1<!doctype html> 2<!--[if IE 7 ]> <html lang="en-gb" class="isie ie7 oldie no-js"> <![endif]--> 3<!--[if IE 8 ]> <html lang="en-gb" class="isie ie8 oldie no-js"> <![endif]--> 4<!--[if IE 9 ]> <html lang="en-gb" class="isie ie9 no-js"> <![endif]--> 5<!--[if (gt IE 9)|!(IE)]><!--> 6<html lang="en-gb" class="no-js"> 7<!--<![endif]--> 8<head> 9 <meta charset="utf-8"> 10 <meta name="viewport" content="width=device-width, initial-scale=1, maximum-scale=1"> 11 <!--[if lt IE 9]> 12 <meta http-equiv="X-UA-Compatible" content="IE=edge,chrome=1"> 13 <![endif]--> 14 <title>Mohamed Helala website</title> 15 <meta name="description" content=""> 16 <meta name="author" content="WebThemez"> 17 <!--[if lt IE 9]> 18
18<script src="http://html5shim.googlecode.com/svn/trunk/html5.js"></script>
18 19 <![endif]--> 20 <!--[if lte IE 8]> 21
21<script type="text/javascript" src="http://explorercanvas.googlecode.com/svn/trunk/excanvas.js"></script>
21 22 <![endif]--> 23 <link rel="stylesheet" href="css/bootstrap-cust.css" /> 24 <link rel="stylesheet" type="text/css" href="css/isotope.css" media="screen" /> 25 <link rel="stylesheet" href="js/fancybox/jquery.fancybox.css" type="text/css" media="screen" /> 26 <link rel="stylesheet" type="text/css" href="css/da-slider.css" /> 27 <!-- Owl Carousel Assets --> 28 <link href="js/owl-carousel/owl.carousel.css" rel="stylesheet"> 29 <link rel="stylesheet" href="css/styles.css" /> 30 31</head> 32 33<body> 34 <header class="header"> 35 <div class="container"> 36 <nav class="navbar navbar-inverse" role="navigation"> 37 <div class="navbar-header"> 38 <button type="button" id="nav-toggle" class="navbar-toggle" data-toggle="collapse" data-target="#main-nav"> 39 <span class="sr-only">Toggle navigation</span> 40 <span class="icon-bar"></span> 41 <span class="icon-bar"></span> 42 <span class="icon-bar"></span> 43 </button> 44 <a href="#" class="navbar-brand scroll-top logo"><b>Mohamed Helala</b></a> 45 </div> 46 <!--/.navbar-header--> 47 <div id="main-nav" class="collapse navbar-collapse"> 48 <ul class="nav navbar-nav" id="mainNav"> 49 <li class="active"><a href="#home" class="scroll-link">Home</a></li> 50 <li><a href="#aboutMe" class="scroll-link">About Me</a></li> 51 <li><a href="#projects" class="scroll-link">Projects</a></li> 52 <li><a href="#publications" class="scroll-link">Publications</a></li> 53 <li><a href="#activities-awards" class="scroll-link">Activities & Awards</a></li> 54 </ul> 55 </div> 56 <!--/.navbar-collapse--> 57 </nav> 58 <!--/.navbar--> 59 </div> 60 <!--/.container--> 61 </header> 62 <!--/.header--> 63 <div id="#top"> 64 <div id='snav' class='en'> 65 <ul> 66 <li> <a href='http://mhelala.blogspot.ca/'> <i class="fa fa-bold"></i> <span>Blog</span> </a> </li> 67 <li> <a href='https://twitter.com/Mohamed_Helala'> <i class="fa fa-twitter"></i> <span>Twitter</span> </a> </li> 68 <li> <a href='https://github.com/mohamed-helala'> <i class="fa fa-github"></i> <span>Git</span> </a> </li> 69 <li> <a href='https://plus.google.com/114765445236633498280/posts'> <i class="fa fa-google-plus"></i> <span>Google Plus</span> </a> </li> 70 <li> <a href='http://www.linkedin.com/pub/mohamed-helala/71/503/681'> <i class="fa fa-linkedin"></i> <span>Linkedin</span> </a> </li> 71 <li> <a href='http://scholar.google.ca/citations?user=Dw5bcNQAAAAJ&hl=en'> <i class="fa fa-book"></i> <span>Google Scholar</span> </a> </li> 72 </ul> 73 </div> 74 </div> 75 <section id="home"> 76 <div class="banner-container"> 77 <!--<img src="images/banner-bg.jpg" alt="banner" />--> 78 <div class="empty-container"></div> 79 <div class="container banner-content"> 80 <div id="da-slider" class="da-slider"> 81 <div class="da-slide"> 82 <h2>Scalable Vision Pipelines</h2> 83 <p><a href="javascript:customScripts.scroll('#stream')">A formal stream algebra for efficient scalable computer vision pipelines. 84 </a></p> 85 <div class="da-img"> <img src="img/stream.png" alt="stream" /></div> 86 </div> 87 <div class="da-slide"> 88 <h2>Image Retrieval</h2> 89 <p><a href="http://mytomcatapp-helala.rhcloud.com/ImageSearch/">Try our demo for content based image retrieval.</a></p> 90 <div class="da-img"> <img src="img/image-ret.png" alt="image retrieval demo" /></div> 91 </div> 92 <div class="da-slide"> 93 <h2>Traffic Video Survillance</h2> 94 <p><a href="javascript:customScripts.scroll('#traffic')">Automatic road and lane boundary detection.</a></p> 95 <div class="da-img"> <img src="img/traffic.png" alt="traffic" /></div> 96 </div> 97 <div class="da-slide"> 98 <h2>Image Correspondance</h2> 99 <p><a href="javascript:customScripts.scroll('#stereo')">Developing cost subvolume filtering for solving pixel labeling problems</a></p> 100 <div class="da-img"> <img src="img/imcoress.png" alt="traffic" /></div> 101 </div> 102 <div class="da-slide"> 103 <h2>Image Mosaicking</h2> 104 <p><a href="javascript:customScripts.scroll('#mosaics')">Multi-view mosaics from near ground aerial imagery</a></p> 105 <div class="da-img"> <img src="img/mosaic.png" alt="traffic" /></div> 106 </div> 107 <!-- <nav class="da-arrows">
