Spaces:
Sleeping
Sleeping
File size: 21,424 Bytes
5d92054 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 |
<!DOCTYPE html>
<html lang="en">
<head>
<meta charset="UTF-8">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>Real-Time Image Processing API Documentation</title>
<script src="https://cdn.tailwindcss.com"></script>
<link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/swagger-ui/4.18.3/swagger-ui.min.css">
<style>
body {
font-family: -apple-system, BlinkMacSystemFont, 'Segoe UI', Roboto, Helvetica, Arial, sans-serif;
margin: 0;
padding: 0;
color: #333;
}
.container {
max-width: 1200px;
margin: 0 auto;
padding: 20px;
}
header {
background-color: #252f3f;
color: white;
padding: 20px;
box-shadow: 0 2px 4px rgba(0,0,0,0.1);
}
header h1 {
margin: 0;
font-size: 2em;
}
header p {
margin-top: 10px;
opacity: 0.8;
}
.endpoint-cards {
display: flex;
flex-wrap: wrap;
gap: 20px;
margin-top: 30px;
}
.endpoint-card {
background-color: white;
border-radius: 8px;
box-shadow: 0 2px 10px rgba(0,0,0,0.1);
padding: 20px;
flex: 1 1 300px;
transition: transform 0.2s, box-shadow 0.2s;
}
.endpoint-card:hover {
transform: translateY(-5px);
box-shadow: 0 5px 15px rgba(0,0,0,0.15);
}
.http-endpoint {
border-left: 5px solid #38a169;
}
.ws-endpoint {
border-left: 5px solid #3182ce;
}
.method {
display: inline-block;
padding: 5px 10px;
border-radius: 4px;
font-weight: bold;
margin-right: 10px;
}
.post {
background-color: #38a169;
color: white;
}
.ws {
background-color: #3182ce;
color: white;
}
.endpoint-title {
font-size: 1.2em;
margin-bottom: 15px;
display: flex;
align-items: center;
}
.section {
margin-top: 40px;
margin-bottom: 30px;
}
h2 {
border-bottom: 1px solid #eee;
padding-bottom: 10px;
color: #252f3f;
}
.code {
background-color: #f7fafc;
border-radius: 4px;
padding: 15px;
font-family: monospace;
overflow-x: auto;
margin: 15px 0;
}
.parameter-table, .response-table {
width: 100%;
border-collapse: collapse;
margin: 15px 0;
}
.parameter-table th, .parameter-table td,
.response-table th, .response-table td {
text-align: left;
padding: 10px;
border-bottom: 1px solid #eee;
}
.parameter-table th, .response-table th {
background-color: #f7fafc;
}
.try-it {
margin-top: 30px;
padding-top: 30px;
border-top: 1px solid #eee;
}
.swagger-ui .wrapper { max-width: 100%; }
#swagger-ui {
margin-top: 30px;
border: 1px solid #eee;
border-radius: 8px;
overflow: hidden;
}
.info-box {
background-color: #ebf8ff;
border-left: 5px solid #3182ce;
padding: 15px;
margin: 20px 0;
border-radius: 4px;
}
.response-example {
background-color: #f0fff4;
border-left: 5px solid #38a169;
padding: 15px;
border-radius: 4px;
margin-top: 20px;
}
/* Updated tabs styles */
.tabs {
display: flex;
margin-top: 30px;
border-bottom: 1px solid #e2e8f0;
align-items: center;
}
.tab {
padding: 10px 20px;
cursor: pointer;
border-bottom: 2px solid transparent;
transition: all 0.2s ease;
}
.tab.active {
border-bottom: 2px solid #3182ce;
color: #3182ce;
font-weight: bold;
}
/* New try-button styles */
.try-button {
margin-left: auto;
display: flex;
align-items: center;
padding: 10px 15px;
font-size: 14px;
font-weight: bold;
border-radius: 4px;
background-color: #4299e1;
color: white;
text-decoration: none;
border: none;
transition: background-color 0.2s;
}
.try-button:hover {
background-color: #3182ce;
}
.try-button svg {
margin-left: 8px;
height: 16px;
width: 16px;
}
