[GSoC] Develop OpenCV.js DNN modules for promising web use cases together with their tutorials
* [Opencv.js doc] Init commit to add image classification example in opencv.js tutorial
* [Opencv.js doc] Make the code snippet interactive and put the functions into code snippet.
* Fix the utils.loadOpenCv for promise module
* [Opencv.js doc] Code modify and fixed layout issue.
* [Opencv.js doc] Add a JSON file to store parameters for models and show in the web page.
* [Opencv.js doc] Change let to const.
* [Opencv.js doc] Init commit to add image classification example with camera in opencv.js tutorial
* [Opencv.js doc] Init commit to add semantic segmentation example in opencv.js tutorial
* [Opencv.js doc] Add object detection example, supprot YOLOv2
* [Opencv.js doc] Support SSD model for object detection example
* [Opencv.js doc] Add fast neural style transfer example with opencv.js
* [Opencv.js doc] Add pose estimation example in opencv.js tutorial
* Delete whitespace for code check
* [Opencv.js doc] Add object detection example with camera
* [Opencv.js doc] Add json files containing model information to each example
* [Opencv.js doc] Add a js file for common function in dnn example
* [Opencv.js doc] Create single function getBlobFromImage
* [Opencv.js doc] Add url of model into webpage
* [OpenCV.js doc] Update UI for running
* [Opencv.js doc] Load dnn model by input button
* [Opencv.js doc] Fix some UI issues
* [Opencv.js doc] Change code format
Co-authored-by: Ningxin Hu <ningxin.hu@intel.com>
--- /dev/null
+getBlobFromImage = function(inputSize, mean, std, swapRB, image) {
+ let mat;
+ if (typeof(image) === 'string') {
+ mat = cv.imread(image);
+ } else {
+ mat = image;
+ }
+
+ let matC3 = new cv.Mat(mat.matSize[0], mat.matSize[1], cv.CV_8UC3);
+ cv.cvtColor(mat, matC3, cv.COLOR_RGBA2BGR);
+ let input = cv.blobFromImage(matC3, std, new cv.Size(inputSize[0], inputSize[1]),
+ new cv.Scalar(mean[0], mean[1], mean[2]), swapRB);
+
+ matC3.delete();
+ return input;
+}
+
+loadLables = async function(labelsUrl) {
+ let response = await fetch(labelsUrl);
+ let label = await response.text();
+ label = label.split('\n');
+ return label;
+}
+
+loadModel = async function(e) {
+ return new Promise((resolve) => {
+ let file = e.target.files[0];
+ let path = file.name;
+ let reader = new FileReader();
+ reader.readAsArrayBuffer(file);
+ reader.onload = function(ev) {
+ if (reader.readyState === 2) {
+ let buffer = reader.result;
+ let data = new Uint8Array(buffer);
+ cv.FS_createDataFile('/', path, data, true, false, false);
+ resolve(path);
+ }
+ }
+ });
+}
+
+getTopClasses = function(probs, labels, topK = 3) {
+ probs = Array.from(probs);
+ let indexes = probs.map((prob, index) => [prob, index]);
+ let sorted = indexes.sort((a, b) => {
+ if (a[0] === b[0]) {return 0;}
+ return a[0] < b[0] ? -1 : 1;
+ });
+ sorted.reverse();
+ let classes = [];
+ for (let i = 0; i < topK; ++i) {
+ let prob = sorted[i][0];
+ let index = sorted[i][1];
+ let c = {
+ label: labels[index],
+ prob: (prob * 100).toFixed(2)
+ }
+ classes.push(c);
+ }
+ return classes;
+}
+
+loadImageToCanvas = function(e, canvasId) {
+ let files = e.target.files;
+ let imgUrl = URL.createObjectURL(files[0]);
+ let canvas = document.getElementById(canvasId);
+ let ctx = canvas.getContext('2d');
+ let img = new Image();
+ img.crossOrigin = 'anonymous';
+ img.src = imgUrl;
+ img.onload = function() {
+ ctx.drawImage(img, 0, 0, canvas.width, canvas.height);
+ };
+}
+
+drawInfoTable = async function(jsonUrl, divId) {
+ let response = await fetch(jsonUrl);
+ let json = await response.json();
+
+ let appendix = document.getElementById(divId);
+ for (key of Object.keys(json)) {
+ let h3 = document.createElement('h3');
+ h3.textContent = key + " model";
+ appendix.appendChild(h3);
+
+ let table = document.createElement('table');
+ let head_tr = document.createElement('tr');
+ for (head of Object.keys(json[key][0])) {
+ let th = document.createElement('th');
+ th.textContent = head;
+ th.style.border = "1px solid black";
+ head_tr.appendChild(th);
+ }
+ table.appendChild(head_tr)
+
+ for (model of json[key]) {
+ let tr = document.createElement('tr');
+ for (params of Object.keys(model)) {
+ let td = document.createElement('td');
+ td.style.border = "1px solid black";
+ if (params !== "modelUrl" && params !== "configUrl" && params !== "labelsUrl") {
+ td.textContent = model[params];
+ tr.appendChild(td);
+ } else {
+ let a = document.createElement('a');
+ let link = document.createTextNode('link');
+ a.append(link);
+ a.href = model[params];
+ td.appendChild(a);
+ tr.appendChild(td);
+ }
+ }
+ table.appendChild(tr);
+ }
+ table.style.width = "800px";
+ table.style.borderCollapse = "collapse";
+ appendix.appendChild(table);
+ }
+}
--- /dev/null
+<!DOCTYPE html>
+<html>
+
+<head>
+ <meta charset="utf-8">
+ <title>Image Classification Example</title>
+ <link href="js_example_style.css" rel="stylesheet" type="text/css" />
+</head>
+
+<body>
+<h2>Image Classification Example</h2>
+<p>
+ This tutorial shows you how to write an image classification example with OpenCV.js.<br>
+ To try the example you should click the <b>modelFile</b> button(and <b>configFile</b> button if needed) to upload inference model.
+ You can find the model URLs and parameters in the <a href="#appendix">model info</a> section.
+ Then You should change the parameters in the first code snippet according to the uploaded model.
+ Finally click <b>Try it</b> button to see the result. You can choose any other images.<br>
+</p>
+
+<div class="control"><button id="tryIt" disabled>Try it</button></div>
+<div>
+ <table cellpadding="0" cellspacing="0" width="0" border="0">
+ <tr>
+ <td>
+ <canvas id="canvasInput" width="400" height="400"></canvas>
+ </td>
+ <td>
+ <table style="visibility: hidden;" id="result">
+ <thead>
+ <tr>
+ <th scope="col">#</th>
+ <th scope="col" width=300>Label</th>
+ <th scope="col">Probability</th>
+ </tr>
+ </thead>
+ <tbody>
+ <tr>
+ <th scope="row">1</th>
+ <td id="label0" align="center"></td>
+ <td id="prob0" align="center"></td>
+ </tr>
+ <tr>
+ <th scope="row">2</th>
+ <td id="label1" align="center"></td>
+ <td id="prob1" align="center"></td>
+ </tr>
+ <tr>
+ <th scope="row">3</th>
+ <td id="label2" align="center"></td>
+ <td id="prob2" align="center"></td>
+ </tr>
+ </tbody>
+ </table>
+ <p id='status' align="left"></p>
+ </td>
+ </tr>
+ <tr>
+ <td>
+ <div class="caption">
+ canvasInput <input type="file" id="fileInput" name="file" accept="image/*">
+ </div>
+ </td>
+ <td></td>
+ </tr>
+ <tr>
+ <td>
+ <div class="caption">
+ modelFile <input type="file" id="modelFile">
+ </div>
+ </td>
+ </tr>
+ <tr>
+ <td>
+ <div class="caption">
+ configFile <input type="file" id="configFile">
+ </div>
+ </td>
+ </tr>
+ </table>
+</div>
+
+<div>
+ <p class="err" id="errorMessage"></p>
+</div>
+
+<div>
+ <h3>Help function</h3>
+ <p>1.The parameters for model inference which you can modify to investigate more models.</p>
+ <textarea class="code" rows="13" cols="100" id="codeEditor" spellcheck="false"></textarea>
+ <p>2.Main loop in which will read the image from canvas and do inference once.</p>
+ <textarea class="code" rows="17" cols="100" id="codeEditor1" spellcheck="false"></textarea>
+ <p>3.Load labels from txt file and process it into an array.</p>
+ <textarea class="code" rows="7" cols="100" id="codeEditor2" spellcheck="false"></textarea>
+ <p>4.Get blob from image as input for net, and standardize it with <b>mean</b> and <b>std</b>.</p>
+ <textarea class="code" rows="17" cols="100" id="codeEditor3" spellcheck="false"></textarea>
+ <p>5.Fetch model file and save to emscripten file system once click the input button.</p>
+ <textarea class="code" rows="17" cols="100" id="codeEditor4" spellcheck="false"></textarea>
+ <p>6.The post-processing, including softmax if needed and get the top classes from the output vector.</p>
+ <textarea class="code" rows="35" cols="100" id="codeEditor5" spellcheck="false"></textarea>
+</div>
+
+<div id="appendix">
+ <h2>Model Info:</h2>
+</div>
+
+<script src="utils.js" type="text/javascript"></script>
+<script src="js_dnn_example_helper.js" type="text/javascript"></script>
+
+<script id="codeSnippet" type="text/code-snippet">
+inputSize = [224,224];
+mean = [104, 117, 123];
+std = 1;
+swapRB = false;
+
+// record if need softmax function for post-processing
+needSoftmax = false;
+
+// url for label file, can from local or Internet
+labelsUrl = "https://raw.githubusercontent.com/opencv/opencv/master/samples/data/dnn/classification_classes_ILSVRC2012.txt";
+</script>
+
+<script id="codeSnippet1" type="text/code-snippet">
+main = async function() {
+ const labels = await loadLables(labelsUrl);
+ const input = getBlobFromImage(inputSize, mean, std, swapRB, 'canvasInput');
+ let net = cv.readNet(configPath, modelPath);
+ net.setInput(input);
+ const start = performance.now();
+ const result = net.forward();
+ const time = performance.now()-start;
+ const probs = softmax(result);
+ const classes = getTopClasses(probs, labels);
+
+ updateResult(classes, time);
+ input.delete();
+ net.delete();
+ result.delete();
+}
+</script>
+
+<script id="codeSnippet5" type="text/code-snippet">
+softmax = function(result) {
+ let arr = result.data32F;
+ if (needSoftmax) {
+ const maxNum = Math.max(...arr);
+ const expSum = arr.map((num) => Math.exp(num - maxNum)).reduce((a, b) => a + b);
+ return arr.map((value, index) => {
+ return Math.exp(value - maxNum) / expSum;
+ });
+ } else {
+ return arr;
+ }
+}
+</script>
+
+<script type="text/javascript">
+ let jsonUrl = "js_image_classification_model_info.json";
+ drawInfoTable(jsonUrl, 'appendix');
+
+ let utils = new Utils('errorMessage');
+ utils.loadCode('codeSnippet', 'codeEditor');
+ utils.loadCode('codeSnippet1', 'codeEditor1');
+
+ let loadLablesCode = 'loadLables = ' + loadLables.toString();
+ document.getElementById('codeEditor2').value = loadLablesCode;
+ let getBlobFromImageCode = 'getBlobFromImage = ' + getBlobFromImage.toString();
+ document.getElementById('codeEditor3').value = getBlobFromImageCode;
+ let loadModelCode = 'loadModel = ' + loadModel.toString();
