added error handling

pull/50/head
Vladimir Mandic 2020-10-16 10:12:12 -04:00
parent 4f160ba86f
commit 5a1b34eaad
18 changed files with 1280 additions and 1111 deletions

View File

@ -7,6 +7,7 @@ const ui = {
baseLabel: 'rgba(255, 200, 255, 0.8)',
baseFont: 'small-caps 1.2rem "Segoe UI"',
baseLineWidth: 16,
busy: false,
};
const config = {
@ -16,13 +17,13 @@ const config = {
enabled: true,
detector: { maxFaces: 10, skipFrames: 10, minConfidence: 0.5, iouThreshold: 0.3, scoreThreshold: 0.7 },
mesh: { enabled: true },
iris: { enabled: true },
iris: { enabled: false },
age: { enabled: true, skipFrames: 10 },
gender: { enabled: true },
emotion: { enabled: true, minConfidence: 0.5, useGrayscale: true },
},
body: { enabled: true, maxDetections: 10, scoreThreshold: 0.7, nmsRadius: 20 },
hand: { enabled: true, skipFrames: 10, minConfidence: 0.5, iouThreshold: 0.3, scoreThreshold: 0.7 },
body: { enabled: false, maxDetections: 10, scoreThreshold: 0.7, nmsRadius: 20 },
hand: { enabled: false, skipFrames: 10, minConfidence: 0.5, iouThreshold: 0.3, scoreThreshold: 0.7 },
};
let settings;
let worker;
@ -245,10 +246,16 @@ function webWorker(input, image, canvas) {
}
async function runHumanDetect(input, canvas) {
const live = input.srcObject ? ((input.srcObject.getVideoTracks()[0].readyState === 'live') && (input.readyState > 2) && (!input.paused)) : false;
timeStamp = performance.now();
// perform detect if live video or not video at all
if (live || !(input instanceof HTMLVideoElement)) {
if (input.srcObject) {
// if video not ready, just redo
const live = (input.srcObject.getVideoTracks()[0].readyState === 'live') && (input.readyState > 2) && (!input.paused);
if (!live) {
if (!input.paused) log(`Video not ready: state: ${input.srcObject.getVideoTracks()[0].readyState} stream state: ${input.readyState}`);
setTimeout(() => runHumanDetect(input, canvas), 500);
return;
}
if (settings.getValue('Use Web Worker')) {
// get image data from video as we cannot send html objects to webworker
const offscreen = new OffscreenCanvas(canvas.width, canvas.height);
@ -265,7 +272,8 @@ async function runHumanDetect(input, canvas) {
} catch (err) {
log('Error during execution:', err.message);
}
drawResults(input, result, canvas);
if (result.error) log(result.error);
else drawResults(input, result, canvas);
}
}
}
@ -333,7 +341,7 @@ function setupUI() {
config.hand.iouThreshold = parseFloat(val);
});
settings.addHTML('title', 'UI Options'); settings.hideTitle('title');
settings.addBoolean('Use Web Worker', true);
settings.addBoolean('Use Web Worker', false);
settings.addBoolean('Draw Boxes', true);
settings.addBoolean('Draw Points', true);
settings.addBoolean('Draw Polygons', true);
@ -342,21 +350,20 @@ function setupUI() {
settings.addRange('FPS', 0, 100, 0, 1);
}
async function setupCanvas(input) {
// setup canvas object to same size as input as camera resolution may change
const canvas = document.getElementById('canvas');
canvas.width = input.width;
canvas.height = input.height;
return canvas;
}
// eslint-disable-next-line no-unused-vars
async function setupCamera() {
log('Setting up camera');
// setup webcam. note that navigator.mediaDevices requires that page is accessed via https
if (ui.busy) return null;
ui.busy = true;
const video = document.getElementById('video');
const canvas = document.getElementById('canvas');
const output = document.getElementById('log');
const live = video.srcObject ? ((video.srcObject.getVideoTracks()[0].readyState === 'live') && (video.readyState > 2) && (!video.paused)) : false;
log('Setting up camera: live:', live);
// setup webcam. note that navigator.mediaDevices requires that page is accessed via https
if (!navigator.mediaDevices) {
document.getElementById('log').innerText = 'Video not supported';
const msg = 'Camera access not supported';
output.innerText = msg;
log(msg);
return null;
}
const stream = await navigator.mediaDevices.getUserMedia({
@ -365,11 +372,15 @@ async function setupCamera() {
});
video.srcObject = stream;
return new Promise((resolve) => {
video.onloadedmetadata = () => {
video.onloadeddata = async () => {
video.width = video.videoWidth;
video.height = video.videoHeight;
video.play();
video.pause();
canvas.width = video.videoWidth;
canvas.height = video.videoHeight;
if (live) video.play();
ui.busy = false;
// do once more because onresize events can be delayed or skipped
if (video.width !== window.innerWidth) await setupCamera();
resolve(video);
};
});
@ -387,16 +398,15 @@ async function setupImage() {
}
async function main() {
log('Human starting ...');
log('Human demo starting ...');
// setup ui control panel
await setupUI();
// setup webcam
const input = await setupCamera();
await setupCamera();
// or setup image
// const input = await setupImage();
// setup output canvas from input object
await setupCanvas(input);
const msg = `Human ready: version: ${human.version} TensorFlow/JS version: ${human.tf.version_core}`;
document.getElementById('log').innerText = msg;
@ -407,4 +417,4 @@ async function main() {
}
window.onload = main;
window.onresize = main;
window.onresize = setupCamera;

