Detect a person in a video on Cloud Storage

import com.google.api.gax.longrunning.OperationFuture;
import com.google.cloud.videointelligence.v1.AnnotateVideoProgress;
import com.google.cloud.videointelligence.v1.AnnotateVideoRequest;
import com.google.cloud.videointelligence.v1.AnnotateVideoResponse;
import com.google.cloud.videointelligence.v1.DetectedAttribute;
import com.google.cloud.videointelligence.v1.DetectedLandmark;
import com.google.cloud.videointelligence.v1.Feature;
import com.google.cloud.videointelligence.v1.PersonDetectionAnnotation;
import com.google.cloud.videointelligence.v1.PersonDetectionConfig;
import com.google.cloud.videointelligence.v1.TimestampedObject;
import com.google.cloud.videointelligence.v1.Track;
import com.google.cloud.videointelligence.v1.VideoAnnotationResults;
import com.google.cloud.videointelligence.v1.VideoContext;
import com.google.cloud.videointelligence.v1.VideoIntelligenceServiceClient;
import com.google.cloud.videointelligence.v1.VideoSegment;

public class DetectPersonGcs {

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

  // Detects people in a video stored in Google Cloud Storage using
  // the Cloud Video Intelligence API.
  public static void detectPersonGcs(String gcsUri) throws Exception {
    try (VideoIntelligenceServiceClient videoIntelligenceServiceClient =
        VideoIntelligenceServiceClient.create()) {
      // Reads a local video file and converts it to base64.

      PersonDetectionConfig personDetectionConfig =
          PersonDetectionConfig.newBuilder()
              // Must set includeBoundingBoxes to true to get poses and attributes.
              .setIncludeBoundingBoxes(true)
              .setIncludePoseLandmarks(true)
              .setIncludeAttributes(true)
              .build();
      VideoContext videoContext =
          VideoContext.newBuilder().setPersonDetectionConfig(personDetectionConfig).build();

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

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

      System.out.println("Waiting for operation to complete...");
      AnnotateVideoResponse response = future.get();
      // Get the first response, since we sent only one video.
      VideoAnnotationResults annotationResult = response.getAnnotationResultsList().get(0);

      // Annotations for list of people detected, tracked and recognized in video.
      for (PersonDetectionAnnotation personDetectionAnnotation :
          annotationResult.getPersonDetectionAnnotationsList()) {
        System.out.print("Person detected:\n");
        for (Track track : personDetectionAnnotation.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 characteristic--e.g. clothes,
          // posture of the person detected.
          TimestampedObject firstTimestampedObject = track.getTimestampedObjects(0);

          // Attributes include unique pieces of clothing, poses (i.e., body landmarks)
          // of the person detected.
          for (DetectedAttribute attribute : firstTimestampedObject.getAttributesList()) {
            System.out.printf(
                "\tAttribute: %s; Value: %s\n", attribute.getName(), attribute.getValue());
          }

          // Landmarks in person detection include body parts.
          for (DetectedLandmark attribute : firstTimestampedObject.getLandmarksList()) {
            System.out.printf(
                "\tLandmark: %s; Vertex: %f, %f\n",
                attribute.getName(), attribute.getPoint().getX(), attribute.getPoint().getY());
          }
        }
      }
    }
  }
}

/**
 * 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').v1;

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

async function detectPersonGCS() {
  const request = {
    inputUri: gcsUri,
    features: ['PERSON_DETECTION'],
    videoContext: {
      personDetectionConfig: {
        // Must set includeBoundingBoxes to true to get poses and attributes.
        includeBoundingBoxes: true,
        includePoseLandmarks: 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 personAnnotations =
    results[0].annotationResults[0].personDetectionAnnotations;

  for (const {tracks} of personAnnotations) {
    console.log('Person detected:');

    for (const {segment, timestampedObjects} of tracks) {
      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 characteristic--e.g. clothes, posture
      // of the person detected.
      const [firstTimestampedObject] = timestampedObjects;

      // Attributes include unique pieces of clothing, poses (i.e., body
      // landmarks) of the person detected.
      for (const {name, value} of firstTimestampedObject.attributes) {
        console.log(`\tAttribute: ${name}; Value: ${value}`);
      }

      // Landmarks in person detection include body parts.
      for (const {name, point} of firstTimestampedObject.landmarks) {
        console.log(`\tLandmark: ${name}; Vertex: ${point.x}, ${point.y}`);
      }
    }
  }
}

detectPersonGCS();

from google.cloud import videointelligence_v1 as videointelligence


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

    client = videointelligence.VideoIntelligenceServiceClient()

    # Configure the request
    config = videointelligence.types.PersonDetectionConfig(
        include_bounding_boxes=True,
        include_attributes=True,
        include_pose_landmarks=True,
    )
    context = videointelligence.types.VideoContext(person_detection_config=config)

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

    print("\nProcessing video for person 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.person_detection_annotations:
        print("Person 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 objects that include
            # characteristics - -e.g.clothes, posture of the person detected.
            # Grab the first timestamped object
            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 unique pieces of clothing,
            # poses, or hair color.
            print("Attributes:")
            for attribute in timestamped_object.attributes:
                print(
                    "\t{}:{} {}".format(
                        attribute.name, attribute.value, attribute.confidence
                    )
                )

            # Landmarks in person detection include body parts such as
            # left_shoulder, right_ear, and right_ankle
            print("Landmarks:")
            for landmark in timestamped_object.landmarks:
                print(
                    "\t{}: {} (x={}, y={})".format(
                        landmark.name,
                        landmark.confidence,
                        landmark.point.x,  # Normalized vertex
                        landmark.point.y,  # Normalized vertex
                    )
                )