# frozen_string_literal: true
# Copyright 2021 Google LLC
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# https://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
# Auto-generated by gapic-generator-ruby. DO NOT EDIT!
module Google
module Cloud
module VideoIntelligence
module V1p3beta1
# Video annotation request.
# @!attribute [rw] input_uri
# @return [::String]
# 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][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.
# @!attribute [rw] input_content
# @return [::String]
# The video data bytes.
# If unset, the input video(s) should be specified via the `input_uri`.
# If set, `input_uri` must be unset.
# @!attribute [rw] features
# @return [::Array<::Google::Cloud::VideoIntelligence::V1p3beta1::Feature>]
# Required. Requested video annotation features.
# @!attribute [rw] video_context
# @return [::Google::Cloud::VideoIntelligence::V1p3beta1::VideoContext]
# Additional video context and/or feature-specific parameters.
# @!attribute [rw] output_uri
# @return [::String]
# 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][google.rpc.Code.INVALID_ARGUMENT]). For
# more information, see [Request
# URIs](https://cloud.google.com/storage/docs/request-endpoints).
# @!attribute [rw] location_id
# @return [::String]
# 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.
class AnnotateVideoRequest
include ::Google::Protobuf::MessageExts
extend ::Google::Protobuf::MessageExts::ClassMethods
end
# Video context and/or feature-specific parameters.
# @!attribute [rw] segments
# @return [::Array<::Google::Cloud::VideoIntelligence::V1p3beta1::VideoSegment>]
# 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.
# @!attribute [rw] label_detection_config
# @return [::Google::Cloud::VideoIntelligence::V1p3beta1::LabelDetectionConfig]
# Config for LABEL_DETECTION.
# @!attribute [rw] shot_change_detection_config
# @return [::Google::Cloud::VideoIntelligence::V1p3beta1::ShotChangeDetectionConfig]
# Config for SHOT_CHANGE_DETECTION.
# @!attribute [rw] explicit_content_detection_config
# @return [::Google::Cloud::VideoIntelligence::V1p3beta1::ExplicitContentDetectionConfig]
# Config for EXPLICIT_CONTENT_DETECTION.
# @!attribute [rw] face_detection_config
# @return [::Google::Cloud::VideoIntelligence::V1p3beta1::FaceDetectionConfig]
# Config for FACE_DETECTION.
# @!attribute [rw] speech_transcription_config
# @return [::Google::Cloud::VideoIntelligence::V1p3beta1::SpeechTranscriptionConfig]
# Config for SPEECH_TRANSCRIPTION.
# @!attribute [rw] text_detection_config
# @return [::Google::Cloud::VideoIntelligence::V1p3beta1::TextDetectionConfig]
# Config for TEXT_DETECTION.
# @!attribute [rw] person_detection_config
# @return [::Google::Cloud::VideoIntelligence::V1p3beta1::PersonDetectionConfig]
# Config for PERSON_DETECTION.
# @!attribute [rw] object_tracking_config
# @return [::Google::Cloud::VideoIntelligence::V1p3beta1::ObjectTrackingConfig]
# Config for OBJECT_TRACKING.
class VideoContext
include ::Google::Protobuf::MessageExts
extend ::Google::Protobuf::MessageExts::ClassMethods
end
# Config for LABEL_DETECTION.
# @!attribute [rw] label_detection_mode
# @return [::Google::Cloud::VideoIntelligence::V1p3beta1::LabelDetectionMode]
# What labels should be detected with LABEL_DETECTION, in addition to
# video-level labels or segment-level labels.
# If unspecified, defaults to `SHOT_MODE`.
# @!attribute [rw] stationary_camera
# @return [::Boolean]
# 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.
# @!attribute [rw] model
# @return [::String]
# Model to use for label detection.
# Supported values: "builtin/stable" (the default if unset) and
# "builtin/latest".
# @!attribute [rw] frame_confidence_threshold
# @return [::Float]
# 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.
# @!attribute [rw] video_confidence_threshold
# @return [::Float]
# 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.
class LabelDetectionConfig
include ::Google::Protobuf::MessageExts
extend ::Google::Protobuf::MessageExts::ClassMethods
end
# Config for SHOT_CHANGE_DETECTION.
# @!attribute [rw] model
# @return [::String]
# Model to use for shot change detection.
# Supported values: "builtin/stable" (the default if unset) and
# "builtin/latest".
class ShotChangeDetectionConfig
include ::Google::Protobuf::MessageExts
extend ::Google::Protobuf::MessageExts::ClassMethods
end
# Config for OBJECT_TRACKING.
# @!attribute [rw] model
# @return [::String]
# Model to use for object tracking.
# Supported values: "builtin/stable" (the default if unset) and
# "builtin/latest".
class ObjectTrackingConfig
include ::Google::Protobuf::MessageExts
extend ::Google::Protobuf::MessageExts::ClassMethods
end
# Config for EXPLICIT_CONTENT_DETECTION.
# @!attribute [rw] model
# @return [::String]
# Model to use for explicit content detection.
# Supported values: "builtin/stable" (the default if unset) and
# "builtin/latest".
class ExplicitContentDetectionConfig
