package google.cloud.videointelligence.v1

Get desktop application:
View/edit binary Protocol Buffers messages

Service that implements Google Cloud Video Intelligence API.

• rpc AnnotateVideo (AnnotateVideoRequest, longrunning.Operation)

  video_intelligence.proto:39

  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).

  message AnnotateVideoRequest

  video_intelligence.proto:45

  Video annotation request.

  • string input_uri = 1

    Input video location. Currently, only [Google Cloud Storage](https://cloud.google.com/storage/) URIs are supported, which must be specified in the following format: `gs://bucket-id/object-id` (other URI formats return [google.rpc.Code.INVALID_ARGUMENT][google.rpc.Code.INVALID_ARGUMENT]). For more information, see [Request URIs](/storage/docs/reference-uris). A video URI may include wildcards in `object-id`, and thus identify multiple videos. 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` should be unset.

  • bytes input_content = 6

    The video data bytes. If unset, the input video(s) should be specified via `input_uri`. If set, `input_uri` should be unset.

  • repeated Feature features = 2

    Requested video annotation features.

  • optional VideoContext video_context = 3

    Additional video context and/or feature-specific parameters.

  • string output_uri = 4

    Optional location where the output (in JSON format) should be stored. Currently, only [Google Cloud Storage](https://cloud.google.com/storage/) URIs are supported, which must be specified in the following format: `gs://bucket-id/object-id` (other URI formats return [google.rpc.Code.INVALID_ARGUMENT][google.rpc.Code.INVALID_ARGUMENT]). For more information, see [Request URIs](/storage/docs/reference-uris).

  • string location_id = 5

    Optional cloud region where annotation should take place. Supported cloud regions: `us-east1`, `us-west1`, `europe-west1`, `asia-east1`. If no region is specified, a region will be determined based on video file location.

Video annotation progress. Included in the `metadata` field of the `Operation` returned by the `GetOperation` call of the `google::longrunning::Operations` service.

• repeated VideoAnnotationProgress annotation_progress = 1

  Progress metadata for all videos specified in `AnnotateVideoRequest`.

Video annotation response. Included in the `response` field of the `Operation` returned by the `GetOperation` call of the `google::longrunning::Operations` service.

• repeated VideoAnnotationResults annotation_results = 1

  Annotation results for all videos specified in `AnnotateVideoRequest`.

Detected entity from video analysis.

Used in: LabelAnnotation

• string entity_id = 1

  Opaque entity ID. Some IDs may be available in [Google Knowledge Graph Search API](https://developers.google.com/knowledge-graph/).

• string description = 2

  Textual description, e.g. `Fixed-gear bicycle`.

• string language_code = 3

  Language code for `description` in BCP-47 format.

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.

Used in: VideoAnnotationResults

• repeated ExplicitContentFrame frames = 1

  All video frames where explicit content was detected.

Config for EXPLICIT_CONTENT_DETECTION.

Used in: VideoContext

• string model = 1

  Model to use for explicit content detection. Supported values: "builtin/stable" (the default if unset) and "builtin/latest".

Video frame level annotation results for explicit content.

Used in: ExplicitContentAnnotation

• optional protobuf.Duration time_offset = 1

  Time-offset, relative to the beginning of the video, corresponding to the video frame for this location.

• Likelihood pornography_likelihood = 2

  Likelihood of the pornography content..

Face annotation.

Used in: VideoAnnotationResults

• bytes thumbnail = 1

  Thumbnail of a representative face view (in JPEG format).

• repeated FaceSegment segments = 2

  All video segments where a face was detected.

• repeated FaceFrame frames = 3

  All video frames where a face was detected.

Config for FACE_DETECTION.

Used in: VideoContext

• string model = 1

  Model to use for face detection. Supported values: "builtin/stable" (the default if unset) and "builtin/latest".

• bool include_bounding_boxes = 2

  Whether bounding boxes be included in the face annotation output.

Video frame level annotation results for face detection.

Used in: FaceAnnotation

• repeated NormalizedBoundingBox normalized_bounding_boxes = 1

  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.