View File

@ -1,7 +1,6 @@
<head>
<script src="https://cdn.jsdelivr.net/npm/quicksettings@latest/quicksettings.min.js"></script>
<script src="../dist/human.js"></script>
<script src="./demo-iife.js"></script>
</head>
<body style="margin: 0; background: black; color: white; font-family: 'Segoe UI'">
<div id="main">
@ -10,4 +9,414 @@
<canvas id="canvas"></canvas>
<div id="log">Starting Human library</div>
</div>
<script>
/* global QuickSettings */
const ui = {
baseColor: 'rgba(255, 200, 255, 0.3)',
baseLabel: 'rgba(255, 200, 255, 0.8)',
baseFont: 'small-caps 1.2rem "Segoe UI"',
baseLineWidth: 16,
};
const config = {
backend: 'webgl',
console: true,
face: {
enabled: true,
detector: { maxFaces: 10, skipFrames: 10, minConfidence: 0.5, iouThreshold: 0.3, scoreThreshold: 0.7 },
mesh: { enabled: true },
iris: { enabled: true },
age: { enabled: true, skipFrames: 10 },
gender: { enabled: true },
emotion: { enabled: true, minConfidence: 0.5, useGrayscale: true },
},
body: { enabled: true, maxDetections: 10, scoreThreshold: 0.7, nmsRadius: 20 },
hand: { enabled: true, skipFrames: 10, minConfidence: 0.5, iouThreshold: 0.3, scoreThreshold: 0.7 },
};
let settings;
let worker;
let timeStamp;
const fps = [];
function str(...msg) {
if (!Array.isArray(msg)) return msg;
let line = '';
for (const entry of msg) {
if (typeof entry === 'object') line += JSON.stringify(entry).replace(/{|}|"|\[|\]/g, '').replace(/,/g, ', ');
else line += entry;
}
return line;
}
const log = (...msg) => {
// eslint-disable-next-line no-console
if (config.console) console.log(...msg);
};
async function drawFace(result, canvas) {
if (!result) return;
const ctx = canvas.getContext('2d');
ctx.strokeStyle = ui.baseColor;
ctx.font = ui.baseFont;
for (const face of result) {
ctx.fillStyle = ui.baseColor;
ctx.lineWidth = ui.baseLineWidth;
ctx.beginPath();
if (settings.getValue('Draw Boxes')) {
ctx.rect(face.box[0], face.box[1], face.box[2], face.box[3]);
}
const labelAgeGender = `${face.gender || ''} ${face.age || ''}`;
const labelIris = face.iris ? `iris: ${face.iris}` : '';
const labelEmotion = face.emotion && face.emotion[0] ? `emotion: ${Math.trunc(100 * face.emotion[0].score)}% ${face.emotion[0].emotion}` : '';
ctx.fillStyle = ui.baseLabel;
ctx.fillText(`${Math.trunc(100 * face.confidence)}% face ${labelAgeGender} ${labelIris} ${labelEmotion}`, face.box[0] + 2, face.box[1] + 22);
ctx.stroke();
ctx.lineWidth = 1;
if (face.mesh) {
if (settings.getValue('Draw Points')) {
for (const point of face.mesh) {
ctx.fillStyle = `rgba(${127.5 + (2 * point[2])}, ${127.5 - (2 * point[2])}, 255, 0.5)`;
ctx.beginPath();
ctx.arc(point[0], point[1], 2, 0, 2 * Math.PI);
ctx.fill();
}
}
if (settings.getValue('Draw Polygons')) {
for (let i = 0; i < human.facemesh.triangulation.length / 3; i++) {
const points = [
human.facemesh.triangulation[i * 3 + 0],
human.facemesh.triangulation[i * 3 + 1],
human.facemesh.triangulation[i * 3 + 2],
].map((index) => face.mesh[index]);
const path = new Path2D();
path.moveTo(points[0][0], points[0][1]);
for (const point of points) {
path.lineTo(point[0], point[1]);
}
path.closePath();
ctx.strokeStyle = `rgba(${127.5 + (2 * points[0][2])}, ${127.5 - (2 * points[0][2])}, 255, 0.3)`;
ctx.stroke(path);
if (settings.getValue('Fill Polygons')) {
ctx.fillStyle = `rgba(${127.5 + (2 * points[0][2])}, ${127.5 - (2 * points[0][2])}, 255, 0.3)`;
ctx.fill(path);
}
}
}
}
}
}
async function drawBody(result, canvas) {
if (!result) return;
const ctx = canvas.getContext('2d');
ctx.fillStyle = ui.baseColor;
ctx.strokeStyle = ui.baseColor;
ctx.font = ui.baseFont;
ctx.lineWidth = ui.baseLineWidth;
for (const pose of result) {
if (settings.getValue('Draw Points')) {
for (const point of pose.keypoints) {
ctx.beginPath();
ctx.arc(point.position.x, point.position.y, 2, 0, 2 * Math.PI);
ctx.fill();
}
}
if (settings.getValue('Draw Polygons')) {
const path = new Path2D();
let part;
// torso
part = pose.keypoints.find((a) => a.part === 'leftShoulder');
path.moveTo(part.position.x, part.position.y);
part = pose.keypoints.find((a) => a.part === 'rightShoulder');
path.lineTo(part.position.x, part.position.y);
part = pose.keypoints.find((a) => a.part === 'rightHip');
path.lineTo(part.position.x, part.position.y);
part = pose.keypoints.find((a) => a.part === 'leftHip');
path.lineTo(part.position.x, part.position.y);
part = pose.keypoints.find((a) => a.part === 'leftShoulder');
path.lineTo(part.position.x, part.position.y);
// legs
part = pose.keypoints.find((a) => a.part === 'leftHip');
path.moveTo(part.position.x, part.position.y);
part = pose.keypoints.find((a) => a.part === 'leftKnee');
path.lineTo(part.position.x, part.position.y);
part = pose.keypoints.find((a) => a.part === 'leftAnkle');
path.lineTo(part.position.x, part.position.y);
part = pose.keypoints.find((a) => a.part === 'rightHip');
path.moveTo(part.position.x, part.position.y);
part = pose.keypoints.find((a) => a.part === 'rightKnee');
path.lineTo(part.position.x, part.position.y);
part = pose.keypoints.find((a) => a.part === 'rightAnkle');
path.lineTo(part.position.x, part.position.y);
// arms
part = pose.keypoints.find((a) => a.part === 'leftShoulder');
path.moveTo(part.position.x, part.position.y);