include ::Google::Protobuf::MessageExts
extend ::Google::Protobuf::MessageExts::ClassMethods
end
# Config for FACE_DETECTION.
# @!attribute [rw] model
# @return [::String]
# Model to use for face detection.
# Supported values: "builtin/stable" (the default if unset) and
# "builtin/latest".
# @!attribute [rw] include_bounding_boxes
# @return [::Boolean]
# Whether bounding boxes are included in the face annotation output.
# @!attribute [rw] include_attributes
# @return [::Boolean]
# Whether to enable face attributes detection, such as glasses, dark_glasses,
# mouth_open etc. Ignored if 'include_bounding_boxes' is set to false.
class FaceDetectionConfig
include ::Google::Protobuf::MessageExts
extend ::Google::Protobuf::MessageExts::ClassMethods
end
# Config for PERSON_DETECTION.
# @!attribute [rw] include_bounding_boxes
# @return [::Boolean]
# Whether bounding boxes are included in the person detection annotation
# output.
# @!attribute [rw] include_pose_landmarks
# @return [::Boolean]
# Whether to enable pose landmarks detection. Ignored if
# 'include_bounding_boxes' is set to false.
# @!attribute [rw] include_attributes
# @return [::Boolean]
# 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.
class PersonDetectionConfig
include ::Google::Protobuf::MessageExts
extend ::Google::Protobuf::MessageExts::ClassMethods
end
# Config for TEXT_DETECTION.
# @!attribute [rw] language_hints
# @return [::Array<::String>]
# 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.
# @!attribute [rw] model
# @return [::String]
# Model to use for text detection.
# Supported values: "builtin/stable" (the default if unset) and
# "builtin/latest".
class TextDetectionConfig
include ::Google::Protobuf::MessageExts
extend ::Google::Protobuf::MessageExts::ClassMethods
end
# Video segment.
# @!attribute [rw] start_time_offset
# @return [::Google::Protobuf::Duration]
# Time-offset, relative to the beginning of the video,
# corresponding to the start of the segment (inclusive).
# @!attribute [rw] end_time_offset
# @return [::Google::Protobuf::Duration]
# Time-offset, relative to the beginning of the video,
# corresponding to the end of the segment (inclusive).
class VideoSegment
include ::Google::Protobuf::MessageExts
extend ::Google::Protobuf::MessageExts::ClassMethods
end
# Video segment level annotation results for label detection.
# @!attribute [rw] segment
# @return [::Google::Cloud::VideoIntelligence::V1p3beta1::VideoSegment]
# Video segment where a label was detected.
# @!attribute [rw] confidence
# @return [::Float]
# Confidence that the label is accurate. Range: [0, 1].
class LabelSegment
include ::Google::Protobuf::MessageExts
extend ::Google::Protobuf::MessageExts::ClassMethods
end
# Video frame level annotation results for label detection.
# @!attribute [rw] time_offset
# @return [::Google::Protobuf::Duration]
# Time-offset, relative to the beginning of the video, corresponding to the
# video frame for this location.
# @!attribute [rw] confidence
# @return [::Float]
# Confidence that the label is accurate. Range: [0, 1].
class LabelFrame
include ::Google::Protobuf::MessageExts
extend ::Google::Protobuf::MessageExts::ClassMethods
end
# Detected entity from video analysis.
# @!attribute [rw] entity_id
# @return [::String]
# Opaque entity ID. Some IDs may be available in
# [Google Knowledge Graph Search
# API](https://developers.google.com/knowledge-graph/).
# @!attribute [rw] description
# @return [::String]
# Textual description, e.g., `Fixed-gear bicycle`.
# @!attribute [rw] language_code
# @return [::String]
# Language code for `description` in BCP-47 format.
class Entity
include ::Google::Protobuf::MessageExts
extend ::Google::Protobuf::MessageExts::ClassMethods
end
# Label annotation.
# @!attribute [rw] entity
# @return [::Google::Cloud::VideoIntelligence::V1p3beta1::Entity]
# Detected entity.
# @!attribute [rw] category_entities
# @return [::Array<::Google::Cloud::VideoIntelligence::V1p3beta1::Entity>]
# 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`.
# @!attribute [rw] segments
# @return [::Array<::Google::Cloud::VideoIntelligence::V1p3beta1::LabelSegment>]
# All video segments where a label was detected.
# @!attribute [rw] frames
# @return [::Array<::Google::Cloud::VideoIntelligence::V1p3beta1::LabelFrame>]
# All video frames where a label was detected.
class LabelAnnotation
include ::Google::Protobuf::MessageExts
extend ::Google::Protobuf::MessageExts::ClassMethods
end
# Video frame level annotation results for explicit content.
# @!attribute [rw] time_offset
# @return [::Google::Protobuf::Duration]
# Time-offset, relative to the beginning of the video, corresponding to the
# video frame for this location.
# @!attribute [rw] pornography_likelihood
# @return [::Google::Cloud::VideoIntelligence::V1p3beta1::Likelihood]
# Likelihood of the pornography content..
class ExplicitContentFrame
