luoyc
/
OpenCV


			
				
					
						
						
							123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324325326327
							<!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>