Annotate a video file in Cloud Storage

func labelURI(w io.Writer, file string) error {
	ctx := context.Background()
	client, err := video.NewClient(ctx)
	if err != nil {
		return fmt.Errorf("video.NewClient: %w", err)
	}
	defer client.Close()

	op, err := client.AnnotateVideo(ctx, &videopb.AnnotateVideoRequest{
		Features: []videopb.Feature{
			videopb.Feature_LABEL_DETECTION,
		},
		InputUri: file,
	})
	if err != nil {
		return fmt.Errorf("AnnotateVideo: %w", err)
	}

	resp, err := op.Wait(ctx)
	if err != nil {
		return fmt.Errorf("Wait: %w", err)
	}

	printLabels := func(labels []*videopb.LabelAnnotation) {
		for _, label := range labels {
			fmt.Fprintf(w, "\tDescription: %s\n", label.Entity.Description)
			for _, category := range label.CategoryEntities {
				fmt.Fprintf(w, "\t\tCategory: %s\n", category.Description)
			}
			for _, segment := range label.Segments {
				start, _ := ptypes.Duration(segment.Segment.StartTimeOffset)
				end, _ := ptypes.Duration(segment.Segment.EndTimeOffset)
				fmt.Fprintf(w, "\t\tSegment: %s to %s\n", start, end)
			}
		}
	}

	// A single video was processed. Get the first result.
	result := resp.AnnotationResults[0]

	fmt.Fprintln(w, "SegmentLabelAnnotations:")
	printLabels(result.SegmentLabelAnnotations)
	fmt.Fprintln(w, "ShotLabelAnnotations:")
	printLabels(result.ShotLabelAnnotations)
	fmt.Fprintln(w, "FrameLabelAnnotations:")
	printLabels(result.FrameLabelAnnotations)

	return nil
}

// Instantiate a com.google.cloud.videointelligence.v1.VideoIntelligenceServiceClient
try (VideoIntelligenceServiceClient client = VideoIntelligenceServiceClient.create()) {
  // Provide path to file hosted on GCS as "gs://bucket-name/..."
  AnnotateVideoRequest request =
      AnnotateVideoRequest.newBuilder()
          .setInputUri(gcsUri)
          .addFeatures(Feature.LABEL_DETECTION)
          .build();
  // Create an operation that will contain the response when the operation completes.
  OperationFuture<AnnotateVideoResponse, AnnotateVideoProgress> response =
      client.annotateVideoAsync(request);

  System.out.println("Waiting for operation to complete...");
  for (VideoAnnotationResults results : response.get().getAnnotationResultsList()) {
    // process video / segment level label annotations
    System.out.println("Locations: ");
    for (LabelAnnotation labelAnnotation : results.getSegmentLabelAnnotationsList()) {
      System.out.println("Video label: " + labelAnnotation.getEntity().getDescription());
      // categories
      for (Entity categoryEntity : labelAnnotation.getCategoryEntitiesList()) {
        System.out.println("Video label category: " + categoryEntity.getDescription());
      }
      // segments
      for (LabelSegment segment : labelAnnotation.getSegmentsList()) {
        double startTime =
            segment.getSegment().getStartTimeOffset().getSeconds()
                + segment.getSegment().getStartTimeOffset().getNanos() / 1e9;
        double endTime =
            segment.getSegment().getEndTimeOffset().getSeconds()
                + segment.getSegment().getEndTimeOffset().getNanos() / 1e9;
        System.out.printf("Segment location: %.3f:%.3f\n", startTime, endTime);
        System.out.println("Confidence: " + segment.getConfidence());
      }
    }

    // process shot label annotations
    for (LabelAnnotation labelAnnotation : results.getShotLabelAnnotationsList()) {
      System.out.println("Shot label: " + labelAnnotation.getEntity().getDescription());
      // categories
      for (Entity categoryEntity : labelAnnotation.getCategoryEntitiesList()) {
        System.out.println("Shot label category: " + categoryEntity.getDescription());
      }
      // segments
      for (LabelSegment segment : labelAnnotation.getSegmentsList()) {
        double startTime =
            segment.getSegment().getStartTimeOffset().getSeconds()
                + segment.getSegment().getStartTimeOffset().getNanos() / 1e9;
        double endTime =
            segment.getSegment().getEndTimeOffset().getSeconds()
                + segment.getSegment().getEndTimeOffset().getNanos() / 1e9;
        System.out.printf("Segment location: %.3f:%.3f\n", startTime, endTime);
        System.out.println("Confidence: " + segment.getConfidence());
      }
    }