part = pose.keypoints.find((a) => a.part === 'leftElbow');
path.lineTo(part.position.x, part.position.y);
part = pose.keypoints.find((a) => a.part === 'leftWrist');
path.lineTo(part.position.x, part.position.y);
// arms
part = pose.keypoints.find((a) => a.part === 'rightShoulder');
path.moveTo(part.position.x, part.position.y);
part = pose.keypoints.find((a) => a.part === 'rightElbow');
path.lineTo(part.position.x, part.position.y);
part = pose.keypoints.find((a) => a.part === 'rightWrist');
path.lineTo(part.position.x, part.position.y);
// draw all
ctx.stroke(path);
}
}
}
async function drawHand(result, canvas) {
if (!result) return;
const ctx = canvas.getContext('2d');
ctx.font = ui.baseFont;
ctx.lineWidth = ui.baseLineWidth;
window.result = result;
for (const hand of result) {
if (settings.getValue('Draw Boxes')) {
ctx.lineWidth = ui.baseLineWidth;
ctx.beginPath();
ctx.fillStyle = ui.baseColor;
ctx.rect(hand.box[0], hand.box[1], hand.box[2], hand.box[3]);
ctx.fillStyle = ui.baseLabel;
ctx.fillText('hand', hand.box[0] + 2, hand.box[1] + 22, hand.box[2]);
ctx.stroke();
}
if (settings.getValue('Draw Points')) {
for (const point of hand.landmarks) {
ctx.fillStyle = `rgba(${127.5 + (2 * point[2])}, ${127.5 - (2 * point[2])}, 255, 0.5)`;
ctx.beginPath();
ctx.arc(point[0], point[1], 2, 0, 2 * Math.PI);
ctx.fill();
}
}
if (settings.getValue('Draw Polygons')) {
const addPart = (part) => {
for (let i = 1; i < part.length; i++) {
ctx.lineWidth = ui.baseLineWidth;
ctx.beginPath();
ctx.strokeStyle = `rgba(${127.5 + (2 * part[i][2])}, ${127.5 - (2 * part[i][2])}, 255, 0.5)`;
ctx.moveTo(part[i - 1][0], part[i - 1][1]);
ctx.lineTo(part[i][0], part[i][1]);
ctx.stroke();
}
};
addPart(hand.annotations.indexFinger);
addPart(hand.annotations.middleFinger);
addPart(hand.annotations.ringFinger);
addPart(hand.annotations.pinky);
addPart(hand.annotations.thumb);
addPart(hand.annotations.palmBase);
}
}
}
async function drawResults(input, result, canvas) {
// update fps
settings.setValue('FPS', Math.round(1000 / (performance.now() - timeStamp)));
fps.push(1000 / (performance.now() - timeStamp));
if (fps.length > 20) fps.shift();
settings.setValue('FPS', Math.round(10 * fps.reduce((a, b) => a + b) / fps.length) / 10);
// eslint-disable-next-line no-use-before-define
requestAnimationFrame(() => runHumanDetect(input, canvas)); // immediate loop
// draw image from video
const ctx = canvas.getContext('2d');
ctx.drawImage(input, 0, 0, input.width, input.height, 0, 0, canvas.width, canvas.height);
// draw all results
drawFace(result.face, canvas);
drawBody(result.body, canvas);
drawHand(result.hand, canvas);
// update log
const engine = await human.tf.engine();
const memory = `${engine.state.numBytes.toLocaleString()} bytes ${engine.state.numDataBuffers.toLocaleString()} buffers ${engine.state.numTensors.toLocaleString()} tensors`;
const gpu = engine.backendInstance ? `GPU: ${engine.backendInstance.numBytesInGPU.toLocaleString()} bytes` : '';
document.getElementById('log').innerText = `
TFJS Version: ${human.tf.version_core} | Backend: ${human.tf.getBackend()} | Memory: ${memory} ${gpu}
Performance: ${str(result.performance)} | Object size: ${(str(result)).length.toLocaleString()} bytes
`;
}
// simple wrapper for worker.postmessage that creates worker if one does not exist
function webWorker(input, image, canvas) {
if (!worker) {
// create new webworker and add event handler only once
log('Creating worker thread');
worker = new Worker('demo-esm-webworker.js', { type: 'module' });
// after receiving message from webworker, parse&draw results and send new frame for processing
worker.addEventListener('message', (msg) => drawResults(input, msg.data, canvas));
}
// pass image data as arraybuffer to worker by reference to avoid copy
worker.postMessage({ image: image.data.buffer, width: canvas.width, height: canvas.height, config }, [image.data.buffer]);
}
async function runHumanDetect(input, canvas) {
const live = input.srcObject ? ((input.srcObject.getVideoTracks()[0].readyState === 'live') && (input.readyState > 2) && (!input.paused)) : false;
timeStamp = performance.now();
// perform detect if live video or not video at all
if (live || !(input instanceof HTMLVideoElement)) {
if (settings.getValue('Use Web Worker')) {
// get image data from video as we cannot send html objects to webworker
const offscreen = new OffscreenCanvas(canvas.width, canvas.height);
const ctx = offscreen.getContext('2d');
ctx.drawImage(input, 0, 0, input.width, input.height, 0, 0, canvas.width, canvas.height);
const data = ctx.getImageData(0, 0, canvas.width, canvas.height);
// perform detection in worker
webWorker(input, data, canvas);
} else {
let result = {};
try {
// perform detection
result = await human.detect(input, config);
} catch (err) {
log('Error during execution:', err.message);
}
drawResults(input, result, canvas);
}
}
}
function setupUI() {
// add all variables to ui control panel
settings = QuickSettings.create(10, 10, 'Settings', document.getElementById('main'));
const style = document.createElement('style');
// style.type = 'text/css';
style.innerHTML = `
.qs_main { font: 1rem "Segoe UI"; }
