检测人员

以下代码示例演示了如何使用 Video Intelligence API 检测视频文件中的人物。

Video Intelligence 可以检测视频文件中是否存在人员并跟踪视频或视频片段中的个人。

通过 Cloud Storage 中的文件进行人员检测

以下演示了如何使用人员动态检测功能向 Video Intelligence 发送注释请求。

REST 和命令行

发送视频注释请求

下面演示了如何向 videos:annotate 方法发送 POST 请求。本示例针对通过 Cloud SDK 为项目设置的服务帐号使用访问令牌。如需了解有关安装 Cloud SDK、使用服务帐号设置项目以及获取访问令牌的说明，请参阅 Video Intelligence API 快速入门。另请参阅 PersonDetectionConfig。

在使用下面的请求数据之前，请先进行以下替换：

inputUri：包含要添加注释的文件的 Cloud Storage 存储分区（包括文件名）。必须以 gs:// 开头。
例如：
"inputUri": "gs://cloud-samples-data/video/googlework_short.mp4"

HTTP 方法和网址：

POST https://videointelligence.googleapis.com/v1p3beta1/videos:annotate

请求 JSON 正文：

{
  "inputUri": "input-uri",
  "features": ["PERSON_DETECTION"],
  "videoContext": {
    "personDetectionConfig": {
      "includeBoundingBoxes": true,
      "includePoseLandmarks": true,
      "includeAttributes": true
     }
  }
}

如需发送您的请求，请展开以下选项之一：

curl（Linux、macOS 或 Cloud Shell）

将请求正文保存在名为 request.json 的文件中，然后执行以下命令：

curl -X POST \
-H "Authorization: Bearer "$(gcloud auth application-default print-access-token) \
-H "Content-Type: application/json; charset=utf-8" \
-d @request.json \
https://videointelligence.googleapis.com/v1p3beta1/videos:annotate

PowerShell (Windows)

将请求正文保存在名为 request.json 的文件中，然后执行以下命令：

$cred = gcloud auth application-default print-access-token
$headers = @{ "Authorization" = "Bearer $cred" }

Invoke-WebRequest `
  -Method POST `
  -Headers $headers `
  -ContentType: "application/json; charset=utf-8" `
  -InFile request.json `
  -Uri "https://videointelligence.googleapis.com/v1p3beta1/videos:annotate" | Select-Object -Expand Content

您应该会收到类似以下内容的 JSON 响应：

响应

{
  "name": "projects/project-number/locations/location-id/operations/operation-id"
}

如果响应成功，Video Intelligence API 将返回您的操作的 name。上面显示了此类响应的示例，其中：

project-number：您项目的编号
location-id：在其中添加注释的 Cloud 区域。支持的云区域为：us-east1、us-west1、europe-west1、asia-east1。如果未指定区域，系统将根据视频文件位置确定区域。
operation-id：是为请求创建的长时间运行的操作的 ID，并在启动操作时在响应中提供，例如 12345...

获取注释结果

要检索操作的结果，请使用从 videos：annotate 调用返回的操作名称发出 GET 请求，如以下示例所示。

在使用下面的请求数据之前，请先进行以下替换：

operation-name：Video Intelligence API 返回的操作名称。操作名称采用 projects/project-number/locations/location-id/operations/operation-id 格式

HTTP 方法和网址：

GET https://videointelligence.googleapis.com/v1/operation-name

如需发送您的请求，请展开以下选项之一：

curl（Linux、macOS 或 Cloud Shell）

执行以下命令：

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

PowerShell (Windows)

执行以下命令：

$cred = gcloud auth application-default print-access-token
$headers = @{ "Authorization" = "Bearer $cred" }

Invoke-WebRequest `
  -Method GET `
  -Headers $headers `
  -Uri "https://videointelligence.googleapis.com/v1/operation-name" | Select-Object -Expand Content

您应该收到类似以下内容的 JSON 响应：

响应

{
  "name": "us-west1.10001026834554604237",
  "metadata": {
    "@type": "type.googleapis.com/google.cloud.videointelligence.v1.AnnotateVideoProgress",
    "annotationProgress": [
      {
        "inputUri": "/cloud-ml-sandbox/video/chicago.mp4",
        "progressPercent": 100,
         "startTime": "2020-02-08T21:26:56.577807Z",
        "updateTime": "2020-02-08T21:28:09.620665Z"
      }
    ]
  },
  "done": true,
  "response": {
    "@type": "type.googleapis.com/google.cloud.videointelligence.v1.AnnotateVideoResponse",
    "annotationResults": [
      {
        "inputUri": "/cloud-ml-sandbox/video/chicago.mp4",
        "personDetectionAnnotations": [
          {
            "tracks": [
              {
                "segment": {
                  "startTimeOffset": "0s",
                  "endTimeOffset": "1.507436s"
                }
              },
              ...
            ]
          }
        ]
      }
    ]
  }
}

