videointelligence

type AnnotateVideoProgress struct {
	// Progress metadata for all videos specified in `AnnotateVideoRequest`.
	AnnotationProgress []*VideoAnnotationProgress `protobuf:"bytes,1,rep,name=annotation_progress,json=annotationProgress" json:"annotation_progress,omitempty"`
}

type AnnotateVideoRequest struct {
	// 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.
	InputUri string `protobuf:"bytes,1,opt,name=input_uri,json=inputUri" json:"input_uri,omitempty"`
	// The video data bytes.
	// If unset, the input video(s) should be specified via `input_uri`.
	// If set, `input_uri` should be unset.
	InputContent []byte `protobuf:"bytes,6,opt,name=input_content,json=inputContent,proto3" json:"input_content,omitempty"`
	// Requested video annotation features.
	Features []Feature `protobuf:"varint,2,rep,packed,name=features,enum=google.cloud.videointelligence.v1p1beta1.Feature" json:"features,omitempty"`
	// Additional video context and/or feature-specific parameters.
	VideoContext *VideoContext `protobuf:"bytes,3,opt,name=video_context,json=videoContext" json:"video_context,omitempty"`
	// 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).
	OutputUri string `protobuf:"bytes,4,opt,name=output_uri,json=outputUri" json:"output_uri,omitempty"`
	// 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.
	LocationId string `protobuf:"bytes,5,opt,name=location_id,json=locationId" json:"location_id,omitempty"`
}

type AnnotateVideoResponse struct {
	// Annotation results for all videos specified in `AnnotateVideoRequest`.
	AnnotationResults []*VideoAnnotationResults `protobuf:"bytes,1,rep,name=annotation_results,json=annotationResults" json:"annotation_results,omitempty"`
}

type Entity struct {
	// Opaque entity ID. Some IDs may be available in
	// [Google Knowledge Graph Search
	// API](https://developers.google.com/knowledge-graph/).
	EntityId string `protobuf:"bytes,1,opt,name=entity_id,json=entityId" json:"entity_id,omitempty"`
	// Textual description, e.g. `Fixed-gear bicycle`.
	Description string `protobuf:"bytes,2,opt,name=description" json:"description,omitempty"`
	// Language code for `description` in BCP-47 format.
	LanguageCode string `protobuf:"bytes,3,opt,name=language_code,json=languageCode" json:"language_code,omitempty"`
}

type ExplicitContentAnnotation struct {
	// All video frames where explicit content was detected.
	Frames []*ExplicitContentFrame `protobuf:"bytes,1,rep,name=frames" json:"frames,omitempty"`
}

type ExplicitContentDetectionConfig struct {
	// Model to use for explicit content detection.
	// Supported values: "builtin/stable" (the default if unset) and
	// "builtin/latest".
	Model string `protobuf:"bytes,1,opt,name=model" json:"model,omitempty"`
}

type ExplicitContentFrame struct {
	// Time-offset, relative to the beginning of the video, corresponding to the
	// video frame for this location.
	TimeOffset *google_protobuf3.Duration `protobuf:"bytes,1,opt,name=time_offset,json=timeOffset" json:"time_offset,omitempty"`
	// Likelihood of the pornography content..
	PornographyLikelihood Likelihood `` /* 175-byte string literal not displayed */
}

type Feature int32

type LabelAnnotation struct {
	// Detected entity.
	Entity *Entity `protobuf:"bytes,1,opt,name=entity" json:"entity,omitempty"`
	// 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`.
	CategoryEntities []*Entity `protobuf:"bytes,2,rep,name=category_entities,json=categoryEntities" json:"category_entities,omitempty"`
	// All video segments where a label was detected.
	Segments []*LabelSegment `protobuf:"bytes,3,rep,name=segments" json:"segments,omitempty"`
	// All video frames where a label was detected.
	Frames []*LabelFrame `protobuf:"bytes,4,rep,name=frames" json:"frames,omitempty"`
}

type LabelDetectionConfig struct {
	// What labels should be detected with LABEL_DETECTION, in addition to
	// video-level labels or segment-level labels.
	// If unspecified, defaults to `SHOT_MODE`.
	LabelDetectionMode LabelDetectionMode `` /* 176-byte string literal not displayed */
	// 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.
	StationaryCamera bool `protobuf:"varint,2,opt,name=stationary_camera,json=stationaryCamera" json:"stationary_camera,omitempty"`
	// Model to use for label detection.
	// Supported values: "builtin/stable" (the default if unset) and
	// "builtin/latest".
	Model string `protobuf:"bytes,3,opt,name=model" json:"model,omitempty"`
}