108 <span class="da-arrows-prev"></span> 109 <span class="da-arrows-next"></span> 110 </nav> --> 111 </div> 112 </div> 113 </div> 114 </section> 115 <section id="introText"> 116 <div class="parlex-back"> 117 <div class=" text-center"> 118 <h2>There are no negatives in life, only challenges to overcome that will make you stronger.</h2><h3>-Eric Bates</h3> 119 </div> 120 <!--/.container--> 121 </div> 122 123 </section> 124 <!--About--> 125 <section id="aboutMe" class="secPad titlebox"> 126 <div class="container"> 127 <div class="row"> 128 <!-- item --> 129 <div class="col-md-3 text-center tileBox"> 130 <div class="txtHead"> 131 <h3><i class="fa fa-edit"></i><span class="id-color">Contact</span></h3></div> 132 <p>Mohamed A. Helala<br> 133 PhD Student in Computer Science, Faculty of Science, UOIT<br> 134 <abbr title="Phone">P:</abbr> (905) 721-8668 <abbr title="extention">ext:</abbr> 2387<br> 135 <a href="mailto:#">mohamed.helala "at" uoit "dot" ca</a></p> 136 </div> 137 <!-- end: --> 138 139 <!-- item --> 140 <div class="col-md-3 text-center tileBox"> 141 <div class="txtHead"> 142 <h3><i class="fa fa-gears"></i> <span class="id-color">Industry</span></h3></div> 143 <p class="text-left">(2007-2011) A Software engineer in <a href="http://www.hoiaste.com/index.php"><span>HOI/Aste</span></a> R&D department. I developed a DXF engine for generating Autocad files and a software system for automatic generation of drawings.</p> 144 </div> 145 <!-- end: --> 146 147 <!-- item --> 148 <div class="col-md-3 text-center tileBox"> 149 <div class="txtHead"> 150 <h3><i class="fa fa-lightbulb-o"></i><span class="id-color">Research</span></h3></div> 151 <p class="text-left">(2011-now) A PhD Student in the UOIT computer vision group with <a href="http://faculty.uoit.ca/qureshi/"><span>Dr. Fasial Qureshi</span></a> and <a href="http://leda.science.uoit.ca/kenpu/"><span>Dr. Ken Pu</span></a>. My interests lie in computer vision and data stream processing.</p> 152 </div> 153 <!-- end: --> 154 155 <!-- item --> 156 <div class="col-md-3 text-center tileBox"> 157 <div class="txtHead"> 158 <h3><i class="fa fa-edit"></i><span class="id-color">Teaching</span></h3></div> 159 <p>I worked as TA in UOIT for several courses such as <a href="http://leda.science.uoit.ca/teaching/compiler/index">compilers</a>, <a href="http://leda.science.uoit.ca/teaching/pl/index">programming languages</a>, <a href="http://leda.science.uoit.ca/teaching/sysdev/index">system development and Integration</a>, and software design and analysis.</p> 160 </div> 161 <!-- end: --> 162 163 </div> 164 165 <div class="container"> 166 <div class="row"> 167 <div id="nt-example2-container" class="col-md-4 centered nt-example2-face"> 168 <ul id="nt-example2"> 169 <li data-infos="I attended ACCV 2014 in NUS, Singapore and presented the paper 'Accelerating Cost Volume Filtering Using Salient Subvolumes and Robust Occlusion Handling'. This paper presents our Accelerated Cost Volume Filtering (ACF) method, which shows speedup over the traditional Cost Volume Filtering (CF) method."> 170 <i class="fa fa-fw fa-play state"></i> 171 <span imgdata="img/accv14.png"></span>Poster in ACCV 2014. 172 </li> 173 <li data-infos="I presented the paper 'Towards Efficient Feedback Control in Streaming Computer Vision Pipelines' in the UCCV 2014 workshop (co-located with ACCV 2014). This paper shows that our stream algebra framework can naturally describe feedback control in computer vision pipelines."> 174 <i class="fa fa-fw fa-play state"></i> 175 <span imgdata="img/uccv14.png"></span>Presentation in UCCV 2014. 176 </li> 177 <li data-infos="The paper 'A Stream Algebra for Computer Vision Pipelines is presented in the VSM 2014 workshop (co-located with CVPR 2014). This paper presents the first formal stream algebra that provides a mathematical description of vision pipelines and depicts the distributed manipulation of image and video streams."