镜头检测注释以 shotAnnotations 列表的形式返回。注意：仅当值为 True 时，才会返回 done 字段。操作未完成的响应中不包含该字段。

Java

在 GitHub 上查看反馈


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.DetectedLandmark;
import com.google.cloud.videointelligence.v1p3beta1.Feature;
import com.google.cloud.videointelligence.v1p3beta1.PersonDetectionAnnotation;
import com.google.cloud.videointelligence.v1p3beta1.PersonDetectionConfig;
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 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, or hair color.
          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());
          }
        }
      }
    }
  }
}

Node.js

在 GitHub 上查看反馈

/**
 * 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 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) {
      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 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();

Python

在 GitHub 上查看反馈

from google.cloud import videointelligence_v1p3beta1 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(
        input_uri=gcs_uri,
        features=[videointelligence.enums.Feature.PERSON_DETECTION],
        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.nanos / 1e9,
                    track.segment.end_time_offset.seconds
                    + track.segment.end_time_offset.nanos / 1e9,
                )
            )

            # 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
                    )
                )

来自本地文件的人员动态检测

以下示例使用人员动态检测功能从本地机器上传的视频文件中查找视频中的实体。

REST 和命令行

发送处理请求

要对本地视频文件执行人员动态检测，请对视频文件的内容进行 base64 编码。如需了解如何对视频文件的内容进行 base64 编码，请参阅 Base64 编码。然后，向 videos:annotate 方法发出 POST 请求。在请求的 inputContent 字段中添加 base64 编码的内容，并指定 PERSON_DETECTION 功能。

以下示例展示了使用 curl 的 POST 请求。本示例针对通过 Cloud SDK 为项目设置的服务帐号使用访问令牌。如需了解有关安装 Cloud SDK、使用服务帐号设置项目以及获取访问令牌的说明，请参阅 Video Intelligence API 快速入门。

在使用下面的请求数据之前，请先进行以下替换：

inputContent: 二进制文件格式的本地视频文件
，例如：AAAAGGZ0eXBtcDQyAAAAAGlzb21tcDQyAAGVYW1vb3YAAABsbXZoZAAAAADWvhlR1r4ZUQABX5ABCOxoAAEAAAEAAAAAAA4

HTTP 方法和网址：

POST https://videointelligence.googleapis.com/v1p3beta1/videos:annotate

请求 JSON 正文：

{
  "inputUri": "Local video file in binary format",
  "features": ["PERSON_DETECTION"],
  "videoContext": {
    "personDetectionConfig": {
      "includeBoundingBoxes": true,
      "includePoseLandmarks": true,
      "includeAttributes": true
     }
  }
}

如需发送您的请求，请展开以下选项之一：

curl（Linux、macOS 或 Cloud Shell）

将请求正文保存在名为 request.json 的文件中，然后执行以下命令：

curl -X POST \
-H "Authorization: Bearer "$(gcloud auth application-default print-access-token) \
-H "Content-Type: application/json; charset=utf-8" \
-d @request.json \
https://videointelligence.googleapis.com/v1p3beta1/videos:annotate

PowerShell (Windows)

将请求正文保存在名为 request.json 的文件中，然后执行以下命令：

$cred = gcloud auth application-default print-access-token
$headers = @{ "Authorization" = "Bearer $cred" }

Invoke-WebRequest `
  -Method POST `
  -Headers $headers `
  -ContentType: "application/json; charset=utf-8" `
  -InFile request.json `
  -Uri "https://videointelligence.googleapis.com/v1p3beta1/videos:annotate" | Select-Object -Expand Content

您应该会收到类似以下内容的 JSON 响应：

响应

{
  "name": "projects/project-number/locations/location-id/operations/operation-id"

}

如果请求成功，则 Video Intelligence 会为您的操作分配 name。上面的示例展示了此类响应的示例，其中 project-number 是您的项目编号，operation-id 是为请求创建的长时间运行的操作的 ID。