+ document.getElementById('codeEditor4').value = loadModelCode;
+
+ utils.loadCode('codeSnippet5', 'codeEditor5');
+ let getTopClassesCode = 'getTopClasses = ' + getTopClasses.toString();
+ document.getElementById('codeEditor5').value += '\n' + '\n' + getTopClassesCode;
+
+ let canvas = document.getElementById('canvasInput');
+ let ctx = canvas.getContext('2d');
+ let img = new Image();
+ img.crossOrigin = 'anonymous';
+ img.src = 'space_shuttle.jpg';
+ img.onload = function() {
+ ctx.drawImage(img, 0, 0, canvas.width, canvas.height);
+ };
+
+ let tryIt = document.getElementById('tryIt');
+ tryIt.addEventListener('click', () => {
+ initStatus();
+ document.getElementById('status').innerHTML = 'Running function main()...';
+ utils.executeCode('codeEditor');
+ utils.executeCode('codeEditor1');
+ if (modelPath === "") {
+ document.getElementById('status').innerHTML = 'Runing failed.';
+ utils.printError('Please upload model file by clicking the button first.');
+ } else {
+ setTimeout(main, 1);
+ }
+ });
+
+ let fileInput = document.getElementById('fileInput');
+ fileInput.addEventListener('change', (e) => {
+ initStatus();
+ loadImageToCanvas(e, 'canvasInput');
+ });
+
+ let configPath = "";
+ let configFile = document.getElementById('configFile');
+ configFile.addEventListener('change', async (e) => {
+ initStatus();
+ configPath = await loadModel(e);
+ document.getElementById('status').innerHTML = `The config file '${configPath}' is created successfully.`;
+ });
+
+ let modelPath = "";
+ let modelFile = document.getElementById('modelFile');
+ modelFile.addEventListener('change', async (e) => {
+ initStatus();
+ modelPath = await loadModel(e);
+ document.getElementById('status').innerHTML = `The model file '${modelPath}' is created successfully.`;
+ configPath = "";
+ configFile.value = "";
+ });
+
+ utils.loadOpenCv(() => {
+ tryIt.removeAttribute('disabled');
+ });
+
+ var main = async function() {};
+ var softmax = function(result){};
+ var getTopClasses = function(mat, labels, topK = 3){};
+
+ utils.executeCode('codeEditor1');
+ utils.executeCode('codeEditor2');
+ utils.executeCode('codeEditor3');
+ utils.executeCode('codeEditor4');
+ utils.executeCode('codeEditor5');
+
+ function updateResult(classes, time) {
+ try{
+ classes.forEach((c,i) => {
+ let labelElement = document.getElementById('label'+i);
+ let probElement = document.getElementById('prob'+i);
+ labelElement.innerHTML = c.label;
+ probElement.innerHTML = c.prob + '%';
+ });
+ let result = document.getElementById('result');
+ result.style.visibility = 'visible';
+ document.getElementById('status').innerHTML = `<b>Model:</b> ${modelPath}<br>
+ <b>Inference time:</b> ${time.toFixed(2)} ms`;
+ } catch(e) {
+ console.log(e);
+ }
+ }
+
+ function initStatus() {
+ document.getElementById('status').innerHTML = '';
+ document.getElementById('result').style.visibility = 'hidden';
+ utils.clearError();
+ }
+
+</script>
+
+</body>
+
+</html>
\ No newline at end of file
--- /dev/null
+{
+ "caffe": [
+ {
+ "model": "alexnet",
+ "mean": "104, 117, 123",
+ "std": "1",
+ "swapRB": "false",
+ "needSoftmax": "false",
+ "labelsUrl": "https://raw.githubusercontent.com/opencv/opencv/master/samples/data/dnn/classification_classes_ILSVRC2012.txt",
+ "modelUrl": "http://dl.caffe.berkeleyvision.org/bvlc_alexnet.caffemodel",
+ "configUrl": "https://raw.githubusercontent.com/BVLC/caffe/master/models/bvlc_alexnet/deploy.prototxt"
+ },
+ {
+ "model": "densenet",
+ "mean": "127.5, 127.5, 127.5",
+ "std": "0.007843",
+ "swapRB": "false",
+ "needSoftmax": "true",
+ "labelsUrl": "https://raw.githubusercontent.com/opencv/opencv/master/samples/data/dnn/classification_classes_ILSVRC2012.txt",
+ "modelUrl": "https://drive.google.com/open?id=0B7ubpZO7HnlCcHlfNmJkU2VPelE",
+ "configUrl": "https://raw.githubusercontent.com/shicai/DenseNet-Caffe/master/DenseNet_121.prototxt"
+ },
+ {
+ "model": "googlenet",
+ "mean": "104, 117, 123",
+ "std": "1",
+ "swapRB": "false",
+ "needSoftmax": "false",
+ "labelsUrl": "https://raw.githubusercontent.com/opencv/opencv/master/samples/data/dnn/classification_classes_ILSVRC2012.txt",
+ "modelUrl": "http://dl.caffe.berkeleyvision.org/bvlc_googlenet.caffemodel",
+ "configUrl": "https://raw.githubusercontent.com/BVLC/caffe/master/models/bvlc_googlenet/deploy.prototxt"
+ },
+ {
+ "model": "squeezenet",
+ "mean": "104, 117, 123",
+ "std": "1",
+ "swapRB": "false",
+ "needSoftmax": "false",
+ "labelsUrl": "https://raw.githubusercontent.com/opencv/opencv/master/samples/data/dnn/classification_classes_ILSVRC2012.txt",
+ "modelUrl": "https://raw.githubusercontent.com/forresti/SqueezeNet/master/SqueezeNet_v1.0/squeezenet_v1.0.caffemodel",
+ "configUrl": "https://raw.githubusercontent.com/forresti/SqueezeNet/master/SqueezeNet_v1.0/deploy.prototxt"
+ },
+ {
+ "model": "VGG",
+ "mean": "104, 117, 123",
+ "std": "1",
+ "swapRB": "false",
+ "needSoftmax": "false",
+ "labelsUrl": "https://raw.githubusercontent.com/opencv/opencv/master/samples/data/dnn/classification_classes_ILSVRC2012.txt",
+ "modelUrl": "http://www.robots.ox.ac.uk/~vgg/software/very_deep/caffe/VGG_ILSVRC_19_layers.caffemodel",
+ "configUrl": "https://gist.githubusercontent.com/ksimonyan/3785162f95cd2d5fee77/raw/f02f8769e64494bcd3d7e97d5d747ac275825721/VGG_ILSVRC_19_layers_deploy.prototxt"
+ }
+ ],
+ "tensorflow": [
+ {
+ "model": "inception",
+ "mean": "123, 117, 104",
+ "std": "1",
+ "swapRB": "true",
+ "needSoftmax": "false",
+ "labelsUrl": "https://raw.githubusercontent.com/petewarden/tf_ios_makefile_example/master/data/imagenet_comp_graph_label_strings.txt",
+ "modelUrl": "https://raw.githubusercontent.com/petewarden/tf_ios_makefile_example/master/data/tensorflow_inception_graph.pb"
+ }
+ ]
+}
\ No newline at end of file
--- /dev/null
+<!DOCTYPE html>
+<html>
+
+<head>
+ <meta charset="utf-8">
+ <title>Image Classification Example with Camera</title>
+ <link href="js_example_style.css" rel="stylesheet" type="text/css" />
+</head>
+
+<body>
+<h2>Image Classification Example with Camera</h2>
+<p>
+ This tutorial shows you how to write an image classification example with camera.<br>
+ To try the example you should click the <b>modelFile</b> button(and <b>configFile</b> button if needed) to upload inference model.
+ You can find the model URLs and parameters in the <a href="#appendix">model info</a> section.
+ Then You should change the parameters in the first code snippet according to the uploaded model.
+ Finally click <b>Start/Stop</b> button to start or stop the camera capture.<br>
+</p>
+
+<div class="control"><button id="startAndStop" disabled>Start</button></div>
+<div>
+ <table cellpadding="0" cellspacing="0" width="0" border="0">
+ <tr>
+ <td>
+ <video id="videoInput" width="400" height="400"></video>
+ </td>
+ <td>
+ <table style="visibility: hidden;" id="result">
+ <thead>
+ <tr>
+ <th scope="col">#</th>
+ <th scope="col" width=300>Label</th>
+ <th scope="col">Probability</th>
+ </tr>
+ </thead>
+ <tbody>
+ <tr>
+ <th scope="row">1</th>
+ <td id="label0" align="center"></td>
+ <td id="prob0" align="center"></td>
+ </tr>
+ <tr>
+ <th scope="row">2</th>
+ <td id="label1" align="center"></td>
+ <td id="prob1" align="center"></td>
+ </tr>
+ <tr>
+ <th scope="row">3</th>
+ <td id="label2" align="center"></td>
+ <td id="prob2" align="center"></td>
+ </tr>
+ </tbody>
+ </table>
+ <p id='status' align="left"></p>
+ </td>
+ </tr>
+ <tr>
+ <td>
+ <div class="caption">
+ videoInput
+ </div>
+ </td>
+ <td></td>
+ </tr>
+ <tr>
+ <td>
+ <div class="caption">
+ modelFile <input type="file" id="modelFile">
+ </div>
+ </td>
+ </tr>
+ <tr>
+ <td>
+ <div class="caption">
+ configFile <input type="file" id="configFile">
+ </div>
+ </td>
+ </tr>
+ </table>
+</div>
+
+<div>
+ <p class="err" id="errorMessage"></p>
+</div>
+
+<div>
+ <h3>Help function</h3>
+ <p>1.The parameters for model inference which you can modify to investigate more models.</p>
+ <textarea class="code" rows="13" cols="100" id="codeEditor" spellcheck="false"></textarea>
+ <p>2.The function to capture video from camera, and the main loop in which will do inference once.</p>
+ <textarea class="code" rows="35" cols="100" id="codeEditor1" spellcheck="false"></textarea>
+ <p>3.Load labels from txt file and process it into an array.</p>
+ <textarea class="code" rows="7" cols="100" id="codeEditor2" spellcheck="false"></textarea>
+ <p>4.Get blob from image as input for net, and standardize it with <b>mean</b> and <b>std</b>.</p>
+ <textarea class="code" rows="17" cols="100" id="codeEditor3" spellcheck="false"></textarea>
+ <p>5.Fetch model file and save to emscripten file system once click the input button.</p>
+ <textarea class="code" rows="17" cols="100" id="codeEditor4" spellcheck="false"></textarea>
+ <p>6.The post-processing, including softmax if needed and get the top classes from the output vector.</p>
+ <textarea class="code" rows="35" cols="100" id="codeEditor5" spellcheck="false"></textarea>
+</div>
+
+<div id="appendix">
+ <h2>Model Info:</h2>
+</div>
+
+<script src="utils.js" type="text/javascript"></script>
+<script src="js_dnn_example_helper.js" type="text/javascript"></script>
+
+<script id="codeSnippet" type="text/code-snippet">
+inputSize = [224,224];
+mean = [104, 117, 123];
+std = 1;
+swapRB = false;
+
+// record if need softmax function for post-processing
+needSoftmax = false;
+
+// url for label file, can from local or Internet
+labelsUrl = "https://raw.githubusercontent.com/opencv/opencv/master/samples/data/dnn/classification_classes_ILSVRC2012.txt";
+</script>
+
+<script id="codeSnippet1" type="text/code-snippet">
+let frame = new cv.Mat(video.height, video.width, cv.CV_8UC4);
+let cap = new cv.VideoCapture(video);
+
+main = async function(frame) {
+ const labels = await loadLables(labelsUrl);
+ const input = getBlobFromImage(inputSize, mean, std, swapRB, frame);
+ let net = cv.readNet(configPath, modelPath);
+ net.setInput(input);
+ const start = performance.now();
+ const result = net.forward();
+ const time = performance.now()-start;
+ const probs = softmax(result);
+ const classes = getTopClasses(probs, labels);
+
+ updateResult(classes, time);