include ::Google::Protobuf::MessageExts
extend ::Google::Protobuf::MessageExts::ClassMethods
end
# 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.
# @!attribute [rw] frames
# @return [::Array<::Google::Cloud::VideoIntelligence::V1p3beta1::ExplicitContentFrame>]
# All video frames where explicit content was detected.
class ExplicitContentAnnotation
include ::Google::Protobuf::MessageExts
extend ::Google::Protobuf::MessageExts::ClassMethods
end
# Normalized bounding box.
# The normalized vertex coordinates are relative to the original image.
# Range: [0, 1].
# @!attribute [rw] left
# @return [::Float]
# Left X coordinate.
# @!attribute [rw] top
# @return [::Float]
# Top Y coordinate.
# @!attribute [rw] right
# @return [::Float]
# Right X coordinate.
# @!attribute [rw] bottom
# @return [::Float]
# Bottom Y coordinate.
class NormalizedBoundingBox
include ::Google::Protobuf::MessageExts
extend ::Google::Protobuf::MessageExts::ClassMethods
end
# For tracking related features.
# An object at time_offset with attributes, and located with
# normalized_bounding_box.
# @!attribute [rw] normalized_bounding_box
# @return [::Google::Cloud::VideoIntelligence::V1p3beta1::NormalizedBoundingBox]
# Normalized Bounding box in a frame, where the object is located.
# @!attribute [rw] time_offset
# @return [::Google::Protobuf::Duration]
# Time-offset, relative to the beginning of the video,
# corresponding to the video frame for this object.
# @!attribute [rw] attributes
# @return [::Array<::Google::Cloud::VideoIntelligence::V1p3beta1::DetectedAttribute>]
# Optional. The attributes of the object in the bounding box.
# @!attribute [rw] landmarks
# @return [::Array<::Google::Cloud::VideoIntelligence::V1p3beta1::DetectedLandmark>]
# Optional. The detected landmarks.
class TimestampedObject
include ::Google::Protobuf::MessageExts
extend ::Google::Protobuf::MessageExts::ClassMethods
end
# A track of an object instance.
# @!attribute [rw] segment
# @return [::Google::Cloud::VideoIntelligence::V1p3beta1::VideoSegment]
# Video segment of a track.
# @!attribute [rw] timestamped_objects
# @return [::Array<::Google::Cloud::VideoIntelligence::V1p3beta1::TimestampedObject>]
# The object with timestamp and attributes per frame in the track.
# @!attribute [rw] attributes
# @return [::Array<::Google::Cloud::VideoIntelligence::V1p3beta1::DetectedAttribute>]
# Optional. Attributes in the track level.
# @!attribute [rw] confidence
# @return [::Float]
# Optional. The confidence score of the tracked object.
class Track
include ::Google::Protobuf::MessageExts
extend ::Google::Protobuf::MessageExts::ClassMethods
end
# A generic detected attribute represented by name in string format.
# @!attribute [rw] name
# @return [::String]
# 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.
# @!attribute [rw] confidence
# @return [::Float]
# Detected attribute confidence. Range [0, 1].
# @!attribute [rw] value
# @return [::String]
# Text value of the detection result. For example, the value for "HairColor"
# can be "black", "blonde", etc.
class DetectedAttribute
include ::Google::Protobuf::MessageExts
extend ::Google::Protobuf::MessageExts::ClassMethods
end
# Celebrity definition.
# @!attribute [rw] name
# @return [::String]
# 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.
# @!attribute [rw] display_name
# @return [::String]
# The celebrity name.
# @!attribute [rw] description
# @return [::String]
# Textual description of additional information about the celebrity, if
# applicable.
class Celebrity
include ::Google::Protobuf::MessageExts
extend ::Google::Protobuf::MessageExts::ClassMethods
end
# The annotation result of a celebrity face track. RecognizedCelebrity field
# could be empty if the face track does not have any matched celebrities.
# @!attribute [rw] celebrities
# @return [::Array<::Google::Cloud::VideoIntelligence::V1p3beta1::CelebrityTrack::RecognizedCelebrity>]
# Top N match of the celebrities for the face in this track.
# @!attribute [rw] face_track
# @return [::Google::Cloud::VideoIntelligence::V1p3beta1::Track]
# A track of a person's face.
class CelebrityTrack
include ::Google::Protobuf::MessageExts
extend ::Google::Protobuf::MessageExts::ClassMethods
# The recognized celebrity with confidence score.
# @!attribute [rw] celebrity
# @return [::Google::Cloud::VideoIntelligence::V1p3beta1::Celebrity]
# The recognized celebrity.
# @!attribute [rw] confidence
# @return [::Float]
# Recognition confidence. Range [0, 1].
class RecognizedCelebrity
include ::Google::Protobuf::MessageExts
extend ::Google::Protobuf::MessageExts::ClassMethods
end
end
# Celebrity recognition annotation per video.
# @!attribute [rw] celebrity_tracks
# @return [::Array<::Google::Cloud::VideoIntelligence::V1p3beta1::CelebrityTrack>]
# The tracks detected from the input video, including recognized celebrities
# and other detected faces in the video.
class CelebrityRecognitionAnnotation
