OpenCV - OpenCV DevZone

1

h1. *Ideas Page for OpenCV Google Summer of Code 2015 (GSoC 2015)*

2

1

3

1

THIS NEEDS UPDATING, RIGHT NOW, JUST A COPY OF 2014

4

1

5

1

6

1

*OpenCV winning the Everingham Award at ICCV 2013 for contributions furthering progress in the computer vision community as a whole.*

7

1

!EveringhamAward.jpg!

8

1

9

1

----

10

1

11

1

h2. General Information:

12

1

13

1

* "GSoC 2014 site: http://www.google-melange.com/gsoc/homepage/google/gsoc2014":http://www.google-melange.com/gsoc/homepage/google/gsoc2014

14

1

* Mailing list for OpenCV GSOC 2014: [email protected]

15

1

** Group site https://groups.google.com/forum/#!forum/opencv-gsoc-2014

16

1

* "Timeline for GSoC 2014":http://www.google-melange.com/gsoc/events/google/gsoc2014

17

1

** *Next important dates:*

18

1

*** -March 21: Final call to register with GSoC and submit a project to OpenCV-

19

1

*** -Interim period all mentors go to https://www.google-melange.com/gsoc/proposal/list/org/google/gsoc2014 and rate the proposals-

20

1

*** -April 6 OpenCV Request how many slots we want-

21

1

*** -April 9 Slot allocations published-

22

1

*** -Talk amongst your orgs for slots-

23

1

*** -April 18: *All mentors must be signed up. Deduplication Meeting*-

24

1

*** -April 21 Project selections announced-

25

1

*** -May 19 Coding starts!-

26

1

*** -June 23-27 Midterm-

27

1

*** -Aug 11 Documentation, Youtube video (*MUST BE DONE*)-

28

1

*** -Aug 18 It's over folks-

29

1

*** -Aug 25 Results are posted-

30

1

*** Oct 23-26 Mentor summit

31

1

32

1

* we'll create a video just like we did last year http://www.youtube.com/watch?v=_TTtN4frMEA

33

1

34

1

*Times:*

35

1

*  UTC to PDT (Pacific Daylight Time == Daylight savings time. In winter it's PST).

36

1

** "utc time converter":http://weatherarc.com/utc-time-conversion

37

1

38

1

*Resources:*

39

1

40

1

* "OpenCV Developers Site":http://code.opencv.org/projects/opencv/wiki

41

1

* "OpenCV User's Site":http://opencv.org

42

1

* [[How_to_contribute|How to Contribute Code]]

43

1

* Source Code can be found at "GitHub":https://github.com/Itseez/opencv.

44

1

** To get the source code, point your git client to @git://github.com/Itseez/opencv.git@. Here are [[Working_with_OpenCV_git_repository|instructions]].

45

1

<pre>

46

1

git clone git://github.com/Itseez/opencv.git

47

1

</pre>

48

1

** The rest of the history plus matches between git commits and SVN revisions are stored at a separate "OpenCV Attic" repository: git://code.opencv.org/opencv_attic.git.

49

1

** Also OpenCV Extra was put to a separate repository: git://code.opencv.org/opencv_extra.git.

50

1

* [[OpenCV Development Process]]

51

1

** [[Meeting_notes|Developer meeting notes]]

52

1

53

1

h2. For students or mentors interested in applying

54

1

55

1

* You *must* already know how to program well in C++

56

1

** Some projects may require Python or Matlab skills

57

1

* Discuss projects below or other ideas with us https://groups.google.com/forum/?fromgroups#!forum/opencv-gsoc-2014

58

1

59

1

h1. Accepted Projects for OpenCV GSoC 2014:

60

1

61

1

OpenCV GSoC 2014 students, projects, mentors are below.

62

1

Mentor "link to spreadsheet and email is here":https://docs.google.com/spreadsheet/ccc?key=0AqJ64DhFuODLdFF1ZnRWSFhTd1NLcHdNaFgtU2M5ekE&usp=sharing .