.qs_label { font: 0.8rem "Segoe UI"; }
.qs_title_bar { display: none; }
.qs_content { background: darkslategray; }
.qs_container { background: transparent; color: white; margin: 6px; padding: 6px; }
.qs_checkbox_label { top: 2px; }
.qs_button { width: -webkit-fill-available; font: 1rem "Segoe UI"; cursor: pointer; }
`;
document.getElementsByTagName('head')[0].appendChild(style);
settings.addButton('Play/Pause', () => {
const video = document.getElementById('video');
const canvas = document.getElementById('canvas');
if (!video.paused) {
document.getElementById('log').innerText = 'Paused ...';
video.pause();
} else {
document.getElementById('log').innerText = 'Starting Human Library ...';
video.play();
}
runHumanDetect(video, canvas);
});
settings.addDropDown('Backend', ['webgl', 'wasm', 'cpu'], async (val) => config.backend = val.value);
settings.addHTML('title', 'Enabled Models'); settings.hideTitle('title');
settings.addBoolean('Face Detect', config.face.enabled, (val) => config.face.enabled = val);
settings.addBoolean('Face Mesh', config.face.mesh.enabled, (val) => config.face.mesh.enabled = val);
settings.addBoolean('Face Iris', config.face.iris.enabled, (val) => config.face.iris.enabled = val);
settings.addBoolean('Face Age', config.face.age.enabled, (val) => config.face.age.enabled = val);
settings.addBoolean('Face Gender', config.face.gender.enabled, (val) => config.face.gender.enabled = val);
settings.addBoolean('Face Emotion', config.face.emotion.enabled, (val) => config.face.emotion.enabled = val);
settings.addBoolean('Body Pose', config.body.enabled, (val) => config.body.enabled = val);
settings.addBoolean('Hand Pose', config.hand.enabled, (val) => config.hand.enabled = val);
settings.addHTML('title', 'Model Parameters'); settings.hideTitle('title');
settings.addRange('Max Objects', 1, 20, 5, 1, (val) => {
config.face.detector.maxFaces = parseInt(val);
config.body.maxDetections = parseInt(val);
});
settings.addRange('Skip Frames', 1, 20, config.face.detector.skipFrames, 1, (val) => {
config.face.detector.skipFrames = parseInt(val);
config.face.emotion.skipFrames = parseInt(val);
config.face.age.skipFrames = parseInt(val);
config.hand.skipFrames = parseInt(val);
});
settings.addRange('Min Confidence', 0.1, 1.0, config.face.detector.minConfidence, 0.05, (val) => {
config.face.detector.minConfidence = parseFloat(val);
config.face.emotion.minConfidence = parseFloat(val);
config.hand.minConfidence = parseFloat(val);
});
settings.addRange('Score Threshold', 0.1, 1.0, config.face.detector.scoreThreshold, 0.05, (val) => {
config.face.detector.scoreThreshold = parseFloat(val);
config.hand.scoreThreshold = parseFloat(val);
config.body.scoreThreshold = parseFloat(val);
});
settings.addRange('IOU Threshold', 0.1, 1.0, config.face.detector.iouThreshold, 0.05, (val) => {
config.face.detector.iouThreshold = parseFloat(val);
config.hand.iouThreshold = parseFloat(val);
});
settings.addHTML('title', 'UI Options'); settings.hideTitle('title');
settings.addBoolean('Use Web Worker', false);
settings.addBoolean('Draw Boxes', true);
settings.addBoolean('Draw Points', true);
settings.addBoolean('Draw Polygons', true);
settings.addBoolean('Fill Polygons', true);
settings.addHTML('line1', '<hr>'); settings.hideTitle('line1');
settings.addRange('FPS', 0, 100, 0, 1);
}
async function setupCanvas(input) {
// setup canvas object to same size as input as camera resolution may change
const canvas = document.getElementById('canvas');
canvas.width = input.width;
canvas.height = input.height;
return canvas;
}
// eslint-disable-next-line no-unused-vars
async function setupCamera() {
log('Setting up camera');
// setup webcam. note that navigator.mediaDevices requires that page is accessed via https
const video = document.getElementById('video');
if (!navigator.mediaDevices) {
document.getElementById('log').innerText = 'Video not supported';
return null;
}
const stream = await navigator.mediaDevices.getUserMedia({
audio: false,
video: { facingMode: 'user', width: window.innerWidth, height: window.innerHeight },
});
video.srcObject = stream;
return new Promise((resolve) => {
video.onloadedmetadata = () => {
video.width = video.videoWidth;
video.height = video.videoHeight;
video.play();
video.pause();
resolve(video);
};
});
}
// eslint-disable-next-line no-unused-vars
async function setupImage() {
const image = document.getElementById('image');
image.width = window.innerWidth;
image.height = window.innerHeight;
return new Promise((resolve) => {
image.onload = () => resolve(image);
image.src = 'sample.jpg';
});
}
async function main() {
log('Human starting ...');
// setup ui control panel
await setupUI();
// setup webcam
const input = await setupCamera();
// or setup image
// const input = await setupImage();
// setup output canvas from input object
await setupCanvas(input);
const msg = `Human ready: version: ${human.version} TensorFlow/JS version: ${human.tf.version_core}`;
document.getElementById('log').innerText = msg;
log(msg);
// run actual detection. if input is video, it will run in a loop else it will run only once
// runHumanDetect(video, canvas);
}
window.onload = main;
window.onresize = main;
</script>
</body>

