", |
| "id": "GoogleCloudVideointelligenceV1beta2_FaceDetectionAnnotation" |
| }, |
| "GoogleCloudVideointelligenceV1_NormalizedBoundingPoly": { |
| "type": "object", |
| "description": "Normalized bounding polygon for text (that might not be aligned with axis). Contains list of the corner points in clockwise order starting from top-left corner. For example, for a rectangular bounding box: When the text is horizontal it might look like: 0----1 | | 3----2 When it's clockwise rotated 180 degrees around the top-left corner it becomes: 2----3 | | 1----0 and the vertex order will still be (0, 1, 2, 3). Note that values can be less than 0, or greater than 1 due to trignometric calculations for location of the box.", |
| "id": "GoogleCloudVideointelligenceV1_NormalizedBoundingPoly", |
| "properties": { |
| "vertices": { |
| "type": "array", |
| "description": "Normalized vertices of the bounding polygon.", |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1_NormalizedVertex" |
| } |
| } |
| } |
| }, |
| "GoogleCloudVideointelligenceV1p2beta1_Entity": { |
| "description": "Detected entity from video analysis.", |
| "properties": { |
| "entityId": { |
| "description": "Opaque entity ID. Some IDs may be available in [Google Knowledge Graph Search API](https://developers.google.com/knowledge-graph/).", |
| "type": "string" |
| }, |
| "languageCode": { |
| "type": "string", |
| "description": "Language code for `description` in BCP-47 format." |
| }, |
| "description": { |
| "description": "Textual description, e.g., `Fixed-gear bicycle`.", |
| "type": "string" |
| } |
| }, |
| "type": "object", |
| "id": "GoogleCloudVideointelligenceV1p2beta1_Entity" |
| }, |
| "GoogleCloudVideointelligenceV1p1beta1_SpeechTranscription": { |
| "type": "object", |
| "properties": { |
| "languageCode": { |
| "readOnly": true, |
| "description": "Output only. The [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tag of the language in this result. This language code was detected to have the most likelihood of being spoken in the audio.", |
| "type": "string" |
| }, |
| "alternatives": { |
| "type": "array", |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1p1beta1_SpeechRecognitionAlternative" |
| }, |
| "description": "May contain one or more recognition hypotheses (up to the maximum specified in `max_alternatives`). These alternatives are ordered in terms of accuracy, with the top (first) alternative being the most probable, as ranked by the recognizer." |
| } |
| }, |
| "description": "A speech recognition result corresponding to a portion of the audio.", |
| "id": "GoogleCloudVideointelligenceV1p1beta1_SpeechTranscription" |
| }, |
| "GoogleCloudVideointelligenceV1_TextSegment": { |
| "id": "GoogleCloudVideointelligenceV1_TextSegment", |
| "description": "Video segment level annotation results for text detection.", |
| "properties": { |
| "segment": { |
| "description": "Video segment where a text snippet was detected.", |
| "$ref": "GoogleCloudVideointelligenceV1_VideoSegment" |
| }, |
| "confidence": { |
| "format": "float", |
| "description": "Confidence for the track of detected text. It is calculated as the highest over all frames where OCR detected text appears.", |
| "type": "number" |
| }, |
| "frames": { |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1_TextFrame" |
| }, |
| "type": "array", |
| "description": "Information related to the frames where OCR detected text appears." |
| } |
| }, |
| "type": "object" |
| }, |
| "GoogleCloudVideointelligenceV1p3beta1_AnnotateVideoResponse": { |
| "description": "Video annotation response. Included in the `response` field of the `Operation` returned by the `GetOperation` call of the `google::longrunning::Operations` service.", |
| "type": "object", |
| "id": "GoogleCloudVideointelligenceV1p3beta1_AnnotateVideoResponse", |
| "properties": { |
| "annotationResults": { |
| "description": "Annotation results for all videos specified in `AnnotateVideoRequest`.", |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1p3beta1_VideoAnnotationResults" |
| }, |
| "type": "array" |
| } |
| } |
| }, |
| "GoogleCloudVideointelligenceV1p2beta1_LogoRecognitionAnnotation": { |
| "type": "object", |
| "description": "Annotation corresponding to one detected, tracked and recognized logo class.", |
| "id": "GoogleCloudVideointelligenceV1p2beta1_LogoRecognitionAnnotation", |
| "properties": { |
| "segments": { |
| "description": "All video segments where the recognized logo appears. There might be multiple instances of the same logo class appearing in one VideoSegment.", |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1p2beta1_VideoSegment" |
| }, |
| "type": "array" |
| }, |
| "tracks": { |
| "description": "All logo tracks where the recognized logo appears. Each track corresponds to one logo instance appearing in consecutive frames.", |
| "type": "array", |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1p2beta1_Track" |
| } |
| }, |
| "entity": { |
| "description": "Entity category information to specify the logo class that all the logo tracks within this LogoRecognitionAnnotation are recognized as.", |
| "$ref": "GoogleCloudVideointelligenceV1p2beta1_Entity" |
| } |
| } |
| }, |
| "GoogleCloudVideointelligenceV1p3beta1_PersonDetectionConfig": { |
| "type": "object", |
| "description": "Config for PERSON_DETECTION.", |
| "properties": { |
| "includePoseLandmarks": { |
| "description": "Whether to enable pose landmarks detection. Ignored if 'include_bounding_boxes' is set to false.", |
| "type": "boolean" |
| }, |
| "includeAttributes": { |
| "description": "Whether to enable person attributes detection, such as cloth color (black, blue, etc), type (coat, dress, etc), pattern (plain, floral, etc), hair, etc. Ignored if 'include_bounding_boxes' is set to false.", |
| "type": "boolean" |
| }, |
| "includeBoundingBoxes": { |
| "description": "Whether bounding boxes are included in the person detection annotation output.", |
| "type": "boolean" |
| } |
| }, |
| "id": "GoogleCloudVideointelligenceV1p3beta1_PersonDetectionConfig" |
