Detect faces in a Cloud Storage file

Detect faces in a video stored in Cloud Storage.

Documentation pages that include this code sample

To view the code sample used in context, see the following documentation:

Code sample

Java


import com.google.api.gax.longrunning.OperationFuture;
import com.google.cloud.videointelligence.v1p3beta1.AnnotateVideoProgress;
import com.google.cloud.videointelligence.v1p3beta1.AnnotateVideoRequest;
import com.google.cloud.videointelligence.v1p3beta1.AnnotateVideoResponse;
import com.google.cloud.videointelligence.v1p3beta1.DetectedAttribute;
import com.google.cloud.videointelligence.v1p3beta1.FaceDetectionAnnotation;
import com.google.cloud.videointelligence.v1p3beta1.FaceDetectionConfig;
import com.google.cloud.videointelligence.v1p3beta1.Feature;
import com.google.cloud.videointelligence.v1p3beta1.TimestampedObject;
import com.google.cloud.videointelligence.v1p3beta1.Track;
import com.google.cloud.videointelligence.v1p3beta1.VideoAnnotationResults;
import com.google.cloud.videointelligence.v1p3beta1.VideoContext;
import com.google.cloud.videointelligence.v1p3beta1.VideoIntelligenceServiceClient;
import com.google.cloud.videointelligence.v1p3beta1.VideoSegment;

public class DetectFacesGcs {

  public static void detectFacesGcs() throws Exception {
    // TODO(developer): Replace these variables before running the sample.
    String gcsUri = "gs://cloud-samples-data/video/googlework_short.mp4";
    detectFacesGcs(gcsUri);
  }

  // Detects faces in a video stored in Google Cloud Storage using the Cloud Video Intelligence API.
  public static void detectFacesGcs(String gcsUri) throws Exception {
    try (VideoIntelligenceServiceClient videoIntelligenceServiceClient =
        VideoIntelligenceServiceClient.create()) {

      FaceDetectionConfig faceDetectionConfig =
          FaceDetectionConfig.newBuilder()
              // Must set includeBoundingBoxes to true to get facial attributes.
              .setIncludeBoundingBoxes(true)
              .setIncludeAttributes(true)
              .build();
      VideoContext videoContext =
          VideoContext.newBuilder().setFaceDetectionConfig(faceDetectionConfig).build();

      AnnotateVideoRequest request =
          AnnotateVideoRequest.newBuilder()
              .setInputUri(gcsUri)
              .addFeatures(Feature.FACE_DETECTION)
              .setVideoContext(videoContext)
              .build();

      // Detects faces in a video
      OperationFuture<AnnotateVideoResponse, AnnotateVideoProgress> future =
          videoIntelligenceServiceClient.annotateVideoAsync(request);

      System.out.println("Waiting for operation to complete...");
      AnnotateVideoResponse response = future.get();

      // Gets annotations for video
      VideoAnnotationResults annotationResult = response.getAnnotationResultsList().get(0);

      // Annotations for list of people detected, tracked and recognized in video.
      for (FaceDetectionAnnotation faceDetectionAnnotation :
          annotationResult.getFaceDetectionAnnotationsList()) {
        System.out.print("Face detected:\n");
        for (Track track : faceDetectionAnnotation.getTracksList()) {
          VideoSegment segment = track.getSegment();
          System.out.printf(
              "\tStart: %d.%.0fs\n",
              segment.getStartTimeOffset().getSeconds(),
              segment.getStartTimeOffset().getNanos() / 1e6);
          System.out.printf(
              "\tEnd: %d.%.0fs\n",
              segment.getEndTimeOffset().getSeconds(), segment.getEndTimeOffset().getNanos() / 1e6);

          // Each segment includes timestamped objects that
          // include characteristics of the face detected.
          TimestampedObject firstTimestampedObject = track.getTimestampedObjects(0);

          for (DetectedAttribute attribute : firstTimestampedObject.getAttributesList()) {
            // Attributes include glasses, headwear, smiling, direction of gaze
            System.out.printf(
                "\tAttribute %s: %s %s\n",
                attribute.getName(), attribute.getValue(), attribute.getConfidence());
          }
        }
      }
    }
  }
}