include ::Google::Protobuf::MessageExts
extend ::Google::Protobuf::MessageExts::ClassMethods
end
# A generic detected landmark represented by name in string format and a 2D
# location.
# @!attribute [rw] name
# @return [::String]
# The name of this landmark, for example, left_hand, right_shoulder.
# @!attribute [rw] point
# @return [::Google::Cloud::VideoIntelligence::V1p3beta1::NormalizedVertex]
# The 2D point of the detected landmark using the normalized image
# coordindate system. The normalized coordinates have the range from 0 to 1.
# @!attribute [rw] confidence
# @return [::Float]
# The confidence score of the detected landmark. Range [0, 1].
class DetectedLandmark
include ::Google::Protobuf::MessageExts
extend ::Google::Protobuf::MessageExts::ClassMethods
end
# Face detection annotation.
# @!attribute [rw] tracks
# @return [::Array<::Google::Cloud::VideoIntelligence::V1p3beta1::Track>]
# The face tracks with attributes.
# @!attribute [rw] thumbnail
# @return [::String]
# The thumbnail of a person's face.
class FaceDetectionAnnotation
include ::Google::Protobuf::MessageExts
extend ::Google::Protobuf::MessageExts::ClassMethods
end
# Person detection annotation per video.
# @!attribute [rw] tracks
# @return [::Array<::Google::Cloud::VideoIntelligence::V1p3beta1::Track>]
# The detected tracks of a person.
class PersonDetectionAnnotation
include ::Google::Protobuf::MessageExts
extend ::Google::Protobuf::MessageExts::ClassMethods
end
# Annotation results for a single video.
# @!attribute [rw] input_uri
# @return [::String]
# Video file location in
# [Cloud Storage](https://cloud.google.com/storage/).
# @!attribute [rw] segment
# @return [::Google::Cloud::VideoIntelligence::V1p3beta1::VideoSegment]
# Video segment on which the annotation is run.
# @!attribute [rw] segment_label_annotations
# @return [::Array<::Google::Cloud::VideoIntelligence::V1p3beta1::LabelAnnotation>]
# Topical label annotations on video level or user-specified segment level.
# There is exactly one element for each unique label.
# @!attribute [rw] segment_presence_label_annotations
# @return [::Array<::Google::Cloud::VideoIntelligence::V1p3beta1::LabelAnnotation>]
# 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.
# @!attribute [rw] shot_label_annotations
# @return [::Array<::Google::Cloud::VideoIntelligence::V1p3beta1::LabelAnnotation>]
# Topical label annotations on shot level.
# There is exactly one element for each unique label.
# @!attribute [rw] shot_presence_label_annotations
# @return [::Array<::Google::Cloud::VideoIntelligence::V1p3beta1::LabelAnnotation>]
# 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.
# @!attribute [rw] frame_label_annotations
# @return [::Array<::Google::Cloud::VideoIntelligence::V1p3beta1::LabelAnnotation>]
# Label annotations on frame level.
# There is exactly one element for each unique label.
# @!attribute [rw] face_detection_annotations
# @return [::Array<::Google::Cloud::VideoIntelligence::V1p3beta1::FaceDetectionAnnotation>]
# Face detection annotations.
# @!attribute [rw] shot_annotations
# @return [::Array<::Google::Cloud::VideoIntelligence::V1p3beta1::VideoSegment>]
# Shot annotations. Each shot is represented as a video segment.
# @!attribute [rw] explicit_annotation
# @return [::Google::Cloud::VideoIntelligence::V1p3beta1::ExplicitContentAnnotation]
# Explicit content annotation.
# @!attribute [rw] speech_transcriptions
# @return [::Array<::Google::Cloud::VideoIntelligence::V1p3beta1::SpeechTranscription>]
# Speech transcription.
# @!attribute [rw] text_annotations
# @return [::Array<::Google::Cloud::VideoIntelligence::V1p3beta1::TextAnnotation>]
# OCR text detection and tracking.
# Annotations for list of detected text snippets. Each will have list of
# frame information associated with it.
# @!attribute [rw] object_annotations
# @return [::Array<::Google::Cloud::VideoIntelligence::V1p3beta1::ObjectTrackingAnnotation>]
# Annotations for list of objects detected and tracked in video.
# @!attribute [rw] logo_recognition_annotations
# @return [::Array<::Google::Cloud::VideoIntelligence::V1p3beta1::LogoRecognitionAnnotation>]
# Annotations for list of logos detected, tracked and recognized in video.
# @!attribute [rw] person_detection_annotations
# @return [::Array<::Google::Cloud::VideoIntelligence::V1p3beta1::PersonDetectionAnnotation>]
# Person detection annotations.
# @!attribute [rw] celebrity_recognition_annotations
# @return [::Google::Cloud::VideoIntelligence::V1p3beta1::CelebrityRecognitionAnnotation]
# Celebrity recognition annotations.
# @!attribute [rw] error
# @return [::Google::Rpc::Status]
# If set, indicates an error. Note that for a single `AnnotateVideoRequest`
# some videos may succeed and some may fail.
class VideoAnnotationResults
include ::Google::Protobuf::MessageExts
extend ::Google::Protobuf::MessageExts::ClassMethods
end