> 178 <i class="fa fa-fw fa-play state"></i> 179 <span imgdata="img/vsm14.png"></span>Presentation in VSM 2014. 180 </li> 181 <li data-infos="I released an online demo for Content Based Image Retrieval (CBIR). This demo uses keyword search to retrieve a relevant set of images, then user can select a query image and a set of features to re-rank results based on similarity."> 182 <i class="fa fa-fw fa-play state"></i> 183 <span imgdata="img/cbirsearch.png">CBIR Online Demo. 184 </li> 185 </ul> 186 <div class="nt-example2-face nt-example2-panel centered"> 187 <i class="fa fa-arrow-left" id="nt-example2-prev"></i> 188 <i class="fa fa-arrow-right" id="nt-example2-next"></i> 189 </div>
190 </div> 191 <div id="nt-example2-infos-container" class = "col-md-8 nt-example2-face"> 192 <div id="nt-example2-infos-triangle"></div> 193 <div id="nt-example2-infos" class="row"> 194 <div class="col-xs-4 centered"> 195 <img src="img/accv14.png" class="infos-image"> 196 </div> 197 <div class="col-xs-8"> 198 <div class="infos-text"> I attended ACCV 2014 in NUS, Singapore and presented the paper 'Accelerating Cost Volume Filtering Using Salient Subvolumes and Robust Occlusion Handling'. This paper presents our Accelerated Cost Volume Filtering (ACF) method, which shows speedup over the traditional Cost Volume Filtering (CF) method. </div> 199 </div> 200 </div> 201 </div> 202 </div> 203 </div> 204 205 </div> 206 </section> 207 <!--Quote--> 208 <section id="quote" class="bg-parlex"> 209 <div class="parlex-back"> 210 <div class="container text-center"> 211 <h2>Research is formalized curiosity. It is poking and prying with a purpose.</h2><h3>-Zora Neale Hurston</h3> 212 </div>. 213 214 <!--/.container--> 215 </div> 216 </section> 217 <!--Experience--> 218 <section id="projects" class="secPad"> 219 <div class="container"> 220 <div class="heading text-center"> 221 <!-- Heading --> 222 <h2>Professional Activities</h2> 223 <p>A timeline for my research activities and developed projects.</p> 224 </div> 225 <div id="timeline"> 226 <div class="row timeline-movement timeline-movement-top"> 227 <div class="timeline-badge timeline-future-movement"> 228 <a href="#"> 229 <span class="glyphicon glyphicon-plus"></span> 230 </a> 231 </div> 232 <div class="timeline-badge timeline-filter-movement"> 233 <a href="#"> 234 <span class="glyphicon glyphicon-time"></span> 235 </a> 236 </div> 237 238 </div> 239 <div id="dyn-rec" class="row timeline-movement"> 240 241 <div class="timeline-badge"> 242 <span class="timeline-balloon-date-day">Jan</span> 243 <span class="timeline-balloon-date-month">2015</span> 244 </div> 245 246 247 <div class="col-sm-6 timeline-item"> 248 <div class="row"> 249 <div class="col-sm-11"> 250 <div class="timeline-panel credits"> 251 <ul class="timeline-panel-ul"> 252 <li><span class="importo">Demo</span></li> 253 <li><span class="causale"> 254 <li><span class="causale"> 255 <div class="embed-responsive embed-responsive-16by9"> 256 <iframe class="embed-responsive-item" src="https://www.youtube.com/embed/eUPf2FJK3ck" allowfullscreen></iframe> 257 </div></span></li> 258 <li class="text-left"><span>Example of running our traffic pipeline on an input video sequence. The pipeline copies the input stream into different stream processing branches. The top view window is for the output branch and the bottom one is for the edges detected by the edge clustering branch. The chart displays the average latency (in red) and period (in green, throughput = 1/period) for the edge clustering branch. The latency is minimized dynamically at runtime by applying load balancing on the clustering branch. Stop the video before and after 00:17 (load balancing) to see the delay between the two branches (difference between the two frame numbers shown in red). </span> </li> 259 <li><p><small class="text-muted"> </small></p> </li> 260 </ul> 261 </div> 262 263 </div> 264 </div> 265 </div> 266 267 <div class="col-sm-6 timeline-item"> 268 <div class="row"> 269 <div class="col-sm-offset-1 col-sm-11"> 270 <div class="timeline-panel debits"> 271 <ul class="timeline-panel-ul"> 272 <li><span class="importo">Dynamic Reconfiguration of Streaming Computer Vision Pipelines</span></li> 273 <li><span class="causale"> We developed a framework for our formal stream algebra and implemented dynamic reconfiguration to select the best execution plan for a given computer vision pipeline. This is currently accomplished by applying load balancing on a linear pipeline of tasks to minimize the pipeline latency at a predefined value of throughput.</span> </li> 274 <a href="javascript:customScripts.scroll('#cvpr14')">[Reference 1]</a> 275 <a href="javascript:customScripts.scroll('#avss12')">[Reference 2]</a> 276 <li><p><small class="text-muted"> 1/1/2015 - 1/03/2015</small></p> </li> 277 </ul> 278 </div> 279 </div> 280 </div> 281 </div> 282 </div>