+ setTimeout(processVideo, 0);
+ input.delete();
+ net.delete();
+ result.delete();
+}
+
+function processVideo() {
+ try {
+ if (!streaming) {
+ return;
+ }
+ cap.read(frame);
+ main(frame);
+ } catch (err) {
+ utils.printError(err);
+ }
+}
+
+setTimeout(processVideo, 0);
+</script>
+
+<script id="codeSnippet5" type="text/code-snippet">
+softmax = function(result) {
+ let arr = result.data32F;
+ if (needSoftmax) {
+ const maxNum = Math.max(...arr);
+ const expSum = arr.map((num) => Math.exp(num - maxNum)).reduce((a, b) => a + b);
+ return arr.map((value, index) => {
+ return Math.exp(value - maxNum) / expSum;
+ });
+ } else {
+ return arr;
+ }
+}
+</script>
+
+<script type="text/javascript">
+ let jsonUrl = "js_image_classification_model_info.json";
+ drawInfoTable(jsonUrl, 'appendix');
+
+ let utils = new Utils('errorMessage');
+ utils.loadCode('codeSnippet', 'codeEditor');
+ utils.loadCode('codeSnippet1', 'codeEditor1');
+
+ let loadLablesCode = 'loadLables = ' + loadLables.toString();
+ document.getElementById('codeEditor2').value = loadLablesCode;
+ let getBlobFromImageCode = 'getBlobFromImage = ' + getBlobFromImage.toString();
+ document.getElementById('codeEditor3').value = getBlobFromImageCode;
+ let loadModelCode = 'loadModel = ' + loadModel.toString();
+ document.getElementById('codeEditor4').value = loadModelCode;
+
+ utils.loadCode('codeSnippet5', 'codeEditor5');
+ let getTopClassesCode = 'getTopClasses = ' + getTopClasses.toString();
+ document.getElementById('codeEditor5').value += '\n' + '\n' + getTopClassesCode;
+
+ let video = document.getElementById('videoInput');
+ let streaming = false;
+ let startAndStop = document.getElementById('startAndStop');
+ startAndStop.addEventListener('click', () => {
+ if (!streaming) {
+ utils.clearError();
+ utils.startCamera('qvga', onVideoStarted, 'videoInput');
+ } else {
+ utils.stopCamera();
+ onVideoStopped();
+ }
+ });
+
+ let configPath = "";
+ let configFile = document.getElementById('configFile');
+ configFile.addEventListener('change', async (e) => {
+ initStatus();
+ configPath = await loadModel(e);
+ document.getElementById('status').innerHTML = `The config file '${configPath}' is created successfully.`;
+ });
+
+ let modelPath = "";
+ let modelFile = document.getElementById('modelFile');
+ modelFile.addEventListener('change', async (e) => {
+ initStatus();
+ modelPath = await loadModel(e);
+ document.getElementById('status').innerHTML = `The model file '${modelPath}' is created successfully.`;
+ configPath = "";
+ configFile.value = "";
+ });
+
+ utils.loadOpenCv(() => {
+ startAndStop.removeAttribute('disabled');
+
+ });
+
+ var main = async function(frame) {};
+ var softmax = function(result){};
+ var getTopClasses = function(mat, labels, topK = 3){};
+
+ utils.executeCode('codeEditor1');
+ utils.executeCode('codeEditor2');
+ utils.executeCode('codeEditor3');
+ utils.executeCode('codeEditor4');
+ utils.executeCode('codeEditor5');
+
+ function onVideoStarted() {
+ streaming = true;
+ startAndStop.innerText = 'Stop';
+ videoInput.width = videoInput.videoWidth;
+ videoInput.height = videoInput.videoHeight;
+ utils.executeCode('codeEditor');
+ utils.executeCode('codeEditor1');
+ }
+
+ function onVideoStopped() {
+ streaming = false;
+ startAndStop.innerText = 'Start';
+ initStatus();
+ }
+
+ function updateResult(classes, time) {
+ try{
+ classes.forEach((c,i) => {
+ let labelElement = document.getElementById('label'+i);
+ let probElement = document.getElementById('prob'+i);
+ labelElement.innerHTML = c.label;
+ probElement.innerHTML = c.prob + '%';
+ });
+ let result = document.getElementById('result');
+ result.style.visibility = 'visible';
+ document.getElementById('status').innerHTML = `<b>Model:</b> ${modelPath}<br>
+ <b>Inference time:</b> ${time.toFixed(2)} ms`;
+ } catch(e) {
+ console.log(e);
+ }
+ }
+
+ function initStatus() {
+ document.getElementById('status').innerHTML = '';
+ document.getElementById('result').style.visibility = 'hidden';
+ utils.clearError();
+ }
+
+</script>
+
+</body>
+
+</html>
\ No newline at end of file
--- /dev/null
+<!DOCTYPE html>
+<html>
+
+<head>
+ <meta charset="utf-8">
+ <title>Object Detection Example</title>
+ <link href="js_example_style.css" rel="stylesheet" type="text/css" />
+</head>
+
+<body>
+<h2>Object Detection Example</h2>
+<p>
+ This tutorial shows you how to write an object detection example with OpenCV.js.<br>
+ To try the example you should click the <b>modelFile</b> button(and <b>configFile</b> button if needed) to upload inference model.
+ You can find the model URLs and parameters in the <a href="#appendix">model info</a> section.
+ Then You should change the parameters in the first code snippet according to the uploaded model.
+ Finally click <b>Try it</b> button to see the result. You can choose any other images.<br>
+</p>
+
+<div class="control"><button id="tryIt" disabled>Try it</button></div>
+<div>
+ <table cellpadding="0" cellspacing="0" width="0" border="0">
+ <tr>
+ <td>
+ <canvas id="canvasInput" width="400" height="400"></canvas>
+ </td>
+ <td>
+ <canvas id="canvasOutput" style="visibility: hidden;" width="400" height="400"></canvas>
+ </td>
+ </tr>
+ <tr>
+ <td>
+ <div class="caption">
+ canvasInput <input type="file" id="fileInput" name="file" accept="image/*">
+ </div>
+ </td>
+ <td>
+ <p id='status' align="left"></p>
+ </td>
+ </tr>
+ <tr>
+ <td>
+ <div class="caption">
+ modelFile <input type="file" id="modelFile" name="file">
+ </div>
+ </td>
+ </tr>
+ <tr>
+ <td>
+ <div class="caption">
+ configFile <input type="file" id="configFile">
+ </div>
+ </td>
+ </tr>
+ </table>
+</div>
+
+<div>
+ <p class="err" id="errorMessage"></p>
+</div>
+
+<div>
+ <h3>Help function</h3>
+ <p>1.The parameters for model inference which you can modify to investigate more models.</p>
+ <textarea class="code" rows="15" cols="100" id="codeEditor" spellcheck="false"></textarea>
+ <p>2.Main loop in which will read the image from canvas and do inference once.</p>
+ <textarea class="code" rows="16" cols="100" id="codeEditor1" spellcheck="false"></textarea>
+ <p>3.Load labels from txt file and process it into an array.</p>
+ <textarea class="code" rows="7" cols="100" id="codeEditor2" spellcheck="false"></textarea>
+ <p>4.Get blob from image as input for net, and standardize it with <b>mean</b> and <b>std</b>.</p>
+ <textarea class="code" rows="17" cols="100" id="codeEditor3" spellcheck="false"></textarea>
+ <p>5.Fetch model file and save to emscripten file system once click the input button.</p>
+ <textarea class="code" rows="17" cols="100" id="codeEditor4" spellcheck="false"></textarea>
+ <p>6.The post-processing, including get boxes from output and draw boxes into the image.</p>
+ <textarea class="code" rows="35" cols="100" id="codeEditor5" spellcheck="false"></textarea>
+</div>
+
+<div id="appendix">
+ <h2>Model Info:</h2>
+</div>
+
+<script src="utils.js" type="text/javascript"></script>
+<script src="js_dnn_example_helper.js" type="text/javascript"></script>
+
+<script id="codeSnippet" type="text/code-snippet">
+inputSize = [300, 300];
+mean = [127.5, 127.5, 127.5];
+std = 0.007843;
+swapRB = false;
+confThreshold = 0.5;
+nmsThreshold = 0.4;
+
+// The type of output, can be YOLO or SSD
+outType = "SSD";
+
+// url for label file, can from local or Internet
+labelsUrl = "https://raw.githubusercontent.com/opencv/opencv/master/samples/data/dnn/object_detection_classes_pascal_voc.txt";
+</script>
+
+<script id="codeSnippet1" type="text/code-snippet">
+main = async function() {
+ const labels = await loadLables(labelsUrl);
+ const input = getBlobFromImage(inputSize, mean, std, swapRB, 'canvasInput');
+ let net = cv.readNet(configPath, modelPath);
+ net.setInput(input);
+ const start = performance.now();
+ const result = net.forward();
+ const time = performance.now()-start;
+ const output = postProcess(result, labels);
+
+ updateResult(output, time);
+ input.delete();
+ net.delete();
+ result.delete();
+}
+</script>
+
+<script id="codeSnippet5" type="text/code-snippet">
+postProcess = function(result, labels) {
+ let canvasOutput = document.getElementById('canvasOutput');
+ const outputWidth = canvasOutput.width;
+ const outputHeight = canvasOutput.height;
+ const resultData = result.data32F;
+
+ // Get the boxes(with class and confidence) from the output
+ let boxes = [];
+ switch(outType) {
+ case "YOLO": {
+ const vecNum = result.matSize[0];
+ const vecLength = result.matSize[1];
+ const classNum = vecLength - 5;
+
+ for (let i = 0; i < vecNum; ++i) {
+ let vector = resultData.slice(i*vecLength, (i+1)*vecLength);
+ let scores = vector.slice(5, vecLength);
+ let classId = scores.indexOf(Math.max(...scores));
+ let confidence = scores[classId];
+ if (confidence > confThreshold) {
+ let center_x = Math.round(vector[0] * outputWidth);
+ let center_y = Math.round(vector[1] * outputHeight);
+ let width = Math.round(vector[2] * outputWidth);
+ let height = Math.round(vector[3] * outputHeight);
+ let left = Math.round(center_x - width / 2);
+ let top = Math.round(center_y - height / 2);
+
+ let box = {
+ scores: scores,
+ classId: classId,
+ confidence: confidence,
+ bounding: [left, top, width, height],
+ toDraw: true
+ }
+ boxes.push(box);
+ }
+ }
+
+ // NMS(Non Maximum Suppression) algorithm
+ let boxNum = boxes.length;
+ let tmp_boxes = [];
+ let sorted_boxes = [];
+ for (let c = 0; c < classNum; ++c) {
+ for (let i = 0; i < boxes.length; ++i) {
+ tmp_boxes[i] = [boxes[i], i];
+ }
+ sorted_boxes = tmp_boxes.sort((a, b) => { return (b[0].scores[c] - a[0].scores[c]); });
+ for (let i = 0; i < boxNum; ++i) {
+ if (sorted_boxes[i][0].scores[c] === 0) continue;
+ else {
+ for (let j = i + 1; j < boxNum; ++j) {
+ if (IOU(sorted_boxes[i][0], sorted_boxes[j][0]) >= nmsThreshold) {
+ boxes[sorted_boxes[j][1]].toDraw = false;
+ }
+ }
+ }
+ }
+ }
+ } break;
+ case "SSD": {
+ const vecNum = result.matSize[2];
+ const vecLength = 7;
+
+ for (let i = 0; i < vecNum; ++i) {
+ let vector = resultData.slice(i*vecLength, (i+1)*vecLength);
+ let confidence = vector[2];
+ if (confidence > confThreshold) {
+ let left, top, right, bottom, width, height;