63

1

64

1

<pre>

65

1

Student                 Project                                           Mentor(s)

66

1

=======                 =======                                           ========

67

1

Lluis Gomez             Improve Scene Text Detection module in OpenCV     Stefano Fabri, Vadim Pisarevsky

68

1

Abid Rahman             Extend of OpenCV-Python Bindings and Tutorials    Vadim Pisarevsky

69

1

Fedor Morozov	       Local feature descriptors                         Pablo Alcantarilla

70

1

Siddharth Kherada       Computational Photography: Image Decomp  Color    spmallick

71

1

Daniel Angelov	      Custom Calibration Pattern                        Sid Bao

72

1

Vitaly Lyudvichenko     New edge-aware filters for OpenCV	             Alexander Mordvintsev

73

1

Alex Leontiev 	      Learning based trackers 	                      Gary Bradski

74

1

Tolga Bridle            Rec & Pose Est of 3D Objects via 3D Features	  Bence Magyar

75

1

Francesco Puja          Saliency improvement for tracking                 Antonella Cascitelli

76

1

edgarriba               Real Time Pose Est Tutorial and DLS impl.         Alexander Shishkov

77

1

Yuri Gitman	         P. Dollar segmentation algorithm                  Alexander Shishkov

78

1

Vlad Shakhuro	       Fastest Pedestrian Detector in the West           Alexander Bovyrin

79

1

biagio	              Geometrical-primitives based localization system  Manuele Tamburrano

80

1

Tomasz Pietruszka	   Optical Flow Estimation â state-of-the-art        Prasanna Krishnasamy

81

1

Paul Foster	         Dense Tracking and Mapping (DTAM) for OpenCV      Vincent Rabaud

82

1

</pre>

83

1

84

1

Project notes are compiled "here":https://sites.google.com/a/opencv.org/opencv/gsoc-2014-project-notes .

85

1

86

1

h1. Project Ideas summary:

87

1

88

1

*Students may propose their own projects (give us a clear summary and why you can do this project). However, below are some of our priorities for this year*

89

1

90

1

Contact us and/or discuss ideas at https://groups.google.com/forum/?fromgroups#!forum/opencv-gsoc-2014

91

1

92

1

+These are not in order of priority+

93

1

94

1

* Finger print detection (Prasanna Krishnasamy)

95

1

** Implement the detectors associated with MINDTCT and other algorithms

96

1

** Full recognition pipeline as done by NIST

97

1

*** Some description can be found here: http://www.nist.gov/itl/iad/ig/nbis.cfm

98

1

99

1

* Quadrotor / quadcopter computer vision (Gary Bradski)

100

1

** Implement hovering, tracking other algorithms

101

1

** Due to the nature of this, you should have a working quad rotor craft with camera and feedback to work with

102

1

103

1

* Expand the Matlab port from GSoC 2013

104

1

** Matlab will likely continue to mentor

105

1

** http://www.mathworks.com/discovery/matlab-opencv.html

106

1

107

1

* Graphics rendering expert: Create a data set generator for OpenCV

108

1

** We want to take a 3D scan or CAD model of a rigid object, and

109

1

*** render it 1000's of times

110

1

*** in different lightings

111

1

*** using settable camera parameters (OpenCV structure)

112

1

*** outputting the rendered image and the ground truth mask and 6DOF pose

113

1

** We also want to do the same thing with humans and/or hands

114

1

*** Use makehuman + blender + poser or any other tool

115

1

*** Create humans/hands in 1000's of poses, lightings etc

116

1

117

1

* We would like to create a "High school robotics competition intelligent vision package" to allow high school robot competitions to be more autonomous

118

1

** In Python

119

1

*** Calibration

120

1

*** Stereo

121

1

*** Planar object detection and tracking

122

1

*** Object tracking (such as balls)

123

1

124

1

* Expand 3D processing in OpenCV already in the "RGBD module":https://github.com/Itseez/opencv_contrib/tree/master/modules/rgbd

125

1

** Surface curvature

126

1

** Basic 3D features

127

1

** ICP step to improve LINE-MOD

128

1

129

1

* Expand OpenCV Viz module

130

1

** +Mentor:+ Anatoly Baksheev

131

1

** Integration message loops highgui & viz. For now they are handled separately by waitKey & Viz3d::spin()

132

1

** More widgets (like human body/hand/skeletons visualization, need to generate more ideas)

133

1

** More widgets (free-fly mode, possible will be done before GSoC by me)

134

1

135

1

* Code up Piotr DollÃ¡r's method of segmentation, make it fast

136

1

** Matlab implementation:

137

1

*** http://vision.ucsd.edu/~pdollar/toolbox/doc/

138

1

** http://vision.ucsd.edu/~pdollar/files/papers/DollarICCV13edges.pdf

139

1

** http://research.microsoft.com/en-us/downloads/389109f6-b4e8-404c-84bf-239f7cbf4e3d/default.aspx

140

1

141

1

* Code up Piotr DollÃ¡r's __The Fastest Pedestrian Detector in the West__

142

1

** Paper: http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.310.8578&rep=rep1&type=pdf

143

1

144

1

* Automatically generating comics:

145

1

** See http://www.physorg.com/news/2012-03-software-automatically-movie-comic.html

146

1

** Do effects like comic life http://plasq.com/products/comiclife/win

147

1

148

1

* Finish off OpenCV's Soft Cascades, use it to detect faces in many orientations

149

1

** Existing OpenCV code documentation: http://docs.opencv.org/trunk/modules/objdetect/doc/soft_cascade.html

150

1

** Original paper: http://www.lubomir.org/academic/softcascade.pdf

151

1

*** training, new features, detection

152

1

*** interframe interpolation and smoothing

153

1

*** outlier supression

154

1

155

1

* Continue on and expand the computational photography project from GSoC 2013

156

1

** http://docs.opencv.org/trunk/doc/py_tutorials/py_photo/py_table_of_contents_photo/py_table_of_contents_photo.html

157

1

** http://docs.opencv.org/modules/photo/doc/photo.html

158

1

** Help support the growth of mobile cameras on tablets and phones. Fun stuff and important

159

1

*** tilt-shift images and movies,

160

1

*** high dynamic range images by composition with different shutter times

161

1

**** another important topic on HDR imaging is squeezing all information from 10-12-14bit raw file into 8-bit, in other words, single-shot HDR. It's true that many modern video cameras have quite small sensor and quite small dynamic range, but we can still try to recover highlight details by careful demosaicing combined with dynamic range optimization.

162

1

*** Fun effects -- converting images and videos to line drawings

163

1

*** Color balance, take a Macbeth color chart and fill in the 3x3 transform look up matrix, implement something like http://graphics.ucsd.edu/~neel/publications/masters_thesis.pdf

164

1

165

1

* Mobile vision app development:

166

1

** Vision apps on phone and tablet. We want a very clear examples to build on to make it easier for the rest to start developing mobile vision applications. People can apply for:

167

1

*** iOS (iPhone) examples

168

1

*** Android example

169

1

170

1

* Tracking -- predator (tracking, detection + learning) or Alien type tracker

171

1

 ** Basically: learning based trackers

172

1

 *** Draw box, resize

173

1

 *** Box distortion

174

1

 *** Look for candidates

175

1

176

1

 * Update solvePnP (fundamental algorithm)

177

1

 ** http://www-users.cs.umn.edu/~joel/index.php?page=software

178

1

179

1

 * Update to state of the art Optical flow

180

1

 ** State of art http://www.ingentaconnect.com/content/klu/visi/2014/00000106/00000002/00000644

181

1

 ** Prepare testing framework for quality

182

1

 *** Have frameworks for features and stereo already

183

1

184

1

* Mech Turk Interface

185

1

** Easily label images for train test in OpenCV

186

1

187

1

* OpenCL Optmization:

188

1

** We have contributors already, get one or more of them to be GSoC students

189

1

190

1

* Object Recognition

191

1

** New, post Line-Mod object recognition

192

1

** +Menor:+ Manuele Tamburano

193

1

*** Binarizzation of a new line descriptor[1] and adapting

194

1

*** "Fast exact nearest neighbor search in Hamming distance on binary codes with Multi-index hashing" code[2].

195

1

**** [1]http://www.sciencedirect.com/science/article/pii/S1047320313000874

196

1

**** [2]https://github.com/norouzi/mih

197

1

** write a trainer for Deva Ramanan's parts-based detector https://github.com/wg-perception/PartsBasedDetector

198

1

199

1

* Camera based 1D and 2D Barcode readers. OpenCV needs this, robotics needs this

200

1

** +Mentor:+ Claudia Rapuano

201

1

** We have a basic datamatrix reader.  Expand to other kinds of barcodes (1D, other 2D).

202

1

203

1

*  Improve tracking API module in contrib created for Gsoc 2013.