• optional protobuf.Duration time_offset = 2

  Time-offset, relative to the beginning of the video, corresponding to the video frame for this location.

Video segment level annotation results for face detection.

Used in: FaceAnnotation

• optional VideoSegment segment = 1

  Video segment where a face was detected.

Video annotation feature.

Used in: AnnotateVideoRequest

• FEATURE_UNSPECIFIED = 0

  Unspecified.

• LABEL_DETECTION = 1

  Label detection. Detect objects, such as dog or flower.

• SHOT_CHANGE_DETECTION = 2

  Shot change detection.

• EXPLICIT_CONTENT_DETECTION = 3

  Explicit content detection.

• FACE_DETECTION = 4

  Human face detection and tracking.

• SPEECH_TRANSCRIPTION = 6

  Speech transcription.

Label annotation.

Used in: VideoAnnotationResults

• optional Entity entity = 1

  Detected entity.

• repeated Entity category_entities = 2

  Common categories for the detected entity. E.g. 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`.

• repeated LabelSegment segments = 3

  All video segments where a label was detected.

• repeated LabelFrame frames = 4

  All video frames where a label was detected.

Config for LABEL_DETECTION.

Used in: VideoContext

• LabelDetectionMode label_detection_mode = 1

  What labels should be detected with LABEL_DETECTION, in addition to video-level labels or segment-level labels. If unspecified, defaults to `SHOT_MODE`.

• bool stationary_camera = 2

  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.

• string model = 3

  Model to use for label detection. Supported values: "builtin/stable" (the default if unset) and "builtin/latest".

Label detection mode.

Used in: LabelDetectionConfig

• LABEL_DETECTION_MODE_UNSPECIFIED = 0

  Unspecified.

• SHOT_MODE = 1

  Detect shot-level labels.

• FRAME_MODE = 2

  Detect frame-level labels.

• SHOT_AND_FRAME_MODE = 3

  Detect both shot-level and frame-level labels.

Video frame level annotation results for label detection.

Used in: LabelAnnotation

• optional protobuf.Duration time_offset = 1

  Time-offset, relative to the beginning of the video, corresponding to the video frame for this location.

• float confidence = 2

  Confidence that the label is accurate. Range: [0, 1].

Video segment level annotation results for label detection.

Used in: LabelAnnotation

• optional VideoSegment segment = 1

  Video segment where a label was detected.

• float confidence = 2

  Confidence that the label is accurate. Range: [0, 1].

Bucketized representation of likelihood.

Used in: ExplicitContentFrame

• LIKELIHOOD_UNSPECIFIED = 0

  Unspecified likelihood.

• VERY_UNLIKELY = 1

  Very unlikely.

• UNLIKELY = 2

  Unlikely.

• POSSIBLE = 3

  Possible.

• LIKELY = 4

  Likely.

• VERY_LIKELY = 5

  Very likely.

Normalized bounding box. The normalized vertex coordinates are relative to the original image. Range: [0, 1].

Used in: FaceFrame

• float left = 1

  Left X coordinate.

• float top = 2

  Top Y coordinate.

• float right = 3

  Right X coordinate.

• float bottom = 4

  Bottom Y coordinate.

Config for SHOT_CHANGE_DETECTION.

Used in: VideoContext

• string model = 1

  Model to use for shot change detection. Supported values: "builtin/stable" (the default if unset) and "builtin/latest".

Provides "hints" to the speech recognizer to favor specific words and phrases in the results.

Used in: SpeechTranscriptionConfig

• repeated string phrases = 1

  *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).

Alternative hypotheses (a.k.a. n-best list).

Used in: SpeechTranscription

• string transcript = 1

  Transcript text representing the words that the user spoke.

• float confidence = 2

  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 typically provided only for the top hypothesis, and only for `is_final=true` results. Clients should not rely on the `confidence` field as it is not guaranteed to be accurate or consistent. The default of 0.0 is a sentinel value indicating `confidence` was not set.