| }, |
| "GoogleCloudVideointelligenceV1_DetectedLandmark": { |
| "description": "A generic detected landmark represented by name in string format and a 2D location.", |
| "type": "object", |
| "id": "GoogleCloudVideointelligenceV1_DetectedLandmark", |
| "properties": { |
| "confidence": { |
| "description": "The confidence score of the detected landmark. Range [0, 1].", |
| "type": "number", |
| "format": "float" |
| }, |
| "name": { |
| "description": "The name of this landmark, for example, left_hand, right_shoulder.", |
| "type": "string" |
| }, |
| "point": { |
| "$ref": "GoogleCloudVideointelligenceV1_NormalizedVertex", |
| "description": "The 2D point of the detected landmark using the normalized image coordindate system. The normalized coordinates have the range from 0 to 1." |
| } |
| } |
| }, |
| "GoogleCloudVideointelligenceV1p3beta1_StreamingAnnotateVideoResponse": { |
| "description": "`StreamingAnnotateVideoResponse` is the only message returned to the client by `StreamingAnnotateVideo`. A series of zero or more `StreamingAnnotateVideoResponse` messages are streamed back to the client.", |
| "type": "object", |
| "properties": { |
| "error": { |
| "description": "If set, returns a google.rpc.Status message that specifies the error for the operation.", |
| "$ref": "GoogleRpc_Status" |
| }, |
| "annotationResults": { |
| "description": "Streaming annotation results.", |
| "$ref": "GoogleCloudVideointelligenceV1p3beta1_StreamingVideoAnnotationResults" |
| }, |
| "annotationResultsUri": { |
| "type": "string", |
| "description": "Google Cloud Storage URI that stores annotation results of one streaming session in JSON format. It is the annotation_result_storage_directory from the request followed by '/cloud_project_number-session_id'." |
| } |
| }, |
| "id": "GoogleCloudVideointelligenceV1p3beta1_StreamingAnnotateVideoResponse" |
| }, |
| "GoogleCloudVideointelligenceV1p2beta1_SpeechTranscription": { |
| "type": "object", |
| "id": "GoogleCloudVideointelligenceV1p2beta1_SpeechTranscription", |
| "properties": { |
| "alternatives": { |
| "type": "array", |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1p2beta1_SpeechRecognitionAlternative" |
| }, |
| "description": "May contain one or more recognition hypotheses (up to the maximum specified in `max_alternatives`). These alternatives are ordered in terms of accuracy, with the top (first) alternative being the most probable, as ranked by the recognizer." |
| }, |
| "languageCode": { |
| "type": "string", |
| "description": "Output only. The [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tag of the language in this result. This language code was detected to have the most likelihood of being spoken in the audio.", |
| "readOnly": true |
| } |
| }, |
| "description": "A speech recognition result corresponding to a portion of the audio." |
| }, |
| "GoogleCloudVideointelligenceV1beta2_DetectedLandmark": { |
| "properties": { |
| "name": { |
| "description": "The name of this landmark, for example, left_hand, right_shoulder.", |
| "type": "string" |
| }, |
| "confidence": { |
| "description": "The confidence score of the detected landmark. Range [0, 1].", |
| "type": "number", |
| "format": "float" |
| }, |
| "point": { |
| "description": "The 2D point of the detected landmark using the normalized image coordindate system. The normalized coordinates have the range from 0 to 1.", |
| "$ref": "GoogleCloudVideointelligenceV1beta2_NormalizedVertex" |
| } |
| }, |
| "type": "object", |
| "id": "GoogleCloudVideointelligenceV1beta2_DetectedLandmark", |
| "description": "A generic detected landmark represented by name in string format and a 2D location." |
| }, |
| "GoogleCloudVideointelligenceV1p1beta1_Track": { |
| "type": "object", |
| "properties": { |
| "timestampedObjects": { |
| "type": "array", |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1p1beta1_TimestampedObject" |
| }, |
| "description": "The object with timestamp and attributes per frame in the track." |
| }, |
| "segment": { |
| "description": "Video segment of a track.", |
| "$ref": "GoogleCloudVideointelligenceV1p1beta1_VideoSegment" |
| }, |
| "attributes": { |
| "type": "array", |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1p1beta1_DetectedAttribute" |
| }, |
| "description": "Optional. Attributes in the track level." |
| }, |
| "confidence": { |
| "description": "Optional. The confidence score of the tracked object.", |
| "type": "number", |
| "format": "float" |
| } |
| }, |
| "description": "A track of an object instance.", |
| "id": "GoogleCloudVideointelligenceV1p1beta1_Track" |
| }, |
| "GoogleCloudVideointelligenceV1p1beta1_FaceAnnotation": { |
| "description": "Deprecated. No effect.", |
| "type": "object", |
| "properties": { |
| "segments": { |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1p1beta1_FaceSegment" |
| }, |
| "description": "All video segments where a face was detected.", |
| "type": "array" |
| }, |
| "thumbnail": { |
| "format": "byte", |
| "type": "string", |
| "description": "Thumbnail of a representative face view (in JPEG format)." |
| }, |
| "frames": { |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1p1beta1_FaceFrame" |
| }, |
| "type": "array", |
| "description": "All video frames where a face was detected." |
| } |
| }, |
| "id": "GoogleCloudVideointelligenceV1p1beta1_FaceAnnotation" |
| }, |
| "GoogleCloudVideointelligenceV1p2beta1_FaceAnnotation": { |
| "description": "Deprecated. No effect.", |
| "id": "GoogleCloudVideointelligenceV1p2beta1_FaceAnnotation", |
| "properties": { |
| "thumbnail": { |
| "format": "byte", |
| "description": "Thumbnail of a representative face view (in JPEG format).", |
| "type": "string" |
| }, |
| "segments": { |
| "description": "All video segments where a face was detected.", |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1p2beta1_FaceSegment" |
| }, |
| "type": "array" |
| }, |
| "frames": { |
| "type": "array", |
| "description": "All video frames where a face was detected.", |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1p2beta1_FaceFrame" |
