Analyzing videos for labels

This page describes how to use Cloud Video Intelligence to label entities shown in a video.

Video Intelligence can detect and extract information about entities shown in video footage. This feature, called label analysis, can identify objects, locations, activities, animal species, products, and more.

Here is an example of performing video analysis for labels on a local file.

Looking for something more in-depth? Check out our detailed Python tutorial.

REST API

To perform annotation on a local video file, base64-encode the contents of the video file. Include the base64-encoded contents in the inputContent field of the request. For information on how to base64-encode the contents of a video file, see Base64 Encoding.

The following shows how to send a POST request to the videos:annotate method. The example uses the access token for a service account set up for the project using the Google Cloud Platform Cloud SDK. For instructions on installing the Cloud SDK, setting up a project with a service account, and obtaining an access token, see the Video Intelligence API Quickstart.

curl -X POST \
     -H "Authorization: Bearer $(gcloud auth application-default print-access-token)" \
     -H "Content-Type: application/json; charset=utf-8" \
     --data "{
      'inputContent': '/9j/7QBEUGhvdG9zaG9...',
      'features': ['LABEL_DETECTION'],
    }" "https://videointelligence.googleapis.com/v1/videos:annotate"

If the request is successful, the Cloud Video Intelligence API returns the name for your operation. The following shows an example of such a response, where project-name is the name of your project and operation-id is the ID of the long running operation created for the request.

{
  "name": "projects/project-name/locations/us-west1/operations/operation-id"
}

To retrieve the result of the operation, make a GET request, using the operation name returned from the call to videos:annotate, as shown in the following example.

curl -H "Authorization: Bearer $(gcloud auth application-default print-access-token)" \
  https://videointelligence.googleapis.com/v1/operation-name

Label search annotations are returned in the annotationResults. For example:

{
  "name": "projects/PROJECT_NAME/locations/us-west1/operations/OPERATION_ID",
  "metadata": {
    "@type": "type.googleapis.com/google.cloud.videointelligence.v1.AnnotateVideoProgress",
    "annotationProgress": [
      {
        "inputContent": "/9j/7QBEUGhvdG9zaG9...base64-encoded-video-content...fXNWzvDEeYxxxzj/Coa6Bax//Z",
        "progressPercent": 100,
        "startTime": "2019-03-12T19:36:09.110351Z",
        "updateTime": "2019-03-12T19:36:17.519069Z"
      }
    ]
  },
  "done": true,
  "response": {
    "@type": "type.googleapis.com/google.cloud.videointelligence.v1.AnnotateVideoResponse",
    "annotationResults": [
      {
        "inputUri": "/cloud-ml-sandbox/video/chicago.mp4",
        "segmentLabelAnnotations": [
          {
            "entity": {
              "entityId": "/m/01prls",
              "description": "land vehicle",
              "languageCode": "en-US"
            },
            "categoryEntities": [
              {
                "entityId": "/m/07yv9",
                "description": "vehicle",
                "languageCode": "en-US"
              }
            ],
            "segments": [
              {
                "segment": {
                  "startTimeOffset": "0s",
                  "endTimeOffset": "38.757872s"
                },
                "confidence": 0.6614419
              }
            ]
          },
          {
            "entity": {
              "entityId": "/m/039jbq",
              "description": "urban area",
              "languageCode": "en-US"
            },
            "categoryEntities": [
              {
                "entityId": "/m/01n32",
                "description": "city",
                "languageCode": "en-US"
              }
            ],
            "segments": [
              {
                "segment": {
                  "startTimeOffset": "0s",
                  "endTimeOffset": "38.757872s"
                },
                "confidence": 0.92337775
              }
            ]
          },
          ...