283 <div id="feedback-ctrl" class="row timeline-movement"> 284 285 <div class="timeline-badge"> 286 <span class="timeline-balloon-date-day">May</span> 287 <span class="timeline-balloon-date-month">2014</span> 288 </div> 289 290 291 <div class="col-sm-6 timeline-item"> 292 <div class="row"> 293 <div class="col-sm-11"> 294 <div class="timeline-panel credits"> 295 <ul class="timeline-panel-ul"> 296 <li><span class="importo">Demo</span></li> 297 <li><span class="causale"> 298 <li><span class="causale"> 299 <div class="embed-responsive embed-responsive-16by9"> 300 <iframe class="embed-responsive-item" src="https://www.youtube.com/embed/gDfvdXNgozI" allowfullscreen></iframe> 301 </div></span></li> 302 <li class="text-left"><span>We copy an input traffic video stream into two streaming pipeline branches. The first branch contains a SIFT keypoint extraction task to generate a set of SIFT keypoints for each frame. The second branch outputs a list of edges for each frame using an edge detection task. We define for each task, a threshold to control the number of output kepoints and edges. 303 A manual change is performed to each thresold and feedback control will automatically tune the thresold value to maintain a predifined output number of edges/points.</span> </li> 304 <li><p><small class="text-muted"> UCCV 2014</small></p> </li> 305 </ul> 306 </div> 307 308 </div> 309 </div> 310 </div> 311 312 <div class="col-sm-6 timeline-item"> 313 <div class="row"> 314 <div class="col-sm-offset-1 col-sm-11"> 315 <div class="timeline-panel debits"> 316 <ul class="timeline-panel-ul"> 317 <li><span class="importo">Feedback Control in Streaming Computer Vision Pipelines</span></li> 318 <li><span class="causale"> Stream processing is currently an active research direction in 319 computer vision. This is due to the existence of many computer 320 vision algorithms that can be expressed as a pipeline of operations, 321 and the increasing demand for online systems that process image and 322 video streams. Recently, a formal stream algebra has been proposed 323 as an abstract framework that mathematically describes computer 324 vision pipelines. The algebra defines a set of concurrent operators 325 that can describe a pipeline of vision tasks, with image and video 326 streams as operands. In this paper, we extend this algebra framework 327 by developing a formal and abstract description of feedback control 328 in computer vision pipelines. Feedback control allows vision 329 pipelines to perform adaptive parameter selection, iterative 330 optimization and performance tuning. We show how our extension can 331 describe feedback control in the vision pipelines of two 332 state-of-the-art techniques.</span> </li> 333 <a href="javascript:customScripts.scroll('#uccv14')">[Reference]</a> 334 <li><p><small class="text-muted"> 15/5/2014 - 1/06/2014</small></p> </li> 335 </ul> 336 </div> 337 </div> 338 </div> 339 </div> 340 </div> 341 <div id="stereo" class="row timeline-movement"> 342 <div class="timeline-badge"> 343 <span class="timeline-balloon-date-day">Feb</span> 344 <span class="timeline-balloon-date-month">2014</span> 345 </div> 346 347 <div class="col-sm-6 timeline-item"> 348 <div class="row"> 349 <div class="col-sm-11"> 350 <div class="timeline-panel credits"> 351 <ul class="timeline-panel-ul"> 352 <li><span class="importo">Supplementary Video</span></li> 353 <li><span class="causale"> 354 <div class="embed-responsive embed-responsive-16by9"> 355 <iframe class="embed-responsive-item" src="http://www.youtube.com/embed/SxcOc7Y22GA" allowfullscreen></iframe> 356 </div></span></li> 357 <li><p><small class="text-muted"> ACCV 2014</small></p> </li> 358 </ul> 359 </div> 360 361 </div> 362 </div> 363 </div> 364 365 <div class="col-sm-6 timeline-item"> 366 <div class="row"> 367 <div class="col-sm-offset-1 col-sm-11"> 368 <div class="timeline-panel debits"> 369 <ul class="timeline-panel-ul"> 370 <li><span class="importo">Stereo Correspondence</span></li> 371 <li><span class="causale">We propose the Accelerated Cost Volume Filtering (ACF) method, which speeds up the traditional Cost Volume Filtering (CF) method. ACf identifies salient subvolumes in the cost volume. Filtering is restricted to these subvolumes, resulting in significant performance gains. We applied our method to disparity estimation from a stereo image pair and developed an occlusion handling method, which acts as a post-processing step that refines the disparity maps computed via filtering. Currently, we are exploring the use of slanted surfaces during the detection of salient subvolumes and we are implementing an efficie