View File

@ -1,317 +0,0 @@
/* global human, QuickSettings */
const ui = {
baseColor: 'rgba(255, 200, 255, 0.3)',
baseFont: 'small-caps 1.2rem "Segoe UI"',
baseLineWidth: 16,
};
const config = {
face: {
enabled: true,
detector: { maxFaces: 10, skipFrames: 10, minConfidence: 0.8, iouThreshold: 0.3, scoreThreshold: 0.75 },
mesh: { enabled: true },
iris: { enabled: true },
age: { enabled: true, skipFrames: 5 },
gender: { enabled: true },
},
body: { enabled: true, maxDetections: 5, scoreThreshold: 0.75, nmsRadius: 20 },
hand: { enabled: true, skipFrames: 10, minConfidence: 0.8, iouThreshold: 0.3, scoreThreshold: 0.75 },
};
let settings;
async function drawFace(result, canvas) {
const ctx = canvas.getContext('2d');
ctx.fillStyle = ui.baseColor;
ctx.strokeStyle = ui.baseColor;
ctx.font = ui.baseFont;
for (const face of result) {
ctx.lineWidth = ui.baseLineWidth;
ctx.beginPath();
if (settings.getValue('Draw Boxes')) {
ctx.rect(face.box[0], face.box[1], face.box[2], face.box[3]);
}
ctx.fillText(`face ${face.gender || ''} ${face.age || ''} ${face.iris ? 'iris: ' + face.iris : ''}`, face.box[0] + 2, face.box[1] + 22, face.box[2]);
ctx.stroke();
ctx.lineWidth = 1;
if (face.mesh) {
if (settings.getValue('Draw Points')) {
for (const point of face.mesh) {
ctx.fillStyle = `rgba(${127.5 + (2 * point[2])}, ${127.5 - (2 * point[2])}, 255, 0.5)`;
ctx.beginPath();
ctx.arc(point[0], point[1], 2, 0, 2 * Math.PI);
ctx.fill();
}
}
if (settings.getValue('Draw Polygons')) {
for (let i = 0; i < human.facemesh.triangulation.length / 3; i++) {
const points = [
human.facemesh.triangulation[i * 3 + 0],
human.facemesh.triangulation[i * 3 + 1],
human.facemesh.triangulation[i * 3 + 2],
].map((index) => face.mesh[index]);
const path = new Path2D();
path.moveTo(points[0][0], points[0][1]);
for (const point of points) {
path.lineTo(point[0], point[1]);
}
path.closePath();
ctx.strokeStyle = `rgba(${127.5 + (2 * points[0][2])}, ${127.5 - (2 * points[0][2])}, 255, 0.3)`;
ctx.stroke(path);
if (settings.getValue('Fill Polygons')) {
ctx.fillStyle = `rgba(${127.5 + (2 * points[0][2])}, ${127.5 - (2 * points[0][2])}, 255, 0.3)`;
ctx.fill(path);
}
}
}
}
}
}
async function drawBody(result, canvas) {
const ctx = canvas.getContext('2d');
ctx.fillStyle = ui.baseColor;
ctx.strokeStyle = ui.baseColor;
ctx.font = ui.baseFont;
ctx.lineWidth = ui.baseLineWidth;
for (const pose of result) {
if (settings.getValue('Draw Points')) {
for (const point of pose.keypoints) {
ctx.beginPath();
ctx.arc(point.position.x, point.position.y, 2, 0, 2 * Math.PI);
ctx.fill();
}
}
if (settings.getValue('Draw Polygons')) {
const path = new Path2D();
let part;
// torso
part = pose.keypoints.find((a) => a.part === 'leftShoulder');
path.moveTo(part.position.x, part.position.y);
part = pose.keypoints.find((a) => a.part === 'rightShoulder');
path.lineTo(part.position.x, part.position.y);
part = pose.keypoints.find((a) => a.part === 'rightHip');
path.lineTo(part.position.x, part.position.y);
part = pose.keypoints.find((a) => a.part === 'leftHip');
path.lineTo(part.position.x, part.position.y);
part = pose.keypoints.find((a) => a.part === 'leftShoulder');
path.lineTo(part.position.x, part.position.y);
// legs
part = pose.keypoints.find((a) => a.part === 'leftHip');
path.moveTo(part.position.x, part.position.y);
part = pose.keypoints.find((a) => a.part === 'leftKnee');
path.lineTo(part.position.x, part.position.y);
part = pose.keypoints.find((a) => a.part === 'leftAnkle');
path.lineTo(part.position.x, part.position.y);
part = pose.keypoints.find((a) => a.part === 'rightHip');
path.moveTo(part.position.x, part.position.y);
part = pose.keypoints.find((a) => a.part === 'rightKnee');
path.lineTo(part.position.x, part.position.y);
part = pose.keypoints.find((a) => a.part === 'rightAnkle');
path.lineTo(part.position.x, part.position.y);
// arms
part = pose.keypoints.find((a) => a.part === 'leftShoulder');
path.moveTo(part.position.x, part.position.y);
part = pose.keypoints.find((a) => a.part === 'leftElbow');
path.lineTo(part.position.x, part.position.y);
part = pose.keypoints.find((a) => a.part === 'leftWrist');
path.lineTo(part.position.x, part.position.y);
// arms
part = pose.keypoints.find((a) => a.part === 'rightShoulder');
path.moveTo(part.position.x, part.position.y);
part = pose.keypoints.find((a) => a.part === 'rightElbow');
path.lineTo(part.position.x, part.position.y);
part = pose.keypoints.find((a) => a.part === 'rightWrist');
path.lineTo(part.position.x, part.position.y);
// draw all
ctx.stroke(path);
}
}
}
async function drawHand(result, canvas) {
const ctx = canvas.getContext('2d');
ctx.font = ui.baseFont;
ctx.lineWidth = ui.baseLineWidth;
window.result = result;
for (const hand of result) {
if (settings.getValue('Draw Boxes')) {
ctx.lineWidth = ui.baseLineWidth;
ctx.beginPath();
ctx.rect(hand.box[0], hand.box[1], hand.box[2], hand.box[3]);
ctx.fillText('hand', hand.box[0] + 2, hand.box[1] + 22, hand.box[2]);
ctx.stroke();
}
if (settings.getValue('Draw Points')) {
for (const point of hand.landmarks) {
ctx.fillStyle = `rgba(${127.5 + (2 * point[2])}, ${127.5 - (2 * point[2])}, 255, 0.5)`;
ctx.beginPath();
ctx.arc(point[0], point[1], 2, 0, 2 * Math.PI);
ctx.fill();
}
}
if (settings.getValue('Draw Polygons')) {
const addPart = (part) => {
for (let i = 1; i < part.length; i++) {
ctx.lineWidth = ui.baseLineWidth;
ctx.beginPath();
ctx.strokeStyle = `rgba(${127.5 + (2 * part[i][2])}, ${127.5 - (2 * part[i][2])}, 255, 0.5)`;
ctx.moveTo(part[i - 1][0], part[i - 1][1]);
ctx.lineTo(part[i][0], part[i][1]);
ctx.stroke();
}
};
addPart(hand.annotations.indexFinger);
addPart(hand.annotations.middleFinger);
addPart(hand.annotations.ringFinger);
addPart(hand.annotations.pinky);
addPart(hand.annotations.thumb);
addPart(hand.annotations.palmBase);
}
}
}
async function runHumanDetect(input, canvas) {
const log = document.getElementById('log');
const live = input.srcObject ? ((input.srcObject.getVideoTracks()[0].readyState === 'live') && (input.readyState > 2) && (!input.paused)) : false;