# Video annotation response. Included in the `response`
# field of the `Operation` returned by the `GetOperation`
# call of the `google::longrunning::Operations` service.
# @!attribute [rw] annotation_results
# @return [::Array<::Google::Cloud::VideoIntelligence::V1p3beta1::VideoAnnotationResults>]
# Annotation results for all videos specified in `AnnotateVideoRequest`.
class AnnotateVideoResponse
include ::Google::Protobuf::MessageExts
extend ::Google::Protobuf::MessageExts::ClassMethods
end
# Annotation progress for a single video.
# @!attribute [rw] input_uri
# @return [::String]
# Video file location in
# [Cloud Storage](https://cloud.google.com/storage/).
# @!attribute [rw] progress_percent
# @return [::Integer]
# Approximate percentage processed thus far. Guaranteed to be
# 100 when fully processed.
# @!attribute [rw] start_time
# @return [::Google::Protobuf::Timestamp]
# Time when the request was received.
# @!attribute [rw] update_time
# @return [::Google::Protobuf::Timestamp]
# Time of the most recent update.
# @!attribute [rw] feature
# @return [::Google::Cloud::VideoIntelligence::V1p3beta1::Feature]
# Specifies which feature is being tracked if the request contains more than
# one feature.
# @!attribute [rw] segment
# @return [::Google::Cloud::VideoIntelligence::V1p3beta1::VideoSegment]
# Specifies which segment is being tracked if the request contains more than
# one segment.
class VideoAnnotationProgress
include ::Google::Protobuf::MessageExts
extend ::Google::Protobuf::MessageExts::ClassMethods
end
# Video annotation progress. Included in the `metadata`
# field of the `Operation` returned by the `GetOperation`
# call of the `google::longrunning::Operations` service.
# @!attribute [rw] annotation_progress
# @return [::Array<::Google::Cloud::VideoIntelligence::V1p3beta1::VideoAnnotationProgress>]
# Progress metadata for all videos specified in `AnnotateVideoRequest`.
class AnnotateVideoProgress
include ::Google::Protobuf::MessageExts
extend ::Google::Protobuf::MessageExts::ClassMethods
end
# Config for SPEECH_TRANSCRIPTION.
# @!attribute [rw] language_code
# @return [::String]
# 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.
# @!attribute [rw] max_alternatives
# @return [::Integer]
# 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.
# @!attribute [rw] filter_profanity
# @return [::Boolean]
# 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.
# @!attribute [rw] speech_contexts
# @return [::Array<::Google::Cloud::VideoIntelligence::V1p3beta1::SpeechContext>]
# Optional. A means to provide context to assist the speech recognition.
# @!attribute [rw] enable_automatic_punctuation
# @return [::Boolean]
# 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."
# @!attribute [rw] audio_tracks
# @return [::Array<::Integer>]
# Optional. For file formats, such as MXF or MKV, supporting multiple audio
# tracks, specify up to two tracks. Default: track 0.
# @!attribute [rw] enable_speaker_diarization
# @return [::Boolean]
# 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.
# @!attribute [rw] diarization_speaker_count
# @return [::Integer]
# 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.
# @!attribute [rw] enable_word_confidence
# @return [::Boolean]
# 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`.
class SpeechTranscriptionConfig
include ::Google::Protobuf::MessageExts
extend ::Google::Protobuf::MessageExts::ClassMethods
end
# Provides "hints" to the speech recognizer to favor specific words and phrases
# in the results.
# @!attribute [rw] phrases
# @return [::Array<::String>]
# 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).
class SpeechContext
include ::Google::Protobuf::MessageExts
extend ::Google::Protobuf::MessageExts::ClassMethods
end
# A speech recognition result corresponding to a portion of the audio.
# @!attribute [rw] alternatives
# @return [::Array<::Google::Cloud::VideoIntelligence::V1p3beta1::SpeechRecognitionAlternative>]
# 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.
# @!attribute [r] language_code
# @return [::String]
# 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.
class SpeechTranscription
include ::Google::Protobuf::MessageExts
extend ::Google::Protobuf::MessageExts::ClassMethods
end
# Alternative hypotheses (a.k.a. n-best list).
# @!attribute [rw] transcript
# @return [::String]
# Transcript text representing the words that the user spoke.
# @!attribute [r] confidence
# @return [::Float]
# 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.
# @!attribute [r] words
# @return [::Array<::Google::Cloud::VideoIntelligence::V1p3beta1::WordInfo>]
# 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.
class SpeechRecognitionAlternative
include ::Google::Protobuf::MessageExts
extend ::Google::Protobuf::MessageExts::ClassMethods
end