C#

public static object AnalyzeLabels(string path)
{
    var client = VideoIntelligenceServiceClient.Create();
    var request = new AnnotateVideoRequest()
    {
        InputContent = Google.Protobuf.ByteString.CopyFrom(File.ReadAllBytes(path)),
        Features = { Feature.LabelDetection }
    };
    var op = client.AnnotateVideo(request).PollUntilCompleted();
    foreach (var result in op.Result.AnnotationResults)
    {
        PrintLabels("Video", result.SegmentLabelAnnotations);
        PrintLabels("Shot", result.ShotLabelAnnotations);
        PrintLabels("Frame", result.FrameLabelAnnotations);
    }
    return 0;
}

static void PrintLabels(string labelName,
    IEnumerable<LabelAnnotation> labelAnnotations)
{
    foreach (var annotation in labelAnnotations)
    {
        Console.WriteLine($"{labelName} label: {annotation.Entity.Description}");
        foreach (var entity in annotation.CategoryEntities)
        {
            Console.WriteLine($"{labelName} label category: {entity.Description}");
        }
        foreach (var segment in annotation.Segments)
        {
            Console.Write("Segment location: ");
            Console.Write(segment.Segment.StartTimeOffset);
            Console.Write(":");
            Console.WriteLine(segment.Segment.EndTimeOffset);
            System.Console.WriteLine($"Confidence: {segment.Confidence}");
        }
    }
}

Go


func label(w io.Writer, file string) error {
	ctx := context.Background()
	client, err := video.NewClient(ctx)
	if err != nil {
		return err
	}

	fileBytes, err := ioutil.ReadFile(file)
	if err != nil {
		return err
	}

	op, err := client.AnnotateVideo(ctx, &videopb.AnnotateVideoRequest{
		Features: []videopb.Feature{
			videopb.Feature_LABEL_DETECTION,
		},
		InputContent: fileBytes,
	})
	if err != nil {
		return err
	}
	resp, err := op.Wait(ctx)
	if err != nil {
		return 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
}

Java

// Instantiate a com.google.cloud.videointelligence.v1.VideoIntelligenceServiceClient
try (VideoIntelligenceServiceClient client = VideoIntelligenceServiceClient.create()) {
  // Read file and encode into Base64
  Path path = Paths.get(filePath);
  byte[] data = Files.readAllBytes(path);

  AnnotateVideoRequest request = AnnotateVideoRequest.newBuilder()
      .setInputContent(ByteString.copyFrom(data))
      .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:%.2f\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:%.2f\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());
      }
    }
  }
}

Node.js

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

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

/**
 * TODO(developer): Uncomment the following line before running the sample.
 */
// const path = 'Local file to analyze, e.g. ./my-file.mp4';

// Reads a local video file and converts it to base64
const readFile = util.promisify(fs.readFile);
const file = await readFile(path);
const inputContent = file.toString('base64');

// Constructs request
const request = {
  inputContent: inputContent,
  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}`);
  });
});

Python

For more information on installing and using the Cloud Video Intelligence API Client Library for Python, refer to Cloud Video Intelligence API Client Libraries.
"""Detect labels given a file path."""
video_client = videointelligence.VideoIntelligenceServiceClient()
features = [videointelligence.enums.Feature.LABEL_DETECTION]

with io.open(path, 'rb') as movie:
    input_content = movie.read()

operation = video_client.annotate_video(
    features=features, input_content=input_content)
print('\nProcessing video for label annotations:')

result = operation.result(timeout=90)
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.nanos / 1e9)
        end_time = (segment.segment.end_time_offset.seconds +
                    segment.segment.end_time_offset.nanos / 1e9)
        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.nanos / 1e9)
        end_time = (shot.segment.end_time_offset.seconds +
                    shot.segment.end_time_offset.nanos / 1e9)
        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.nanos / 1e9
    print('\tFirst frame time offset: {}s'.format(time_offset))
    print('\tFirst frame confidence: {}'.format(frame.confidence))
    print('\n')

PHP

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

/** Uncomment and populate these variables in your code */
// $uri = 'The cloud storage object to analyze (gs://your-bucket-name/your-object-name)';
// $options = [];

# Instantiate a client.
$video = new VideoIntelligenceServiceClient();

# Execute a request.
$operation = $video->annotateVideo([
    'inputUri' => $uri,
    'features' => [Feature::LABEL_DETECTION]
]);