+ left = Math.round(vector[3]);
+ top = Math.round(vector[4]);
+ right = Math.round(vector[5]);
+ bottom = Math.round(vector[6]);
+ width = right - left + 1;
+ height = bottom - top + 1;
+ if (width <= 2 || height <= 2) {
+ left = Math.round(vector[3] * outputWidth);
+ top = Math.round(vector[4] * outputHeight);
+ right = Math.round(vector[5] * outputWidth);
+ bottom = Math.round(vector[6] * outputHeight);
+ width = right - left + 1;
+ height = bottom - top + 1;
+ }
+ let box = {
+ classId: vector[1] - 1,
+ confidence: confidence,
+ bounding: [left, top, width, height],
+ toDraw: true
+ }
+ boxes.push(box);
+ }
+ }
+ } break;
+ default:
+ console.error(`Unsupported output type ${outType}`)
+ }
+
+ // Draw the saved box into the image
+ let image = cv.imread("canvasInput");
+ let output = new cv.Mat(outputWidth, outputHeight, cv.CV_8UC3);
+ cv.cvtColor(image, output, cv.COLOR_RGBA2RGB);
+ let boxNum = boxes.length;
+ for (let i = 0; i < boxNum; ++i) {
+ if (boxes[i].toDraw) {
+ drawBox(boxes[i]);
+ }
+ }
+
+ return output;
+
+
+ // Calculate the IOU(Intersection over Union) of two boxes
+ function IOU(box1, box2) {
+ let bounding1 = box1.bounding;
+ let bounding2 = box2.bounding;
+ let s1 = bounding1[2] * bounding1[3];
+ let s2 = bounding2[2] * bounding2[3];
+
+ let left1 = bounding1[0];
+ let right1 = left1 + bounding1[2];
+ let left2 = bounding2[0];
+ let right2 = left2 + bounding2[2];
+ let overlapW = calOverlap([left1, right1], [left2, right2]);
+
+ let top1 = bounding2[1];
+ let bottom1 = top1 + bounding1[3];
+ let top2 = bounding2[1];
+ let bottom2 = top2 + bounding2[3];
+ let overlapH = calOverlap([top1, bottom1], [top2, bottom2]);
+
+ let overlapS = overlapW * overlapH;
+ return overlapS / (s1 + s2 + overlapS);
+ }
+
+ // Calculate the overlap range of two vector
+ function calOverlap(range1, range2) {
+ let min1 = range1[0];
+ let max1 = range1[1];
+ let min2 = range2[0];
+ let max2 = range2[1];
+
+ if (min2 > min1 && min2 < max1) {
+ return max1 - min2;
+ } else if (max2 > min1 && max2 < max1) {
+ return max2 - min1;
+ } else {
+ return 0;
+ }
+ }
+
+ // Draw one predict box into the origin image
+ function drawBox(box) {
+ let bounding = box.bounding;
+ let left = bounding[0];
+ let top = bounding[1];
+ let width = bounding[2];
+ let height = bounding[3];
+
+ cv.rectangle(output, new cv.Point(left, top), new cv.Point(left + width, top + height),
+ new cv.Scalar(0, 255, 0));
+ cv.rectangle(output, new cv.Point(left, top), new cv.Point(left + width, top + 15),
+ new cv.Scalar(255, 255, 255), cv.FILLED);
+ let text = `${labels[box.classId]}: ${box.confidence.toFixed(4)}`;
+ cv.putText(output, text, new cv.Point(left, top + 10), cv.FONT_HERSHEY_SIMPLEX, 0.3,
+ new cv.Scalar(0, 0, 0));
+ }
+}
+</script>
+
+<script type="text/javascript">
+ let jsonUrl = "js_object_detection_model_info.json";
+ drawInfoTable(jsonUrl, 'appendix');
+
+ let utils = new Utils('errorMessage');
+ utils.loadCode('codeSnippet', 'codeEditor');
+ utils.loadCode('codeSnippet1', 'codeEditor1');
+
+ let loadLablesCode = 'loadLables = ' + loadLables.toString();
+ document.getElementById('codeEditor2').value = loadLablesCode;
+ let getBlobFromImageCode = 'getBlobFromImage = ' + getBlobFromImage.toString();
+ document.getElementById('codeEditor3').value = getBlobFromImageCode;
+ let loadModelCode = 'loadModel = ' + loadModel.toString();
+ document.getElementById('codeEditor4').value = loadModelCode;
+
+ utils.loadCode('codeSnippet5', 'codeEditor5');
+
+ let canvas = document.getElementById('canvasInput');
+ let ctx = canvas.getContext('2d');
+ let img = new Image();
+ img.crossOrigin = 'anonymous';
+ img.src = 'lena.png';
+ img.onload = function() {
+ ctx.drawImage(img, 0, 0, canvas.width, canvas.height);
+ };
+
+ let tryIt = document.getElementById('tryIt');
+ tryIt.addEventListener('click', () => {
+ initStatus();
+ document.getElementById('status').innerHTML = 'Running function main()...';
+ utils.executeCode('codeEditor');
+ utils.executeCode('codeEditor1');
+ if (modelPath === "") {
+ document.getElementById('status').innerHTML = 'Runing failed.';
+ utils.printError('Please upload model file by clicking the button first.');
+ } else {
+ setTimeout(main, 1);
+ }
+ });
+
+ let fileInput = document.getElementById('fileInput');
+ fileInput.addEventListener('change', (e) => {
+ initStatus();
+ loadImageToCanvas(e, 'canvasInput');
+ });
+
+ let configPath = "";
+ let configFile = document.getElementById('configFile');
+ configFile.addEventListener('change', async (e) => {
+ initStatus();
+ configPath = await loadModel(e);
+ document.getElementById('status').innerHTML = `The config file '${configPath}' is created successfully.`;
+ });
+
+ let modelPath = "";
+ let modelFile = document.getElementById('modelFile');
+ modelFile.addEventListener('change', async (e) => {
+ initStatus();
+ modelPath = await loadModel(e);
+ document.getElementById('status').innerHTML = `The model file '${modelPath}' is created successfully.`;
+ configPath = "";
+ configFile.value = "";
+ });
+
+ utils.loadOpenCv(() => {
+ tryIt.removeAttribute('disabled');
+ });
+
+ var main = async function() {};
+ var postProcess = function(result, labels) {};
+
+ utils.executeCode('codeEditor1');
+ utils.executeCode('codeEditor2');
+ utils.executeCode('codeEditor3');
+ utils.executeCode('codeEditor4');
+ utils.executeCode('codeEditor5');
+
+
+ function updateResult(output, time) {
+ try{
+ let canvasOutput = document.getElementById('canvasOutput');
+ canvasOutput.style.visibility = "visible";
+ cv.imshow('canvasOutput', output);
+ document.getElementById('status').innerHTML = `<b>Model:</b> ${modelPath}<br>
+ <b>Inference time:</b> ${time.toFixed(2)} ms`;
+ } catch(e) {
+ console.log(e);
+ }
+ }
+
+ function initStatus() {
+ document.getElementById('status').innerHTML = '';
+ document.getElementById('canvasOutput').style.visibility = "hidden";
+ utils.clearError();
+ }
+
+</script>
+
+</body>
+
+</html>
\ No newline at end of file
--- /dev/null
+{
+ "caffe": [
+ {
+ "model": "mobilenet_SSD",
+ "inputSize": "300, 300",
+ "mean": "127.5, 127.5, 127.5",
+ "std": "0.007843",
+ "swapRB": "false",
+ "outType": "SSD",
+ "labelsUrl": "https://raw.githubusercontent.com/opencv/opencv/master/samples/data/dnn/object_detection_classes_pascal_voc.txt",
+ "modelUrl": "https://raw.githubusercontent.com/chuanqi305/MobileNet-SSD/master/mobilenet_iter_73000.caffemodel",
+ "configUrl": "https://raw.githubusercontent.com/chuanqi305/MobileNet-SSD/master/deploy.prototxt"
+ },
+ {
+ "model": "VGG_SSD",
+ "inputSize": "300, 300",
+ "mean": "104, 117, 123",
+ "std": "1",
+ "swapRB": "false",
+ "outType": "SSD",
+ "labelsUrl": "https://raw.githubusercontent.com/opencv/opencv/master/samples/data/dnn/object_detection_classes_pascal_voc.txt",
+ "modelUrl": "https://drive.google.com/uc?id=0BzKzrI_SkD1_WVVTSmQxU0dVRzA&export=download",
+ "configUrl": "https://drive.google.com/uc?id=0BzKzrI_SkD1_WVVTSmQxU0dVRzA&export=download"
+ }
+ ],
+ "darknet": [
+ {
+ "model": "yolov2_tiny",
+ "inputSize": "416, 416",
+ "mean": "0, 0, 0",
+ "std": "0.00392",
+ "swapRB": "false",
+ "outType": "YOLO",
+ "labelsUrl": "https://raw.githubusercontent.com/opencv/opencv/master/samples/data/dnn/object_detection_classes_yolov3.txt",
+ "modelUrl": "https://pjreddie.com/media/files/yolov2-tiny.weights",
+ "configUrl": "https://raw.githubusercontent.com/pjreddie/darknet/master/cfg/yolov2-tiny.cfg"
+ }
+ ]
+}
\ No newline at end of file
--- /dev/null
+<!DOCTYPE html>
+<html>
+
+<head>
+ <meta charset="utf-8">
+ <title>Object Detection Example with Camera</title>
+ <link href="js_example_style.css" rel="stylesheet" type="text/css" />
+</head>
+
+<body>
+<h2>Object Detection Example with Camera </h2>
+<p>
+ This tutorial shows you how to write an object detection example with camera.<br>
+ To try the example you should click the <b>modelFile</b> button(and <b>configInput</b> button if needed) to upload inference model.
+ You can find the model URLs and parameters in the <a href="#appendix">model info</a> section.
+ Then You should change the parameters in the first code snippet according to the uploaded model.
+ Finally click <b>Start/Stop</b> button to start or stop the camera capture.<br>
+</p>
+
+<div class="control"><button id="startAndStop" disabled>Start</button></div>
+<div>
+ <table cellpadding="0" cellspacing="0" width="0" border="0">
+ <tr>
+ <td>
+ <video id="videoInput" width="400" height="400"></video>
+ </td>
+ <td>
+ <canvas id="canvasOutput" style="visibility: hidden;" width="400" height="400"></canvas>
+ </td>
+ </tr>
+ <tr>
+ <td>
+ <div class="caption">
+ videoInput
+ </div>
+ </td>
+ <td>
+ <p id='status' align="left"></p>
+ </td>
+ </tr>
+ <tr>
+ <td>
+ <div class="caption">
+ modelFile <input type="file" id="modelFile" name="file">
+ </div>
+ </td>
+ </tr>
+ <tr>
+ <td>
+ <div class="caption">
+ configFile <input type="file" id="configFile">
+ </div>
+ </td>
+ </tr>
+ </table>
+</div>
+
+<div>
+ <p class="err" id="errorMessage"></p>
+</div>
+
+<div>
+ <h3>Help function</h3>
+ <p>1.The parameters for model inference which you can modify to investigate more models.</p>
+ <textarea class="code" rows="15" cols="100" id="codeEditor" spellcheck="false"></textarea>
+ <p>2.The function to capture video from camera, and the main loop in which will do inference once.</p>
+ <textarea class="code" rows="34" cols="100" id="codeEditor1" spellcheck="false"></textarea>
+ <p>3.Load labels from txt file and process it into an array.</p>
+ <textarea class="code" rows="7" cols="100" id="codeEditor2" spellcheck="false"></textarea>
+ <p>4.Get blob from image as input for net, and standardize it with <b>mean</b> and <b>std</b>.</p>
+ <textarea class="code" rows="17" cols="100" id="codeEditor3" spellcheck="false"></textarea>
+ <p>5.Fetch model file and save to emscripten file system once click the input button.</p>
+ <textarea class="code" rows="17" cols="100" id="codeEditor4" spellcheck="false"></textarea>
+ <p>6.The post-processing, including get boxes from output and draw boxes into the image.</p>
+ <textarea class="code" rows="35" cols="100" id="codeEditor5" spellcheck="false"></textarea>
