OpenCV - OpenCV DevZone

1

h1. *Ideas Page for OpenCV Google Summer of Code 2016 (GSoC 2016)*

2

1

3

1

4

1

*OpenCV 3D recognition and pose from last year.*

5

1

!3D_recog.jpg!

6

1

7

1

----

8

1

9

1

h2. General Information:

10

1

11

1

* "GSoC 2016 site: https://developers.google.com/open-source/gsoc/":https://developers.google.com/open-source/gsoc/

12

1

* Mailing list for OpenCV GSOC 2015: [email protected]

13

1

** Group site https://groups.google.com/forum/#!forum/opencv-gsoc-2015

14

1

* "Timeline for GSoC 2015":http://www.google-melange.com/gsoc/events/google/gsoc2015

15

1

16

1

** *Next important dates:*

17

1

*** -Feb 20 19:00 UTC: Organization Application Deadline.- *DONE!*

18

1

*** -Mar 02 19:00 UTC: List of accepted Organizations.- *We're in!*

19

1

*** -Mar 16 16:00 UTC: Student Application period begins!- *Students Apply!*

20

1

*** -Mar 27 19:00 UTC: Student Application period ends!- *Closed*

21

1

*** -Apr 13 Deadline for OpenCV to request # of slots.- *Submitted*

22

1

*** -Apr 15 Google publishes how many slots we get.- *Excellent!*

23

1

*** -Apr 21 Try to eliminate duplication of students.-

24

1

*** -Apr 24 IRC for OpenCV to resolve all duplications.-

25

1

*** -Apr 27 19:00 UTC: Accepted students announced.-

26

1

*** -May 25 Let Coding begin!-

27

1

*** -Jun 26 19:00 UTC: Mid term evaluation begins.- *Pull requests must be in*

28

1

*** -Jul 03 19:00 UTC:  Mid term end.-

29

1

*** -Aug 21 19:00 UTC: Coding stop; Pull requests must be in;- Mentors: final evaluation begins...

30

1

*** -Aug 28 19:00 UTC: Final evaluation deadline; Students begin submitting code.- *All 14 remaining projects have pull requests for opencv_contrib*

31

1

*** -Sept 25 19:00 UTC: Deadline for Google Code submission-

32

1

*** -Nov 7: Mentor Summit!-

33

1

34

1

*Times:*

35

1

*  UTC to PDT (California uses PST in the winter (from Nov 1st) and PDT in the summer (from March 8)).

36

1

** "utc time converter":http://www.timebie.com/std/gmt.php

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 do a pull request/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. How you will be evaluated if you are an accepted student

54

1

55

1

* Student projects to be paid only if:

56

1

** *Midterm:*

57

1

*** You must generate a pull request

58

1

**** That builds

59

1

**** Has at least stubbed out functionality

60

1

**** With appropriate Doxygen documentation

61

1

**** Has at least stubbed out unit test

62

1

**** Has a stubbed out example of use that builds

63

1

** *End of summer:*

64

1

*** A full pull request

65

1

**** Full Doxygen documentation

66

1

**** A good unit test

67

1

**** Example of use code

68

1

*** Create a (short!) Movie (preferably on Youtube, but any movie) that demonstrates your code

69

1

**** We use this to create an overall summary. Past years:

70

1

***** "The 2015 Movie":https://www.youtube.com/watch?v=OUbUFn71S4s

71

1

***** "The 2014 Movie":https://www.youtube.com/watch?v=3f76HCHJJRA

72

1

***** "The 2013 Movie":https://www.youtube.com/watch?v=_TTtN4frMEA

73

1

74

1

75

1

h2. For students interested in applying

76

1

77

1

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

78

1

** Some projects may require Python or Matlab skills

79

1

# Discuss projects below or other ideas with us https://groups.google.com/forum/?fromgroups#!forum/opencv-gsoc-2015

80

1

# Go to the "GSoC site":http://www.google-melange.com/gsoc/homepage/google/gsoc2015 and sign up

81

1

# Post the project from below or your own agreed on project on the GSoC site to the Open Source Computer Vision organization