# 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`.
# @!attribute [rw] start_time
# @return [::Google::Protobuf::Duration]
# 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.
# @!attribute [rw] end_time
# @return [::Google::Protobuf::Duration]
# 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.
# @!attribute [rw] word
# @return [::String]
# The word corresponding to this set of information.
# @!attribute [r] confidence
# @return [::Float]
# 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.
# @!attribute [r] speaker_tag
# @return [::Integer]
# 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.
class WordInfo
include ::Google::Protobuf::MessageExts
extend ::Google::Protobuf::MessageExts::ClassMethods
end
# 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.
# @!attribute [rw] x
# @return [::Float]
# X coordinate.
# @!attribute [rw] y
# @return [::Float]
# Y coordinate.
class NormalizedVertex
include ::Google::Protobuf::MessageExts
extend ::Google::Protobuf::MessageExts::ClassMethods
end
# 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.
# @!attribute [rw] vertices
# @return [::Array<::Google::Cloud::VideoIntelligence::V1p3beta1::NormalizedVertex>]
# Normalized vertices of the bounding polygon.
class NormalizedBoundingPoly
include ::Google::Protobuf::MessageExts
extend ::Google::Protobuf::MessageExts::ClassMethods
end
# Video segment level annotation results for text detection.
# @!attribute [rw] segment
# @return [::Google::Cloud::VideoIntelligence::V1p3beta1::VideoSegment]
# Video segment where a text snippet was detected.
# @!attribute [rw] confidence
# @return [::Float]
# Confidence for the track of detected text. It is calculated as the highest
# over all frames where OCR detected text appears.
# @!attribute [rw] frames
# @return [::Array<::Google::Cloud::VideoIntelligence::V1p3beta1::TextFrame>]
# Information related to the frames where OCR detected text appears.
class TextSegment
include ::Google::Protobuf::MessageExts
extend ::Google::Protobuf::MessageExts::ClassMethods
end
# 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.
# @!attribute [rw] rotated_bounding_box
# @return [::Google::Cloud::VideoIntelligence::V1p3beta1::NormalizedBoundingPoly]
# Bounding polygon of the detected text for this frame.
# @!attribute [rw] time_offset
# @return [::Google::Protobuf::Duration]
# Timestamp of this frame.
class TextFrame
include ::Google::Protobuf::MessageExts
extend ::Google::Protobuf::MessageExts::ClassMethods
end
# Annotations related to one detected OCR text snippet. This will contain the
# corresponding text, confidence value, and frame level information for each
# detection.
# @!attribute [rw] text
# @return [::String]
# The detected text.
# @!attribute [rw] segments
# @return [::Array<::Google::Cloud::VideoIntelligence::V1p3beta1::TextSegment>]
# All video segments where OCR detected text appears.
class TextAnnotation
include ::Google::Protobuf::MessageExts
extend ::Google::Protobuf::MessageExts::ClassMethods
end
# Video frame level annotations for object detection and tracking. This field
# stores per frame location, time offset, and confidence.
# @!attribute [rw] normalized_bounding_box
# @return [::Google::Cloud::VideoIntelligence::V1p3beta1::NormalizedBoundingBox]
# The normalized bounding box location of this object track for the frame.
# @!attribute [rw] time_offset
# @return [::Google::Protobuf::Duration]
# The timestamp of the frame in microseconds.
class ObjectTrackingFrame
include ::Google::Protobuf::MessageExts
extend ::Google::Protobuf::MessageExts::ClassMethods
end
# Annotations corresponding to one tracked object.
# @!attribute [rw] segment
# @return [::Google::Cloud::VideoIntelligence::V1p3beta1::VideoSegment]
# Non-streaming batch mode ONLY.
# Each object track corresponds to one video segment where it appears.
# @!attribute [rw] track_id
# @return [::Integer]
# 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.
# @!attribute [rw] entity
# @return [::Google::Cloud::VideoIntelligence::V1p3beta1::Entity]
# Entity to specify the object category that this track is labeled as.
# @!attribute [rw] confidence
# @return [::Float]
# Object category's labeling confidence of this track.
# @!attribute [rw] frames
# @return [::Array<::Google::Cloud::VideoIntelligence::V1p3beta1::ObjectTrackingFrame>]
# 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.
class ObjectTrackingAnnotation
include ::Google::Protobuf::MessageExts
extend ::Google::Protobuf::MessageExts::ClassMethods
end
# Annotation corresponding to one detected, tracked and recognized logo class.
# @!attribute [rw] entity
# @return [::Google::Cloud::VideoIntelligence::V1p3beta1::Entity]
# Entity category information to specify the logo class that all the logo
# tracks within this LogoRecognitionAnnotation are recognized as.
# @!attribute [rw] tracks
# @return [::Array<::Google::Cloud::VideoIntelligence::V1p3beta1::Track>]
# All logo tracks where the recognized logo appears. Each track corresponds
# to one logo instance appearing in consecutive frames.
# @!attribute [rw] segments
# @return [::Array<::Google::Cloud::VideoIntelligence::V1p3beta1::VideoSegment>]
# All video segments where the recognized logo appears. There might be
# multiple instances of the same logo class appearing in one VideoSegment.
class LogoRecognitionAnnotation