+</div>
+
+<div id="appendix">
+ <h2>Model Info:</h2>
+</div>
+
+<script src="utils.js" type="text/javascript"></script>
+<script src="js_dnn_example_helper.js" type="text/javascript"></script>
+
+<script id="codeSnippet" type="text/code-snippet">
+inputSize = [300, 300];
+mean = [127.5, 127.5, 127.5];
+std = 0.007843;
+swapRB = false;
+confThreshold = 0.5;
+nmsThreshold = 0.4;
+
+// the type of output, can be YOLO or SSD
+outType = "SSD";
+
+// url for label file, can from local or Internet
+labelsUrl = "https://raw.githubusercontent.com/opencv/opencv/master/samples/data/dnn/object_detection_classes_pascal_voc.txt";
+</script>
+
+<script id="codeSnippet1" type="text/code-snippet">
+let frame = new cv.Mat(videoInput.height, videoInput.width, cv.CV_8UC4);
+let cap = new cv.VideoCapture(videoInput);
+
+main = async function(frame) {
+ const labels = await loadLables(labelsUrl);
+ const input = getBlobFromImage(inputSize, mean, std, swapRB, frame);
+ let net = cv.readNet(configPath, modelPath);
+ net.setInput(input);
+ const start = performance.now();
+ const result = net.forward();
+ const time = performance.now()-start;
+ const output = postProcess(result, labels, frame);
+
+ updateResult(output, time);
+ setTimeout(processVideo, 0);
+ input.delete();
+ net.delete();
+ result.delete();
+}
+
+function processVideo() {
+ try {
+ if (!streaming) {
+ return;
+ }
+ cap.read(frame);
+ main(frame);
+ } catch (err) {
+ utils.printError(err);
+ }
+}
+
+setTimeout(processVideo, 0);
+</script>
+
+<script id="codeSnippet5" type="text/code-snippet">
+postProcess = function(result, labels, frame) {
+ let canvasOutput = document.getElementById('canvasOutput');
+ const outputWidth = canvasOutput.width;
+ const outputHeight = canvasOutput.height;
+ const resultData = result.data32F;
+
+ // Get the boxes(with class and confidence) from the output
+ let boxes = [];
+ switch(outType) {
+ case "YOLO": {
+ const vecNum = result.matSize[0];
+ const vecLength = result.matSize[1];
+ const classNum = vecLength - 5;
+
+ for (let i = 0; i < vecNum; ++i) {
+ let vector = resultData.slice(i*vecLength, (i+1)*vecLength);
+ let scores = vector.slice(5, vecLength);
+ let classId = scores.indexOf(Math.max(...scores));
+ let confidence = scores[classId];
+ if (confidence > confThreshold) {
+ let center_x = Math.round(vector[0] * outputWidth);
+ let center_y = Math.round(vector[1] * outputHeight);
+ let width = Math.round(vector[2] * outputWidth);
+ let height = Math.round(vector[3] * outputHeight);
+ let left = Math.round(center_x - width / 2);
+ let top = Math.round(center_y - height / 2);
+
+ let box = {
+ scores: scores,
+ classId: classId,
+ confidence: confidence,
+ bounding: [left, top, width, height],
+ toDraw: true
+ }
+ boxes.push(box);
+ }
+ }
+
+ // NMS(Non Maximum Suppression) algorithm
+ let boxNum = boxes.length;
+ let tmp_boxes = [];
+ let sorted_boxes = [];
+ for (let c = 0; c < classNum; ++c) {
+ for (let i = 0; i < boxes.length; ++i) {
+ tmp_boxes[i] = [boxes[i], i];
+ }
+ sorted_boxes = tmp_boxes.sort((a, b) => { return (b[0].scores[c] - a[0].scores[c]); });
+ for (let i = 0; i < boxNum; ++i) {
+ if (sorted_boxes[i][0].scores[c] === 0) continue;
+ else {
+ for (let j = i + 1; j < boxNum; ++j) {
+ if (IOU(sorted_boxes[i][0], sorted_boxes[j][0]) >= nmsThreshold) {
+ boxes[sorted_boxes[j][1]].toDraw = false;
+ }
+ }
+ }
+ }
+ }
+ } break;
+ case "SSD": {
+ const vecNum = result.matSize[2];
+ const vecLength = 7;
+
+ for (let i = 0; i < vecNum; ++i) {
+ let vector = resultData.slice(i*vecLength, (i+1)*vecLength);
+ let confidence = vector[2];
+ if (confidence > confThreshold) {
+ let left, top, right, bottom, width, height;
+ left = Math.round(vector[3]);
+ top = Math.round(vector[4]);
+ right = Math.round(vector[5]);
+ bottom = Math.round(vector[6]);
+ width = right - left + 1;
+ height = bottom - top + 1;
+ if (width <= 2 || height <= 2) {
+ left = Math.round(vector[3] * outputWidth);
+ top = Math.round(vector[4] * outputHeight);
+ right = Math.round(vector[5] * outputWidth);
+ bottom = Math.round(vector[6] * outputHeight);
+ width = right - left + 1;
+ height = bottom - top + 1;
+ }
+ let box = {
+ classId: vector[1] - 1,
+ confidence: confidence,
+ bounding: [left, top, width, height],
+ toDraw: true
+ }
+ boxes.push(box);
+ }
+ }
+ } break;
+ default:
+ console.error(`Unsupported output type ${outType}`)
+ }
+
+ // Draw the saved box into the image
+ let output = new cv.Mat(outputWidth, outputHeight, cv.CV_8UC3);
+ cv.cvtColor(frame, output, cv.COLOR_RGBA2RGB);
+ let boxNum = boxes.length;
+ for (let i = 0; i < boxNum; ++i) {
+ if (boxes[i].toDraw) {
+ drawBox(boxes[i]);
+ }
+ }
+
+ return output;
+
+
+ // Calculate the IOU(Intersection over Union) of two boxes
+ function IOU(box1, box2) {
+ let bounding1 = box1.bounding;
+ let bounding2 = box2.bounding;
+ let s1 = bounding1[2] * bounding1[3];
+ let s2 = bounding2[2] * bounding2[3];
+
+ let left1 = bounding1[0];
+ let right1 = left1 + bounding1[2];
+ let left2 = bounding2[0];
+ let right2 = left2 + bounding2[2];
+ let overlapW = calOverlap([left1, right1], [left2, right2]);
+
+ let top1 = bounding2[1];
+ let bottom1 = top1 + bounding1[3];
+ let top2 = bounding2[1];
+ let bottom2 = top2 + bounding2[3];
+ let overlapH = calOverlap([top1, bottom1], [top2, bottom2]);
+
+ let overlapS = overlapW * overlapH;
+ return overlapS / (s1 + s2 + overlapS);
+ }
+
+ // Calculate the overlap range of two vector
+ function calOverlap(range1, range2) {
+ let min1 = range1[0];
+ let max1 = range1[1];
+ let min2 = range2[0];
+ let max2 = range2[1];
+
+ if (min2 > min1 && min2 < max1) {
+ return max1 - min2;
+ } else if (max2 > min1 && max2 < max1) {
+ return max2 - min1;
+ } else {
+ return 0;
+ }
+ }
+
+ // Draw one predict box into the origin image
+ function drawBox(box) {
+ let bounding = box.bounding;
+ let left = bounding[0];
+ let top = bounding[1];
+ let width = bounding[2];
+ let height = bounding[3];
+
+ cv.rectangle(output, new cv.Point(left, top), new cv.Point(left + width, top + height),
+ new cv.Scalar(0, 255, 0));
+ cv.rectangle(output, new cv.Point(left, top), new cv.Point(left + width, top + 15),
+ new cv.Scalar(255, 255, 255), cv.FILLED);
+ let text = `${labels[box.classId]}: ${box.confidence.toFixed(4)}`;
+ cv.putText(output, text, new cv.Point(left, top + 10), cv.FONT_HERSHEY_SIMPLEX, 0.3,
+ new cv.Scalar(0, 0, 0));
+ }
+}
+</script>
+
+<script type="text/javascript">
+ let jsonUrl = "js_object_detection_model_info.json";
+ drawInfoTable(jsonUrl, 'appendix');
+
+ let utils = new Utils('errorMessage');
+ utils.loadCode('codeSnippet', 'codeEditor');
+ utils.loadCode('codeSnippet1', 'codeEditor1');
+
+ let loadLablesCode = 'loadLables = ' + loadLables.toString();
+ document.getElementById('codeEditor2').value = loadLablesCode;
+ let getBlobFromImageCode = 'getBlobFromImage = ' + getBlobFromImage.toString();
+ document.getElementById('codeEditor3').value = getBlobFromImageCode;
+ let loadModelCode = 'loadModel = ' + loadModel.toString();
+ document.getElementById('codeEditor4').value = loadModelCode;
+
+ utils.loadCode('codeSnippet5', 'codeEditor5');
+
+ let videoInput = document.getElementById('videoInput');
+ let streaming = false;
+ let startAndStop = document.getElementById('startAndStop');
+ startAndStop.addEventListener('click', () => {
+ if (!streaming) {
+ utils.clearError();
+ utils.startCamera('qvga', onVideoStarted, 'videoInput');
+ } else {
+ utils.stopCamera();
+ onVideoStopped();
+ }
+ });
+
+ let configPath = "";
+ let configFile = document.getElementById('configFile');
+ configFile.addEventListener('change', async (e) => {
+ initStatus();
+ configPath = await loadModel(e);
+ document.getElementById('status').innerHTML = `The config file '${configPath}' is created successfully.`;
+ });
+
+ let modelPath = "";
+ let modelFile = document.getElementById('modelFile');
+ modelFile.addEventListener('change', async (e) => {
+ initStatus();
+ modelPath = await loadModel(e);
+ document.getElementById('status').innerHTML = `The model file '${modelPath}' is created successfully.`;
+ configPath = "";
+ configFile.value = "";
+ });
+
+ utils.loadOpenCv(() => {
+ startAndStop.removeAttribute('disabled');
+ });
+
+ var main = async function(frame) {};
+ var postProcess = function(result, labels, frame) {};
+
+ utils.executeCode('codeEditor1');
+ utils.executeCode('codeEditor2');
+ utils.executeCode('codeEditor3');
+ utils.executeCode('codeEditor4');
+ utils.executeCode('codeEditor5');
+
+ function onVideoStarted() {
+ streaming = true;
+ startAndStop.innerText = 'Stop';
+ videoInput.width = videoInput.videoWidth;
+ videoInput.height = videoInput.videoHeight;
+ utils.executeCode('codeEditor');
+ utils.executeCode('codeEditor1');
+ }
+
+ function onVideoStopped() {
+ streaming = false;
+ startAndStop.innerText = 'Start';
+ initStatus();
+ }
+
+ function updateResult(output, time) {
+ try{
+ let canvasOutput = document.getElementById('canvasOutput');
+ canvasOutput.style.visibility = "visible";
+ cv.imshow('canvasOutput', output);
+ document.getElementById('status').innerHTML = `<b>Model:</b> ${modelPath}<br>
+ <b>Inference time:</b> ${time.toFixed(2)} ms`;
+ } catch(e) {
+ console.log(e);
+ }
+ }
+
+ function initStatus() {
+ document.getElementById('status').innerHTML = '';
+ document.getElementById('canvasOutput').style.visibility = "hidden";
+ utils.clearError();
+ }
+
+</script>
+
+</body>
+
+</html>
\ No newline at end of file
--- /dev/null
+<!DOCTYPE html>
+<html>
+
+<head>
+ <meta charset="utf-8">
+ <title>Pose Estimation Example</title>
+ <link href="js_example_style.css" rel="stylesheet" type="text/css" />
+</head>
+
+<body>
+<h2>Pose Estimation Example</h2>
+<p>
+ This tutorial shows you how to write an pose estimation example with OpenCV.js.<br>
+ To try the example you should click the <b>modelFile</b> button(and <b>configInput</b> button if needed) to upload inference model.
+ You can find the model URLs and parameters in the <a href="#appendix">model info</a> section.
+ Then You should change the parameters in the first code snippet according to the uploaded model.