82

1

83

1

h2. For computer vision professionals interested in mentoring

84

1

85

1

# Go to the "GSoC site":http://www.google-melange.com/gsoc/homepage/google/gsoc2015 and sign up.

86

1

# Request to be a mentor for OpenCV there.

87

1

# We accept or reject you

88

1

# Students submit projects and you

89

1

** find a project you want to mentor (several students might try for the same project)

90

1

** contact us about it through [email protected] so we can be sure there is not someone already handling that project

91

1

** contact the students to assess which one if any are capable of coding that up in a summer.

92

1

# We get a slot allocation from Google, the administrators then _"spend"_ the slots in order of priority

93

1

# Students must finally actually accept to do that project (some sign up for multiple organizations and then choose)

94

1

95

1

*If* you are accepted as a mentor *and* you find a suitable student *and* we give you a slot *and* the student signs up for it, +*then*+ you are a mentor.

96

1

** It sounds harder than it is.

97

1

98

1

99

1

<pre>

100

1

\/  \/  \/  \/  \/  \/  \/  \/  \/  \/  \/  \/  \/  \/  \/  \/  \/  \/  \/  \/  \/  \/  \/  \/  \/  \/  \/  \/  \/  \/

101

1

</pre>

102

1

103

1

h1. 2016 Project Ideas:

104

1

105

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* Contact us and/or discuss ideas at https://groups.google.com/forum/?fromgroups#!forum/opencv-gsoc-2015

106

1

107

1

_These are not in order of priority_

108

1

109

1

*1 Google Cardboard*

110

1

* Do visual odometry, SLAM etc for Google Cardboard

111

1

112

1

*2 Projection mapping (Projected Augmented Reality)*

113

1

* Calibrate a camera to a projector

114

1

* Put out structured light to learn the 3D map of what's in front of the camera

115

1

* Project the camera image, suitably rotated and shifted onto the scene

116

1

* Unity or some other program to start transforming the scene for projection mapping

117

1

** See http://www.creativebloq.com/video/projection-mapping-912849 to get ideas of what you can do with this

118

1

119

1

*3 Update OpenCV file storage so that it's readable by Python in OpenCV (move to YAML 1.2 Edition 3)*

120

1

* Mentor Prasanna

121

1

* OpenCV C++ writes out its own YAML tags which makes it incompatible with it's own Python and with external python readers

122

1

* Speedup fs reading/writing, add JSON support, add base64 (+RLE) support for large amounts of numerical data

123

1

* References

124

1

** YAML http://www.yaml.org

125

1

** Problem statement: http://stackoverflow.com/questions/11141336/filestorage-for-opencv-python-api

126

1

127

1

*4 Stereo correspondence improvements*

128

1

* More accurate and faster stereo correspondence (StereoBM/StereoSGBM) by using LBP/BRIEF/DAISY etc. per-pixel descriptors instead of sum-of-absolute-differences.

129

1

130

1

*5 Self-contained video codec(s)*

131

1

* There is draft version of self-contained motion jpeg encoder to be integrated to OpenCV.

132

1

* We will also need decoder, 12-bit jpeg support, multi-threaded encoder and decoder.

133

1

* There are some other codecs, like libvpx, which we can support and link right into highgui, without dependency from ffmpeg/libav.

134

1

135

1

*6 Deep learning*

136

1

* It would be cool if OpenCV could load and run deep networks trained with popular DNN packages like Caffe, Theano or Torch.

137

1

* GPU/OpenCL optimization and/or other optimizations (that can partly be contributed back to the upstream projects) are also encouraged.

138

1

139

1

*7 Better interactive camera calibration*

140

1

* Modern algorithms would allow us to recompute camera parameters after almost each frame, compute reprojection error, compute confidence intervals for the parameters.

141

1

* the partially occluded calibration patterns could be handled somehow to, especially if we want to estimate intrinsic parameters only.

142

1

* the application may show us the areas where the corner borders have been shown so that user can see how good are the data

143

1

144

1

*9 Color Calibration and white balance*

145

1

* With McBeth chart and with gray world algorithm (improve exisiting color constancy algorithms)

146

1

* Possibly collect deep learning way of doing this (needs large training set)

147

1

148

1

*10 Realtime image preprocessing algorithms (real time on mobile)*

149

1

* We and many other OpenCV users would definitely enjoy very fast denoising, color improvements, white balance etc. algorithms.

150

1

151

1

*11 Tracking improvements*

152

1

* TLD algorithm is implemented in OpenCV, but it needs improvements and optimizations.

