Seminar: CSE 741 Fall 2007
Current Problems in Computer Vision


 

A. Course objectives and preliminaries


This is the website for my Fall '07 seminar on computer vision. The purpose of the seminar is to explore (take a guess) current problems in computer vision: those issues, approaches and applications evoking notable current research interest and promise. At the end of the seminar, participants should be aware of trends and directions in current computer vision research and have explored at least one in some depth, given a thorough tutorial presentation on it, and written a report including original research ideas in that domain.

After a few weeks of general survey of selected topics led by the course director Peter Scott (that's me), each registered student will select a topic from the list of selected topics (or chosen by him/herself with my concurrence), and deliver a presentation on that topic.  This website will serve mainly as a repository of files and links relevant to the course. As student presentations come available, they will be added.

Enrollment is limited to grad students with at least one previous course in image processing or computer vision. The group will meet weekly for one 2 1/2 hour session at a time that fits into everyone's schedule. On the first day of class for the Fall semester, Monday Sep 28, I will email everyone who has registered for the course and ask their class and teaching schedules. I will then send another email around indicating what our regular meeting time and place for the semester will be. If you are interested in attending but do not register for the course, please check my office door (Bell 136), I will post the time and place for our meetings as soon as this information is available.

I will have office hours this semester 2:30-3:30PM MWR Bell 136 and can be reached by email at peter@buffalo.edu or phone at 716-645-3180 x 137.

 

B. Syllabus

 

This is the current syllabus, with a useful introductory reference for each topic linked. Registered students are asked to review these references before the class in which they will be surveyed. These references are just basic tutorial  introductions, which give the flavor of the topic but should not be expected to supply detail and technical information adequate for a thorough understanding.



1. Image processing from still images


1.1 Segmentation: fast marching   http://math.berkeley.edu/%7Esethian/Explanations/fast_marching_explain.html
1.2 Shape recovery: level sets  http://math.berkeley.edu/%7Esethian/Explanations/level_set_explain.html
1.3 Segmentation: graph cuts  http://www.cis.upenn.edu/~jshi/GraphTutorial/Tutorial-ImageSegmentationGraph-cut1-Shi.pdf
1.4 Registration: rigid vs non-rigid  http://www.cs.wright.edu/~agoshtas/CVPR04_Registration_Tutorial.html
1.5 Registration of images with maps  Haala_2003.pdf
1.6 JPEG2000   http://stargate.ecn.purdue.edu/~ips/tutorials/j2k/


2. Computer vision from still images

2.1 OR: SVM methods  http://www.support-vector.net/icml-tutorial.pdf
2.2 OR: Learning  LeCun_2004.pdf
2.3 Free-viewpoint rendering http://iphome.hhi.de/smolic/docs/Smolic_ICIP04_FVV.pdf
2.4 Multi-view 3D reconstruction  Vogiatzis_2005.pdf
2.5 Multi-sensor image fusion   http://www.ece.lehigh.edu/SPCRL/IF/image_fusion.htm


3. Video processing

3.1 Particle filters for tracking Li_2004.pdf
3.2 MPEG-4/H.264 video coding  http://www.m4if.org/resources/IEEESpectrum/mpeg-4.htm
3.3 Model-based tracking  http://csdl2.computer.org/comp/proceedings/ismar/2003/2006/00/20060313.pdf
3.4 Tracking using Bayes' nets  http://www.cs.ubc.ca/~murphyk/Software/BNT/Talks/BNT_mathworks.ppt
3.5 Free-viewpoint video  http://www.merl.com/reports/docs/TR2003-137.pdf
3.6 Motion detection  http://lear.inrialpes.fr/people/triggs/events/iccv03/cdrom/iccv03/0734_viola.pdf
3.7 Motion segmentation Weiss_2003.pdf


4. Computer vision from video

4.1 Detecting surprises, abnormalities Koller_2002.pdf
4.2 Modelling, identifying behavior  Gong_2002.pdf
4.3 Detecting, tracking people  Cutler_2003.pdf
4.4 Wayfinding for the vis impaired  Nagarajan_2003.pdf


5. Mathematical foundations

5.1 Representation: wavelets http://www.amara.com/IEEEwave/IEEEwavelet.html

5.2 Superresolution  http://cmc.rice.edu/docs/docs/Wag2004Apr5ImageSuper.pdf

5.3 Learning Weng_2000.pdf

5.4 Modelling uncertainty: prob, belief, fuzzy, rough sets, intervals, etc. Smets_1999.pdf

5.5 Evaluation methods Martens_2002.pdf

5.6 Mosaicking Hsieh_2003.pdf

5.7 A contrario detection methods VISTA_2004.pdf

5.8 Belief and image uncertainty Sun_2003.pdf



6. Architectures and hardware

6.1 FPGA architectures http://www.us.design-reuse.com/articles/article10943.html

6.2 Vision on a chip http://www.nasatech.com/Briefs/Feb00/NPO20449.html

6.3 Smart cameras Leeser_2004.pdf



7. Miscellaneous

7.1 Watermarking  Perez_200X.pdf

7.2 Image steganography Johnson_1997.pdf

7.3 Inpainting methods http://www.math.ucla.edu/~imagers/htmls/inp.html



8. Topics not discussed (duplicates other courses)

1. No face recognition
2. No image indexing or retrieval
3. No biometrics (eg. fingerprints)
4. No cv for bioinformatics
5. No active or animate vision

 

 Class Schedule

Student presenters and their topics will be filled in as they become scheduled.

 

Date

Presenter

Topic

Prep Readings

Aug 31

 

No meeting

 

Sep   7

Peter Scott

Organizational meeting

 

Sep 14

Peter Scott

Overview of Topics I

1.1-2.5

Sep 21

Peter Scott

Overview of Topics II

1.5-3.7

Sep 28

Peter Scott

Overview of Topics III

4.1-7.3

Oct  5

Hung Ho

2.3 Free viewpoint rendering

Carranza. Kameda

Oct 12

Thomas Tiju

3.6 Motion detection

Tian

Oct 19

Vincent Chen

4.3 Detecting, tracking people

Cutler, Ramanan

Oct 26

Omkar Mehendale

7.2 Image steganography

Gan, Queirolo

Nov 2

Damien Jose

5.9 Gaussian mixture models

Goldberger

Nov 9

Prashant Gokhale

3.2 MPEG-4

Sikora

Nov 16


No class


Nov 23

Fall Break

No class

 

Nov 30

 

Siddharth Jayaraman
Ganesh Talele

OR Learning with SVMs (ppt, pdf)

Inpainting methods (ppt, pdf)

LeCun, Pontil

Bertalmio, Oleveira