+ Finally click <b>Try it</b> button to see the result. You can choose any other images.<br>
+</p>
+
+<div class="control"><button id="tryIt" disabled>Try it</button></div>
+<div>
+ <table cellpadding="0" cellspacing="0" width="0" border="0">
+ <tr>
+ <td>
+ <canvas id="canvasInput" width="400" height="250"></canvas>
+ </td>
+ <td>
+ <canvas id="canvasOutput" style="visibility: hidden;" width="400" height="250"></canvas>
+ </td>
+ </tr>
+ <tr>
+ <td>
+ <div class="caption">
+ canvasInput <input type="file" id="fileInput" name="file" accept="image/*">
+ </div>
+ </td>
+ <td>
+ <p id='status' align="left"></p>
+ </td>
+ </tr>
+ <tr>
+ <td>
+ <div class="caption">
+ modelFile <input type="file" id="modelFile" name="file">
+ </div>
+ </td>
+ </tr>
+ <tr>
+ <td>
+ <div class="caption">
+ configFile <input type="file" id="configFile">
+ </div>
+ </td>
+ </tr>
+ </table>
+</div>
+
+<div>
+ <p class="err" id="errorMessage"></p>
+</div>
+
+<div>
+ <h3>Help function</h3>
+ <p>1.The parameters for model inference which you can modify to investigate more models.</p>
+ <textarea class="code" rows="9" cols="100" id="codeEditor" spellcheck="false"></textarea>
+ <p>2.Main loop in which will read the image from canvas and do inference once.</p>
+ <textarea class="code" rows="15" cols="100" id="codeEditor1" spellcheck="false"></textarea>
+ <p>3.Get blob from image as input for net, and standardize it with <b>mean</b> and <b>std</b>.</p>
+ <textarea class="code" rows="17" cols="100" id="codeEditor2" spellcheck="false"></textarea>
+ <p>4.Fetch model file and save to emscripten file system once click the input button.</p>
+ <textarea class="code" rows="17" cols="100" id="codeEditor3" spellcheck="false"></textarea>
+ <p>5.The pairs of keypoints of different dataset.</p>
+ <textarea class="code" rows="30" cols="100" id="codeEditor4" spellcheck="false"></textarea>
+ <p>6.The post-processing, including get the predicted points and draw lines into the image.</p>
+ <textarea class="code" rows="30" cols="100" id="codeEditor5" spellcheck="false"></textarea>
+</div>
+
+<div id="appendix">
+ <h2>Model Info:</h2>
+</div>
+
+<script src="utils.js" type="text/javascript"></script>
+<script src="js_dnn_example_helper.js" type="text/javascript"></script>
+
+<script id="codeSnippet" type="text/code-snippet">
+inputSize = [368, 368];
+mean = [0, 0, 0];
+std = 0.00392;
+swapRB = false;
+threshold = 0.1;
+
+// the pairs of keypoint, can be "COCO", "MPI" and "BODY_25"
+dataset = "COCO";
+</script>
+
+<script id="codeSnippet1" type="text/code-snippet">
+main = async function() {
+ const input = getBlobFromImage(inputSize, mean, std, swapRB, 'canvasInput');
+ let net = cv.readNet(configPath, modelPath);
+ net.setInput(input);
+ const start = performance.now();
+ const result = net.forward();
+ const time = performance.now()-start;
+ const output = postProcess(result);
+
+ updateResult(output, time);
+ input.delete();
+ net.delete();
+ result.delete();
+}
+</script>
+
+<script id="codeSnippet4" type="text/code-snippet">
+BODY_PARTS = {};
+POSE_PAIRS = [];
+
+if (dataset === 'COCO') {
+ BODY_PARTS = { "Nose": 0, "Neck": 1, "RShoulder": 2, "RElbow": 3, "RWrist": 4,
+ "LShoulder": 5, "LElbow": 6, "LWrist": 7, "RHip": 8, "RKnee": 9,
+ "RAnkle": 10, "LHip": 11, "LKnee": 12, "LAnkle": 13, "REye": 14,
+ "LEye": 15, "REar": 16, "LEar": 17, "Background": 18 };
+
+ POSE_PAIRS = [ ["Neck", "RShoulder"], ["Neck", "LShoulder"], ["RShoulder", "RElbow"],
+ ["RElbow", "RWrist"], ["LShoulder", "LElbow"], ["LElbow", "LWrist"],
+ ["Neck", "RHip"], ["RHip", "RKnee"], ["RKnee", "RAnkle"], ["Neck", "LHip"],
+ ["LHip", "LKnee"], ["LKnee", "LAnkle"], ["Neck", "Nose"], ["Nose", "REye"],
+ ["REye", "REar"], ["Nose", "LEye"], ["LEye", "LEar"] ]
+} else if (dataset === 'MPI') {
+ BODY_PARTS = { "Head": 0, "Neck": 1, "RShoulder": 2, "RElbow": 3, "RWrist": 4,
+ "LShoulder": 5, "LElbow": 6, "LWrist": 7, "RHip": 8, "RKnee": 9,
+ "RAnkle": 10, "LHip": 11, "LKnee": 12, "LAnkle": 13, "Chest": 14,
+ "Background": 15 }
+
+ POSE_PAIRS = [ ["Head", "Neck"], ["Neck", "RShoulder"], ["RShoulder", "RElbow"],
+ ["RElbow", "RWrist"], ["Neck", "LShoulder"], ["LShoulder", "LElbow"],
+ ["LElbow", "LWrist"], ["Neck", "Chest"], ["Chest", "RHip"], ["RHip", "RKnee"],
+ ["RKnee", "RAnkle"], ["Chest", "LHip"], ["LHip", "LKnee"], ["LKnee", "LAnkle"] ]
+} else if (dataset === 'BODY_25') {
+ BODY_PARTS = { "Nose": 0, "Neck": 1, "RShoulder": 2, "RElbow": 3, "RWrist": 4,
+ "LShoulder": 5, "LElbow": 6, "LWrist": 7, "MidHip": 8, "RHip": 9,
+ "RKnee": 10, "RAnkle": 11, "LHip": 12, "LKnee": 13, "LAnkle": 14,
+ "REye": 15, "LEye": 16, "REar": 17, "LEar": 18, "LBigToe": 19,
+ "LSmallToe": 20, "LHeel": 21, "RBigToe": 22, "RSmallToe": 23,
+ "RHeel": 24, "Background": 25 }
+
+ POSE_PAIRS = [ ["Neck", "Nose"], ["Neck", "RShoulder"],
+ ["Neck", "LShoulder"], ["RShoulder", "RElbow"],
+ ["RElbow", "RWrist"], ["LShoulder", "LElbow"],
+ ["LElbow", "LWrist"], ["Nose", "REye"],
+ ["REye", "REar"], ["Neck", "LEye"],
+ ["LEye", "LEar"], ["Neck", "MidHip"],
+ ["MidHip", "RHip"], ["RHip", "RKnee"],
+ ["RKnee", "RAnkle"], ["RAnkle", "RBigToe"],
+ ["RBigToe", "RSmallToe"], ["RAnkle", "RHeel"],
+ ["MidHip", "LHip"], ["LHip", "LKnee"],
+ ["LKnee", "LAnkle"], ["LAnkle", "LBigToe"],
+ ["LBigToe", "LSmallToe"], ["LAnkle", "LHeel"] ]
+}
+</script>
+
+<script id="codeSnippet5" type="text/code-snippet">
+postProcess = function(result) {
+ const resultData = result.data32F;
+ const matSize = result.matSize;
+ const size1 = matSize[1];
+ const size2 = matSize[2];
+ const size3 = matSize[3];
+ const mapSize = size2 * size3;
+
+ let canvasOutput = document.getElementById('canvasOutput');
+ const outputWidth = canvasOutput.width;
+ const outputHeight = canvasOutput.height;
+
+ let image = cv.imread("canvasInput");
+ let output = new cv.Mat(outputWidth, outputHeight, cv.CV_8UC3);
+ cv.cvtColor(image, output, cv.COLOR_RGBA2RGB);
+
+ // get position of keypoints from output
+ let points = [];
+ for (let i = 0; i < Object.keys(BODY_PARTS).length; ++i) {
+ heatMap = resultData.slice(i*mapSize, (i+1)*mapSize);
+
+ let maxIndex = 0;
+ let maxConf = heatMap[0];
+ for (index in heatMap) {
+ if (heatMap[index] > heatMap[maxIndex]) {
+ maxIndex = index;
+ maxConf = heatMap[index];
+ }
+ }
+
+ if (maxConf > threshold) {
+ indexX = maxIndex % size3;
+ indexY = maxIndex / size3;
+
+ x = outputWidth * indexX / size3;
+ y = outputHeight * indexY / size2;
+
+ points[i] = [Math.round(x), Math.round(y)];
+ }
+ }
+
+ // draw the points and lines into the image
+ for (pair of POSE_PAIRS) {
+ partFrom = pair[0];
+ partTo = pair[1];
+ idFrom = BODY_PARTS[partFrom];
+ idTo = BODY_PARTS[partTo];
+ pointFrom = points[idFrom];
+ pointTo = points[idTo];
+
+ if (points[idFrom] && points[idTo]) {
+ cv.line(output, new cv.Point(pointFrom[0], pointFrom[1]),
+ new cv.Point(pointTo[0], pointTo[1]), new cv.Scalar(0, 255, 0), 3);
+ cv.ellipse(output, new cv.Point(pointFrom[0], pointFrom[1]), new cv.Size(3, 3), 0, 0, 360,
+ new cv.Scalar(0, 0, 255), cv.FILLED);
+ cv.ellipse(output, new cv.Point(pointTo[0], pointTo[1]), new cv.Size(3, 3), 0, 0, 360,
+ new cv.Scalar(0, 0, 255), cv.FILLED);
+ }
+ }
+
+ return output;
+}
+</script>
+
+<script type="text/javascript">
+ let jsonUrl = "js_pose_estimation_model_info.json";
+ drawInfoTable(jsonUrl, 'appendix');
+
+ let utils = new Utils('errorMessage');
+ utils.loadCode('codeSnippet', 'codeEditor');
+ utils.loadCode('codeSnippet1', 'codeEditor1');
+
+ let getBlobFromImageCode = 'getBlobFromImage = ' + getBlobFromImage.toString();
+ document.getElementById('codeEditor2').value = getBlobFromImageCode;
+ let loadModelCode = 'loadModel = ' + loadModel.toString();
+ document.getElementById('codeEditor3').value = loadModelCode;
+
+ utils.loadCode('codeSnippet4', 'codeEditor4');
+ utils.loadCode('codeSnippet5', 'codeEditor5');
+
+ let canvas = document.getElementById('canvasInput');
+ let ctx = canvas.getContext('2d');
+ let img = new Image();
+ img.crossOrigin = 'anonymous';
+ img.src = 'roi.jpg';
+ img.onload = function() {
+ ctx.drawImage(img, 0, 0, canvas.width, canvas.height);
+ };
+
+ let tryIt = document.getElementById('tryIt');
+ tryIt.addEventListener('click', () => {
+ initStatus();
+ document.getElementById('status').innerHTML = 'Running function main()...';
+ utils.executeCode('codeEditor');
+ utils.executeCode('codeEditor1');
+ if (modelPath === "") {
+ document.getElementById('status').innerHTML = 'Runing failed.';
+ utils.printError('Please upload model file by clicking the button first.');
+ } else {
+ setTimeout(main, 1);
+ }
+ });
+
+ let fileInput = document.getElementById('fileInput');
+ fileInput.addEventListener('change', (e) => {
+ initStatus();
+ loadImageToCanvas(e, 'canvasInput');
+ });
+
+ let configPath = "";
+ let configFile = document.getElementById('configFile');
+ configFile.addEventListener('change', async (e) => {
+ initStatus();
+ configPath = await loadModel(e);
+ document.getElementById('status').innerHTML = `The config file '${configPath}' is created successfully.`;
+ });
+
+ let modelPath = "";
+ let modelFile = document.getElementById('modelFile');
+ modelFile.addEventListener('change', async (e) => {
+ initStatus();
+ modelPath = await loadModel(e);
+ document.getElementById('status').innerHTML = `The model file '${modelPath}' is created successfully.`;
+ configPath = "";
+ configFile.value = "";
+ });
+
+ utils.loadOpenCv(() => {
+ tryIt.removeAttribute('disabled');
+ });
+
+ var main = async function() {};
+ var postProcess = function(result) {};
+
+ utils.executeCode('codeEditor');
+ utils.executeCode('codeEditor1');
+ utils.executeCode('codeEditor2');
+ utils.executeCode('codeEditor3');
+ utils.executeCode('codeEditor4');
+ utils.executeCode('codeEditor5');
+
+ function updateResult(output, time) {
+ try{
+ let canvasOutput = document.getElementById('canvasOutput');
+ canvasOutput.style.visibility = "visible";
+ let resized = new cv.Mat(canvasOutput.width, canvasOutput.height, cv.CV_8UC4);
+ cv.resize(output, resized, new cv.Size(canvasOutput.width, canvasOutput.height));
+ cv.imshow('canvasOutput', resized);
+ document.getElementById('status').innerHTML = `<b>Model:</b> ${modelPath}<br>
+ <b>Inference time:</b> ${time.toFixed(2)} ms`;
+ } catch(e) {
+ console.log(e);
+ }
+ }
+
+ function initStatus() {
+ document.getElementById('status').innerHTML = '';
+ document.getElementById('canvasOutput').style.visibility = "hidden";
+ utils.clearError();
+ }
+
+</script>
+
+</body>
+
+</html>
\ No newline at end of file
--- /dev/null
+{
+ "caffe": [
+ {
+ "model": "body_25",
+ "inputSize": "368, 368",
+ "mean": "0, 0, 0",
+ "std": "0.00392",
+ "swapRB": "false",
+ "dataset": "BODY_25",
+ "modelUrl": "http://posefs1.perception.cs.cmu.edu/OpenPose/models/pose/body_25/pose_iter_584000.caffemodel",
+ "configUrl": "https://raw.githubusercontent.com/CMU-Perceptual-Computing-Lab/openpose/master/models/pose/body_25/pose_deploy.prototxt"
+ },
+ {
+ "model": "coco",
+ "inputSize": "368, 368",
+ "mean": "0, 0, 0",
+ "std": "0.00392",
+ "swapRB": "false",
+ "dataset": "COCO",
+ "modelUrl": "http://posefs1.perception.cs.cmu.edu/OpenPose/models/pose/coco/pose_iter_440000.caffemodel",
+ "configUrl": "https://raw.githubusercontent.com/CMU-Perceptual-Computing-Lab/openpose/master/models/pose/coco/pose_deploy_linevec.prototxt"
+ },
+ {
+ "model": "mpi",
+ "inputSize": "368, 368",
+ "mean": "0, 0, 0",
+ "std": "0.00392",
+ "swapRB": "false",
+ "dataset": "MPI",
+ "modelUrl": "http://posefs1.perception.cs.cmu.edu/OpenPose/models/pose/mpi/pose_iter_160000.caffemodel",
+ "configUrl": "https://raw.githubusercontent.com/CMU-Perceptual-Computing-Lab/openpose/master/models/pose/mpi/pose_deploy_linevec.prototxt"
+ }
+ ]
+}
\ No newline at end of file
--- /dev/null
+<!DOCTYPE html>
+<html>
+
+<head>
+ <meta charset="utf-8">
+ <title>Semantic Segmentation Example</title>
+ <link href="js_example_style.css" rel="stylesheet" type="text/css" />
+</head>
+
+<body>
+<h2>Semantic Segmentation Example</h2>
+<p>
+ This tutorial shows you how to write an semantic segmentation example with OpenCV.js.<br>
+ To try the example you should click the <b>modelFile</b> button(and <b>configInput</b> button if needed) to upload inference model.