153

1

* ASM/AAM can also be implemented, as well as the particle filter.

154

1

155

1

156

1

*12 PBM (part-based models) improvements*

157

1

* There is latentsvm package in opencv_contrib that needs to be improved (quality-wise and speed-wise).

158

1

* Adding training, even if it involves execution of external svmperf or other tool, is definitely appreciated too.

159

1

160

1

*13 Improving ICF/ACF + <some>Boost training and detection*

161

1

* In opencv_contrib there is initial version of the training application and detector based on integral channel features and boosting. Further improvements of this part would be really useful.

162

1

163

1

*14 lua+OpenCV*

164

1

* the other language that is now used more often for ML and CV (thanks to Torch) is Lua; there are old bindings for a tiny part of OpenCV; could be useful to extend our autogenerated bindings to Lua.

165

1

166

1

*15 human interaction*

167

1

* gesture recognition

168

1

* human skeleton based on 2d or 3d

169

1

170

1

*17 Quad Rotor Contrib*

171

1

* Apply much of the above into a quad rotor drone automatic tracking, mapping navigation etc module

172

1

173

1

174

1

New 2016 ideas:

175

1

176

1

*Architecture

177

1

* Exceptions in OpenCV need to be easily disabled ? (need to check if that's the case or not)

178

1

* Minimal OpenCV: give the functions you want, it gives you a minimal version of the library.

179

1

* reduce the size of OpenCV on Anddroid

180

1

* create a more C++ type (to be able to deal with constness and separate the pointer from the type)

181

1

* create an image type (that would also have color information, maybe calibration too) and implement a proper resize algorithm for that type

182

1

183

1

*Tracking

184

1

* David Tanâs tracking

185

1

2d: https://www.youtube.com/watch?v=W689ffCMDF4

186

1

3d: https://www.youtube.com/watch?v=TqyFEZzhPbE

187

1

188

1

*misc

189

1

* convexHull is implemented with Sklansky's second, 1982 algorithm, which is incorrect in some case, and suboptimal complexity-wise. cf. http://cgm.cs.mcgill.ca/~athens/cs601/.

190

1

cv::contourArea(cv::convexHull(contour)) for a convex contour is different from cv::contourArea(contour), somtimes by nearly 30%.

191

192

193

194

<pre>

195

1

/\  /\  /\  /\  /\  /\  /\  /\  /\  /\  /\  /\  /\  /\ /\  /\  /\  /\  /\  /\  /\  /\  /\  /\  /\  /\  /\  /\  /\  /\  /\

196

1

</pre>

197

1

198

1

199

1

h1. Accepted Projects for OpenCV GSoC 2015:

200

1

201

1

OpenCV GSoC 2015 students, projects, mentors are below. *WHEN THEY ARE KNOWN*

202

1

203

1

204

1

*GSoC Progress. Need Pull requests (don't have to be complete) to pass by July 3rd*

205

1

206

1

*Mailing Lists (only for use of Mentors and Students, please to not request to join these lists otherwise):*

207

1

* Mentors

208

1

** opencv-gsoc2015-mentors

209

1

* Students

210

1

** opencv-gsoc2015-students

211

1

212

1

* [[How_to_contribute|How to do a pull request]]

213

1

214

1

*Pre-Midterm status:*

215

1

* *Pull Request In* Antonella Cascitelli - Vladimir Tyan ([email protected]): TLD improvements - https://www.google-melange.com/gsoc/proposal/review/org/google/gsoc2015/auron/5629499534213120.

216

1

* *Pull Request In* Bo Li - Baisheng Lai ([email protected]). Omnidirectional Cameras Calibration and Stereo 3D Reconstruction. https://www.google-melange.com/gsoc/proposal/review/org/google/gsoc2015/baisheng/5629499534213120

217

1

* _*No Pull Request*_ Vincent Rabaud - Edgar Riba ([email protected]). Structure From Motion module. https://www.google-melange.com/gsoc/proposal/review/org/google/gsoc2015/edgarriba/5693417237512192

218

1

* *Pull Request In* Bence Magyar - Jiaolong Xu ([email protected]). Improving PBM in OpenCV. https://www.google-melange.com/gsoc/proposal/review/org/google/gsoc2015/jiaolong/5718998062727168