# Wait for the request to complete.
$operation->pollUntilComplete($options);

# 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());
}

Ruby

# path = "Path to a local video file: path/to/file.mp4"

require "google/cloud/video_intelligence"

video = Google::Cloud::VideoIntelligence.new

video_contents = File.binread path

# Register a callback during the method call
operation = video.annotate_video input_content: video_contents, features: [:LABEL_DETECTION] do |operation|
  raise operation.results.message? if operation.error?
  puts "Finished Processing."

  labels = operation.results.annotation_results.first.segment_label_annotations

  labels.each do |label|
    puts "Label description: #{label.entity.description}"

    label.category_entities.each do |category_entity|
      puts "Label category description: #{category_entity.description}"
    end

    label.segments.each do |segment|
      start_time = (segment.segment.start_time_offset.seconds +
                     segment.segment.start_time_offset.nanos / 1e9)
      end_time =   (segment.segment.end_time_offset.seconds +
                     segment.segment.end_time_offset.nanos / 1e9)

      puts "Segment: #{start_time} to #{end_time}"
      puts "Confidence: #{segment.confidence}"
    end
  end
end

puts "Processing video for label annotations:"
operation.wait_until_done!

Here is an example of performing video analysis for labels on a file located in Google Cloud Storage.

REST API

The following shows how to send a POST request to the videos:annotate method. The example uses the access token for a service account set up for the project using the Google Cloud Platform Cloud SDK. For instructions on installing the Cloud SDK, setting up a project with a service account, and obtaining an access token, see the Video Intelligence API Quickstart.

curl -X POST \
     -H "Authorization: Bearer $(gcloud auth application-default print-access-token)" \
     -H "Content-Type: application/json; charset=utf-8" \
     --data '{
      "inputUri": "gs://demomaker/cat.mp4",
      "features": ["LABEL_DETECTION"],
    }' "https://videointelligence.googleapis.com/v1/videos:annotate"

If the request is successful, the Cloud Video Intelligence API returns the name for your operation. The following shows an example of such a response, where project-name is the name of your project and operation-id is the ID of the long running operation created for the request.

{
  "name": "projects/project-name/locations/us-west1/operations/operation-id"
}

To retrieve the result of the operation, make a GET request, using the operation name returned from the call to videos:annotate, as shown in the following example.

curl -H "Authorization: Bearer $(gcloud auth application-default print-access-token)" \
  https://videointelligence.googleapis.com/v1/operation-name

Label search annotations are returned in the annotationResults. For example:

{
  "name": "projects/PROJECT_NAME/locations/us-west1/operations/OPERATION_ID",
  "metadata": {
    "@type": "type.googleapis.com/google.cloud.videointelligence.v1.AnnotateVideoProgress",
    "annotationProgress": [
      {
        "inputUri": "/demomaker/cat.mp4",
        "progressPercent": 100,
        "startTime": "2019-03-12T19:36:09.110351Z",
        "updateTime": "2019-03-12T19:36:17.519069Z"
      }
    ]
  },
  "done": true,
  "response": {
    "@type": "type.googleapis.com/google.cloud.videointelligence.v1.AnnotateVideoResponse",
    "annotationResults": [
      {
        "inputUri": "/cloud-ml-sandbox/video/chicago.mp4",
        "segmentLabelAnnotations": [
          {
            "entity": {
              "entityId": "/m/01prls",
              "description": "land vehicle",
              "languageCode": "en-US"
            },
            "categoryEntities": [
              {
                "entityId": "/m/07yv9",
                "description": "vehicle",
                "languageCode": "en-US"
              }
            ],
            "segments": [
              {
                "segment": {
                  "startTimeOffset": "0s",
                  "endTimeOffset": "38.757872s"
                },
                "confidence": 0.6614419
              }
            ]
          },
          {
            "entity": {
              "entityId": "/m/039jbq",
              "description": "urban area",
              "languageCode": "en-US"
            },
            "categoryEntities": [
              {
                "entityId": "/m/01n32",
                "description": "city",
                "languageCode": "en-US"
              }
            ],
            "segments": [
              {
                "segment": {
                  "startTimeOffset": "0s",
                  "endTimeOffset": "38.757872s"
                },
                "confidence": 0.92337775
              }
            ]
          },
          ...