    // process frame label annotations
    for (LabelAnnotation labelAnnotation : results.getFrameLabelAnnotationsList()) {
      System.out.println("Frame label: " + labelAnnotation.getEntity().getDescription());
      // categories
      for (Entity categoryEntity : labelAnnotation.getCategoryEntitiesList()) {
        System.out.println("Frame label category: " + categoryEntity.getDescription());
      }
      // segments
      for (LabelSegment segment : labelAnnotation.getSegmentsList()) {
        double startTime =
            segment.getSegment().getStartTimeOffset().getSeconds()
                + segment.getSegment().getStartTimeOffset().getNanos() / 1e9;
        double endTime =
            segment.getSegment().getEndTimeOffset().getSeconds()
                + segment.getSegment().getEndTimeOffset().getNanos() / 1e9;
        System.out.printf("Segment location: %.3f:%.2f\n", startTime, endTime);
        System.out.println("Confidence: " + segment.getConfidence());
      }
    }
  }
}

// Imports the Google Cloud Video Intelligence library
const video = require('@google-cloud/video-intelligence').v1;

// Creates a client
const client = new video.VideoIntelligenceServiceClient();

/**
 * TODO(developer): Uncomment the following line before running the sample.
 */
// const gcsUri = 'GCS URI of the video to analyze, e.g. gs://my-bucket/my-video.mp4';

const request = {
  inputUri: gcsUri,
  features: ['LABEL_DETECTION'],
};

// Detects labels in a video
const [operation] = await client.annotateVideo(request);
console.log('Waiting for operation to complete...');
const [operationResult] = await operation.promise();

// Gets annotations for video
const annotations = operationResult.annotationResults[0];

const labels = annotations.segmentLabelAnnotations;
labels.forEach(label => {
  console.log(`Label ${label.entity.description} occurs at:`);
  label.segments.forEach(segment => {
    const time = segment.segment;
    if (time.startTimeOffset.seconds === undefined) {
      time.startTimeOffset.seconds = 0;
    }
    if (time.startTimeOffset.nanos === undefined) {
      time.startTimeOffset.nanos = 0;
    }
    if (time.endTimeOffset.seconds === undefined) {
      time.endTimeOffset.seconds = 0;
    }
    if (time.endTimeOffset.nanos === undefined) {
      time.endTimeOffset.nanos = 0;
    }
    console.log(
      `\tStart: ${time.startTimeOffset.seconds}` +
        `.${(time.startTimeOffset.nanos / 1e6).toFixed(0)}s`
    );
    console.log(
      `\tEnd: ${time.endTimeOffset.seconds}.` +
        `${(time.endTimeOffset.nanos / 1e6).toFixed(0)}s`
    );
    console.log(`\tConfidence: ${segment.confidence}`);
  });
});

use Google\Cloud\VideoIntelligence\V1\AnnotateVideoRequest;
use Google\Cloud\VideoIntelligence\V1\Client\VideoIntelligenceServiceClient;
use Google\Cloud\VideoIntelligence\V1\Feature;

/**
 * @param string $uri The cloud storage object to analyze (gs://your-bucket-name/your-object-name)
 * @param int $pollingIntervalSeconds
 */
function analyze_labels_gcs(string $uri, int $pollingIntervalSeconds = 0)
{
    # Instantiate a client.
    $video = new VideoIntelligenceServiceClient();

    # Execute a request.
    $features = [Feature::LABEL_DETECTION];
    $request = (new AnnotateVideoRequest())
        ->setInputUri($uri)
        ->setFeatures($features);
    $operation = $video->annotateVideo($request);

    # Wait for the request to complete.
    $operation->pollUntilComplete([
        'pollingIntervalSeconds' => $pollingIntervalSeconds
    ]);

    # Print the results.
    if ($operation->operationSucceeded()) {
        $results = $operation->getResult()->getAnnotationResults()[0];