219

1

* *Pull Request In* Fernando J. Iglesias Garcia - Laksono Kurnianggoro ([email protected]). Real-time Multi-object Tracking using Kernelized Correlation Filter. https://www.google-melange.com/gsoc/proposal/review/org/google/gsoc2015/kurnianggoro/5629499534213120

220

1

* _*No Pull Request*_, but previously Vadim Pisarevsky - Lluis Gomez ([email protected]). Improve and expand Scene Text Detection module in OpenCV. https://www.google-melange.com/gsoc/proposal/review/org/google/gsoc2015/lluisgomez/5751725713522688

221

1

* _*No Pull Request*_ Michael Harville, Gary Bradski - Naoto Hieda ([email protected]). Projection mapping (Projected Augmented Reality). https://www.google-melange.com/gsoc/proposal/review/org/google/gsoc2015/micuat/5707702298738688

222

1

* *Pull Request In* [email protected] - Mircea Paul Muresan ([email protected]). Stereo correspondence improvements. https://www.google-melange.com/gsoc/proposal/review/org/google/gsoc2015/mmp131316/5741031244955648[Andrey can not mentor the student. Does anyone want to take one?]

223

1

* *Pull Request In* Delia, Stefano Fabri, Claudia Rapuano - RobertaRavanelli ([email protected]). Structured-Light System Calibration for OpenCV. https://www.google-melange.com/gsoc/proposal/review/org/google/gsoc2015/roberta_ravanelli/5676830073815040

224

1

* "done" Pull Maksim Shabunin - Alexander Bokov ([email protected]). Recent advances in edge-aware filtering. https://www.google-melange.com/gsoc/proposal/review/org/google/gsoc2015/sbokov/5629499534213120

225

1

* _*No Pull Request*_ Prasanna, Gary Bradski - Sergio Garrido ([email protected]). Charuco board: Chessboard+ArUco for camera calibration. https://www.google-melange.com/gsoc/proposal/review/org/google/gsoc2015/sgarrido/5629499534213120

226

1

* _*No Pull Request*_ Alexander Bovyrin - Vlad Shakhuro ([email protected]). ICF detector improvements. https://www.google-melange.com/gsoc/proposal/review/org/google/gsoc2015/shahurik/5717271485874176

227

1

* *Pull Request In* Vadim Pisarevsky - Seon-Wook Park ([email protected]). Real-time image preprocessing on ARM. https://www.google-melange.com/gsoc/proposal/review/org/google/gsoc2015/swook/5798429187899392

228

1

* *Pull Request In* Anatoly Baksheev, Douglas Lee - Vitaliy Lyudvichenko ([email protected]). Implementation of universal interface for deep neural network frameworks. https://www.google-melange.com/gsoc/proposal/review/org/google/gsoc2015/vludv/5657382461898752

229

1

* *Pull Request In* Manuele Tamburrano, Stefano Fabri - Yida Wang ([email protected]). Deep Learning & GPU Implementation Proposal. https://www.google-melange.com/gsoc/proposal/review/org/google/gsoc2015/wangyida/5629499534213120

230

1

231

1

Project notes will be compiled "here":https://sites.google.com/a/opencv.org/opencv/gsoc-2015-project-notes .

232

233

234

235

h2. Mentors

236

1

237

1

*Actual signed up mentors*

238

1

239

1

* Alexander Mordvintsev	zzznah(+)gmail.com

240

1

* Sid Bao	ybao(+)magicleap.com

241

1

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

242

1

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

243

1

* Adrian Kaehler	therealadrian(+)gmail.com

244

1

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

245

1

* spmallick	spmallick(+)taaz.com

246

1

* Serge Belongie	sjb344(+)cornell.edu

247

1

* Stefano	s.fabri10(+)gmail.com

248

1

* Prasanna	pras.bits(+)gmail.com

249

1

* Pablo Alcantarilla	pablofdezalc(+)gmail.com

250

1

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

251

1

* Manuele	manuele.tamburrano(+)gmail.com

252

1

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

253

1

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

254

1

* Douglas Lee	dougabug(+)gmail.com

255

1

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

256

1

* Antonella Cascitelli	antonellacascitelli(+)gmail.com

257

1

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

258

1

* Alexander	alexander.shishkov(+)itseez.com

259

1

* Alexander Smorkalov	alexander.smorkalov(+)itseez.com

260

1

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

261

262

263

264

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

265

1

266

1

 Anatoly Baksheev

267

1

 Researcher, Vision Algorithms on GPU

268

1

 Argus/Itseez

269

1

 [email protected]

270

1

271

1

  Alexander Bovyrin

272

1

  PhD, Senior Researcher

273

1

  Argus/Itseez founder

274

1

  NNU Lecturer

275

1

  [email protected]

276

1

277

1

 Gary Bradski

278

1

 Founder, Industrial Perception Inc.