| } |
| } |
| }, |
| "type": "object" |
| }, |
| "GoogleCloudVideointelligenceV1p2beta1_AnnotateVideoProgress": { |
| "type": "object", |
| "id": "GoogleCloudVideointelligenceV1p2beta1_AnnotateVideoProgress", |
| "description": "Video annotation progress. Included in the `metadata` field of the `Operation` returned by the `GetOperation` call of the `google::longrunning::Operations` service.", |
| "properties": { |
| "annotationProgress": { |
| "type": "array", |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1p2beta1_VideoAnnotationProgress" |
| }, |
| "description": "Progress metadata for all videos specified in `AnnotateVideoRequest`." |
| } |
| } |
| }, |
| "GoogleCloudVideointelligenceV1p1beta1_ObjectTrackingAnnotation": { |
| "type": "object", |
| "id": "GoogleCloudVideointelligenceV1p1beta1_ObjectTrackingAnnotation", |
| "properties": { |
| "entity": { |
| "description": "Entity to specify the object category that this track is labeled as.", |
| "$ref": "GoogleCloudVideointelligenceV1p1beta1_Entity" |
| }, |
| "trackId": { |
| "format": "int64", |
| "type": "string", |
| "description": "Streaming mode ONLY. In streaming mode, we do not know the end time of a tracked object before it is completed. Hence, there is no VideoSegment info returned. Instead, we provide a unique identifiable integer track_id so that the customers can correlate the results of the ongoing ObjectTrackAnnotation of the same track_id over time." |
| }, |
| "frames": { |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1p1beta1_ObjectTrackingFrame" |
| }, |
| "type": "array", |
| "description": "Information corresponding to all frames where this object track appears. Non-streaming batch mode: it may be one or multiple ObjectTrackingFrame messages in frames. Streaming mode: it can only be one ObjectTrackingFrame message in frames." |
| }, |
| "segment": { |
| "$ref": "GoogleCloudVideointelligenceV1p1beta1_VideoSegment", |
| "description": "Non-streaming batch mode ONLY. Each object track corresponds to one video segment where it appears." |
| }, |
| "version": { |
| "description": "Feature version.", |
| "type": "string" |
| }, |
| "confidence": { |
| "format": "float", |
| "description": "Object category's labeling confidence of this track.", |
| "type": "number" |
| } |
| }, |
| "description": "Annotations corresponding to one tracked object." |
| }, |
| "GoogleCloudVideointelligenceV1p1beta1_DetectedLandmark": { |
| "type": "object", |
| "description": "A generic detected landmark represented by name in string format and a 2D location.", |
| "id": "GoogleCloudVideointelligenceV1p1beta1_DetectedLandmark", |
| "properties": { |
| "confidence": { |
| "description": "The confidence score of the detected landmark. Range [0, 1].", |
| "type": "number", |
| "format": "float" |
| }, |
| "point": { |
| "description": "The 2D point of the detected landmark using the normalized image coordindate system. The normalized coordinates have the range from 0 to 1.", |
| "$ref": "GoogleCloudVideointelligenceV1p1beta1_NormalizedVertex" |
| }, |
| "name": { |
| "type": "string", |
| "description": "The name of this landmark, for example, left_hand, right_shoulder." |
| } |
| } |
| }, |
| "GoogleCloudVideointelligenceV1beta2_NormalizedVertex": { |
| "id": "GoogleCloudVideointelligenceV1beta2_NormalizedVertex", |
| "properties": { |
| "y": { |
| "description": "Y coordinate.", |
| "type": "number", |
| "format": "float" |
| }, |
| "x": { |
| "description": "X coordinate.", |
| "format": "float", |
| "type": "number" |
| } |
| }, |
| "type": "object", |
| "description": "A vertex represents a 2D point in the image. NOTE: the normalized vertex coordinates are relative to the original image and range from 0 to 1." |
| }, |
| "GoogleCloudVideointelligenceV1p3beta1_DetectedAttribute": { |
| "properties": { |
| "confidence": { |
| "type": "number", |
| "description": "Detected attribute confidence. Range [0, 1].", |
| "format": "float" |
| }, |
| "value": { |
| "type": "string", |
| "description": "Text value of the detection result. For example, the value for \"HairColor\" can be \"black\", \"blonde\", etc." |
| }, |
| "name": { |
| "description": "The name of the attribute, for example, glasses, dark_glasses, mouth_open. A full list of supported type names will be provided in the document.", |
| "type": "string" |
| } |
| }, |
| "id": "GoogleCloudVideointelligenceV1p3beta1_DetectedAttribute", |
| "description": "A generic detected attribute represented by name in string format.", |
| "type": "object" |
| }, |
| "GoogleCloudVideointelligenceV1p3beta1_Entity": { |
| "id": "GoogleCloudVideointelligenceV1p3beta1_Entity", |
| "properties": { |
| "entityId": { |
| "type": "string", |
| "description": "Opaque entity ID. Some IDs may be available in [Google Knowledge Graph Search API](https://developers.google.com/knowledge-graph/)." |
| }, |
| "languageCode": { |
| "type": "string", |
| "description": "Language code for `description` in BCP-47 format." |
| }, |
| "description": { |
| "type": "string", |
| "description": "Textual description, e.g., `Fixed-gear bicycle`." |
| } |
| }, |
| "type": "object", |
| "description": "Detected entity from video analysis." |
| }, |
| "GoogleCloudVideointelligenceV1p3beta1_NormalizedVertex": { |
| "properties": { |
| "y": { |
| "type": "number", |
| "description": "Y coordinate.", |
| "format": "float" |
| }, |
| "x": { |
| "description": "X coordinate.", |
| "format": "float", |
| "type": "number" |
| } |
| }, |
| "description": "A vertex represents a 2D point in the image. NOTE: the normalized vertex coordinates are relative to the original image and range from 0 to 1.", |
| "type": "object", |
| "id": "GoogleCloudVideointelligenceV1p3beta1_NormalizedVertex" |
| }, |
| "GoogleCloudVideointelligenceV1p1beta1_LabelAnnotation": { |
| "type": "object", |
| "id": "GoogleCloudVideointelligenceV1p1beta1_LabelAnnotation", |
| "properties": { |
| "entity": { |
| "$ref": "GoogleCloudVideointelligenceV1p1beta1_Entity", |