{ "name": "us-west1.17122464255125931980" }

获取结果

要检索操作结果，请向 operations 端点发送 GET 请求并指定操作名称。

在使用下面的请求数据之前，请先进行以下替换：

operation-name：Video Intelligence API 返回的操作名称。操作名称采用 projects/project-number/locations/location-id/operations/operation-id 格式

HTTP 方法和网址：

GET https://videointelligence.googleapis.com/v1/operation-name

如需发送您的请求，请展开以下选项之一：

curl（Linux、macOS 或 Cloud Shell）

执行以下命令：

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

PowerShell (Windows)

执行以下命令：

$cred = gcloud auth application-default print-access-token
$headers = @{ "Authorization" = "Bearer $cred" }

Invoke-WebRequest `
  -Method GET `
  -Headers $headers `
  -Uri "https://videointelligence.googleapis.com/v1/operation-name" | Select-Object -Expand Content

您应该收到类似以下内容的 JSON 响应：

响应

{
  "name": "us-west1.10001026834554604237",
  "metadata": {
    "@type": "type.googleapis.com/google.cloud.videointelligence.v1.AnnotateVideoProgress",
    "annotationProgress": [
      {
        "progressPercent": 100,
        "startTime": "2020-02-08T21:26:56.577807Z",
        "updateTime": "2020-02-08T21:28:09.620665Z"
      }
    ]
  },
  "done": true,
  "response": {
    "@type": "type.googleapis.com/google.cloud.videointelligence.v1.AnnotateVideoResponse",
    "annotationResults": [
      {
        "personDetectionAnnotations": [
          {
            "tracks": [
              {
                "segment": {
                  "startTimeOffset": "0s",
                  "endTimeOffset": "1.507436s"
                }
              },
              ...
            ]
          }
        ]
      }
    ]
  }
}

Java

在 GitHub 上查看反馈

/*
 * Copyright 2020 Google LLC
 *
 * 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.
 */

package com.example.video;

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.DetectedLandmark;
import com.google.cloud.videointelligence.v1p3beta1.Feature;
import com.google.cloud.videointelligence.v1p3beta1.PersonDetectionAnnotation;
import com.google.cloud.videointelligence.v1p3beta1.PersonDetectionConfig;
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;
import com.google.protobuf.ByteString;
import java.nio.file.Files;
import java.nio.file.Path;
import java.nio.file.Paths;

public class DetectPerson {

  public static void detectPerson() throws Exception {
    // TODO(developer): Replace these variables before running the sample.
    String localFilePath = "resources/googlework_short.mp4";
    detectPerson(localFilePath);
  }

  // Detects people in a video stored in a local file using the Cloud Video Intelligence API.
  public static void detectPerson(String localFilePath) throws Exception {
    try (VideoIntelligenceServiceClient videoIntelligenceServiceClient =
        VideoIntelligenceServiceClient.create()) {
      // Reads a local video file and converts it to base64.
      Path path = Paths.get(localFilePath);
      byte[] data = Files.readAllBytes(path);
      ByteString inputContent = ByteString.copyFrom(data);

      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()
              .setInputContent(inputContent)
              .addFeatures(Feature.PERSON_DETECTION)
              .setVideoContext(videoContext)
              .build();

      // Detects people in a video
      // We get the first result because only one video is processed.
      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 (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, or hair color.
          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());
          }
        }
      }
    }
  }
}

Node.js

在 GitHub 上查看反馈

/**
 * 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;
const fs = require('fs');
// Creates a client
const video = 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 file = fs.readFileSync(path);
const inputContent = file.toString('base64');

async function detectPerson() {
  const request = {
    inputContent: inputContent,
    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) {
      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 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}`);
      }
    }
  }
}

detectPerson();

Python

在 GitHub 上查看反馈

# Copyright 2020 Google LLC
#
# 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
#
#     https://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.

import io

from google.cloud import videointelligence_v1p3beta1 as videointelligence

def detect_person(local_file_path="path/to/your/video-file.mp4"):
    """Detects people in a video from a local file."""

    client = videointelligence.VideoIntelligenceServiceClient()

    with io.open(local_file_path, "rb") as f:
        input_content = f.read()

    # 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(
        input_content=input_content,
        features=[videointelligence.enums.Feature.PERSON_DETECTION],
        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.nanos / 1e9,
                    track.segment.end_time_offset.seconds
                    + track.segment.end_time_offset.nanos / 1e9,
                )
            )

            # Each segment includes timestamped objects that include
            # characteristic - -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
                    )
                )