// perform detect if live video or not video at all
if (live || !(input instanceof HTMLVideoElement)) {
// perform detection
const t0 = performance.now();
const result = await human.detect(input, config);
if (!result) return;
const t1 = performance.now();
// update fps
settings.setValue('FPS', Math.round(1000 / (t1 - t0)));
// draw image from video
const ctx = canvas.getContext('2d');
ctx.drawImage(input, 0, 0, input.width, input.height, 0, 0, canvas.width, canvas.height);
// draw all results
drawFace(result.face, canvas);
drawBody(result.body, canvas);
drawHand(result.hand, canvas);
// update log
const engine = await human.tf.engine();
log.innerText = `
TFJS Version: ${human.tf.version_core} Memory: ${engine.state.numBytes.toLocaleString()} bytes ${engine.state.numDataBuffers.toLocaleString()} buffers ${engine.state.numTensors.toLocaleString()} tensors
GPU Memory: used ${engine.backendInstance.numBytesInGPU.toLocaleString()} bytes free ${Math.floor(1024 * 1024 * engine.backendInstance.numMBBeforeWarning).toLocaleString()} bytes
Result Object Size: Face: ${(JSON.stringify(result.face)).length.toLocaleString()} bytes Body: ${(JSON.stringify(result.body)).length.toLocaleString()} bytes Hand: ${(JSON.stringify(result.hand)).length.toLocaleString()} bytes
`;
// rinse & repeate
// if (input.readyState) setTimeout(() => runHumanDetect(), 1000); // slow loop for debugging purposes
if (input.readyState) requestAnimationFrame(() => runHumanDetect(input, canvas)); // immediate loop
}
}
function setupGUI() {
// add all variables to ui control panel
settings = QuickSettings.create(10, 10, 'Settings', document.getElementById('main'));
settings.addRange('FPS', 0, 100, 0, 1);
settings.addBoolean('Pause', false, (val) => {
const video = document.getElementById('video');
const canvas = document.getElementById('canvas');
if (val) video.pause();
else video.play();
runHumanDetect(video, canvas);
});
settings.addHTML('line1', '<hr>'); settings.hideTitle('line1');
settings.addBoolean('Draw Boxes', false);
settings.addBoolean('Draw Points', true);
settings.addBoolean('Draw Polygons', true);
settings.addBoolean('Fill Polygons', true);
settings.bindText('baseColor', ui.baseColor, config);
settings.bindText('baseFont', ui.baseFont, config);
settings.bindRange('baseLineWidth', 1, 100, ui.baseLineWidth, 1, config);
settings.addHTML('line2', '<hr>'); settings.hideTitle('line2');
settings.addBoolean('Face Detect', config.face.enabled, (val) => config.face.enabled = val);
settings.addBoolean('Face Mesh', config.face.mesh.enabled, (val) => config.face.mesh.enabled = val);
settings.addBoolean('Face Iris', config.face.iris.enabled, (val) => config.face.iris.enabled = val);
settings.addBoolean('Face Age', config.face.age.enabled, (val) => config.face.age.enabled = val);
settings.addBoolean('Face Gender', config.face.gender.enabled, (val) => config.face.gender.enabled = val);
settings.addBoolean('Body Pose', config.body.enabled, (val) => config.body.enabled = val);
settings.addBoolean('Hand Pose', config.hand.enabled, (val) => config.hand.enabled = val);
settings.addHTML('line3', '<hr>'); settings.hideTitle('line3');
settings.addRange('Max Objects', 1, 20, 5, 1, (val) => {
config.face.detector.maxFaces = parseInt(val);
config.body.maxDetections = parseInt(val);
});
settings.addRange('Skip Frames', 1, 20, config.face.detector.skipFrames, 1, (val) => {
config.face.detector.skipFrames = parseInt(val);
config.face.age.skipFrames = parseInt(val);
config.hand.skipFrames = parseInt(val);
});
settings.addRange('Min Confidence', 0.1, 1.0, config.face.detector.minConfidence, 0.05, (val) => {
config.face.detector.minConfidence = parseFloat(val);
config.hand.minConfidence = parseFloat(val);
});
settings.addRange('Score Threshold', 0.1, 1.0, config.face.detector.scoreThreshold, 0.05, (val) => {
config.face.detector.scoreThreshold = parseFloat(val);
config.hand.scoreThreshold = parseFloat(val);
config.body.scoreThreshold = parseFloat(val);
});
settings.addRange('IOU Threshold', 0.1, 1.0, config.face.detector.iouThreshold, 0.05, (val) => {
config.face.detector.iouThreshold = parseFloat(val);
config.hand.iouThreshold = parseFloat(val);
});
}
async function setupCanvas(input) {
// setup canvas object to same size as input as camera resolution may change
const canvas = document.getElementById('canvas');
canvas.width = input.width;
canvas.height = input.height;
return canvas;
}
// eslint-disable-next-line no-unused-vars
async function setupCamera() {
// setup webcam. note that navigator.mediaDevices requires that page is accessed via https
const video = document.getElementById('video');
if (!navigator.mediaDevices) {
document.getElementById('log').innerText = 'Video not supported';
return null;
}
const stream = await navigator.mediaDevices.getUserMedia({
audio: false,
video: { facingMode: 'user', width: window.innerWidth, height: window.innerHeight },
});
video.srcObject = stream;
return new Promise((resolve) => {
video.onloadedmetadata = () => {
video.width = video.videoWidth;
video.height = video.videoHeight;
video.play();
resolve(video);
};
});
}
// eslint-disable-next-line no-unused-vars
async function setupImage() {
const image = document.getElementById('image');
image.width = window.innerWidth;
image.height = window.innerHeight;
return new Promise((resolve) => {
image.onload = () => resolve(image);
image.src = 'sample.jpg';
});
}
async function main() {
// initialize tensorflow
await human.tf.setBackend('webgl');
await human.tf.ready();
// setup ui control panel
await setupGUI();
// setup webcam
const video = await setupCamera();
// or setup image
// const image = await setupImage();
// setup output canvas from input object, select video or image
const canvas = await setupCanvas(video);
// run actual detection. if input is video, it will run in a loop else it will run only once
runHumanDetect(video, canvas);
}
window.onload = main;
window.onresize = main;