.tab-content {
display: none;
padding: 20px 0;
}
.tab-content.active {
display: block;
}
button {
background-color: #4299e1;
color: white;
border: none;
padding: 10px 15px;
border-radius: 4px;
cursor: pointer;
font-weight: bold;
transition: background-color 0.2s;
}
button:hover {
background-color: #3182ce;
}
</style>
</head>
<body>
<header>
<div class="container">
<h1>Advanced Driver Vision Assistance with Near Collision Estimation System</h1>
<p>API for object detection, depth estimation, and distance prediction using computer vision models</p>
</div>
</header>
<div class="container">
<section class="section">
<h2>Overview</h2>
<p>This API provides access to advanced computer vision models for real-time image processing. It leverages:</p>
<ul>
<li><strong>DETR (DEtection TRansformer)</strong> - For accurate object detection</li>
<li><strong>GLPN (Global-Local Path Networks)</strong> - For depth estimation</li>
<li><strong>LSTM Model</strong> - For Z-location prediction</li>
</ul>
<p>The API supports both HTTP and WebSocket protocols:</p>
<div class="endpoint-cards">
<div class="endpoint-card http-endpoint">
<div class="endpoint-title">
<span class="method post">POST</span>
<span>/api/predict</span>
</div>
<p>Process a single image via HTTP request</p>
</div>
<div class="endpoint-card ws-endpoint">
<div class="endpoint-title">
<span class="method ws">WS</span>
<span>/ws/predict</span>
</div>
<p>Stream images for real-time processing via WebSocket</p>
</div>
</div>
</section>
<div class="tabs">
<div class="tab active" onclick="switchTab('http-api')">HTTP API</div>
<div class="tab" onclick="switchTab('websocket-api')">WebSocket API</div>
<div class="tab">
<a href="./try_page" class="ml-2 inline-flex items-center px-4 py-2 border border-transparent text-sm font-medium rounded-md shadow-sm text-white bg-blue-600 hover:bg-blue-700 focus:outline-none focus:ring-2 focus:ring-offset-2 focus:ring-blue-500 transition-all duration-200">
Try it
<svg xmlns="http://www.w3.org/2000/svg" class="ml-1 h-4 w-4" fill="none" viewBox="0 0 24 24" stroke="currentColor">
<path stroke-linecap="round" stroke-linejoin="round" stroke-width="2" d="M14 5l7 7m0 0l-7 7m7-7H3" />
</svg>
</a>
</div>
</div>
<div id="http-api" class="tab-content active">
<section class="section">
<h2>HTTP API Reference</h2>
<h3>POST /api/predict</h3>
<p>Process a single image for object detection, depth estimation, and distance prediction.</p>
<h4>Request</h4>
<p><strong>Content-Type:</strong> multipart/form-data</p>
<table class="parameter-table">
<tr>
<th>Parameter</th>
<th>Type</th>
<th>Required</th>
<th>Description</th>
</tr>
<tr>
<td>file</td>
<td>File</td>
<td>Yes</td>
<td>The image file to process (JPEG, PNG)</td>
</tr>
</table>
<h4>Request Example</h4>
<div class="code">
# Python example using requests
import requests
url = "http://localhost:8000/api/predict"
files = {"file": open("image.jpg", "rb")}
response = requests.post(url, files=files)
data = response.json()
print(data)
</div>
<h4>Response</h4>
<p>Returns a JSON object containing:</p>
<table class="response-table">
<tr>
<th>Field</th>
<th>Type</th>
<th>Description</th>
</tr>
<tr>
<td>objects</td>
<td>Array</td>
<td>Array of detected objects with their properties</td>
</tr>
<tr>
<td>objects[].class</td>
<td>String</td>
<td>Class of the detected object (e.g., 'car', 'person')</td>
</tr>
<tr>
