Pen Settings

HTML

CSS

CSS Base

Vendor Prefixing

Add External Stylesheets/Pens

Any URLs added here will be added as <link>s in order, and before the CSS in the editor. You can use the CSS from another Pen by using its URL and the proper URL extension.

+ add another resource

JavaScript

Babel includes JSX processing.

Add External Scripts/Pens

Any URL's added here will be added as <script>s in order, and run before the JavaScript in the editor. You can use the URL of any other Pen and it will include the JavaScript from that Pen.

+ add another resource

Packages

Add Packages

Search for and use JavaScript packages from npm here. By selecting a package, an import statement will be added to the top of the JavaScript editor for this package.

Behavior

Auto Save

If active, Pens will autosave every 30 seconds after being saved once.

Auto-Updating Preview

If enabled, the preview panel updates automatically as you code. If disabled, use the "Run" button to update.

Format on Save

If enabled, your code will be formatted when you actively save your Pen. Note: your code becomes un-folded during formatting.

Editor Settings

Code Indentation

Want to change your Syntax Highlighting theme, Fonts and more?

Visit your global Editor Settings.

HTML

              
                <!-- Copyright 2023 The MediaPipe Authors.

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. -->

<link href="https://unpkg.com/material-components-web@latest/dist/material-components-web.min.css" rel="stylesheet">
<script src="https://unpkg.com/material-components-web@latest/dist/material-components-web.min.js"></script>

<h1>Multiple object detection using the MediaPipe Object Detector task</h1>

<section id="demos" class="invisible">
  <h2>Demo: Detecting Images</h2>
  <p><b>Click on an image below</b> to detect objects in the image.</p>

  <div class="detectOnClick">
    <img src="https://assets.codepen.io/9177687/coupledog.jpeg" width="100%" crossorigin="anonymous" title="Click to get classification!" />
  </div>
  <div class="detectOnClick">
    <img src="https://assets.codepen.io/9177687/doggo.jpeg" width="100%" crossorigin="anonymous" title="Click to get classification!" />
  </div>

  <h2>Demo: Webcam continuous detection</h2>
  <p>Hold some objects up close to your webcam to get a real-time detection! When ready click "enable webcam" below and accept access to the webcam.</p>
  <div>This demo uses a model trained on the COCO dataset. It can identify 80 different classes of object in an image. <a href="https://github.com/amikelive/coco-labels/blob/master/coco-labels-2014_2017.txt" target="_blank">See a list of available classes</a></div>
  <div id="liveView" class="videoView">
    <button id="webcamButton" class="mdc-button mdc-button--raised">
      <span class="mdc-button__ripple"></span>
      <span class="mdc-button__label">ENABLE WEBCAM</span>
    </button>
    <video id="webcam" autoplay playsinline></video>
  </div>
</section>
              
            
!

CSS

              
                /* Copyright 2023 The MediaPipe Authors.

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. */

@use "@material";
body {
  font-family: roboto;
  margin: 2em;
  color: #3d3d3d;
  --mdc-theme-primary: #007f8b;
  --mdc-theme-on-primary: #f1f3f4;
}

h1 {
  color: #007f8b;
}

h2 {
  clear: both;
}

em {
  font-weight: bold;
}

video {
  clear: both;
  display: block;
  transform: rotateY(180deg);
  -webkit-transform: rotateY(180deg);
  -moz-transform: rotateY(180deg);
}

section {
  opacity: 1;
  transition: opacity 500ms ease-in-out;
}

.mdc-button.mdc-button--raised.removed {
  display: none;
}

.invisible {
  opacity: 0.2;
}

.videoView,
.detectOnClick {
  position: relative;
  float: left;
  width: 48%;
  margin: 2% 1%;
  cursor: pointer;
}

.detectOnClick p {
  position: absolute;
  padding: 5px;
  background-color: #007f8b;
  color: #fff;
  border: 1px dashed rgba(255, 255, 255, 0.7);
  z-index: 2;
  font-size: 12px;
  margin: 0;
}

.videoView p {
  position: absolute;
  padding-bottom: 5px;
  padding-top: 5px;
  background-color: #007f8b;
  color: #fff;
  border: 1px dashed rgba(255, 255, 255, 0.7);
  z-index: 2;
  font-size: 12px;
  margin: 0;
}

.highlighter {
  background: rgba(0, 255, 0, 0.25);
  border: 1px dashed #fff;
  z-index: 1;
  position: absolute;
}

.detectOnClick {
  z-index: 0;
}

.detectOnClick img {
  width: 100%;
}

              
            
!