• repeated WordInfo words = 3

  A list of word-specific information for each recognized word.

A speech recognition result corresponding to a portion of the audio.

Used in: VideoAnnotationResults

• repeated SpeechRecognitionAlternative alternatives = 1

  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.

• string language_code = 2

  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.

Config for SPEECH_TRANSCRIPTION.

Used in: VideoContext

• string language_code = 1

  *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.

• int32 max_alternatives = 2

  *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.

• bool filter_profanity = 3

  *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.

• repeated SpeechContext speech_contexts = 4

  *Optional* A means to provide context to assist the speech recognition.

• bool enable_automatic_punctuation = 5

  *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."

• repeated int32 audio_tracks = 6

  *Optional* For file formats, such as MXF or MKV, supporting multiple audio tracks, specify up to two tracks. Default: track 0.

• bool enable_speaker_diarization = 7

  *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 responses. This is done in order to improve our speaker tags as our models learn to identify the speakers in the conversation over time.

• int32 diarization_speaker_count = 8

  *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.

• bool enable_word_confidence = 9

  *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`.

Annotation progress for a single video.

Used in: AnnotateVideoProgress

• string input_uri = 1

  Video file location in [Google Cloud Storage](https://cloud.google.com/storage/).

• int32 progress_percent = 2

  Approximate percentage processed thus far. Guaranteed to be 100 when fully processed.

• optional protobuf.Timestamp start_time = 3

  Time when the request was received.

• optional protobuf.Timestamp update_time = 4

  Time of the most recent update.

Annotation results for a single video.

Used in: AnnotateVideoResponse

• string input_uri = 1

  Video file location in [Google Cloud Storage](https://cloud.google.com/storage/).

• repeated LabelAnnotation segment_label_annotations = 2

  Label annotations on video level or user specified segment level. There is exactly one element for each unique label.

• repeated LabelAnnotation shot_label_annotations = 3

  Label annotations on shot level. There is exactly one element for each unique label.

• repeated LabelAnnotation frame_label_annotations = 4

  Label annotations on frame level. There is exactly one element for each unique label.

• repeated FaceAnnotation face_annotations = 5

  Face annotations. There is exactly one element for each unique face.

• repeated VideoSegment shot_annotations = 6

  Shot annotations. Each shot is represented as a video segment.

• optional ExplicitContentAnnotation explicit_annotation = 7

  Explicit content annotation.

• repeated SpeechTranscription speech_transcriptions = 11

  Speech transcription.

• optional rpc.Status error = 9

  If set, indicates an error. Note that for a single `AnnotateVideoRequest` some videos may succeed and some may fail.

Video context and/or feature-specific parameters.

Used in: AnnotateVideoRequest

• repeated VideoSegment segments = 1

  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.

• optional LabelDetectionConfig label_detection_config = 2

  Config for LABEL_DETECTION.

• optional ShotChangeDetectionConfig shot_change_detection_config = 3

  Config for SHOT_CHANGE_DETECTION.

• optional ExplicitContentDetectionConfig explicit_content_detection_config = 4

  Config for EXPLICIT_CONTENT_DETECTION.

• optional FaceDetectionConfig face_detection_config = 5

  Config for FACE_DETECTION.

• optional SpeechTranscriptionConfig speech_transcription_config = 6

  Config for SPEECH_TRANSCRIPTION.

Video segment.

Used in: FaceSegment, LabelSegment, VideoAnnotationResults, VideoContext

• optional protobuf.Duration start_time_offset = 1

  Time-offset, relative to the beginning of the video, corresponding to the start of the segment (inclusive).

• optional protobuf.Duration end_time_offset = 2

  Time-offset, relative to the beginning of the video, corresponding to the end of the segment (inclusive).

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`.

Used in: SpeechRecognitionAlternative

• optional protobuf.Duration start_time = 1

  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.

• optional protobuf.Duration end_time = 2

  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.

• string word = 3

  The word corresponding to this set of information.

• float confidence = 4

  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.

• int32 speaker_tag = 5

  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.