View File

@ -2,7 +2,7 @@ const tf = require('@tensorflow/tfjs-node');
const fs = require('fs');
const process = require('process');
const console = require('console');
const human = require('..'); // this would be '@vladmandic/human'
const human = require('..'); // this resolves to project root which is '@vladmandic/human'
const logger = new console.Console({
stdout: process.stdout,
@ -24,6 +24,8 @@ const logger = new console.Console({
});
const config = {
backend: 'tensorflow',
console: true,
face: {
enabled: false,
detector: { modelPath: 'file://models/blazeface/model.json', inputSize: 128, maxFaces: 10, skipFrames: 10, minConfidence: 0.8, iouThreshold: 0.3, scoreThreshold: 0.75 },

View File

@ -93,6 +93,8 @@ var require_blazeface = __commonJS((exports2) => {
this.scoreThreshold = config2.detector.scoreThreshold;
}
async getBoundingBoxes(inputImage) {
if (!inputImage || inputImage.isDisposedInternal || inputImage.shape.length !== 4 || inputImage.shape[1] < 1 || inputImage.shape[2] < 1)
return null;
const [detectedOutputs, boxes, scores] = tf2.tidy(() => {
const resizedImage = inputImage.resizeBilinear([this.width, this.height]);
const normalizedImage = tf2.mul(tf2.sub(resizedImage.div(255), 0.5), 2);
@ -5047,6 +5049,8 @@ var require_config = __commonJS((exports2) => {
default: () => config_default
});
var config_default = {
backend: "webgl",
console: true,
face: {
enabled: true,
detector: {
@ -5122,10 +5126,10 @@ var require_config = __commonJS((exports2) => {
var require_package = __commonJS((exports2, module2) => {
module2.exports = {
name: "@vladmandic/human",
version: "0.3.2",
version: "0.3.3",
description: "human: 3D Face Detection, Iris Tracking and Age & Gender Prediction",
sideEffects: false,
main: "dist/human.cjs",
main: "dist/human-nobundle.cjs",
module: "dist/human.esm.js",
browser: "dist/human.esm.js",
author: "Vladimir Mandic <mandic00@live.com>",
@ -5200,6 +5204,11 @@ const models = {
gender: null,
emotion: null
};
const now = () => {
if (typeof performance !== "undefined")
return performance.now();
return parseInt(Number(process.hrtime.bigint()) / 1e3 / 1e3);
};
const log = (...msg) => {
if (config.console)
console.log(...msg);
@ -5221,9 +5230,29 @@ function mergeDeep(...objects) {
return prev;
}, {});
}
function sanity(input) {
if (!input)
return "input is not defined";
const width = input.naturalWidth || input.videoWidth || input.width || input.shape && input.shape[1] > 0;
if (!width || width === 0)
return "input is empty";
if (input.readyState && input.readyState <= 2)
return "input is not ready";
try {
tf.getBackend();
} catch {
return "backend not loaded";
}
return null;
}
async function detect(input, userConfig) {
return new Promise(async (resolve) => {
config = mergeDeep(defaults, userConfig);
const error = sanity(input);
if (error) {
log(error, input);
return {error};
}
return new Promise(async (resolve) => {
const loadedModels = Object.values(models).filter((a) => a).length;
if (loadedModels === 0)
log("Human library starting");
@ -5251,29 +5280,33 @@ async function detect(input, userConfig) {
models.emotion = await emotion.load(config);
const perf = {};
let timeStamp;
timeStamp = performance.now();
timeStamp = now();
tf.engine().startScope();
const poseRes = config.body.enabled ? await models.posenet.estimatePoses(input, config.body) : [];
tf.engine().endScope();
perf.body = Math.trunc(performance.now() - timeStamp);
timeStamp = performance.now();
perf.body = Math.trunc(now() - timeStamp);
timeStamp = now();
tf.engine().startScope();
const handRes = config.hand.enabled ? await models.handpose.estimateHands(input, config.hand) : [];
tf.engine().endScope();
perf.hand = Math.trunc(performance.now() - timeStamp);
perf.hand = Math.trunc(now() - timeStamp);
const faceRes = [];
if (config.face.enabled) {
timeStamp = performance.now();
timeStamp = now();
tf.engine().startScope();
const faces = await models.facemesh.estimateFaces(input, config.face);
perf.face = Math.trunc(performance.now() - timeStamp);
perf.face = Math.trunc(now() - timeStamp);
for (const face of faces) {
timeStamp = performance.now();
if (!face.image || face.image.isDisposedInternal) {
log("face object is disposed:", face.image);
continue;
}
timeStamp = now();
const ssrData = config.face.age.enabled || config.face.gender.enabled ? await ssrnet.predict(face.image, config) : {};
perf.agegender = Math.trunc(performance.now() - timeStamp);
timeStamp = performance.now();
perf.agegender = Math.trunc(now() - timeStamp);
timeStamp = now();
const emotionData = config.face.emotion.enabled ? await emotion.predict(face.image, config) : {};
perf.emotion = Math.trunc(performance.now() - timeStamp);
perf.emotion = Math.trunc(now() - timeStamp);
face.image.dispose();
const iris = face.annotations.leftEyeIris && face.annotations.rightEyeIris ? Math.max(face.annotations.leftEyeIris[3][0] - face.annotations.leftEyeIris[1][0], face.annotations.rightEyeIris[3][0] - face.annotations.rightEyeIris[1][0]) : 0;
faceRes.push({