371nt version of ACF for optical flow computation. </span> </li> 372 <a href="javascript:customScripts.scroll('#accv14')">[Reference]</a> 373 <li><p><small class="text-muted"> 18/02/2014 - 30/05/2014</small></p> </li> 374 </ul> 375 </div> 376 377 </div> 378 </div> 379 </div> 380 </div> 381 <div id="stream" class="row timeline-movement"> 382 383 <div class="timeline-badge"> 384 <span class="timeline-balloon-date-day">Jan</span> 385 <span class="timeline-balloon-date-month">2013</span> 386 </div> 387 388 389 <div class="col-sm-6 timeline-item"> 390 <div class="row"> 391 <div class="col-sm-11"> 392 <div class="timeline-panel credits"> 393 <ul class="timeline-panel-ul"> 394 <li><span class="importo">Implementing a Traffic Analysis Pipeline</span></li> 395 <li><span class="causale"><img src="img/traffic-pip.png" class="img-responsive"></span> </li> 396 <li><p><small class="text-muted"> 1/06/2013 - Present</small></p> </li> 397 </ul> 398 </div> 399 400 </div> 401 </div> 402 </div> 403 404 <div class="col-sm-6 timeline-item"> 405 <div class="row"> 406 <div class="col-sm-offset-1 col-sm-11"> 407 <div class="timeline-panel debits"> 408 <ul class="timeline-panel-ul"> 409 <li><span class="importo">Stream Algebra Framework</span></li> 410 <li><span class="causale"> We propose a formal stream algebra as an abstract framework that mathematically describes computer vision pipelines. The algebra defines a set of concurrent operators that can describe a pipeline of vision tasks, with image and video streams as operands. We also extend the algebra framework by developing a formal and abstract description of feedback control in computer vision pipelines. Currently, we are studying feedback control to perform adaptive parameter selection, iterative optimization and performance tuning.</span> </li> 411 <a href="javascript:customScripts.scroll('#cvpr14')">[Reference]</a> 412 <li><p><small class="text-muted"> 1/06/2013 - Present</small></p> </li> 413 </ul> 414 </div> 415 </div> 416 </div> 417 </div> 418 </div> 419 420 <!--due --> 421 <div id="mosaics" class="row timeline-movement"> 422 <div class="timeline-badge"> 423 <span class="timeline-balloon-date-day">May</span> 424 <span class="timeline-balloon-date-month">2012</span> 425 </div> 426 427 <div class="col-sm-6 timeline-item"> 428 <div class="row"> 429 <div class="col-sm-11"> 430 <div class="timeline-panel credits"> 431 <ul class="timeline-panel-ul"> 432 <li><span class="importo">Supplementary Video</span></li> 433 <li><span class="causale"> 434 <div class="embed-responsive embed-responsive-16by9"> 435 <iframe class="embed-responsive-item" src="http://www.youtube.com/embed/qZaElUp0Pc4" allowfullscreen></iframe> 436 </div> </span> </li> 437 <li><p><small class="text-muted">
437Creating view dependent mosaics</small></p> </li> 438 </ul> 439 </div> 440 441 </div> 442 </div> 443 </div> 444 445 <div class="col-sm-6 timeline-item"> 446 <div class="row"> 447 <div class="col-sm-offset-1 col-sm-11"> 448 <div class="timeline-panel debits"> 449 <ul class="timeline-panel-ul"> 450 <li><span class="importo">Video Mosaicing</span></li> 451 <li><span class="causale">We are developing new techniques for generating large-scale mosaics from near ground UAV videos. Such techniques should be able to handle several challenges such as the parallax effects of buildings toward camera motion, the generation of high-quality mosaics and the support of different camera motion models.</span> </li> 452 <a href="javascript:customScripts.scroll('#icdsc12')">[Reference]</a> 453 <li><p><small class="text-muted"> 1/05/2012 - 1/09/2012</small></p> </li> 454 </ul> 455 </div> 456 457 </div> 458 </div> 459 </div> 460 </div> 461 <div id="traffic" class="row timeline-movement"> 462 <div class="timeline-badge"> 463 <span class="timeline-balloon-date-day">Jan</span> 464 <span class="timeline-balloon-date-month">2012</span> 465 </div> 466 467 <div class="col-sm-6 timeline-item"> 468 <div class="row"> 469 <div class="col-sm-11"> 470 <div class="timeline-panel credits"> 471 <ul class="timeline-panel-ul"> 472 <li><span class="importo">Sample Results</span></li> 473 <li><span class="causale"><img src="img/road-detection.png" class="img-responsive"></span> </li> 474 <li><p><small class="text-muted">Road boundary detection using our traffic video analysis pipeline.