| "description": "Detected entity." |
| }, |
| "frames": { |
| "description": "All video frames where a label was detected.", |
| "type": "array", |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1p1beta1_LabelFrame" |
| } |
| }, |
| "version": { |
| "description": "Feature version.", |
| "type": "string" |
| }, |
| "segments": { |
| "type": "array", |
| "description": "All video segments where a label was detected.", |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1p1beta1_LabelSegment" |
| } |
| }, |
| "categoryEntities": { |
| "type": "array", |
| "description": "Common categories for the detected entity. For example, when the label is `Terrier`, the category is likely `dog`. And in some cases there might be more than one categories e.g., `Terrier` could also be a `pet`.", |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1p1beta1_Entity" |
| } |
| } |
| }, |
| "description": "Label annotation." |
| }, |
| "GoogleCloudVideointelligenceV1beta2_ObjectTrackingFrame": { |
| "type": "object", |
| "id": "GoogleCloudVideointelligenceV1beta2_ObjectTrackingFrame", |
| "description": "Video frame level annotations for object detection and tracking. This field stores per frame location, time offset, and confidence.", |
| "properties": { |
| "normalizedBoundingBox": { |
| "description": "The normalized bounding box location of this object track for the frame.", |
| "$ref": "GoogleCloudVideointelligenceV1beta2_NormalizedBoundingBox" |
| }, |
| "timeOffset": { |
| "description": "The timestamp of the frame in microseconds.", |
| "format": "google-duration", |
| "type": "string" |
| } |
| } |
| }, |
| "GoogleCloudVideointelligenceV1p2beta1_WordInfo": { |
| "properties": { |
| "endTime": { |
| "type": "string", |
| "description": "Time offset relative to the beginning of the audio, and corresponding to the end of the spoken word. This field is only set if `enable_word_time_offsets=true` and only in the top hypothesis. This is an experimental feature and the accuracy of the time offset can vary.", |
| "format": "google-duration" |
| }, |
| "confidence": { |
| "type": "number", |
| "format": "float", |
| "description": "Output only. The confidence estimate between 0.0 and 1.0. A higher number indicates an estimated greater likelihood that the recognized words are correct. This field is set only for the top alternative. This field is not guaranteed to be accurate and users should not rely on it to be always provided. The default of 0.0 is a sentinel value indicating `confidence` was not set.", |
| "readOnly": true |
| }, |
| "word": { |
| "type": "string", |
| "description": "The word corresponding to this set of information." |
| }, |
| "startTime": { |
| "format": "google-duration", |
| "type": "string", |
| "description": "Time offset relative to the beginning of the audio, and corresponding to the start of the spoken word. This field is only set if `enable_word_time_offsets=true` and only in the top hypothesis. This is an experimental feature and the accuracy of the time offset can vary." |
| }, |
| "speakerTag": { |
| "description": "Output only. A distinct integer value is assigned for every speaker within the audio. This field specifies which one of those speakers was detected to have spoken this word. Value ranges from 1 up to diarization_speaker_count, and is only set if speaker diarization is enabled.", |
| "type": "integer", |
| "format": "int32", |
| "readOnly": true |
| } |
| }, |
| "type": "object", |
| "id": "GoogleCloudVideointelligenceV1p2beta1_WordInfo", |
| "description": "Word-specific information for recognized words. Word information is only included in the response when certain request parameters are set, such as `enable_word_time_offsets`." |
| }, |
| "GoogleCloudVideointelligenceV1_WordInfo": { |
| "type": "object", |
| "properties": { |
| "speakerTag": { |
| "format": "int32", |
| "readOnly": true, |
| "description": "Output only. A distinct integer value is assigned for every speaker within the audio. This field specifies which one of those speakers was detected to have spoken this word. Value ranges from 1 up to diarization_speaker_count, and is only set if speaker diarization is enabled.", |
| "type": "integer" |
| }, |
| "startTime": { |
| "format": "google-duration", |
| "description": "Time offset relative to the beginning of the audio, and corresponding to the start of the spoken word. This field is only set if `enable_word_time_offsets=true` and only in the top hypothesis. This is an experimental feature and the accuracy of the time offset can vary.", |
| "type": "string" |
| }, |
| "word": { |
| "description": "The word corresponding to this set of information.", |
| "type": "string" |
| }, |
| "confidence": { |
| "readOnly": true, |
| "description": "Output only. The confidence estimate between 0.0 and 1.0. A higher number indicates an estimated greater likelihood that the recognized words are correct. This field is set only for the top alternative. This field is not guaranteed to be accurate and users should not rely on it to be always provided. The default of 0.0 is a sentinel value indicating `confidence` was not set.", |
| "type": "number", |
| "format": "float" |
| }, |
| "endTime": { |
| "type": "string", |
| "description": "Time offset relative to the beginning of the audio, and corresponding to the end of the spoken word. This field is only set if `enable_word_time_offsets=true` and only in the top hypothesis. This is an experimental feature and the accuracy of the time offset can vary.", |
| "format": "google-duration" |
| } |
| }, |
| "id": "GoogleCloudVideointelligenceV1_WordInfo", |
| "description": "Word-specific information for recognized words. Word information is only included in the response when certain request parameters are set, such as `enable_word_time_offsets`." |
| }, |
| "GoogleCloudVideointelligenceV1beta2_FaceSegment": { |
| "type": "object", |
| "description": "Video segment level annotation results for face detection.", |
| "id": "GoogleCloudVideointelligenceV1beta2_FaceSegment", |
| "properties": { |