<td>objects[].distance_estimated</td>
<td>Number</td>
<td>Estimated distance of the object</td>
</tr>
<tr>
<td>objects[].features</td>
<td>Object</td>
<td>Features used for prediction (bounding box, depth information)</td>
</tr>
<tr>
<td>frame_id</td>
<td>Number</td>
<td>ID of the processed frame (0 for HTTP requests)</td>
</tr>
<tr>
<td>timings</td>
<td>Object</td>
<td>Processing time metrics for each step</td>
</tr>
</table>
<div class="response-example">
<h4>Response Example</h4>
<pre class="code">
{
"objects": [
{
"class": "car",
"distance_estimated": 15.42,
"features": {
"xmin": 120.5,
"ymin": 230.8,
"xmax": 350.2,
"ymax": 480.3,
"mean_depth": 0.75,
"depth_mean_trim": 0.72,
"depth_median": 0.71,
"width": 229.7,
"height": 249.5
}
},
{
"class": "person",
"distance_estimated": 8.76,
"features": {
"xmin": 450.1,
"ymin": 200.4,
"xmax": 510.8,
"ymax": 380.2,
"mean_depth": 0.58,
"depth_mean_trim": 0.56,
"depth_median": 0.55,
"width": 60.7,
"height": 179.8
}
}
],
"frame_id": 0,
"timings": {
"decode_time": 0.015,
"models_time": 0.452,
"process_time": 0.063,
"json_time": 0.021,
"total_time": 0.551
}
}
</pre>
</div>
<h4>HTTP Status Codes</h4>
<table class="response-table">
<tr>
<th>Status Code</th>
<th>Description</th>
</tr>
<tr>
<td>200</td>
<td>OK - Request was successful</td>
</tr>
<tr>
<td>400</td>
<td>Bad Request - Empty file or invalid format</td>
</tr>
<tr>
<td>500</td>
<td>Internal Server Error - Processing error</td>
</tr>
</table>
</section>
</div>
<div id="websocket-api" class="tab-content">
<section class="section">
<h2>WebSocket API Reference</h2>
<h3>WebSocket /ws/predict</h3>
<p>
Stream images for real-time processing and get instant results.
Ideal for video feeds and applications requiring continuous processing.
</p>
<div class="info-box">
<p><strong>Note:</strong> WebSocket offers better performance for real-time applications. Use this endpoint for processing video feeds or when you need to process multiple images in rapid succession.</p>
</div>
<h4>Connection</h4>
<div class="code">
# JavaScript example
const socket = new WebSocket('ws://localhost:8000/ws/predict');
socket.onopen = function(e) {
console.log('Connection established');
};
socket.onmessage = function(event) {
const response = JSON.parse(event.data);
console.log('Received:', response);
};
socket.onclose = function(event) {
console.log('Connection closed');
};
</div>
<h4>Sending Images</h4>
<p>Send binary image data directly over the WebSocket connection:</p>
<div class="code">
// JavaScript example: Sending an image from canvas or file
function sendImageFromCanvas(canvas) {
canvas.toBlob(function(blob) {
const reader = new FileReader();
reader.onload = function() {
socket.send(reader.result);
};
reader.readAsArrayBuffer(blob);
}, 'image/jpeg');
}
// Or from input file
fileInput.onchange = function() {
const file = this.files[0];
const reader = new FileReader();
reader.onload = function() {
socket.send(reader.result);
};
reader.readAsArrayBuffer(file);
};
</div>
<h4>Response Format</h4>
<p>The WebSocket API returns the same JSON structure as the HTTP API, with incrementing frame_id values.</p>
<div class="response-example">
<h4>Response Example</h4>
<pre class="code">
{
"objects": [
{
"class": "car",
"distance_estimated": 14.86,
"features": {
"xmin": 125.3,
"ymin": 235.1,
"xmax": 355.7,
"ymax": 485.9,
"mean_depth": 0.77,
"depth_mean_trim": 0.74,
"depth_median": 0.73,
