// Copyright 2017 Google Inc.
//
// 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
//
//     http://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.

syntax = "proto3";

package google.cloud.videointelligence.v1beta2;

import "google/api/annotations.proto";
import "google/longrunning/operations.proto";
import "google/protobuf/duration.proto";
import "google/protobuf/timestamp.proto";
import "google/rpc/status.proto";

option csharp_namespace = "Google.Cloud.VideoIntelligence.V1Beta2";
option go_package = "google.golang.org/genproto/googleapis/cloud/videointelligence/v1beta2;videointelligence";
option java_multiple_files = true;
option java_outer_classname = "VideoIntelligenceServiceProto";
option java_package = "com.google.cloud.videointelligence.v1beta2";
option php_namespace = "Google\\Cloud\\VideoIntelligence\\V1beta2";
option ruby_package = "Google::Cloud::VideoIntelligence::V1beta2";

// Service that implements Google Cloud Video Intelligence API.
service VideoIntelligenceService {
  // 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).
  rpc AnnotateVideo(AnnotateVideoRequest)
      returns (google.longrunning.Operation) {
    option (google.api.http) = {
      post: "/v1beta2/videos:annotate"
      body: "*"
    };
  }
}

// Video annotation request.
message AnnotateVideoRequest {
  // 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.
  string input_uri = 1;

  // The video data bytes.
  // If unset, the input video(s) should be specified via `input_uri`.
  // If set, `input_uri` should be unset.
  bytes input_content = 6;

  // Requested video annotation features.
  repeated Feature features = 2;

  // Additional video context and/or feature-specific parameters.
  VideoContext video_context = 3;

  // 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 output_uri = 4;

  // 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.
  string location_id = 5;
}

// Video context and/or feature-specific parameters.
message VideoContext {
  // 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.
  repeated VideoSegment segments = 1;

  // Config for LABEL_DETECTION.
  LabelDetectionConfig label_detection_config = 2;

  // Config for SHOT_CHANGE_DETECTION.
  ShotChangeDetectionConfig shot_change_detection_config = 3;

  // Config for EXPLICIT_CONTENT_DETECTION.
  ExplicitContentDetectionConfig explicit_content_detection_config = 4;

  // Config for FACE_DETECTION.
  FaceDetectionConfig face_detection_config = 5;
}

// Config for LABEL_DETECTION.
message LabelDetectionConfig {
  // 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 label_detection_mode = 1;

  // 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.
  bool stationary_camera = 2;

  // Model to use for label detection.
  // Supported values: "builtin/stable" (the default if unset) and
  // "builtin/latest".
  string model = 3;
}

// Config for SHOT_CHANGE_DETECTION.
message ShotChangeDetectionConfig {
  // Model to use for shot change detection.
  // Supported values: "builtin/stable" (the default if unset) and
  // "builtin/latest".
  string model = 1;
}

// Config for EXPLICIT_CONTENT_DETECTION.
message ExplicitContentDetectionConfig {
  // Model to use for explicit content detection.
  // Supported values: "builtin/stable" (the default if unset) and
  // "builtin/latest".
  string model = 1;
}

// Config for FACE_DETECTION.
message FaceDetectionConfig {
  // Model to use for face detection.
  // Supported values: "builtin/stable" (the default if unset) and
  // "builtin/latest".
  string model = 1;

  // Whether bounding boxes be included in the face annotation output.
  bool include_bounding_boxes = 2;
}

// Video segment.
message VideoSegment {
  // Time-offset, relative to the beginning of the video,
  // corresponding to the start of the segment (inclusive).
  google.protobuf.Duration start_time_offset = 1;

  // Time-offset, relative to the beginning of the video,
  // corresponding to the end of the segment (inclusive).
  google.protobuf.Duration end_time_offset = 2;
}

// Video segment level annotation results for label detection.
message LabelSegment {
  // Video segment where a label was detected.
  VideoSegment segment = 1;

  // Confidence that the label is accurate. Range: [0, 1].
  float confidence = 2;
}

// Video frame level annotation results for label detection.
message LabelFrame {
  // Time-offset, relative to the beginning of the video, corresponding to the
  // video frame for this location.
  google.protobuf.Duration time_offset = 1;

  // Confidence that the label is accurate. Range: [0, 1].
  float confidence = 2;
}

// Detected entity from video analysis.
message Entity {
  // Opaque entity ID. Some IDs may be available in
  // [Google Knowledge Graph Search
  // API](https://developers.google.com/knowledge-graph/).
  string entity_id = 1;