| "segment": { |
| "$ref": "GoogleCloudVideointelligenceV1beta2_VideoSegment", |
| "description": "Video segment where a face was detected." |
| } |
| } |
| }, |
| "GoogleCloudVideointelligenceV1_SpeechTranscription": { |
| "properties": { |
| "languageCode": { |
| "description": "Output only. The [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tag of the language in this result. This language code was detected to have the most likelihood of being spoken in the audio.", |
| "readOnly": true, |
| "type": "string" |
| }, |
| "alternatives": { |
| "description": "May contain one or more recognition hypotheses (up to the maximum specified in `max_alternatives`). These alternatives are ordered in terms of accuracy, with the top (first) alternative being the most probable, as ranked by the recognizer.", |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1_SpeechRecognitionAlternative" |
| }, |
| "type": "array" |
| } |
| }, |
| "type": "object", |
| "id": "GoogleCloudVideointelligenceV1_SpeechTranscription", |
| "description": "A speech recognition result corresponding to a portion of the audio." |
| }, |
| "GoogleCloudVideointelligenceV1p2beta1_VideoSegment": { |
| "id": "GoogleCloudVideointelligenceV1p2beta1_VideoSegment", |
| "type": "object", |
| "properties": { |
| "startTimeOffset": { |
| "format": "google-duration", |
| "type": "string", |
| "description": "Time-offset, relative to the beginning of the video, corresponding to the start of the segment (inclusive)." |
| }, |
| "endTimeOffset": { |
| "type": "string", |
| "format": "google-duration", |
| "description": "Time-offset, relative to the beginning of the video, corresponding to the end of the segment (inclusive)." |
| } |
| }, |
| "description": "Video segment." |
| }, |
| "GoogleCloudVideointelligenceV1_FaceAnnotation": { |
| "id": "GoogleCloudVideointelligenceV1_FaceAnnotation", |
| "description": "Deprecated. No effect.", |
| "type": "object", |
| "properties": { |
| "segments": { |
| "description": "All video segments where a face was detected.", |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1_FaceSegment" |
| }, |
| "type": "array" |
| }, |
| "frames": { |
| "type": "array", |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1_FaceFrame" |
| }, |
| "description": "All video frames where a face was detected." |
| }, |
| "thumbnail": { |
| "format": "byte", |
| "description": "Thumbnail of a representative face view (in JPEG format).", |
| "type": "string" |
| } |
| } |
| }, |
| "GoogleCloudVideointelligenceV1p3beta1_VideoAnnotationResults": { |
| "type": "object", |
| "description": "Annotation results for a single video.", |
| "properties": { |
| "logoRecognitionAnnotations": { |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1p3beta1_LogoRecognitionAnnotation" |
| }, |
| "description": "Annotations for list of logos detected, tracked and recognized in video.", |
| "type": "array" |
| }, |
| "personDetectionAnnotations": { |
| "description": "Person detection annotations.", |
| "type": "array", |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1p3beta1_PersonDetectionAnnotation" |
| } |
| }, |
| "explicitAnnotation": { |
| "description": "Explicit content annotation.", |
| "$ref": "GoogleCloudVideointelligenceV1p3beta1_ExplicitContentAnnotation" |
| }, |
| "faceDetectionAnnotations": { |
| "description": "Face detection annotations.", |
| "type": "array", |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1p3beta1_FaceDetectionAnnotation" |
| } |
| }, |
| "shotAnnotations": { |
| "type": "array", |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1p3beta1_VideoSegment" |
| }, |
| "description": "Shot annotations. Each shot is represented as a video segment." |
| }, |
| "segment": { |
| "$ref": "GoogleCloudVideointelligenceV1p3beta1_VideoSegment", |
| "description": "Video segment on which the annotation is run." |
| }, |
| "segmentLabelAnnotations": { |
| "type": "array", |
| "description": "Topical label annotations on video level or user-specified segment level. There is exactly one element for each unique label.", |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1p3beta1_LabelAnnotation" |
| } |
| }, |
| "objectAnnotations": { |
| "description": "Annotations for list of objects detected and tracked in video.", |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1p3beta1_ObjectTrackingAnnotation" |
| }, |
| "type": "array" |
| }, |
| "textAnnotations": { |
| "type": "array", |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1p3beta1_TextAnnotation" |
| }, |
| "description": "OCR text detection and tracking. Annotations for list of detected text snippets. Each will have list of frame information associated with it." |
| }, |
| "error": { |
| "description": "If set, indicates an error. Note that for a single `AnnotateVideoRequest` some videos may succeed and some may fail.", |
| "$ref": "GoogleRpc_Status" |
| }, |
| "faceAnnotations": { |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1p3beta1_FaceAnnotation" |
| }, |
| "type": "array", |
| "description": "Deprecated. Please use `face_detection_annotations` instead." |
| }, |
| "frameLabelAnnotations": { |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1p3beta1_LabelAnnotation" |
| }, |
| "description": "Label annotations on frame level. There is exactly one element for each unique label.", |
| "type": "array" |
| }, |
| "shotPresenceLabelAnnotations": { |
| "type": "array", |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1p3beta1_LabelAnnotation" |
| }, |
| "description": "Presence label annotations on shot level. There is exactly one element for each unique label. Compared to the existing topical `shot_label_annotations`, this field presents more fine-grained, shot-level labels detected in video content and is made available only when the client sets `LabelDetectionConfig.model` to \"builtin/latest\" in the request." |
| }, |
| "celebrityRecognitionAnnotations": { |
| "$ref": "GoogleCloudVideointelligenceV1p3beta1_CelebrityRecognitionAnnotation", |