C#

public static object AnalyzeLabelsGcs(string uri)
{
    var client = VideoIntelligenceServiceClient.Create();
    var request = new AnnotateVideoRequest()
    {
        InputUri = uri,
        Features = { Feature.LabelDetection }
    };
    var op = client.AnnotateVideo(request).PollUntilCompleted();
    foreach (var result in op.Result.AnnotationResults)
    {
        PrintLabels("Video", result.SegmentLabelAnnotations);
        PrintLabels("Shot", result.ShotLabelAnnotations);
        PrintLabels("Frame", result.FrameLabelAnnotations);
    }
    return 0;
}

static void PrintLabels(string labelName,
    IEnumerable<LabelAnnotation> labelAnnotations)
{
    foreach (var annotation in labelAnnotations)
    {
        Console.WriteLine($"{labelName} label: {annotation.Entity.Description}");
        foreach (var entity in annotation.CategoryEntities)
        {
            Console.WriteLine($"{labelName} label category: {entity.Description}");
        }
        foreach (var segment in annotation.Segments)
        {
            Console.Write("Segment location: ");
            Console.Write(segment.Segment.StartTimeOffset);
            Console.Write(":");
            Console.WriteLine(segment.Segment.EndTimeOffset);
            System.Console.WriteLine($"Confidence: {segment.Confidence}");
        }
    }
}

Go


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

	op, err := client.AnnotateVideo(ctx, &videopb.AnnotateVideoRequest{
		Features: []videopb.Feature{
			videopb.Feature_LABEL_DETECTION,
		},
		InputUri: file,
	})
	if err != nil {
		return err
	}
	resp, err := op.Wait(ctx)
	if err != nil {
		return 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
}

Java

// 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());
      }
    }
  }
}

Node.js

// 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}`);
  });
});

Python

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

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

operation = video_client.annotate_video(
    path, features=features, 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.nanos / 1e9)
        end_time = (segment.segment.end_time_offset.seconds +
                    segment.segment.end_time_offset.nanos / 1e9)
        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.nanos / 1e9)
        end_time = (shot.segment.end_time_offset.seconds +
                    shot.segment.end_time_offset.nanos / 1e9)
        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.nanos / 1e9)
    print('\tFirst frame time offset: {}s'.format(time_offset))
    print('\tFirst frame confidence: {}'.format(frame.confidence))
    print('\n')

PHP

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

/** Uncomment and populate these variables in your code */
// $path = 'File path to a video file to analyze';
// $options = [];

# Instantiate a client.
$video = new VideoIntelligenceServiceClient();

# Read the local video file
$inputContent = file_get_contents($path);

# Execute a request.
$operation = $video->annotateVideo([
    'inputContent' => $inputContent,
    'features' => [Feature::LABEL_DETECTION]
]);

# Wait for the request to complete.
$operation->pollUntilComplete($options);

# 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());
}

Ruby

# path = "Path to a video file on Google Cloud Storage: gs://bucket/video.mp4"

require "google/cloud/video_intelligence"

video = Google::Cloud::VideoIntelligence.new

# Register a callback during the method call
operation = video.annotate_video input_uri: path, features: [:LABEL_DETECTION] do |operation|
  raise operation.results.message? if operation.error?
  puts "Finished Processing."

  labels = operation.results.annotation_results.first.segment_label_annotations

  labels.each do |label|
    puts "Label description: #{label.entity.description}"

    label.category_entities.each do |category_entity|
      puts "Label category description: #{category_entity.description}"
    end

    label.segments.each do |segment|
      start_time = (segment.segment.start_time_offset.seconds +
                     segment.segment.start_time_offset.nanos / 1e9)
      end_time =   (segment.segment.end_time_offset.seconds +
                     segment.segment.end_time_offset.nanos / 1e9)

      puts "Segment: #{start_time} to #{end_time}"
      puts "Confidence: #{segment.confidence}"
    end
  end
end

puts "Processing video for label annotations:"
operation.wait_until_done!

هل كانت هذه الصفحة مفيدة؟ يرجى تقييم أدائنا:

إرسال تعليقات حول...

Cloud Video Intelligence API Documentation