type LabelDetectionMode int32

type LabelFrame struct {
	// Time-offset, relative to the beginning of the video, corresponding to the
	// video frame for this location.
	TimeOffset *google_protobuf3.Duration `protobuf:"bytes,1,opt,name=time_offset,json=timeOffset" json:"time_offset,omitempty"`
	// Confidence that the label is accurate. Range: [0, 1].
	Confidence float32 `protobuf:"fixed32,2,opt,name=confidence" json:"confidence,omitempty"`
}

type LabelSegment struct {
	// Video segment where a label was detected.
	Segment *VideoSegment `protobuf:"bytes,1,opt,name=segment" json:"segment,omitempty"`
	// Confidence that the label is accurate. Range: [0, 1].
	Confidence float32 `protobuf:"fixed32,2,opt,name=confidence" json:"confidence,omitempty"`
}

type Likelihood int32

type NormalizedBoundingBox struct {
	// Left X coordinate.
	Left float32 `protobuf:"fixed32,1,opt,name=left" json:"left,omitempty"`
	// Top Y coordinate.
	Top float32 `protobuf:"fixed32,2,opt,name=top" json:"top,omitempty"`
	// Right X coordinate.
	Right float32 `protobuf:"fixed32,3,opt,name=right" json:"right,omitempty"`
	// Bottom Y coordinate.
	Bottom float32 `protobuf:"fixed32,4,opt,name=bottom" json:"bottom,omitempty"`
}

type ShotChangeDetectionConfig struct {
	// Model to use for shot change detection.
	// Supported values: "builtin/stable" (the default if unset) and
	// "builtin/latest".
	Model string `protobuf:"bytes,1,opt,name=model" json:"model,omitempty"`
}

type SpeechContext struct {
	// *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).
	Phrases []string `protobuf:"bytes,1,rep,name=phrases" json:"phrases,omitempty"`
}

type SpeechRecognitionAlternative struct {
	// Output only. Transcript text representing the words that the user spoke.
	Transcript string `protobuf:"bytes,1,opt,name=transcript" json:"transcript,omitempty"`
	// 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 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.
	Confidence float32 `protobuf:"fixed32,2,opt,name=confidence" json:"confidence,omitempty"`
	// Output only. A list of word-specific information for each recognized word.
	Words []*WordInfo `protobuf:"bytes,3,rep,name=words" json:"words,omitempty"`
}

type SpeechTranscription struct {
	// Output only. 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.
	Alternatives []*SpeechRecognitionAlternative `protobuf:"bytes,1,rep,name=alternatives" json:"alternatives,omitempty"`
}

type SpeechTranscriptionConfig struct {
	// *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.
	LanguageCode string `protobuf:"bytes,1,opt,name=language_code,json=languageCode" json:"language_code,omitempty"`
	// *Optional* Maximum number of recognition hypotheses to be returned.
	// Specifically, the maximum number of `SpeechRecognitionAlternative` messages
	// within each `SpeechRecognitionResult`. 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.
	MaxAlternatives int32 `protobuf:"varint,2,opt,name=max_alternatives,json=maxAlternatives" json:"max_alternatives,omitempty"`
	// *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.
	FilterProfanity bool `protobuf:"varint,3,opt,name=filter_profanity,json=filterProfanity" json:"filter_profanity,omitempty"`
	// *Optional* A means to provide context to assist the speech recognition.
	SpeechContexts []*SpeechContext `protobuf:"bytes,4,rep,name=speech_contexts,json=speechContexts" json:"speech_contexts,omitempty"`
	// *Optional* For file formats, such as MXF or MKV, supporting multiple audio
	// tracks, specify up to two tracks. Default: track 0.
	AudioTracks []int32 `protobuf:"varint,6,rep,packed,name=audio_tracks,json=audioTracks" json:"audio_tracks,omitempty"`
}

type VideoAnnotationProgress struct {
	// Video file location in
	// [Google Cloud Storage](https://cloud.google.com/storage/).
	InputUri string `protobuf:"bytes,1,opt,name=input_uri,json=inputUri" json:"input_uri,omitempty"`
	// Approximate percentage processed thus far.
	// Guaranteed to be 100 when fully processed.
	ProgressPercent int32 `protobuf:"varint,2,opt,name=progress_percent,json=progressPercent" json:"progress_percent,omitempty"`
	// Time when the request was received.
	StartTime *google_protobuf4.Timestamp `protobuf:"bytes,3,opt,name=start_time,json=startTime" json:"start_time,omitempty"`
	// Time of the most recent update.
	UpdateTime *google_protobuf4.Timestamp `protobuf:"bytes,4,opt,name=update_time,json=updateTime" json:"update_time,omitempty"`
}