+ You can find the model URLs and parameters in the <a href="#appendix">model info</a> section.
+ Then You should change the parameters in the first code snippet according to the uploaded model.
+ Finally click <b>Try it</b> button to see the result. You can choose any other images.<br>
+</p>
+
+<div class="control"><button id="tryIt" disabled>Try it</button></div>
+<div>
+ <table cellpadding="0" cellspacing="0" width="0" border="0">
+ <tr>
+ <td>
+ <canvas id="canvasInput" width="400" height="400"></canvas>
+ </td>
+ <td>
+ <canvas id="canvasOutput" style="visibility: hidden;" width="400" height="400"></canvas>
+ </td>
+ </tr>
+ <tr>
+ <td>
+ <div class="caption">
+ canvasInput <input type="file" id="fileInput" name="file" accept="image/*">
+ </div>
+ </td>
+ <td>
+ <p id='status' align="left"></p>
+ </td>
+ </tr>
+ <tr>
+ <td>
+ <div class="caption">
+ modelFile <input type="file" id="modelFile" name="file">
+ </div>
+ </td>
+ </tr>
+ <tr>
+ <td>
+ <div class="caption">
+ configFile <input type="file" id="configFile">
+ </div>
+ </td>
+ </tr>
+ </table>
+</div>
+
+<div>
+ <p class="err" id="errorMessage"></p>
+</div>
+
+<div>
+ <h3>Help function</h3>
+ <p>1.The parameters for model inference which you can modify to investigate more models.</p>
+ <textarea class="code" rows="5" cols="100" id="codeEditor" spellcheck="false"></textarea>
+ <p>2.Main loop in which will read the image from canvas and do inference once.</p>
+ <textarea class="code" rows="16" cols="100" id="codeEditor1" spellcheck="false"></textarea>
+ <p>3.Get blob from image as input for net, and standardize it with <b>mean</b> and <b>std</b>.</p>
+ <textarea class="code" rows="17" cols="100" id="codeEditor2" spellcheck="false"></textarea>
+ <p>4.Fetch model file and save to emscripten file system once click the input button.</p>
+ <textarea class="code" rows="17" cols="100" id="codeEditor3" spellcheck="false"></textarea>
+ <p>5.The post-processing, including gengerate colors for different classes and argmax to get the classes for each pixel.</p>
+ <textarea class="code" rows="34" cols="100" id="codeEditor4" spellcheck="false"></textarea>
+</div>
+
+<div id="appendix">
+ <h2>Model Info:</h2>
+</div>
+
+<script src="utils.js" type="text/javascript"></script>
+<script src="js_dnn_example_helper.js" type="text/javascript"></script>
+
+<script id="codeSnippet" type="text/code-snippet">
+inputSize = [513, 513];
+mean = [127.5, 127.5, 127.5];
+std = 0.007843;
+swapRB = false;
+</script>
+
+<script id="codeSnippet1" type="text/code-snippet">
+main = async function() {
+ const input = getBlobFromImage(inputSize, mean, std, swapRB, 'canvasInput');
+ let net = cv.readNet(configPath, modelPath);
+ net.setInput(input);
+ const start = performance.now();
+ const result = net.forward();
+ const time = performance.now()-start;
+ const colors = generateColors(result);
+ const output = argmax(result, colors);
+
+ updateResult(output, time);
+ input.delete();
+ net.delete();
+ result.delete();
+}
+</script>
+
+<script id="codeSnippet4" type="text/code-snippet">
+generateColors = function(result) {
+ const numClasses = result.matSize[1];
+ let colors = [0,0,0];
+ while(colors.length < numClasses*3){
+ colors.push(Math.round((Math.random()*255 + colors[colors.length-3]) / 2));
+ }
+ return colors;
+}
+
+argmax = function(result, colors) {
+ const C = result.matSize[1];
+ const H = result.matSize[2];
+ const W = result.matSize[3];
+ const resultData = result.data32F;
+ const imgSize = H*W;
+
+ let classId = [];
+ for (i = 0; i<imgSize; ++i) {
+ let id = 0;
+ for (j = 0; j < C; ++j) {
+ if (resultData[j*imgSize+i] > resultData[id*imgSize+i]) {
+ id = j;
+ }
+ }
+ classId.push(colors[id*3]);
+ classId.push(colors[id*3+1]);
+ classId.push(colors[id*3+2]);
+ classId.push(255);
+ }
+
+ output = cv.matFromArray(H,W,cv.CV_8UC4,classId);
+ return output;
+}
+</script>
+
+<script type="text/javascript">
+ let jsonUrl = "js_semantic_segmentation_model_info.json";
+ drawInfoTable(jsonUrl, 'appendix');
+
+ let utils = new Utils('errorMessage');
+ utils.loadCode('codeSnippet', 'codeEditor');
+ utils.loadCode('codeSnippet1', 'codeEditor1');
+
+ let getBlobFromImageCode = 'getBlobFromImage = ' + getBlobFromImage.toString();
+ document.getElementById('codeEditor2').value = getBlobFromImageCode;
+ let loadModelCode = 'loadModel = ' + loadModel.toString();
+ document.getElementById('codeEditor3').value = loadModelCode;
+
+ utils.loadCode('codeSnippet4', 'codeEditor4');
+
+ let canvas = document.getElementById('canvasInput');
+ let ctx = canvas.getContext('2d');
+ let img = new Image();
+ img.crossOrigin = 'anonymous';
+ img.src = 'roi.jpg';
+ img.onload = function() {
+ ctx.drawImage(img, 0, 0, canvas.width, canvas.height);
+ };
+
+ let tryIt = document.getElementById('tryIt');
+ tryIt.addEventListener('click', () => {
+ initStatus();
+ document.getElementById('status').innerHTML = 'Running function main()...';
+ utils.executeCode('codeEditor');
+ utils.executeCode('codeEditor1');
+ if (modelPath === "") {
+ document.getElementById('status').innerHTML = 'Runing failed.';
+ utils.printError('Please upload model file by clicking the button first.');
+ } else {
+ setTimeout(main, 1);
+ }
+ });
+
+ let fileInput = document.getElementById('fileInput');
+ fileInput.addEventListener('change', (e) => {
+ initStatus();
+ loadImageToCanvas(e, 'canvasInput');
+ });
+
+ let configPath = "";
+ let configFile = document.getElementById('configFile');
+ configFile.addEventListener('change', async (e) => {
+ initStatus();
+ configPath = await loadModel(e);
+ document.getElementById('status').innerHTML = `The config file '${configPath}' is created successfully.`;
+ });
+
+ let modelPath = "";
+ let modelFile = document.getElementById('modelFile');
+ modelFile.addEventListener('change', async (e) => {
+ initStatus();
+ modelPath = await loadModel(e);
+ document.getElementById('status').innerHTML = `The model file '${modelPath}' is created successfully.`;
+ configPath = "";
+ configFile.value = "";
+ });
+
+ utils.loadOpenCv(() => {
+ tryIt.removeAttribute('disabled');
+ });
+
+ var main = async function() {};
+ var generateColors = function(result) {};
+ var argmax = function(result, colors) {};
+
+ utils.executeCode('codeEditor1');
+ utils.executeCode('codeEditor2');
+ utils.executeCode('codeEditor3');
+ utils.executeCode('codeEditor4');
+
+ function updateResult(output, time) {
+ try{
+ let canvasOutput = document.getElementById('canvasOutput');
+ canvasOutput.style.visibility = "visible";
+ let resized = new cv.Mat(canvasOutput.width, canvasOutput.height, cv.CV_8UC4);
+ cv.resize(output, resized, new cv.Size(canvasOutput.width, canvasOutput.height));
+ cv.imshow('canvasOutput', resized);
+ document.getElementById('status').innerHTML = `<b>Model:</b> ${modelPath}<br>
+ <b>Inference time:</b> ${time.toFixed(2)} ms`;
+ } catch(e) {
+ console.log(e);
+ }
+ }
+
+ function initStatus() {
+ document.getElementById('status').innerHTML = '';
+ document.getElementById('canvasOutput').style.visibility = "hidden";
+ utils.clearError();
+ }
+
+</script>
+
+</body>
+
+</html>
\ No newline at end of file
--- /dev/null
+{
+ "tensorflow": [
+ {
+ "model": "deeplabv3",
+ "inputSize": "513, 513",
+ "mean": "127.5, 127.5, 127.5",
+ "std": "0.007843",
+ "swapRB": "false",
+ "modelUrl": "https://drive.google.com/uc?id=1v-hfGenaE9tiGOzo5qdgMNG_gqQ5-Xn4&export=download"
+ }
+ ]
+}
\ No newline at end of file
--- /dev/null
+<!DOCTYPE html>
+<html>
+
+<head>
+ <meta charset="utf-8">
+ <title>Style Transfer Example</title>
+ <link href="js_example_style.css" rel="stylesheet" type="text/css" />
+</head>
+
+<body>
+<h2>Style Transfer Example</h2>
+<p>
+ This tutorial shows you how to write an style transfer example with OpenCV.js.<br>
+ To try the example you should click the <b>modelFile</b> button(and <b>configFile</b> button if needed) to upload inference model.
+ You can find the model URLs and parameters in the <a href="#appendix">model info</a> section.
+ Then You should change the parameters in the first code snippet according to the uploaded model.