include ::Google::Protobuf::MessageExts
extend ::Google::Protobuf::MessageExts::ClassMethods
end
# The top-level message sent by the client for the `StreamingAnnotateVideo`
# method. Multiple `StreamingAnnotateVideoRequest` messages are sent.
# The first message must only contain a `StreamingVideoConfig` message.
# All subsequent messages must only contain `input_content` data.
# @!attribute [rw] video_config
# @return [::Google::Cloud::VideoIntelligence::V1p3beta1::StreamingVideoConfig]
# Provides information to the annotator, specifing how to process the
# request. The first `AnnotateStreamingVideoRequest` message must only
# contain a `video_config` message.
# @!attribute [rw] input_content
# @return [::String]
# The video data to be annotated. Chunks of video data are sequentially
# sent in `StreamingAnnotateVideoRequest` messages. Except the initial
# `StreamingAnnotateVideoRequest` message containing only
# `video_config`, all subsequent `AnnotateStreamingVideoRequest`
# messages must only contain `input_content` field.
# Note: as with all bytes fields, protobuffers use a pure binary
# representation (not base64).
class StreamingAnnotateVideoRequest
include ::Google::Protobuf::MessageExts
extend ::Google::Protobuf::MessageExts::ClassMethods
end
# Provides information to the annotator that specifies how to process the
# request.
# @!attribute [rw] shot_change_detection_config
# @return [::Google::Cloud::VideoIntelligence::V1p3beta1::StreamingShotChangeDetectionConfig]
# Config for STREAMING_SHOT_CHANGE_DETECTION.
# @!attribute [rw] label_detection_config
# @return [::Google::Cloud::VideoIntelligence::V1p3beta1::StreamingLabelDetectionConfig]
# Config for STREAMING_LABEL_DETECTION.
# @!attribute [rw] explicit_content_detection_config
# @return [::Google::Cloud::VideoIntelligence::V1p3beta1::StreamingExplicitContentDetectionConfig]
# Config for STREAMING_EXPLICIT_CONTENT_DETECTION.
# @!attribute [rw] object_tracking_config
# @return [::Google::Cloud::VideoIntelligence::V1p3beta1::StreamingObjectTrackingConfig]
# Config for STREAMING_OBJECT_TRACKING.
# @!attribute [rw] automl_action_recognition_config
# @return [::Google::Cloud::VideoIntelligence::V1p3beta1::StreamingAutomlActionRecognitionConfig]
# Config for STREAMING_AUTOML_ACTION_RECOGNITION.
# @!attribute [rw] automl_classification_config
# @return [::Google::Cloud::VideoIntelligence::V1p3beta1::StreamingAutomlClassificationConfig]
# Config for STREAMING_AUTOML_CLASSIFICATION.
# @!attribute [rw] automl_object_tracking_config
# @return [::Google::Cloud::VideoIntelligence::V1p3beta1::StreamingAutomlObjectTrackingConfig]
# Config for STREAMING_AUTOML_OBJECT_TRACKING.
# @!attribute [rw] feature
# @return [::Google::Cloud::VideoIntelligence::V1p3beta1::StreamingFeature]
# Requested annotation feature.
# @!attribute [rw] storage_config
# @return [::Google::Cloud::VideoIntelligence::V1p3beta1::StreamingStorageConfig]
# Streaming storage option. By default: storage is disabled.
class StreamingVideoConfig
include ::Google::Protobuf::MessageExts
extend ::Google::Protobuf::MessageExts::ClassMethods
end
# `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.
# @!attribute [rw] error
# @return [::Google::Rpc::Status]
# If set, returns a {::Google::Rpc::Status google.rpc.Status} message that
# specifies the error for the operation.
# @!attribute [rw] annotation_results
# @return [::Google::Cloud::VideoIntelligence::V1p3beta1::StreamingVideoAnnotationResults]
# Streaming annotation results.
# @!attribute [rw] annotation_results_uri
# @return [::String]
# Google Cloud Storage(GCS) 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'.
class StreamingAnnotateVideoResponse
include ::Google::Protobuf::MessageExts
extend ::Google::Protobuf::MessageExts::ClassMethods
end
# Streaming annotation results corresponding to a portion of the video
# that is currently being processed.
# @!attribute [rw] shot_annotations
# @return [::Array<::Google::Cloud::VideoIntelligence::V1p3beta1::VideoSegment>]
# Shot annotation results. Each shot is represented as a video segment.
# @!attribute [rw] label_annotations
# @return [::Array<::Google::Cloud::VideoIntelligence::V1p3beta1::LabelAnnotation>]
# Label annotation results.
# @!attribute [rw] explicit_annotation
# @return [::Google::Cloud::VideoIntelligence::V1p3beta1::ExplicitContentAnnotation]
# Explicit content annotation results.
# @!attribute [rw] object_annotations
# @return [::Array<::Google::Cloud::VideoIntelligence::V1p3beta1::ObjectTrackingAnnotation>]
# Object tracking results.
class StreamingVideoAnnotationResults
include ::Google::Protobuf::MessageExts
extend ::Google::Protobuf::MessageExts::ClassMethods
end