        # Process video/segment level label annotations
        foreach ($results->getSegmentLabelAnnotations() as $label) {
            printf('Video label description: %s' . PHP_EOL, $label->getEntity()->getDescription());
            foreach ($label->getCategoryEntities() as $categoryEntity) {
                printf('  Category: %s' . PHP_EOL, $categoryEntity->getDescription());
            }
            foreach ($label->getSegments() as $segment) {
                $start = $segment->getSegment()->getStartTimeOffset();
                $end = $segment->getSegment()->getEndTimeOffset();
                printf('  Segment: %ss to %ss' . PHP_EOL,
                    $start->getSeconds() + $start->getNanos() / 1000000000.0,
                    $end->getSeconds() + $end->getNanos() / 1000000000.0);
                printf('  Confidence: %f' . PHP_EOL, $segment->getConfidence());
            }
        }
        print(PHP_EOL);

        # Process shot level label annotations
        foreach ($results->getShotLabelAnnotations() as $label) {
            printf('Shot label description: %s' . PHP_EOL, $label->getEntity()->getDescription());
            foreach ($label->getCategoryEntities() as $categoryEntity) {
                printf('  Category: %s' . PHP_EOL, $categoryEntity->getDescription());
            }
            foreach ($label->getSegments() as $shot) {
                $start = $shot->getSegment()->getStartTimeOffset();
                $end = $shot->getSegment()->getEndTimeOffset();
                printf('  Shot: %ss to %ss' . PHP_EOL,
                    $start->getSeconds() + $start->getNanos() / 1000000000.0,
                    $end->getSeconds() + $end->getNanos() / 1000000000.0);
                printf('  Confidence: %f' . PHP_EOL, $shot->getConfidence());
            }
        }
        print(PHP_EOL);
    } else {
        print_r($operation->getError());
    }
}

"""Detects labels given a GCS path."""
video_client = videointelligence.VideoIntelligenceServiceClient()
features = [videointelligence.Feature.LABEL_DETECTION]

mode = videointelligence.LabelDetectionMode.SHOT_AND_FRAME_MODE
config = videointelligence.LabelDetectionConfig(label_detection_mode=mode)
context = videointelligence.VideoContext(label_detection_config=config)

operation = video_client.annotate_video(
    request={"features": features, "input_uri": path, "video_context": context}
)
print("\nProcessing video for label annotations:")

result = operation.result(timeout=180)
print("\nFinished processing.")

# Process video/segment level label annotations
segment_labels = result.annotation_results[0].segment_label_annotations
for i, segment_label in enumerate(segment_labels):
    print("Video label description: {}".format(segment_label.entity.description))
    for category_entity in segment_label.category_entities:
        print(
            "\tLabel category description: {}".format(category_entity.description)
        )

    for i, segment in enumerate(segment_label.segments):
        start_time = (
            segment.segment.start_time_offset.seconds
            + segment.segment.start_time_offset.microseconds / 1e6
        )
        end_time = (
            segment.segment.end_time_offset.seconds
            + segment.segment.end_time_offset.microseconds / 1e6
        )
        positions = "{}s to {}s".format(start_time, end_time)
        confidence = segment.confidence
        print("\tSegment {}: {}".format(i, positions))
        print("\tConfidence: {}".format(confidence))
    print("\n")

# Process shot level label annotations
shot_labels = result.annotation_results[0].shot_label_annotations
for i, shot_label in enumerate(shot_labels):
    print("Shot label description: {}".format(shot_label.entity.description))
    for category_entity in shot_label.category_entities:
        print(
            "\tLabel category description: {}".format(category_entity.description)
        )

    for i, shot in enumerate(shot_label.segments):
        start_time = (
            shot.segment.start_time_offset.seconds
            + shot.segment.start_time_offset.microseconds / 1e6
        )
        end_time = (
            shot.segment.end_time_offset.seconds
            + shot.segment.end_time_offset.microseconds / 1e6
        )
        positions = "{}s to {}s".format(start_time, end_time)
        confidence = shot.confidence
        print("\tSegment {}: {}".format(i, positions))
        print("\tConfidence: {}".format(confidence))
    print("\n")

# Process frame level label annotations
frame_labels = result.annotation_results[0].frame_label_annotations
for i, frame_label in enumerate(frame_labels):
    print("Frame label description: {}".format(frame_label.entity.description))
    for category_entity in frame_label.category_entities:
        print(
            "\tLabel category description: {}".format(category_entity.description)
        )

    # Each frame_label_annotation has many frames,
    # here we print information only about the first frame.
    frame = frame_label.frames[0]
    time_offset = frame.time_offset.seconds + frame.time_offset.microseconds / 1e6
    print("\tFirst frame time offset: {}s".format(time_offset))
    print("\tFirst frame confidence: {}".format(frame.confidence))
    print("\n")