+ Finally click <b>Try it</b> button to see the result. You can choose any other images.<br>
+</p>
+
+<div class="control"><button id="tryIt" disabled>Try it</button></div>
+<div>
+ <table cellpadding="0" cellspacing="0" width="0" border="0">
+ <tr>
+ <td>
+ <canvas id="canvasInput" width="400" height="400"></canvas>
+ </td>
+ <td>
+ <canvas id="canvasOutput" style="visibility: hidden;" width="400" height="400"></canvas>
+ </td>
+ </tr>
+ <tr>
+ <td>
+ <div class="caption">
+ canvasInput <input type="file" id="fileInput" name="file" accept="image/*">
+ </div>
+ </td>
+ <td>
+ <p id='status' align="left"></p>
+ </td>
+ </tr>
+ <tr>
+ <td>
+ <div class="caption">
+ modelFile <input type="file" id="modelFile" name="file">
+ </div>
+ </td>
+ </tr>
+ <tr>
+ <td>
+ <div class="caption">
+ configFile <input type="file" id="configFile">
+ </div>
+ </td>
+ </tr>
+ </table>
+</div>
+
+<div>
+ <p class="err" id="errorMessage"></p>
+</div>
+
+<div>
+ <h3>Help function</h3>
+ <p>1.The parameters for model inference which you can modify to investigate more models.</p>
+ <textarea class="code" rows="5" cols="100" id="codeEditor" spellcheck="false"></textarea>
+ <p>2.Main loop in which will read the image from canvas and do inference once.</p>
+ <textarea class="code" rows="15" cols="100" id="codeEditor1" spellcheck="false"></textarea>
+ <p>3.Get blob from image as input for net, and standardize it with <b>mean</b> and <b>std</b>.</p>
+ <textarea class="code" rows="17" cols="100" id="codeEditor2" spellcheck="false"></textarea>
+ <p>4.Fetch model file and save to emscripten file system once click the input button.</p>
+ <textarea class="code" rows="17" cols="100" id="codeEditor3" spellcheck="false"></textarea>
+ <p>5.The post-processing, including scaling and reordering.</p>
+ <textarea class="code" rows="21" cols="100" id="codeEditor4" spellcheck="false"></textarea>
+</div>
+
+<div id="appendix">
+ <h2>Model Info:</h2>
+</div>
+
+<script src="utils.js" type="text/javascript"></script>
+<script src="js_dnn_example_helper.js" type="text/javascript"></script>
+
+<script id="codeSnippet" type="text/code-snippet">
+inputSize = [224, 224];
+mean = [104, 117, 123];
+std = 1;
+swapRB = false;
+</script>
+
+<script id="codeSnippet1" type="text/code-snippet">
+main = async function() {
+ const input = getBlobFromImage(inputSize, mean, std, swapRB, 'canvasInput');
+ let net = cv.readNet(configPath, modelPath);
+ net.setInput(input);
+ const start = performance.now();
+ const result = net.forward();
+ const time = performance.now()-start;
+ const output = postProcess(result);
+
+ updateResult(output, time);
+ input.delete();
+ net.delete();
+ result.delete();
+}
+</script>
+
+<script id="codeSnippet4" type="text/code-snippet">
+postProcess = function(result) {
+ const resultData = result.data32F;
+ const C = result.matSize[1];
+ const H = result.matSize[2];
+ const W = result.matSize[3];
+ const mean = [104, 117, 123];
+
+ let normData = [];
+ for (let h = 0; h < H; ++h) {
+ for (let w = 0; w < W; ++w) {
+ for (let c = 0; c < C; ++c) {
+ normData.push(resultData[c*H*W + h*W + w] + mean[c]);
+ }
+ normData.push(255);
+ }
+ }
+
+ let output = new cv.matFromArray(H, W, cv.CV_8UC4, normData);
+ return output;
+}
+</script>
+
+<script type="text/javascript">
+ let jsonUrl = "js_style_transfer_model_info.json";
+ drawInfoTable(jsonUrl, 'appendix');
+
+ let utils = new Utils('errorMessage');
+ utils.loadCode('codeSnippet', 'codeEditor');
+ utils.loadCode('codeSnippet1', 'codeEditor1');
+
+ let getBlobFromImageCode = 'getBlobFromImage = ' + getBlobFromImage.toString();
+ document.getElementById('codeEditor2').value = getBlobFromImageCode;
+ let loadModelCode = 'loadModel = ' + loadModel.toString();
+ document.getElementById('codeEditor3').value = loadModelCode;
+
+ utils.loadCode('codeSnippet4', 'codeEditor4');
+
+ let canvas = document.getElementById('canvasInput');
+ let ctx = canvas.getContext('2d');
+ let img = new Image();
+ img.crossOrigin = 'anonymous';
+ img.src = 'lena.png';
+ img.onload = function() {
+ ctx.drawImage(img, 0, 0, canvas.width, canvas.height);
+ };
+
+ let tryIt = document.getElementById('tryIt');
+ tryIt.addEventListener('click', () => {
+ initStatus();
+ document.getElementById('status').innerHTML = 'Running function main()...';
+ utils.executeCode('codeEditor');
+ utils.executeCode('codeEditor1');
+ if (modelPath === "") {
+ document.getElementById('status').innerHTML = 'Runing failed.';
+ utils.printError('Please upload model file by clicking the button first.');
+ } else {
+ setTimeout(main, 1);
+ }
+ });
+
+ let fileInput = document.getElementById('fileInput');
+ fileInput.addEventListener('change', (e) => {
+ initStatus();
+ loadImageToCanvas(e, 'canvasInput');
+ });
+
+ let configPath = "";
+ let configFile = document.getElementById('configFile');
+ configFile.addEventListener('change', async (e) => {
+ initStatus();
+ configPath = await loadModel(e);
+ document.getElementById('status').innerHTML = `The config file '${configPath}' is created successfully.`;
+ });
+
+ let modelPath = "";
+ let modelFile = document.getElementById('modelFile');
+ modelFile.addEventListener('change', async (e) => {
+ initStatus();
+ modelPath = await loadModel(e);
+ document.getElementById('status').innerHTML = `The model file '${modelPath}' is created successfully.`;
+ configPath = "";
+ configFile.value = "";
+ });
+
+ utils.loadOpenCv(() => {
+ tryIt.removeAttribute('disabled');
+ });
+
+ var main = async function() {};
+ var postProcess = function(result) {};
+
+ utils.executeCode('codeEditor1');
+ utils.executeCode('codeEditor2');
+ utils.executeCode('codeEditor3');
+ utils.executeCode('codeEditor4');
+
+ function updateResult(output, time) {
+ try{
+ let canvasOutput = document.getElementById('canvasOutput');
+ canvasOutput.style.visibility = "visible";
+ let resized = new cv.Mat(canvasOutput.width, canvasOutput.height, cv.CV_8UC4);
+ cv.resize(output, resized, new cv.Size(canvasOutput.width, canvasOutput.height));
+ cv.imshow('canvasOutput', resized);
+ document.getElementById('status').innerHTML = `<b>Model:</b> ${modelPath}<br>
+ <b>Inference time:</b> ${time.toFixed(2)} ms`;
+ } catch(e) {
+ console.log(e);
+ }
+ }
+
+ function initStatus() {
+ document.getElementById('status').innerHTML = '';
+ document.getElementById('canvasOutput').style.visibility = "hidden";
+ utils.clearError();
+ }
+
+</script>
+
+</body>
+
+</html>
\ No newline at end of file
--- /dev/null
+{
+ "torch": [
+ {
+ "model": "candy.t7",
+ "inputSize": "224, 224",
+ "mean": "104, 117, 123",
+ "std": "1",
+ "swapRB": "false",
+ "modelUrl": "https://cs.stanford.edu/people/jcjohns/fast-neural-style/models//instance_norm/candy.t7"
+ },
+ {
+ "model": "composition_vii.t7",
+ "inputSize": "224, 224",
+ "mean": "104, 117, 123",
+ "std": "1",
+ "swapRB": "false",
+ "modelUrl": "https://cs.stanford.edu/people/jcjohns/fast-neural-style/models//eccv16/composition_vii.t7"
+ },
+ {
+ "model": "feathers.t7",
+ "inputSize": "224, 224",
+ "mean": "104, 117, 123",
+ "std": "1",
+ "swapRB": "false",
+ "modelUrl": "https://cs.stanford.edu/people/jcjohns/fast-neural-style/models//instance_norm/feathers.t7"
+ },
+ {
+ "model": "la_muse.t7",
+ "inputSize": "224, 224",
+ "mean": "104, 117, 123",
+ "std": "1",
+ "swapRB": "false",
+ "modelUrl": "https://cs.stanford.edu/people/jcjohns/fast-neural-style/models//instance_norm/la_muse.t7"
+ },
+ {
+ "model": "mosaic.t7",
+ "inputSize": "224, 224",
+ "mean": "104, 117, 123",
+ "std": "1",
+ "swapRB": "false",
+ "modelUrl": "https://cs.stanford.edu/people/jcjohns/fast-neural-style/models//instance_norm/mosaic.t7"
+ },
+ {
+ "model": "starry_night.t7",
+ "inputSize": "224, 224",
+ "mean": "104, 117, 123",
+ "std": "1",
+ "swapRB": "false",
+ "modelUrl": "https://cs.stanford.edu/people/jcjohns/fast-neural-style/models//eccv16/starry_night.t7"
+ },
+ {
+ "model": "the_scream.t7",
+ "inputSize": "224, 224",
+ "mean": "104, 117, 123",
+ "std": "1",
+ "swapRB": "false",
+ "modelUrl": "https://cs.stanford.edu/people/jcjohns/fast-neural-style/models//instance_norm/the_scream.t7"
+ },
+ {
+ "model": "the_wave.t7",
+ "inputSize": "224, 224",
+ "mean": "104, 117, 123",
+ "std": "1",
+ "swapRB": "false",
+ "modelUrl": "https://cs.stanford.edu/people/jcjohns/fast-neural-style/models//eccv16/the_wave.t7"
+ },
+ {
+ "model": "udnie.t7",
+ "inputSize": "224, 224",
+ "mean": "104, 117, 123",
+ "std": "1",
+ "swapRB": "false",
+ "modelUrl": "https://cs.stanford.edu/people/jcjohns/fast-neural-style/models//instance_norm/udnie.t7"
+ }
+ ]
+}
\ No newline at end of file
let script = document.createElement('script');
script.setAttribute('async', '');
script.setAttribute('type', 'text/javascript');
- script.addEventListener('load', () => {
+ script.addEventListener('load', async () => {
if (cv.getBuildInformation)
{
console.log(cv.getBuildInformation());
else
{
// WASM
- cv['onRuntimeInitialized']=()=>{
+ if (cv instanceof Promise) {
+ cv = await cv;
console.log(cv.getBuildInformation());
onloadCallback();
+ } else {
+ cv['onRuntimeInitialized']=()=>{
+ console.log(cv.getBuildInformation());
+ onloadCallback();
+ }
}
}
});
--- /dev/null
+Image Classification Example {#tutorial_js_image_classification}
+=======================================
+
+Goal
+----
+
+- In this tutorial you will learn how to use OpenCV.js dnn module for image classification.
+
+\htmlonly
+<iframe src="../../js_image_classification.html" width="100%"
+ onload="this.style.height=this.contentDocument.body.scrollHeight +'px';">
+</iframe>
+\endhtmlonly
\ No newline at end of file
--- /dev/null
+Image Classification Example with Camera {#tutorial_js_image_classification_with_camera}
+=======================================
+
+Goal
+----
+
+- In this tutorial you will learn how to use OpenCV.js dnn module for image classification example with camera.
+
+@note If you don't know how to capture video from camera, please review @ref tutorial_js_video_display.
+
+\htmlonly
+<iframe src="../../js_image_classification_with_camera.html" width="100%"
+ onload="this.style.height=this.contentDocument.body.scrollHeight +'px';">
+</iframe>
+\endhtmlonly
\ No newline at end of file
--- /dev/null
+Object Detection Example {#tutorial_js_object_detection}
+=======================================
+
+Goal
+----
+
+- In this tutorial you will learn how to use OpenCV.js dnn module for object detection.
+
+\htmlonly
+<iframe src="../../js_object_detection.html" width="100%"
+ onload="this.style.height=this.contentDocument.body.scrollHeight +'px';">
+</iframe>
+\endhtmlonly
\ No newline at end of file
--- /dev/null
+Object Detection Example with Camera{#tutorial_js_object_detection_with_camera}
+=======================================
+
+Goal
+----
+
+- In this tutorial you will learn how to use OpenCV.js dnn module for object detection with camera.
+
+\htmlonly
+<iframe src="../../js_object_detection_with_camera.html" width="100%"
+ onload="this.style.height=this.contentDocument.body.scrollHeight +'px';">
+</iframe>
+\endhtmlonly
\ No newline at end of file
--- /dev/null
+Pose Estimation Example {#tutorial_js_pose_estimation}
+=======================================
+
+Goal
+----
+
+- In this tutorial you will learn how to use OpenCV.js dnn module for pose estimation.
+
+\htmlonly
+<iframe src="../../js_pose_estimation.html" width="100%"
+ onload="this.style.height=this.contentDocument.body.scrollHeight +'px';">
+</iframe>
+\endhtmlonly
\ No newline at end of file
--- /dev/null
+Semantic Segmentation Example {#tutorial_js_semantic_segmentation}
+=======================================
+
+Goal
+----
+
+- In this tutorial you will learn how to use OpenCV.js dnn module for semantic segmentation.
+
+\htmlonly
+<iframe src="../../js_semantic_segmentation.html" width="100%"
+ onload="this.style.height=this.contentDocument.body.scrollHeight +'px';">
+</iframe>
+\endhtmlonly
\ No newline at end of file
--- /dev/null
+Style Transfer Example {#tutorial_js_style_transfer}
+=======================================
+
+Goal
+----
+
+- In this tutorial you will learn how to use OpenCV.js dnn module for style transfer.
+
+\htmlonly
+<iframe src="../../js_style_transfer.html" width="100%"
+ onload="this.style.height=this.contentDocument.body.scrollHeight +'px';">
+</iframe>
+\endhtmlonly
\ No newline at end of file
--- /dev/null
+Deep Neural Networks (dnn module) {#tutorial_js_table_of_contents_dnn}
+============
+
+- @subpage tutorial_js_image_classification
+
+ Image classification example
+
+- @subpage tutorial_js_image_classification_with_camera
+
+ Image classification example with camera
+
+- @subpage tutorial_js_object_detection
+
+ Object detection example
+
+- @subpage tutorial_js_object_detection_with_camera
+
+ Object detection example with camera
+
+- @subpage tutorial_js_semantic_segmentation
+
+ Semantic segmentation example
+
+- @subpage tutorial_js_style_transfer
+
+ Style transfer example
+
+- @subpage tutorial_js_pose_estimation
+
+ Pose estimation example
In this section you
will object detection techniques like face detection etc.
+
+- @subpage tutorial_js_table_of_contents_dnn
+
+ These tutorials show how to use dnn module in JavaScript