"width": 230.4,
"height": 250.8
}
}
],
"frame_id": 42,
"timings": {
"decode_time": 0.014,
"models_time": 0.445,
"process_time": 0.061,
"json_time": 0.020,
"total_time": 0.540
}
}
</pre>
</div>
</section>
</div>
<div id="try-it" class="tab-content">
<section class="section">
<h2>Try The API</h2>
<p>You can test the API directly using the interactive Swagger UI below:</p>
<div id="swagger-ui"></div>
<h3>Simple WebSocket Client</h3>
<p>Upload an image to test the WebSocket endpoint:</p>
<div>
<input type="file" id="wsFileInput" accept="image/*">
<button id="connectWsButton">Connect to WebSocket</button>
<button id="disconnectWsButton" disabled>Disconnect</button>
</div>
<div>
<p><strong>Status: </strong><span id="wsStatus">Disconnected</span></p>
<p><strong>Last Response: </strong></p>
<pre id="wsResponse" class="code" style="max-height: 300px; overflow-y: auto;"></pre>
</div>
</section>
</div>
</div>
<script src="https://cdnjs.cloudflare.com/ajax/libs/swagger-ui/4.18.3/swagger-ui-bundle.js"></script>
<script>
// Handle tab switching
function switchTab(tabId) {
document.querySelectorAll('.tab').forEach(tab => tab.classList.remove('active'));
document.querySelectorAll('.tab-content').forEach(content => content.classList.remove('active'));
document.querySelector(`.tab[onclick="switchTab('${tabId}')"]`).classList.add('active');
document.getElementById(tabId).classList.add('active');
}
// Initialize Swagger UI
window.onload = function() {
SwaggerUIBundle({
url: "/api/openapi.json",
dom_id: '#swagger-ui',
presets: [
SwaggerUIBundle.presets.apis,
SwaggerUIBundle.SwaggerUIStandalonePreset
],
layout: "BaseLayout",
deepLinking: true
});
// WebSocket client setup
let socket = null;
const connectButton = document.getElementById('connectWsButton');
const disconnectButton = document.getElementById('disconnectWsButton');
const fileInput = document.getElementById('wsFileInput');
const statusElement = document.getElementById('wsStatus');
const responseElement = document.getElementById('wsResponse');
connectButton.addEventListener('click', () => {
if (socket) {
socket.close();
}
const wsUrl = window.location.protocol === 'https:'
? `wss://${window.location.host}/ws/predict`
: `ws://${window.location.host}/ws/predict`;
socket = new WebSocket(wsUrl);
socket.onopen = function() {
statusElement.textContent = 'Connected';
statusElement.style.color = 'green';
connectButton.disabled = true;
disconnectButton.disabled = false;
};
socket.onmessage = function(event) {
const response = JSON.parse(event.data);
responseElement.textContent = JSON.stringify(response, null, 2);
};
socket.onclose = function() {
statusElement.textContent = 'Disconnected';
statusElement.style.color = 'red';
connectButton.disabled = false;
disconnectButton.disabled = true;
socket = null;
};
socket.onerror = function(error) {
statusElement.textContent = 'Error: ' + error.message;
statusElement.style.color = 'red';
};
});
disconnectButton.addEventListener('click', () => {
if (socket) {
socket.close();
}
});
fileInput.addEventListener('change', () => {
if (!socket || socket.readyState !== WebSocket.OPEN) {
alert('Please connect to WebSocket first');
return;
}
const file = fileInput.files[0];
if (!file) return;
const reader = new FileReader();
reader.onload = function() {
socket.send(reader.result);
};
reader.readAsArrayBuffer(file);
});
};
</script>
</body>
</html> |