204

1

** +Mentor:+ Antonella Cascitell

205

1

** Add Reidentification on the tracking (allows tracking to re-find the object if lost)

206

1

** Add camera network activity sub-modual

207

1

** Add saliency module for the tracking modual

208

1

209

1

* Natural barcodes:

210

1

* +Mentor:+ Gary Bradski

211

1

** OpenCV can read calibration patterns.

212

1

*** Calibrate a camera,

213

1

*** rectify it's output.

214

1

*** Put a picture next to a calibration pattern in a scene.

215

1

*** Find 2D interest points with features2D.

216

1

*** Measure them in the image using the calibration pattern.

217

1

*** Use the pattern of interest points and their measures to turn the picture into a calibration pattern/barcode so that the computer recognizes the picture and knows where it is in relation to the iamge.

218

1

** Stretch goal, embeded and retrieve watermarks in the image.

219

1

220

1

* Ego-centric vision:

221

1

** maybe something like "Pixel-level Hand Detection for Ego-centric Videos." in CVPR 2013

222

1

** Combine with depth sensing from the kinect

223

1

224

1

* Geometry:

225

1

** DTAM implementation

226

1

** write tutorials for the libmv integration from the previous years (on "GitHub":https://github.com/wg-perception/libmv), improve the CERES integration

227

1

** create a structure for camera matrix information (K, D, colorspace ...)

228

1

229

1

* Tutorials:

230

1

** Continue with "OpenCV Tutorials":http://opencv.itseez.com/doc/tutorials/tutorials.html

231

1

232

1

* OpenCV Documentation:

233

1

** Add to the general documentation for all platforms: C++, CUDA, OpenCL, Python 2/3, Java, ... and smart search.

234

1

** Help create an _*inverted index*_ of functionality to functions.  That is, say, _edge detection_ would list Sobel, Scharr, Canny etc.

235

1

236

1

* Course-ware:

237

1

** We want to start offering vision courses using OpenCV.

238

1

*** If you are expert in a topic (say it's your area of graduate research, or you've just finished a project or course in a particular topic and can explain it well)

239

1

*** Write up the topic, the math and then develop a step by step example of it using OpenCV.

240

1

241

1

* Expose OpenCV GPU functionality into Python API

242

1

** Current Python OpenCV wrappers use @cv::Mat@ <=> Numpy array mapping for passing data between C++ and Python worlds. Aim of this project is to adopt "PyCuda GPUArray":http://documen.tician.de/pycuda/array.html as a counterpart of @GpuMat@.

243

1

** This would allow to extend cv2 wrapper generator to expose CUDA-powered OpenCV functions.

244

1

** Project requires good knowledge of C++ and Python and willingness to dive into the internals of OpenCV, Python and PyCuda.

245

1

** Expect all sorts of gotchas, subtle issues and design discussion with mentors.

246

1

** The resulting design decisions can be used to wrap the OpenCV's OpenCL functionality with "PyOpenCL":http://mathema.tician.de/software/pyopencl

247

248

249

250

h2. Mentors

251

1

252

1

*Actual signed up mentors*

253

1

254

1

* Alexander Mordvintsev	zzznah(+)gmail.com

255

1

* Sid Bao	ybao(+)magicleap.com

256

1

* Vincent Rabaud	vincent.rabaud(+)gmail.com

257

1

* Vadim Pisarevsky	vadim.pisarevsky(+)gmail.com

258

1

* Adrian Kaehler	therealadrian(+)gmail.com

259

1

* Terry Boult	tboult(+)vast.uccs.edu

260

1

* spmallick	spmallick(+)taaz.com

261

1

* Serge Belongie	sjb344(+)cornell.edu

262

1

* Stefano	s.fabri10(+)gmail.com

263

1

* Prasanna	pras.bits(+)gmail.com

264

1

* Pablo Alcantarilla	pablofdezalc(+)gmail.com

265

1

* Bence Magyar	mw.mzperx(+)gmail.com

266

1

* Manuele	manuele.tamburrano(+)gmail.com

267

1

* Grace Vesom	grace.vesom(+)gmail.com

268

1

* Open Source Computer Vision Library (OpenCV)	garybradski(+)gmail.com

269

1

* Douglas Lee	dougabug(+)gmail.com

270

1

* Claudia Rapuano	c.rapuano(+)gmail.com

271

1

* Antonella Cascitelli	antonellacascitelli(+)gmail.com

272

1

* Anatoly Baksheev	anatoly.baksheev(+)itseez.com

273

1

* Alexander	alexander.shishkov(+)itseez.com

274

1

* Alexander Bovyrin	alexander.bovyrin(+)itseez.com

275

276

277

278

In the below, get rid of the ''-delete-'' to make the emails work.