File diff suppressed because one or more lines are too long

486
dist/human.cjs vendored

File diff suppressed because one or more lines are too long

4
dist/human.cjs.map vendored

File diff suppressed because one or more lines are too long

File diff suppressed because one or more lines are too long

File diff suppressed because one or more lines are too long

486
dist/human.esm.js vendored

File diff suppressed because one or more lines are too long

File diff suppressed because one or more lines are too long

486
dist/human.js vendored

File diff suppressed because one or more lines are too long

4
dist/human.js.map vendored

File diff suppressed because one or more lines are too long

View File

@ -3,7 +3,7 @@
"version": "0.3.3",
"description": "human: 3D Face Detection, Iris Tracking and Age & Gender Prediction",
"sideEffects": false,
"main": "dist/human.cjs",
"main": "dist/human-nobundle.cjs",
"module": "dist/human.esm.js",
"browser": "dist/human.esm.js",
"author": "Vladimir Mandic <mandic00@live.com>",

View File

@ -1,4 +1,6 @@
export default {
backend: 'webgl',
console: true,
face: {
enabled: true, // refers to detector, but since all other face modules rely on detector, it should be a global
detector: {

View File

@ -83,6 +83,8 @@ class BlazeFaceModel {
}
async getBoundingBoxes(inputImage) {
// sanity check on input
if ((!inputImage) || (inputImage.isDisposedInternal) || (inputImage.shape.length !== 4) || (inputImage.shape[1] < 1) || (inputImage.shape[2] < 1)) return null;
const [detectedOutputs, boxes, scores] = tf.tidy(() => {
const resizedImage = inputImage.resizeBilinear([this.width, this.height]);
const normalizedImage = tf.mul(tf.sub(resizedImage.div(255), 0.5), 2);
@ -101,7 +103,6 @@ class BlazeFaceModel {
const decodedBounds = decodeBounds(prediction, this.anchors, this.inputSize);
const logits = tf.slice(prediction, [0, 0], [-1, 1]);
const scoresOut = tf.sigmoid(logits).squeeze();
// console.log(prediction, decodedBounds, logits, scoresOut);
return [prediction, decodedBounds, scoresOut];
});

View File

@ -19,6 +19,10 @@ const models = {
gender: null,
emotion: null,
};
const now = () => {
if (typeof performance !== 'undefined') return performance.now();
return parseInt(Number(process.hrtime.bigint()) / 1000 / 1000);
};
const log = (...msg) => {
// eslint-disable-next-line no-console
@ -44,11 +48,31 @@ function mergeDeep(...objects) {
}, {});
}
function sanity(input) {
if (!input) return 'input is not defined';
const width = input.naturalWidth || input.videoWidth || input.width || (input.shape && (input.shape[1] > 0));
if (!width || (width === 0)) return 'input is empty';
if (input.readyState && (input.readyState <= 2)) return 'input is not ready';
try {
tf.getBackend();
} catch {
return 'backend not loaded';
}
return null;
}
async function detect(input, userConfig) {
// eslint-disable-next-line no-async-promise-executor
return new Promise(async (resolve) => {
config = mergeDeep(defaults, userConfig);
// sanity checks
const error = sanity(input);
if (error) {
log(error, input);
return { error };
}
// eslint-disable-next-line no-async-promise-executor
return new Promise(async (resolve) => {
// check number of loaded models
const loadedModels = Object.values(models).filter((a) => a).length;
if (loadedModels === 0) log('Human library starting');
@ -78,35 +102,40 @@ async function detect(input, userConfig) {
let timeStamp;
// run posenet
timeStamp = performance.now();
timeStamp = now();
tf.engine().startScope();
const poseRes = config.body.enabled ? await models.posenet.estimatePoses(input, config.body) : [];
tf.engine().endScope();
perf.body = Math.trunc(performance.now() - timeStamp);
perf.body = Math.trunc(now() - timeStamp);
// run handpose
timeStamp = performance.now();
timeStamp = now();
tf.engine().startScope();
const handRes = config.hand.enabled ? await models.handpose.estimateHands(input, config.hand) : [];
tf.engine().endScope();
perf.hand = Math.trunc(performance.now() - timeStamp);
perf.hand = Math.trunc(now() - timeStamp);
// run facemesh, includes blazeface and iris
const faceRes = [];
if (config.face.enabled) {
timeStamp = performance.now();
timeStamp = now();
tf.engine().startScope();
const faces = await models.facemesh.estimateFaces(input, config.face);
perf.face = Math.trunc(performance.now() - timeStamp);
perf.face = Math.trunc(now() - timeStamp);
for (const face of faces) {
// is something went wrong, skip the face
if (!face.image || face.image.isDisposedInternal) {
log('face object is disposed:', face.image);
continue;
}
// run ssr-net age & gender, inherits face from blazeface
timeStamp = performance.now();
timeStamp = now();
const ssrData = (config.face.age.enabled || config.face.gender.enabled) ? await ssrnet.predict(face.image, config) : {};
perf.agegender = Math.trunc(performance.now() - timeStamp);
perf.agegender = Math.trunc(now() - timeStamp);
// run emotion, inherits face from blazeface
timeStamp = performance.now();
timeStamp = now();
const emotionData = config.face.emotion.enabled ? await emotion.predict(face.image, config) : {};
perf.emotion = Math.trunc(performance.now() - timeStamp);
perf.emotion = Math.trunc(now() - timeStamp);
face.image.dispose();
// calculate iris distance
// iris: array[ bottom, left, top, right, center ]