跟踪js中人脸检测后如何捕获图像

how to capture image after face detection in tracking js

本文关键字：何捕获 图像 检测 js 跟踪      更新时间：2023-09-26

我正在使用跟踪js进行人脸检测。我成功地检测到了人脸，但是我不知道如何捕捉图像帧。我想将检测到的人脸保存为图像。这是我的HTML页面:

<!doctype html>
<html>
<head>
  <meta charset="utf-8">
  <title>tracking.js - face with camera</title>
  <script src="../tracking.js-master/build/tracking-min.js" type="text/javascript"></script>
  <script src="../tracking.js-master/build/data/face-min.js"></script>
  <link rel="stylesheet" type="text/css" href="face.css">
</head>
<body>
  <div class="demo-frame">
      <video id="video" class="face-video" width="740" height="560" preload autoplay loop muted></video>
      <canvas id="canvas" class="face-canvas" width="740" height="560">    </canvas>
  </div>
  <script src="faceDetection.js" type="text/javascript"></script>
</body>
</html>
这是我的faceDetection.js文件: 
window.onload = function() {
  var video = document.getElementById('video');
  var canvas = document.getElementById('canvas');
  var context = canvas.getContext('2d');
  var tracker = new tracking.ObjectTracker('face');
  tracker.setInitialScale(6);
  tracker.setStepSize(2);
  tracker.setEdgesDensity(0.1);
  tracking.track('#video', tracker, { camera: true });
  tracker.on('track', function(event) {
    context.clearRect(0, 0, canvas.width, canvas.height);
    event.data.forEach(function(rect) {
      context.strokeStyle = '#ff0000';
      context.strokeRect(rect.x, rect.y, rect.width, rect.height);
      context.font = '11px Helvetica';
      context.fillStyle = "#fff";
      context.fillText('x: ' + rect.x + 'px', rect.x + rect.width + 5, rect.y + 11);
      context.fillText('y: ' + rect.y + 'px', rect.x + rect.width + 5, rect.y + 22);
    });
  });
};

您可以使用getUserMedia api并在<a>元素上使用download属性。这有点棘手，并不是在所有浏览器上都可用:

首先在画布上绘制视频:

tracker.on('track', function(event) {
  context.clearRect(0, 0, canvas.width, canvas.height);
  event.data.forEach(function(rect) {
    context.strokeStyle = '#ff0000';
    context.strokeRect(rect.x, rect.y, rect.width, rect.height);
    context.font = '11px Helvetica';
    context.fillStyle = "#fff";
    context.fillText('x: ' + rect.x + 'px', rect.x + rect.width + 5, rect.y + 11);
    context.fillText('y: ' + rect.y + 'px', rect.x + rect.width + 5, rect.y + 22);
    context.drawImage(video, rect.x, rect.y, rect.width, rect.height, rect.x, rect.y, rect.width, rect.height);
  });
});

创建触发快照的方法:

var snapshot = function() {
  if (localMediaStream) {
    document.querySelector('a').href = canvas.toDataURL('image/webp');
  }
}
video.addEventListener('click', snapshot, false);

保留对用户媒体的引用:

navigator.getUserMedia({video: true}, function(stream) {
  localMediaStream = stream;
}, function(error){console.error(error)});

在这里查看所有代码的粗略演示。点击视频和图像应该保存(注意:使用最新的Chrome;你可能需要微调坐标;

相关文章：