| "description": "Celebrity recognition annotations." |
| }, |
| "speechTranscriptions": { |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1p3beta1_SpeechTranscription" |
| }, |
| "type": "array", |
| "description": "Speech transcription." |
| }, |
| "shotLabelAnnotations": { |
| "type": "array", |
| "description": "Topical label annotations on shot level. There is exactly one element for each unique label.", |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1p3beta1_LabelAnnotation" |
| } |
| }, |
| "segmentPresenceLabelAnnotations": { |
| "type": "array", |
| "description": "Presence label annotations on video level or user-specified segment level. There is exactly one element for each unique label. Compared to the existing topical `segment_label_annotations`, this field presents more fine-grained, segment-level labels detected in video content and is made available only when the client sets `LabelDetectionConfig.model` to \"builtin/latest\" in the request.", |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1p3beta1_LabelAnnotation" |
| } |
| }, |
| "inputUri": { |
| "description": "Video file location in [Cloud Storage](https://cloud.google.com/storage/).", |
| "type": "string" |
| } |
| }, |
| "id": "GoogleCloudVideointelligenceV1p3beta1_VideoAnnotationResults" |
| }, |
| "GoogleCloudVideointelligenceV1p2beta1_LabelSegment": { |
| "type": "object", |
| "properties": { |
| "segment": { |
| "description": "Video segment where a label was detected.", |
| "$ref": "GoogleCloudVideointelligenceV1p2beta1_VideoSegment" |
| }, |
| "confidence": { |
| "type": "number", |
| "format": "float", |
| "description": "Confidence that the label is accurate. Range: [0, 1]." |
| } |
| }, |
| "id": "GoogleCloudVideointelligenceV1p2beta1_LabelSegment", |
| "description": "Video segment level annotation results for label detection." |
| }, |
| "GoogleCloudVideointelligenceV1p3beta1_ExplicitContentFrame": { |
| "description": "Video frame level annotation results for explicit content.", |
| "properties": { |
| "timeOffset": { |
| "type": "string", |
| "description": "Time-offset, relative to the beginning of the video, corresponding to the video frame for this location.", |
| "format": "google-duration" |
| }, |
| "pornographyLikelihood": { |
| "enumDescriptions": [ |
| "Unspecified likelihood.", |
| "Very unlikely.", |
| "Unlikely.", |
| "Possible.", |
| "Likely.", |
| "Very likely." |
| ], |
| "enum": [ |
| "LIKELIHOOD_UNSPECIFIED", |
| "VERY_UNLIKELY", |
| "UNLIKELY", |
| "POSSIBLE", |
| "LIKELY", |
| "VERY_LIKELY" |
| ], |
| "description": "Likelihood of the pornography content..", |
| "type": "string" |
| } |
| }, |
| "type": "object", |
| "id": "GoogleCloudVideointelligenceV1p3beta1_ExplicitContentFrame" |
| }, |
| "GoogleCloudVideointelligenceV1p3beta1_ShotChangeDetectionConfig": { |
| "description": "Config for SHOT_CHANGE_DETECTION.", |
| "properties": { |
| "model": { |
| "type": "string", |
| "description": "Model to use for shot change detection. Supported values: \"builtin/stable\" (the default if unset) and \"builtin/latest\"." |
| } |
| }, |
| "type": "object", |
| "id": "GoogleCloudVideointelligenceV1p3beta1_ShotChangeDetectionConfig" |
| }, |
| "GoogleCloudVideointelligenceV1p2beta1_LabelFrame": { |
| "type": "object", |
| "description": "Video frame level annotation results for label detection.", |
| "properties": { |
| "confidence": { |
| "format": "float", |
| "type": "number", |
| "description": "Confidence that the label is accurate. Range: [0, 1]." |
| }, |
| "timeOffset": { |
| "format": "google-duration", |
| "description": "Time-offset, relative to the beginning of the video, corresponding to the video frame for this location.", |
| "type": "string" |
| } |
| }, |
| "id": "GoogleCloudVideointelligenceV1p2beta1_LabelFrame" |
| }, |
| "GoogleCloudVideointelligenceV1p3beta1_SpeechTranscriptionConfig": { |
| "id": "GoogleCloudVideointelligenceV1p3beta1_SpeechTranscriptionConfig", |
| "type": "object", |
| "properties": { |
| "diarizationSpeakerCount": { |
| "type": "integer", |
| "description": "Optional. If set, specifies the estimated number of speakers in the conversation. If not set, defaults to '2'. Ignored unless enable_speaker_diarization is set to true.", |
| "format": "int32" |
| }, |
| "audioTracks": { |
| "description": "Optional. For file formats, such as MXF or MKV, supporting multiple audio tracks, specify up to two tracks. Default: track 0.", |
| "items": { |
| "type": "integer", |
| "format": "int32" |
| }, |
| "type": "array" |
| }, |
| "filterProfanity": { |
| "type": "boolean", |
| "description": "Optional. If set to `true`, the server will attempt to filter out profanities, replacing all but the initial character in each filtered word with asterisks, e.g. \"f***\". If set to `false` or omitted, profanities won't be filtered out." |
| }, |
| "languageCode": { |
| "type": "string", |
| "description": "Required. *Required* The language of the supplied audio as a [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tag. Example: \"en-US\". See [Language Support](https://cloud.google.com/speech/docs/languages) for a list of the currently supported language codes." |
| }, |
| "maxAlternatives": { |
| "format": "int32", |
| "type": "integer", |
| "description": "Optional. Maximum number of recognition hypotheses to be returned. Specifically, the maximum number of `SpeechRecognitionAlternative` messages within each `SpeechTranscription`. The server may return fewer than `max_alternatives`. Valid values are `0`-`30`. A value of `0` or `1` will return a maximum of one. If omitted, will return a maximum of one." |
| }, |
| "speechContexts": { |
| "type": "array", |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1p3beta1_SpeechContext" |
| }, |
| "description": "Optional. A means to provide context to assist the speech recognition." |
| }, |
| "enableWordConfidence": { |
| "description": "Optional. If `true`, the top result includes a list of words and the confidence for those words. If `false`, no word-level confidence information is returned. The default is `false`.", |