JS

              
                // Copyright 2023 The MediaPipe Authors.

// 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.

import {
  ObjectDetector,
  FilesetResolver,
  Detection,
  ObjectDetectionResult
} from "https://cdn.jsdelivr.net/npm/@mediapipe/tasks-vision@0.10.2";

const demosSection = document.getElementById("demos") as HTMLElement;

let objectDetector: ObjectDetector;
let runningMode = "IMAGE";

// Initialize the object detector
const initializeObjectDetector = async () => {
  const vision = await FilesetResolver.forVisionTasks(
    "https://cdn.jsdelivr.net/npm/@mediapipe/tasks-vision@0.10.2/wasm"
  );
  objectDetector = await ObjectDetector.createFromOptions(vision, {
    baseOptions: {
      modelAssetPath: `https://storage.googleapis.com/mediapipe-models/object_detector/efficientdet_lite0/float16/1/efficientdet_lite0.tflite`,
      delegate: "GPU"
    },
    scoreThreshold: 0.5,
    runningMode: runningMode
  });
  demosSection.classList.remove("invisible");
};
initializeObjectDetector();

/********************************************************************
 // Demo 1: Grab a bunch of images from the page and detection them
 // upon click.
 ********************************************************************/

const imageContainers = document.getElementsByClassName(
  "detectOnClick"
) as HTMLDivElement;

for (let imageContainer of imageContainers) {
  imageContainer.children[0].addEventListener("click", handleClick);
}

/**
 * Detect objects in still images on click
 */
async function handleClick(event) {
  const highlighters = event.target.parentNode.getElementsByClassName(
    "highlighter"
  );
  while (highlighters[0]) {
    highlighters[0].parentNode.removeChild(highlighters[0]);
  }

  const infos = event.target.parentNode.getElementsByClassName("info");
  while (infos[0]) {
    infos[0].parentNode.removeChild(infos[0]);
  }

  if (!objectDetector) {
    alert("Object Detector is still loading. Please try again.");
    return;
  }

  // if video mode is initialized, set runningMode to image
  if (runningMode === "VIDEO") {
    runningMode = "IMAGE";
    await objectDetector.setOptions({ runningMode: "IMAGE" });
  }

  const ratio = event.target.height / event.target.naturalHeight;

  // objectDetector.detect returns a promise which, when resolved, is an array of Detection objects
  const detections = objectDetector.detect(event.target);
  displayImageDetections(detections, event.target);
}

function displayImageDetections(
  result: ObjectDetectionResult,
  resultElement: HTMLElement
) {
  const ratio = resultElement.height / resultElement.naturalHeight;
  console.log(ratio);

  for (let detection of result.detections) {
    // Description text
    const p = document.createElement("p");
    p.setAttribute("class", "info");
    p.innerText =
      detection.categories[0].categoryName +
      " - with " +
      Math.round(parseFloat(detection.categories[0].score) * 100) +
      "% confidence.";
    // Positioned at the top left of the bounding box.
    // Height is whatever the text takes up.
    // Width subtracts text padding in CSS so fits perfectly.
    p.style =
      "left: " +
      detection.boundingBox.originX * ratio +
      "px;" +
      "top: " +
      detection.boundingBox.originY * ratio +
      "px; " +
      "width: " +
      (detection.boundingBox.width * ratio - 10) +
      "px;";
    const highlighter = document.createElement("div");
    highlighter.setAttribute("class", "highlighter");
    highlighter.style =
      "left: " +
      detection.boundingBox.originX * ratio +
      "px;" +
      "top: " +
      detection.boundingBox.originY * ratio +
      "px;" +
      "width: " +
      detection.boundingBox.width * ratio +
      "px;" +
      "height: " +
      detection.boundingBox.height * ratio +
      "px;";

    resultElement.parentNode.appendChild(highlighter);
    resultElement.parentNode.appendChild(p);
  }
}