Node.js

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

// Imports the Google Cloud Video Intelligence library + Node's fs library
const Video = require('@google-cloud/video-intelligence').v1p3beta1;

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

async function detectFacesGCS() {
  const request = {
    inputUri: gcsUri,
    features: ['FACE_DETECTION'],
    videoContext: {
      faceDetectionConfig: {
        // Must set includeBoundingBoxes to true to get facial attributes.
        includeBoundingBoxes: true,
        includeAttributes: true,
      },
    },
  };
  // Detects faces in a video
  // We get the first result because we only process 1 video
  const [operation] = await video.annotateVideo(request);
  const results = await operation.promise();
  console.log('Waiting for operation to complete...');

  // Gets annotations for video
  const faceAnnotations =
    results[0].annotationResults[0].faceDetectionAnnotations;

  for (const {tracks} of faceAnnotations) {
    console.log('Face detected:');

    for (const {segment, timestampedObjects} of tracks) {
      if (segment.startTimeOffset.seconds === undefined) {
        segment.startTimeOffset.seconds = 0;
      }
      if (segment.startTimeOffset.nanos === undefined) {
        segment.startTimeOffset.nanos = 0;
      }
      if (segment.endTimeOffset.seconds === undefined) {
        segment.endTimeOffset.seconds = 0;
      }
      if (segment.endTimeOffset.nanos === undefined) {
        segment.endTimeOffset.nanos = 0;
      }
      console.log(
        `\tStart: ${segment.startTimeOffset.seconds}.` +
          `${(segment.startTimeOffset.nanos / 1e6).toFixed(0)}s`
      );
      console.log(
        `\tEnd: ${segment.endTimeOffset.seconds}.` +
          `${(segment.endTimeOffset.nanos / 1e6).toFixed(0)}s`
      );

      // Each segment includes timestamped objects that
      // include characteristics of the face detected.
      const [firstTimestapedObject] = timestampedObjects;

      for (const {name} of firstTimestapedObject.attributes) {
        // Attributes include 'glasses', 'headwear', 'smiling'.
        console.log(`\tAttribute: ${name}; `);
      }
    }
  }
}

detectFacesGCS();

Python

from google.cloud import videointelligence_v1p3beta1 as videointelligence


def detect_faces(gcs_uri="gs://YOUR_BUCKET_ID/path/to/your/video.mp4"):
    """Detects faces in a video."""

    client = videointelligence.VideoIntelligenceServiceClient()

    # Configure the request
    config = videointelligence.FaceDetectionConfig(
        include_bounding_boxes=True, include_attributes=True
    )
    context = videointelligence.VideoContext(face_detection_config=config)

    # Start the asynchronous request
    operation = client.annotate_video(
        request={
            "features": [videointelligence.Feature.FACE_DETECTION],
            "input_uri": gcs_uri,
            "video_context": context,
        }
    )

    print("\nProcessing video for face detection annotations.")
    result = operation.result(timeout=300)

    print("\nFinished processing.\n")

    # Retrieve the first result, because a single video was processed.
    annotation_result = result.annotation_results[0]

    for annotation in annotation_result.face_detection_annotations:
        print("Face detected:")
        for track in annotation.tracks:
            print(
                "Segment: {}s to {}s".format(
                    track.segment.start_time_offset.seconds
                    + track.segment.start_time_offset.microseconds / 1e6,
                    track.segment.end_time_offset.seconds
                    + track.segment.end_time_offset.microseconds / 1e6,
                )
            )

            # Each segment includes timestamped faces that include
            # characteristics of the face detected.
            # Grab the first timestamped face
            timestamped_object = track.timestamped_objects[0]
            box = timestamped_object.normalized_bounding_box
            print("Bounding box:")
            print("\tleft  : {}".format(box.left))
            print("\ttop   : {}".format(box.top))
            print("\tright : {}".format(box.right))
            print("\tbottom: {}".format(box.bottom))

            # Attributes include glasses, headwear, smiling, direction of gaze
            print("Attributes:")
            for attribute in timestamped_object.attributes:
                print(
                    "\t{}:{} {}".format(
                        attribute.name, attribute.value, attribute.confidence
                    )
                )