| "type": "boolean" |
| }, |
| "enableSpeakerDiarization": { |
| "description": "Optional. If 'true', enables speaker detection for each recognized word in the top alternative of the recognition result using a speaker_tag provided in the WordInfo. Note: When this is true, we send all the words from the beginning of the audio for the top alternative in every consecutive response. This is done in order to improve our speaker tags as our models learn to identify the speakers in the conversation over time.", |
| "type": "boolean" |
| }, |
| "enableAutomaticPunctuation": { |
| "description": "Optional. If 'true', adds punctuation to recognition result hypotheses. This feature is only available in select languages. Setting this for requests in other languages has no effect at all. The default 'false' value does not add punctuation to result hypotheses. NOTE: \"This is currently offered as an experimental service, complimentary to all users. In the future this may be exclusively available as a premium feature.\"", |
| "type": "boolean" |
| } |
| }, |
| "description": "Config for SPEECH_TRANSCRIPTION." |
| }, |
| "GoogleCloudVideointelligenceV1p2beta1_TextFrame": { |
| "id": "GoogleCloudVideointelligenceV1p2beta1_TextFrame", |
| "description": "Video frame level annotation results for text annotation (OCR). Contains information regarding timestamp and bounding box locations for the frames containing detected OCR text snippets.", |
| "type": "object", |
| "properties": { |
| "timeOffset": { |
| "description": "Timestamp of this frame.", |
| "type": "string", |
| "format": "google-duration" |
| }, |
| "rotatedBoundingBox": { |
| "$ref": "GoogleCloudVideointelligenceV1p2beta1_NormalizedBoundingPoly", |
| "description": "Bounding polygon of the detected text for this frame." |
| } |
| } |
| }, |
| "GoogleCloudVideointelligenceV1p3beta1_LabelAnnotation": { |
| "description": "Label annotation.", |
| "type": "object", |
| "id": "GoogleCloudVideointelligenceV1p3beta1_LabelAnnotation", |
| "properties": { |
| "segments": { |
| "type": "array", |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1p3beta1_LabelSegment" |
| }, |
| "description": "All video segments where a label was detected." |
| }, |
| "categoryEntities": { |
| "description": "Common categories for the detected entity. For example, when the label is `Terrier`, the category is likely `dog`. And in some cases there might be more than one categories e.g., `Terrier` could also be a `pet`.", |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1p3beta1_Entity" |
| }, |
| "type": "array" |
| }, |
| "entity": { |
| "description": "Detected entity.", |
| "$ref": "GoogleCloudVideointelligenceV1p3beta1_Entity" |
| }, |
| "version": { |
| "description": "Feature version.", |
| "type": "string" |
| }, |
| "frames": { |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1p3beta1_LabelFrame" |
| }, |
| "type": "array", |
| "description": "All video frames where a label was detected." |
| } |
| } |
| }, |
| "GoogleCloudVideointelligenceV1beta2_VideoAnnotationResults": { |
| "type": "object", |
| "description": "Annotation results for a single video.", |
| "id": "GoogleCloudVideointelligenceV1beta2_VideoAnnotationResults", |
| "properties": { |
| "faceDetectionAnnotations": { |
| "type": "array", |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1beta2_FaceDetectionAnnotation" |
| }, |
| "description": "Face detection annotations." |
| }, |
| "speechTranscriptions": { |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1beta2_SpeechTranscription" |
| }, |
| "description": "Speech transcription.", |
| "type": "array" |
| }, |
| "segmentLabelAnnotations": { |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1beta2_LabelAnnotation" |
| }, |
| "type": "array", |
| "description": "Topical label annotations on video level or user-specified segment level. There is exactly one element for each unique label." |
| }, |
| "explicitAnnotation": { |
| "description": "Explicit content annotation.", |
| "$ref": "GoogleCloudVideointelligenceV1beta2_ExplicitContentAnnotation" |
| }, |
| "inputUri": { |
| "description": "Video file location in [Cloud Storage](https://cloud.google.com/storage/).", |
| "type": "string" |
| }, |
| "error": { |
| "description": "If set, indicates an error. Note that for a single `AnnotateVideoRequest` some videos may succeed and some may fail.", |
| "$ref": "GoogleRpc_Status" |
| }, |
| "objectAnnotations": { |
| "type": "array", |
| "description": "Annotations for list of objects detected and tracked in video.", |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1beta2_ObjectTrackingAnnotation" |
| } |
| }, |
| "segmentPresenceLabelAnnotations": { |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1beta2_LabelAnnotation" |
| }, |
| "description": "Presence label annotations on video level or user-specified segment level. There is exactly one element for each unique label. Compared to the existing topical `segment_label_annotations`, this field presents more fine-grained, segment-level labels detected in video content and is made available only when the client sets `LabelDetectionConfig.model` to \"builtin/latest\" in the request.", |
| "type": "array" |
| }, |
| "segment": { |
| "description": "Video segment on which the annotation is run.", |
| "$ref": "GoogleCloudVideointelligenceV1beta2_VideoSegment" |
| }, |
| "logoRecognitionAnnotations": { |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1beta2_LogoRecognitionAnnotation" |
| }, |
| "description": "Annotations for list of logos detected, tracked and recognized in video.", |
| "type": "array" |
| }, |
| "shotLabelAnnotations": { |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1beta2_LabelAnnotation" |
| }, |
| "description": "Topical label annotations on shot level. There is exactly one element for each unique label.", |
| "type": "array" |
| }, |
| "faceAnnotations": { |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1beta2_FaceAnnotation" |
| }, |