  // Textual description, e.g. `Fixed-gear bicycle`.
  string description = 2;

  // Language code for `description` in BCP-47 format.
  string language_code = 3;
}

// Label annotation.
message LabelAnnotation {
  // Detected entity.
  Entity entity = 1;

  // 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 Entity category_entities = 2;

  // All video segments where a label was detected.
  repeated LabelSegment segments = 3;

  // All video frames where a label was detected.
  repeated LabelFrame frames = 4;
}

// Video frame level annotation results for explicit content.
message ExplicitContentFrame {
  // Time-offset, relative to the beginning of the video, corresponding to the
  // video frame for this location.
  google.protobuf.Duration time_offset = 1;

  // Likelihood of the pornography content..
  Likelihood pornography_likelihood = 2;
}

// 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.
message ExplicitContentAnnotation {
  // All video frames where explicit content was detected.
  repeated ExplicitContentFrame frames = 1;
}

// Normalized bounding box.
// The normalized vertex coordinates are relative to the original image.
// Range: [0, 1].
message NormalizedBoundingBox {
  // Left X coordinate.
  float left = 1;

  // Top Y coordinate.
  float top = 2;

  // Right X coordinate.
  float right = 3;

  // Bottom Y coordinate.
  float bottom = 4;
}

// Video segment level annotation results for face detection.
message FaceSegment {
  // Video segment where a face was detected.
  VideoSegment segment = 1;
}

// Video frame level annotation results for face detection.
message FaceFrame {
  // 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.
  repeated NormalizedBoundingBox normalized_bounding_boxes = 1;

  // Time-offset, relative to the beginning of the video,
  // corresponding to the video frame for this location.
  google.protobuf.Duration time_offset = 2;
}

// Face annotation.
message FaceAnnotation {
  // Thumbnail of a representative face view (in JPEG format).
  bytes thumbnail = 1;

  // All video segments where a face was detected.
  repeated FaceSegment segments = 2;

  // All video frames where a face was detected.
  repeated FaceFrame frames = 3;
}

// Annotation results for a single video.
message VideoAnnotationResults {
  // Video file location in
  // [Google Cloud Storage](https://cloud.google.com/storage/).
  string input_uri = 1;

  // Label annotations on video level or user specified segment level.
  // There is exactly one element for each unique label.
  repeated LabelAnnotation segment_label_annotations = 2;

  // Label annotations on shot level.
  // There is exactly one element for each unique label.
  repeated LabelAnnotation shot_label_annotations = 3;

  // Label annotations on frame level.
  // There is exactly one element for each unique label.
  repeated LabelAnnotation frame_label_annotations = 4;

  // Face annotations. There is exactly one element for each unique face.
  repeated FaceAnnotation face_annotations = 5;

  // Shot annotations. Each shot is represented as a video segment.
  repeated VideoSegment shot_annotations = 6;

  // Explicit content annotation.
  ExplicitContentAnnotation explicit_annotation = 7;

  // If set, indicates an error. Note that for a single `AnnotateVideoRequest`
  // some videos may succeed and some may fail.
  google.rpc.Status error = 9;
}

// Video annotation response. Included in the `response`
// field of the `Operation` returned by the `GetOperation`
// call of the `google::longrunning::Operations` service.
message AnnotateVideoResponse {
  // Annotation results for all videos specified in `AnnotateVideoRequest`.
  repeated VideoAnnotationResults annotation_results = 1;
}

// Annotation progress for a single video.
message VideoAnnotationProgress {
  // Video file location in
  // [Google Cloud Storage](https://cloud.google.com/storage/).
  string input_uri = 1;

  // Approximate percentage processed thus far.
  // Guaranteed to be 100 when fully processed.
  int32 progress_percent = 2;

  // Time when the request was received.
  google.protobuf.Timestamp start_time = 3;

  // Time of the most recent update.
  google.protobuf.Timestamp update_time = 4;
}

// Video annotation progress. Included in the `metadata`
// field of the `Operation` returned by the `GetOperation`
// call of the `google::longrunning::Operations` service.
message AnnotateVideoProgress {
  // Progress metadata for all videos specified in `AnnotateVideoRequest`.
  repeated VideoAnnotationProgress annotation_progress = 1;
}

// Video annotation feature.
enum 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 and tracking.
  FACE_DETECTION = 4;
}

// Label detection mode.
enum 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;
}

// Bucketized representation of likelihood.
enum 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;
}