279

1

 Consulting Prof. Stanford U.

280

1

 OpenCV Founder, Technical Content Owner, GSoC Admin

281

1

 Co-author of Learning OpenCV Book

282

1

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

283

1

 [email protected]

284

1

285

1

 Antonella Cascitelli

286

1

 Grad student, University of Rome

287

1

 [email protected]

288

1

289

1

 Eric Christiansen

290

1

 PhD, UCSD

291

1

 [email protected]

292

1

293

1

 Stefano Fabri

294

1

 CRR Team leader, University of Rome

295

1

 [email protected]

296

1

297

1

 Victor Eruhimov

298

1

 OpenCV founding team/Senior Researcher

299

1

 Argus/Itseez founder

300

1

 NNU Lecturer

301

1

 [email protected]

302

1

303

1

 Adrian Kaehler

304

1

 Principle Engineer, Applied Minds

305

1

 Co-author of Learning OpenCV Book.

306

1

 [email protected]

307

1

308

1

 Peter Karasev

309

1

 PhD Student, MINERVA Research Group

310

1

 Georgia Tech

311

1

 [email protected]

312

1

313

1

 Vadim Pisarevsky

314

1

 OpenCV founding team/Czar

315

1

 [email protected]

316

1

317

1

 Manuele Tamburrano

318

1

 Grad Student, University of Rome

319

1

 [email protected]

320

1

321

1

 Vincent Rabaud

322

1

 Principle Engineer, Aldebaran Robotics

323

1

 [email protected]

324

1

325

1

  Claudia Rapuano

326

1

  Grad student, University of Rome

327

1

  [email protected]

328

1

329

1

 Grace Vesom

330

1

 Senior Software Engineer, Magic Leap

331

1

 -delete-grace.vesom@-delete_gmail.com

332

1

333

1

 Bence Magyar

334

1

 Pal Robotics

335

1

 [email protected]

336

1

337

1

 Pablo Alcantarilla

338

1

 Toshiba Research Europe Ltd.

339

1

 [email protected]

340

1

341

1

h3.  Back up Mentors

342

1

343

1

 Mark Asbach

344

1

 Fraunhofer IAIS

345

1

 Schloss Birlinghoven

346

1

 Sankt Augustin, Germany

347

1

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

348

1

 [email protected]

349

1

350

1

351

1

 Nicolas Saunier, Ph.D.

352

1

 Assistant Professor

353

1

 Civil, Geological and Mining Department (CGM)

354

1

 Ãcole Polytechnique de MontrÃ©al

355

1

 http://nicolas.saunier.confins.net

356

1

 [email protected]

357

1

358

1

359

1

 Alexander Mordvintsev

360

1

 Software Engineer

361

1

 http://znah.net

362

1

 [email protected]

363

1

364

1

 Andrey Morozov

365

1

 Software Engineer

366

1

 Argus/Itseez

367

1

 [email protected]

368

1

369

1

h2. OpenCV Org. Application to GSoC 2015

370

1

371

1

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

372

1

373

1

h2. Previous Years

374

1

375

1

* 2015 "GSoC 2015 Ideas Page":http://code.opencv.org/projects/opencv/wiki/GSoC_2015

376

1

** "The 2015 Movie":https://www.youtube.com/watch?v=OUbUFn71S4s

377

1

* 2014 "GSoC 2014 Ideas Page":http://code.opencv.org/projects/opencv/wiki/GSoC_2014

378

1

** "The 2014 Movie":https://www.youtube.com/watch?v=3f76HCHJJRA

379

1

* 2013 "GSoC 2013 Ideas Page":http://code.opencv.org/projects/gsoc2013/wiki

380

1

** "The 2013 Movie":https://www.youtube.com/watch?v=_TTtN4frMEA

381

1

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

382

1

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

383

1

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

384

1

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

385

1

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

386

1

387

1

----

Login	Password