# Config for STREAMING_SHOT_CHANGE_DETECTION.
class StreamingShotChangeDetectionConfig
include ::Google::Protobuf::MessageExts
extend ::Google::Protobuf::MessageExts::ClassMethods
end
# Config for STREAMING_LABEL_DETECTION.
# @!attribute [rw] stationary_camera
# @return [::Boolean]
# Whether the video has been captured from a stationary (i.e. non-moving)
# camera. When set to true, might improve detection accuracy for moving
# objects. Default: false.
class StreamingLabelDetectionConfig
include ::Google::Protobuf::MessageExts
extend ::Google::Protobuf::MessageExts::ClassMethods
end
# Config for STREAMING_EXPLICIT_CONTENT_DETECTION.
class StreamingExplicitContentDetectionConfig
include ::Google::Protobuf::MessageExts
extend ::Google::Protobuf::MessageExts::ClassMethods
end
# Config for STREAMING_OBJECT_TRACKING.
class StreamingObjectTrackingConfig
include ::Google::Protobuf::MessageExts
extend ::Google::Protobuf::MessageExts::ClassMethods
end
# Config for STREAMING_AUTOML_ACTION_RECOGNITION.
# @!attribute [rw] model_name
# @return [::String]
# Resource name of AutoML model.
# Format: `projects/{project_id}/locations/{location_id}/models/{model_id}`
class StreamingAutomlActionRecognitionConfig
include ::Google::Protobuf::MessageExts
extend ::Google::Protobuf::MessageExts::ClassMethods
end
# Config for STREAMING_AUTOML_CLASSIFICATION.
# @!attribute [rw] model_name
# @return [::String]
# Resource name of AutoML model.
# Format:
# `projects/{project_number}/locations/{location_id}/models/{model_id}`
class StreamingAutomlClassificationConfig
include ::Google::Protobuf::MessageExts
extend ::Google::Protobuf::MessageExts::ClassMethods
end
# Config for STREAMING_AUTOML_OBJECT_TRACKING.
# @!attribute [rw] model_name
# @return [::String]
# Resource name of AutoML model.
# Format: `projects/{project_id}/locations/{location_id}/models/{model_id}`
class StreamingAutomlObjectTrackingConfig
include ::Google::Protobuf::MessageExts
extend ::Google::Protobuf::MessageExts::ClassMethods
end
# Config for streaming storage option.
# @!attribute [rw] enable_storage_annotation_result
# @return [::Boolean]
# Enable streaming storage. Default: false.
# @!attribute [rw] annotation_result_storage_directory
# @return [::String]
# Cloud Storage URI to store all annotation results for one client. Client
# should specify this field as the top-level storage directory. Annotation
# results of different sessions will be put into different sub-directories
# denoted by project_name and session_id. All sub-directories will be auto
# generated by program and will be made accessible to client in response
# proto. URIs must be specified in the following format:
# `gs://bucket-id/object-id` `bucket-id` should be a valid Cloud Storage
# bucket created by client and bucket permission shall also be configured
# properly. `object-id` can be arbitrary string that make sense to client.
# Other URI formats will return error and cause Cloud Storage write failure.
class StreamingStorageConfig
include ::Google::Protobuf::MessageExts
extend ::Google::Protobuf::MessageExts::ClassMethods
end
# Label detection mode.
module LabelDetectionMode
# Unspecified.
LABEL_DETECTION_MODE_UNSPECIFIED = 0
# Detect shot-level labels.
SHOT_MODE = 1
# Detect frame-level labels.
FRAME_MODE = 2
# Detect both shot-level and frame-level labels.
SHOT_AND_FRAME_MODE = 3
end
# Bucketized representation of likelihood.
module Likelihood
# Unspecified likelihood.
LIKELIHOOD_UNSPECIFIED = 0
# Very unlikely.
VERY_UNLIKELY = 1
# Unlikely.
UNLIKELY = 2
# Possible.
POSSIBLE = 3
# Likely.
LIKELY = 4
# Very likely.
VERY_LIKELY = 5
end
# Streaming video annotation feature.
module StreamingFeature
# Unspecified.
STREAMING_FEATURE_UNSPECIFIED = 0
# Label detection. Detect objects, such as dog or flower.
STREAMING_LABEL_DETECTION = 1
# Shot change detection.
STREAMING_SHOT_CHANGE_DETECTION = 2
# Explicit content detection.
STREAMING_EXPLICIT_CONTENT_DETECTION = 3
# Object detection and tracking.
STREAMING_OBJECT_TRACKING = 4
# Action recognition based on AutoML model.
STREAMING_AUTOML_ACTION_RECOGNITION = 23
# Video classification based on AutoML model.
STREAMING_AUTOML_CLASSIFICATION = 21
# Object detection and tracking based on AutoML model.
STREAMING_AUTOML_OBJECT_TRACKING = 22
end
# Video annotation feature.
module Feature
# Unspecified.
FEATURE_UNSPECIFIED = 0
# Label detection. Detect objects, such as dog or flower.
LABEL_DETECTION = 1
# Shot change detection.
SHOT_CHANGE_DETECTION = 2
# Explicit content detection.
EXPLICIT_CONTENT_DETECTION = 3
# Human face detection.
FACE_DETECTION = 4
# Speech transcription.
SPEECH_TRANSCRIPTION = 6
# OCR text detection and tracking.
TEXT_DETECTION = 7
# Object detection and tracking.
OBJECT_TRACKING = 9
# Logo detection, tracking, and recognition.
LOGO_RECOGNITION = 12
# Celebrity recognition.
CELEBRITY_RECOGNITION = 13
# Person detection.
PERSON_DETECTION = 14
end
end
end
end
end