/********************************************************************
 // Demo 2: Continuously grab image from webcam stream and detect it.
 ********************************************************************/

let video = document.getElementById("webcam");
const liveView = document.getElementById("liveView");
let enableWebcamButton: HTMLButtonElement;
// Check if webcam access is supported.
function hasGetUserMedia() {
  return !!(navigator.mediaDevices && navigator.mediaDevices.getUserMedia);
}

// Keep a reference of all the child elements we create
// so we can remove them easilly on each render.
var children = [];

// If webcam supported, add event listener to button for when user
// wants to activate it.
if (hasGetUserMedia()) {
  enableWebcamButton = document.getElementById("webcamButton");
  enableWebcamButton.addEventListener("click", enableCam);
} else {
  console.warn("getUserMedia() is not supported by your browser");
}

// Enable the live webcam view and start detection.
async function enableCam(event) {
  if (!objectDetector) {
    console.log("Wait! objectDetector not loaded yet.");
    return;
  }

  // Hide the button.
  enableWebcamButton.classList.add("removed");

  // getUsermedia parameters
  const constraints = {
    video: true
  };

  // Activate the webcam stream.
  navigator.mediaDevices
    .getUserMedia(constraints)
    .then(function (stream) {
      video.srcObject = stream;
      video.addEventListener("loadeddata", predictWebcam);
    })
    .catch((err) => {
      console.error(err);
      /* handle the error */
    });
}

let lastVideoTime = -1;
async function predictWebcam() {
  // if image mode is initialized, create a new classifier with video runningMode.
  if (runningMode === "IMAGE") {
    runningMode = "VIDEO";
    await objectDetector.setOptions({ runningMode: "VIDEO" });
  }
  let startTimeMs = performance.now();

  // Detect objects using detectForVideo.
  if (video.currentTime !== lastVideoTime) {
    lastVideoTime = video.currentTime;
    const detections = objectDetector.detectForVideo(video, startTimeMs);
    displayVideoDetections(detections);
  }
  // Call this function again to keep predicting when the browser is ready.
  window.requestAnimationFrame(predictWebcam);
}

function displayVideoDetections(result: ObjectDetectionResult) {
  // Remove any highlighting from previous frame.
  for (let child of children) {
    liveView.removeChild(child);
  }
  children.splice(0);
  // Iterate through predictions and draw them to the live view
  for (let detection of result.detections) {
    const p = document.createElement("p");
    p.innerText =
      detection.categories[0].categoryName +
      " - with " +
      Math.round(parseFloat(detection.categories[0].score) * 100) +
      "% confidence.";
    p.style =
      "left: " +
      (video.offsetWidth -
        detection.boundingBox.width -
        detection.boundingBox.originX) +
      "px;" +
      "top: " +
      detection.boundingBox.originY +
      "px; " +
      "width: " +
      (detection.boundingBox.width - 10) +
      "px;";

    const highlighter = document.createElement("div");
    highlighter.setAttribute("class", "highlighter");
    highlighter.style =
      "left: " +
      (video.offsetWidth -
        detection.boundingBox.width -
        detection.boundingBox.originX) +
      "px;" +
      "top: " +
      detection.boundingBox.originY +
      "px;" +
      "width: " +
      (detection.boundingBox.width - 10) +
      "px;" +
      "height: " +
      detection.boundingBox.height +
      "px;";

    liveView.appendChild(highlighter);
    liveView.appendChild(p);

    // Store drawn objects in memory so they are queued to delete at next call.
    children.push(highlighter);
    children.push(p);
  }
}

              
            
!
999px

Console