</small></p> </li> 475 </ul> 476 </div> 477 478 </div> 479 </div> 480 </div> 481 482 <div class="col-sm-6 timeline-item"> 483 <div class="row"> 484 <div class="col-sm-offset-1 col-sm-11"> 485 <div class="timeline-panel debits"> 486 <ul class="timeline-panel-ul"> 487 <li><span class="importo">Traffic Survillance</span></li> 488 <li><span class="causale">We are studying automatic techniques for analyzing traffic video under challenging environmental conditions. We addressed the problem of automatic road and lane boundary detection under severe vision scenarios, such as partially occluded roads and unlit highways. Currently, we are addressing the problems of measuring accurate traffic statistics, identify ongoing and incoming lanes, dynamic camera calibration, and adaption of view changes due to wind or human operators.</span> </li> 489 <a href="javascript:customScripts.scroll('#avss12')">[Reference]</a> 490 <li><p><small class="text-muted"> 1/01/2012 - 30/05/2012 </small></p> </li> 491 </ul> 492 </div> 493 494 </div> 495 </div> 496 </div> 497 </div> 498 <div id="cbir" class="row timeline-movement"> 499 <div class="timeline-badge">
500 <span class="timeline-balloon-date-day">Jan</span> 501 <span class="timeline-balloon-date-month">2010</span> 502 </div> 503 <div class="col-sm-6 timeline-item"> 504 <div class="row"> 505 <div class="col-sm-11"> 506 <div class="timeline-panel credits"> 507 <ul class="timeline-panel-ul"> 508 <li><span class="importo">Online Demonstration</span></li> 509 <li><span class="causale"><a href="http://mytomcatapp-helala.rhcloud.com/ImageSearch"><img src="img/image-ret.png" class="img-responsive"></a><a href="http://mytomcatapp-helala.rhcloud.com/ImageSearch">Try it now</a></span> </li> 510 <li><p><small class="text-muted">Re-ranking keyword search results using a query image.</small></p> </li> 511 </ul> 512 </div> 513 514 </div> 515 </div> 516 </div> 517 518 <div class="col-sm-6 timeline-item"> 519 <div class="row"> 520 <div class="col-sm-offset-1 col-sm-11"> 521 <div class="timeline-panel debits"> 522 <ul class="timeline-panel-ul"> 523 <li><span class="importo">Content Based Image Retrieval (CBIR)</span></li> 524 <li><span class="causale">During my master work, I studied CBIR, where I addressed broad domain image search and retrieval in large image collections by evaluating recent approaches and developing new techniques to provide more precise image description and better retrieval accuracy.</span> </li> 525 <a href="javascript:customScripts.scroll('#ijcsi12')">[Reference]</a> 526 <li><p><small class="text-muted"> 1/01/2010 - 1/11/2010</small></p> </li> 527 </ul> 528 </div> 529 530 </div> 531 </div> 532 </div> 533 </div> 534 </div> 535 </div> 536 </section> 537 538 <!--Contact --> 539 <section id="publications" class="secPad"> 540 <div class="container"> 541 <div class="heading text-center"> 542 <!-- Heading --> 543 <h2>Publications</h2> 544 </div> 545 <div class="row mrgn30 ref-panel"> 546 <div class="list2"> 547 <ol> 548 <li><p> 549 <a href="#" id="icdsc16" class="papertitle">"Fast Estimation of Large Displacement Optical Flow Using Dominant Motion Patterns & Sub-Volume PatchMatch Filtering."</a>, 550 <span class="paperauth">Mohamed A. Helala</span>, 551 Faisal Z. Qureshi, 552 <span class="papervenue">14th Conference on Computer and Robot Vision (CRV)</span>, 553 Edmonton, Alberta, Canada, May 2017 (Best Paper Award). 554 </p></li> 555 <li><p> 556 <a href="http://vclab.ca/wp-content/papercite-data/pdf/16-icdsc-c.pdf" id="icdsc16" class="papertitle">"A Formal Algebra Implementation for Distributed Image and Video Stream Processing."</a>, 557 <span class="paperauth">Mohamed A. Helala</span>, 558 Ken Q. Pu, Faisal Z. Qureshi, 559 <span class="papervenue">Proc.10th ACM/IEEE International Conference on Distributed Smart Cameras (ICDSC)</span>, 560 Paris, France, September 2016. 561 </p></li> 562 <li><p> 563 <a href="http://vclab.ca/wp-content/papercite-data/pdf/16-wacv-2-c.pdf" id="wacv16" class="papertitle">"Constructing Image Mosaics Using Focus Based Depth Analysis."</a>, 564 <span class="paperauth">Mohamed A. Helala</span>, 565 Faisal Z. Qureshi, 566 <span class="papervenue">IEEE Winter Conference on Applications of Computer Vision (WACV)</span>, 567 Lake Placid, NY, USA, March 2016. 568 </p></li> 569 <li><p> 570 <a href="http://vclab.ca/wp-content/papercite-data/pdf/15-jei-j.pdf" id="spie15" class="papertitle">"Automatic Parsing of Lane and Road Boundaries in Challenging 571 Traffic Scenes."</a>,
