1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
|
<!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/4.x/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>
|