type VideoAnnotationResults struct {
	// Video file location in
	// [Google Cloud Storage](https://cloud.google.com/storage/).
	InputUri string `protobuf:"bytes,1,opt,name=input_uri,json=inputUri" json:"input_uri,omitempty"`
	// Label annotations on video level or user specified segment level.
	// There is exactly one element for each unique label.
	SegmentLabelAnnotations []*LabelAnnotation `protobuf:"bytes,2,rep,name=segment_label_annotations,json=segmentLabelAnnotations" json:"segment_label_annotations,omitempty"`
	// Label annotations on shot level.
	// There is exactly one element for each unique label.
	ShotLabelAnnotations []*LabelAnnotation `protobuf:"bytes,3,rep,name=shot_label_annotations,json=shotLabelAnnotations" json:"shot_label_annotations,omitempty"`
	// Label annotations on frame level.
	// There is exactly one element for each unique label.
	FrameLabelAnnotations []*LabelAnnotation `protobuf:"bytes,4,rep,name=frame_label_annotations,json=frameLabelAnnotations" json:"frame_label_annotations,omitempty"`
	// Shot annotations. Each shot is represented as a video segment.
	ShotAnnotations []*VideoSegment `protobuf:"bytes,6,rep,name=shot_annotations,json=shotAnnotations" json:"shot_annotations,omitempty"`
	// Explicit content annotation.
	ExplicitAnnotation *ExplicitContentAnnotation `protobuf:"bytes,7,opt,name=explicit_annotation,json=explicitAnnotation" json:"explicit_annotation,omitempty"`
	// Speech transcription.
	SpeechTranscriptions []*SpeechTranscription `protobuf:"bytes,11,rep,name=speech_transcriptions,json=speechTranscriptions" json:"speech_transcriptions,omitempty"`
	// If set, indicates an error. Note that for a single `AnnotateVideoRequest`
	// some videos may succeed and some may fail.
	Error *google_rpc.Status `protobuf:"bytes,9,opt,name=error" json:"error,omitempty"`
}

type VideoContext struct {
	// 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.
	Segments []*VideoSegment `protobuf:"bytes,1,rep,name=segments" json:"segments,omitempty"`
	// Config for LABEL_DETECTION.
	LabelDetectionConfig *LabelDetectionConfig `protobuf:"bytes,2,opt,name=label_detection_config,json=labelDetectionConfig" json:"label_detection_config,omitempty"`
	// Config for SHOT_CHANGE_DETECTION.
	ShotChangeDetectionConfig *ShotChangeDetectionConfig `` /* 133-byte string literal not displayed */
	// Config for EXPLICIT_CONTENT_DETECTION.
	ExplicitContentDetectionConfig *ExplicitContentDetectionConfig `` /* 148-byte string literal not displayed */
	// Config for SPEECH_TRANSCRIPTION.
	SpeechTranscriptionConfig *SpeechTranscriptionConfig `` /* 131-byte string literal not displayed */
}

type VideoIntelligenceServiceClient interface {
	// 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).
	AnnotateVideo(ctx context.Context, in *AnnotateVideoRequest, opts ...grpc.CallOption) (*google_longrunning.Operation, error)
}

type VideoIntelligenceServiceServer interface {
	// 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).
	AnnotateVideo(context.Context, *AnnotateVideoRequest) (*google_longrunning.Operation, error)
}

type VideoSegment struct {
	// Time-offset, relative to the beginning of the video,
	// corresponding to the start of the segment (inclusive).
	StartTimeOffset *google_protobuf3.Duration `protobuf:"bytes,1,opt,name=start_time_offset,json=startTimeOffset" json:"start_time_offset,omitempty"`
	// Time-offset, relative to the beginning of the video,
	// corresponding to the end of the segment (inclusive).
	EndTimeOffset *google_protobuf3.Duration `protobuf:"bytes,2,opt,name=end_time_offset,json=endTimeOffset" json:"end_time_offset,omitempty"`
}

type WordInfo struct {
	// Output only. 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.
	StartTime *google_protobuf3.Duration `protobuf:"bytes,1,opt,name=start_time,json=startTime" json:"start_time,omitempty"`
	// Output only. 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.
	EndTime *google_protobuf3.Duration `protobuf:"bytes,2,opt,name=end_time,json=endTime" json:"end_time,omitempty"`
	// Output only. The word corresponding to this set of information.
	Word string `protobuf:"bytes,3,opt,name=word" json:"word,omitempty"`
}