572 <span class="paperauth">Mohamed A. Helala</span>, 573 Faisal Z. Qureshi, Ken Q. Pu, 574 <span class="papervenue">SPIE Journal of Electronic Imaging</span>, 575 2015. 576 </p></li> 577 <li><p> 578 <a href="http://vclab.ca/wp-content/papercite-data/pdf/14-uccv-w.pdf" id="uccv14" class="papertitle">"Towards Efficient Feedback Control in Streaming Computer Vision Pipelines."</a>, 579 <span class="paperauth">Mohamed A. Helala</span>, 580 Ken Q. Pu, Faisal Z. Qureshi, 581 <span class="papervenue">2nd Workshop on User-Centered Computer Vision (UCCV) in conjunction with ACCV 2014</span>, 582 Singapore, Nov. 2014. 583 </p></li> 584 <li><p><a href="http://vclab.ca/wp-content/papercite-data/pdf/14-accv-c.pdf" id="accv14" class="papertitle">"Accelerating Cost Volume Filtering Using Salient Subvolumes and Robust Occlusion Handling."</a>, 585 <span class="paperauth">Mohamed A. Helala</span>, 586 Faisal Z. Qureshi, 587 <span class="papervenue">12th Asian Conference on Computer Vision (ACCV)</span>, 588 Singapore, Nov. 2014. 589 </p></li> 590 <li><p><a href="http://www.cv-foundation.org/openaccess/content_cvpr_workshops_2014/W20/papers/Helala_A_Stream_Algebra_2014_CVPR_paper.pdf" id="cvpr14" class="papertitle">"A Stream Algebra For Computer Vision Pipelines."</a>, 591 <span class="paperauth">Mohamed A. Helala</span>, 592 Ken Q. Pu, Faisal Z. Qureshi, 593 <span class="papervenue">2nd Workshop on Web-scale Vision and Social Media (VSM) in conjunction with CVPR 2014</span>, 594 Columbus, Ohio, June. 2014. 595 </p></li> 596 <li><p><a href="files/12-icdsc-c.pdf" id="icdsc12" class="papertitle">"Mosaic of Near Ground UAV Videos Under Parallax Effects"</a>, 597 <span class="paperauth">Mohamed A. Helala</span>, 598 Luis A. Zarrabeitia, Faisal Z. Qureshi, 599 <span class="papervenue">Proc. 6th ACM/IEEE International Conference on Distributed Smart Cameras (ICDSC)</span>, 600 Hong Kong, China, Oct. 2012. 601 </p></li> 602 <li><p><a href="files/12-avss-c.pdf" id="avss12" class="papertitle">"Road Boundary Detection in Challenging Scenarios"</a>, 603 <span class="paperauth">Mohamed A. Helala</span>, 604 Ken Q. Pu, Faisal Z. Qureshi, 605 <span class="papervenue">Proc. 9th IEEE International Conference on Advanced Video and Signal-Based Surveillance (AVSS) 606 </span>, Beijing, China, Sept. 2012. 607 </p></li> 608 <li><p><a href="files/master-thesis.pdf" id="master10" class="papertitle">"Quantitative image search based on feature integration"</a>, 609 <span class="paperauth">Mohamed A. Helala</span> 610 <span class="papervenue">Master Thesis, Benha University 611 </span>, Cairo, Egypt, Dec. 2010. 612 </p></li> 613 <li><p><a href="http://www.ijcsi.org/papers/IJCSI-9-4-1-204-213.pdf" id="ijcsi12" class="papertitle">"A Content Based Image Retrieval Approach Based On Principal Regions Detection"</a>, 614 <span class="paperauth">Mohamed A. Helala</span>, 615 Mazen M. Selim, Hala H. Zayed, 616 <span class="papervenue">International Journal of Computer Science Issues (IJCSI)</span>, 617 Vol. 9, Issue 4, No 1, Jul. 2012. 618 </p></li> 619 <li><p><a href="http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=5380453" id="iccee12" class="papertitle">"An Image Retrieval Approach Based on Composite Features and Graph Matching"</a>, 620 <span class="paperauth">Mohamed A. Helala</span>, 621 Mazen M. Selim, Hala H. Zayed, 622 <span class="papervenue">Proc. IEEE International Conference on Computer and Electrical Engineering (ICCEE)</span>, 623 Dubai, Emirate, Dec. 2009. 624 </p></li> 625 </ol> 626 </div> 627 </div> 628 </div> 629 <!--/.container--> 630 </section> 631 632 <section id="activities-awards" class="secPad titlebox"> 633 <div class="container"> 634 <div class="row"> 635 <!-- item --> 636 <div class="col-md-6 text-center tileBox"> 637 <div class="txtHead"> 638 <h3><i class="fa fa-pencil"></i><span class="id-color">Activities</span></h3></div> 639 <ol class="list3 content"> 640 <li><p><em>Discussion Group</em>A weekly seminar where all students in the <a href="http://vclab.science.uoit.ca/">visual computing 641 lab</a> discuss recent research in computer vision and graphics.