279

1

280

1

 Anatoly Baksheev

281

1

 Researcher, Vision Algorithms on GPU

282

1

 Argus/Itseez

283

1

 [email protected]

284

1

285

1

  Alexander Bovyrin

286

1

  PhD, Senior Researcher

287

1

  Argus/Itseez founder

288

1

  NNU Lecturer

289

1

  [email protected]

290

1

291

1

 Gary Bradski

292

1

 Founder, Industrial Perception Inc.

293

1

 Consulting Prof. Stanford U.

294

1

 OpenCV Founder, Technical Content Owner, GSoC Admin

295

1

 Co-author of Learning OpenCV Book

296

1

 http://www.willowgarage.com/pages/people/gary-bradski-senior-researcher

297

1

 [email protected]

298

1

299

1

 Antonella Cascitelli

300

1

 Grad student, University of Rome

301

1

 [email protected]

302

1

303

1

 Eric Christiansen

304

1

 PhD, UCSD

305

1

 [email protected]

306

1

307

1

 Stefano Fabri

308

1

 CRR Team leader, University of Rome

309

1

 [email protected]

310

1

311

1

 Victor Eruhimov

312

1

 OpenCV founding team/Senior Researcher

313

1

 Argus/Itseez founder

314

1

 NNU Lecturer

315

1

 [email protected]

316

1

317

1

 Adrian Kaehler

318

1

 Principle Engineer, Applied Minds

319

1

 Co-author of Learning OpenCV Book.

320

1

 [email protected]

321

1

322

1

 Peter Karasev

323

1

 PhD Student, MINERVA Research Group

324

1

 Georgia Tech

325

1

 [email protected]

326

1

327

1

 Vadim Pisarevsky

328

1

 OpenCV founding team/Czar

329

1

 [email protected]

330

1

331

1

 Manuele Tamburrano

332

1

 Grad Student, University of Rome

333

1

 [email protected]

334

1

335

1

 Vincent Rabaud

336

1

 Principle Engineer, Aldebaran Robotics

337

1

 [email protected]

338

1

339

1

  Claudia Rapuano

340

1

  Grad student, University of Rome

341

1

  [email protected]

342

1

343

1

 Grace Vesom

344

1

 Lawrence Livermore

345

1

 -delete-grace.vesom@-delete_gmail.com

346

1

347

1

 Bence Magyar

348

1

 Pal Robotics

349

1

 [email protected]

350

1

351

1

 Pablo Alcantarilla

352

1

 Toshiba Research Europe Ltd.

353

1

 [email protected]

354

1

355

1

h3.  Back up Mentors

356

1

357

1

 Mark Asbach

358

1

 Fraunhofer IAIS

359

1

 Schloss Birlinghoven

360

1

 Sankt Augustin, Germany

361

1

 http://mmprec.iais.fraunhofer.de/asbach.html

362

1

 [email protected]

363

1

364

1

365

1

 Nicolas Saunier, Ph.D.

366

1

 Assistant Professor

367

1

 Civil, Geological and Mining Department (CGM)

368

1

 Ãcole Polytechnique de MontrÃ©al

369

1

 http://nicolas.saunier.confins.net

370

1

 [email protected]

371

1

372

1

373

1

 Alexander Mordvintsev

374

1

 Software Engineer

375

1

 http://znah.net

376

1

 [email protected]

377

1

378

1

 Andrey Morozov

379

1

 Software Engineer

380

1

 Argus/Itseez

381

1

 [email protected]

382

1

383

1

h2. OpenCV Org. Application to GSoC 2014

384

1

385

1

"OpenCV GSoC Application":http://code.opencv.org/projects/gsoc2013/wiki/GSoC2013OpenCVApplication

386

1

387

1

h2. Previous Years

388

1

389

1

* "Google Summer of Code 2013 (GSoC 2013) Ideas Page":http://code.opencv.org/projects/gsoc2013/wiki

390

1

* 2012 Ideas site http://code.opencv.org/projects/gsoc2012/wiki/Wiki/

391

1

* 2011 Ideas site http://opencv.willowgarage.com/wiki/GSOC_OpenCV2011

392

1

** 2011 Application GSoC page is http://opencv.willowgarage.com/wiki/GSoC2011OpenCVApplication

393

1

* 2010 Ideas site http://opencv.willowgarage.com/wiki/GSOC_OpenCV2010

394

1

** 2010 Application page http://opencv.willowgarage.com/wiki/ApplicationGSOC2010

395

1

396

1

----

Login	Password