| "description": "Deprecated. Please use `face_detection_annotations` instead.", |
| "type": "array" |
| }, |
| "personDetectionAnnotations": { |
| "type": "array", |
| "description": "Person detection annotations.", |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1beta2_PersonDetectionAnnotation" |
| } |
| }, |
| "textAnnotations": { |
| "description": "OCR text detection and tracking. Annotations for list of detected text snippets. Each will have list of frame information associated with it.", |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1beta2_TextAnnotation" |
| }, |
| "type": "array" |
| }, |
| "frameLabelAnnotations": { |
| "type": "array", |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1beta2_LabelAnnotation" |
| }, |
| "description": "Label annotations on frame level. There is exactly one element for each unique label." |
| }, |
| "shotAnnotations": { |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1beta2_VideoSegment" |
| }, |
| "type": "array", |
| "description": "Shot annotations. Each shot is represented as a video segment." |
| }, |
| "shotPresenceLabelAnnotations": { |
| "description": "Presence label annotations on shot level. There is exactly one element for each unique label. Compared to the existing topical `shot_label_annotations`, this field presents more fine-grained, shot-level labels detected in video content and is made available only when the client sets `LabelDetectionConfig.model` to \"builtin/latest\" in the request.", |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1beta2_LabelAnnotation" |
| }, |
| "type": "array" |
| } |
| } |
| }, |
| "GoogleCloudVideointelligenceV1beta2_NormalizedBoundingPoly": { |
| "properties": { |
| "vertices": { |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1beta2_NormalizedVertex" |
| }, |
| "type": "array", |
| "description": "Normalized vertices of the bounding polygon." |
| } |
| }, |
| "description": "Normalized bounding polygon for text (that might not be aligned with axis). Contains list of the corner points in clockwise order starting from top-left corner. For example, for a rectangular bounding box: When the text is horizontal it might look like: 0----1 | | 3----2 When it's clockwise rotated 180 degrees around the top-left corner it becomes: 2----3 | | 1----0 and the vertex order will still be (0, 1, 2, 3). Note that values can be less than 0, or greater than 1 due to trignometric calculations for location of the box.", |
| "type": "object", |
| "id": "GoogleCloudVideointelligenceV1beta2_NormalizedBoundingPoly" |
| }, |
| "GoogleCloudVideointelligenceV1p1beta1_AnnotateVideoResponse": { |
| "id": "GoogleCloudVideointelligenceV1p1beta1_AnnotateVideoResponse", |
| "description": "Video annotation response. Included in the `response` field of the `Operation` returned by the `GetOperation` call of the `google::longrunning::Operations` service.", |
| "properties": { |
| "annotationResults": { |
| "items": { |
| "$ref": "GoogleCloudVideointelligenceV1p1beta1_VideoAnnotationResults" |
| }, |
| "type": "array", |
| "description": "Annotation results for all videos specified in `AnnotateVideoRequest`." |
| } |
| }, |
| "type": "object" |
| } |
| }, |
| "mtlsRootUrl": "https://videointelligence.mtls.googleapis.com/", |
| "revision": "20201002", |
| "parameters": { |
| "alt": { |
| "enumDescriptions": [ |
| "Responses with Content-Type of application/json", |
| "Media download with context-dependent Content-Type", |
| "Responses with Content-Type of application/x-protobuf" |
| ], |
| "description": "Data format for response.", |
| "type": "string", |
| "enum": [ |
| "json", |
| "media", |
| "proto" |
| ], |
| "default": "json", |
| "location": "query" |
| }, |
| "callback": { |
| "type": "string", |
| "description": "JSONP", |
| "location": "query" |
| }, |
| "$.xgafv": { |
| "type": "string", |
| "enumDescriptions": [ |
| "v1 error format", |
| "v2 error format" |
| ], |
| "description": "V1 error format.", |
| "enum": [ |
| "1", |
| "2" |
| ], |
| "location": "query" |
| }, |
| "quotaUser": { |
| "location": "query", |
| "description": "Available to use for quota purposes for server-side applications. Can be any arbitrary string assigned to a user, but should not exceed 40 characters.", |
| "type": "string" |
| }, |
| "oauth_token": { |
| "description": "OAuth 2.0 token for the current user.", |
| "type": "string", |
| "location": "query" |
| }, |
| "access_token": { |
| "description": "OAuth access token.", |
| "type": "string", |
| "location": "query" |
| }, |
| "key": { |
| "location": "query", |
| "type": "string", |
| "description": "API key. Your API key identifies your project and provides you with API access, quota, and reports. Required unless you provide an OAuth 2.0 token." |
| }, |
| "prettyPrint": { |
| "location": "query", |
| "type": "boolean", |
| "description": "Returns response with indentations and line breaks.", |
| "default": "true" |
| }, |
| "uploadType": { |
| "type": "string", |
| "location": "query", |
| "description": "Legacy upload protocol for media (e.g. \"media\", \"multipart\")." |
| }, |
| "fields": { |
| "location": "query", |
| "type": "string", |
| "description": "Selector specifying which fields to include in a partial response." |
| }, |
| "upload_protocol": { |
| "location": "query", |
| "description": "Upload protocol for media (e.g. \"raw\", \"multipart\").", |
| "type": "string" |
| } |
| }, |
| "version": "v1p3beta1", |
| "discoveryVersion": "v1", |
| "auth": { |
| "oauth2": { |
| "scopes": { |
| "https://www.googleapis.com/auth/cloud-platform": { |
| "description": "View and manage your data across Google Cloud Platform services" |
| } |
| } |
| } |
| }, |
| "baseUrl": "https://videointelligence.googleapis.com/", |
| "title": "Cloud Video Intelligence API", |
| "servicePath": "", |
| "name": "videointelligence", |
| "rootUrl": "https://videointelligence.googleapis.com/", |
| "ownerDomain": "google.com", |
| "basePath": "", |
| "fullyEncodeReservedExpansion": true, |
| "protocol": "rest", |
| "canonicalName": "Cloud Video Intelligence" |
| } |