</p></li> 642 <li><p><em>Blog</em><a href="http://mhelala.blogspot.ca/">My Personal Blog</a></p></li> 643 <li><p><em>Reading</em>Currently, I'm reading the book "Decision Forests for Computer Vision and Medical Image Analysis". This book dives into the theory and applications of random forests in computer vision. I like playing with the Sherwood library that accompanies the book. 644 </p></li> 645 </ol> 646 </div> 647 <!-- end: --> 648 649 <!-- item --> 650 <div class="col-md-6 text-center tileBox"> 651 <div class="txtHead"> 652 <h3><i class="fa fa-certificate"></i> <span class="id-color">Awards</span></h3></div> 653 <ol class="list3 content"> 654 <li><p><em>2017</em>Best Paper Award - Canadian Conference on Computer and Robot Vision (CRV)</p></li> 655 <li><p><em>2015</em>
655Honorable Mention in IBM HackStreams Challenge</p></li> 656 <li><p><em>2011</em>Awarded the <a href="http://gradstudies.uoit.ca/current_students/student_finances/graduate_student_funding/external_awards/ontario-trillium-scholarship.php">Ontario Trillium Scholarship (OTS) Award</a> </p></li> 657 <li><p><em>2011</em>Nominated for Fulbright scholarship by the binational Fulbright commission in Egypt(only 10 nominations in all fields each year)[Left for commitment with the OTS award]</p></li> 658 <li><p><em>2011</em>Egyptian Government PhD Scholarship Award [Left for commitment with the OTS award]</p></li> 659 <li><p><em>2004</em>The Honor Degree for Academic Distinction</p></li> 660 <li><p><em>2004</em>Deanâs Gold Medal for Graduating First Place in B.Sc. Electrical and Computer Engineering 661</p></li> 662 </ol> 663 </div> 664 <!-- end: --> 665 </div> 666 </div> 667 </section> 668 669 <footer> 670 <div class="container"> 671 <div class="social text-center"> 672 <a href="https://twitter.com/Mohamed_Helala"><i class="fa fa-twitter"></i></a> 673 <a href="https://www.facebook.com/mohamed.helala.1"><i class="fa fa-facebook"></i></a> 674 <a href="https://plus.google.com/114765445236633498280/posts"><i class="fa fa-google-plus"></i></a> 675 <a href='http://mhelala.blogspot.ca/'> <i class="fa fa-bold"></i></a> 676 <a href="https://github.com/mohamed-helala"><i class="fa fa-github"></i></a> 677 </div> 678 <div class="clear"></div> 679 <!--CLEAR FLOATS--> 680 </div> 681 </footer> 682 <a href="#top" class="topHome"><i class="fa fa-chevron-up fa-2x"></i></a> 683 684 <!--[if lte IE 8]>
684<script src="//ajax.googleapis.com/ajax/libs/jquery/1.11.0/jquery.min.js"></script>
684<![endif]--> 685
685<script src="js/modernizr-latest.js"></script>
685 686
686<script src="js/jquery-1.8.2.min.js" type="text/javascript"></script>
686 687
687<script src="js/jquery.newsTicker.js" type="text/javascript"></script>
687 688
688<script src="js/bootstrap.min.js" type="text/javascript"></script>
688 689
689<script src="js/jquery.isotope.min.js" type="text/javascript"></script>
689 690
690<script src="js/fancybox/jquery.fancybox.pack.js" type="text/javascript"></script>
690 691
691<script src="js/jquery.nav.js" type="text/javascript"></script>
691 692
692<script src="js/jquery.cslider.js" type="text/javascript"></script>
692 693
693<script src="js/custom.js" type="text/javascript"></script>
693 694
694<script src="js/owl-carousel/owl.carousel.js"></script>
694 695
695<script> 696 var nt_example2 = $('#nt-example2').newsTicker({ 697 row_height: 60, 698 max_rows: 1, 699 speed: 300, 700 duration: 6000, 701 prevButton: $('#nt-example2-prev'), 702 nextButton: $('#nt-example2-next'), 703 hasMoved: function() { 704 $('#nt-example2-infos-container').fadeOut(200, function(){ 705 $('#nt-example2-infos .infos-image').attr("src", $('#nt-example2 li:first span').attr("imgdata")); 706 $('#nt-example2-infos .infos-text').text($('#nt-example2 li:first').data('infos')); 707 $(this).fadeIn(400); 708 }); 709 }, 710 pause: function() { 711 $('#nt-example2 li i').removeClass('fa-play').addClass('fa-pause'); 712 }, 713 unpause: function() { 714 $('#nt-example2 li i').removeClass('fa-pause').addClass('fa-play'); 715 } 716 }); 717 $('#nt-example2-infos').hover(function() { 718 nt_example2.newsTicker('pause'); 719 }, function() { 720 nt_example2.newsTicker('unpause'); 721 }); 722 </script>
722 723</body> 724</html>
Line numbers count LF bytes from the start of the resource, as the search results do. Vendor segments are library code the classifier recognised; they are stored but not indexed. Bytes are shown as Latin1 characters, one per byte.