Important Notes:

Project: Brief (one paragraph) proposal due Tues 7 Feb. If you require help selecting a project, please contact me. If you can't decide on a project, consider implementing some of the algorithm(s) discussed in class (eg., Optical flow, Factorization method for structure from motion, etc). I can provide you with sample data.

Course account:

Administrivia:

Time: Winter 2006; Lectures T,Th 11:30-1:00, MC4042.  Office hours Th 3:30-5:00 (DC2510).  Tutorial time TBA.  Note: Tutorials will be given only when necessary (eg., help with assignments). Dates will be announced in class.

Instructor: Richard Mann, DC2510, x3006, mannr@uwaterloo.ca, http://www.cs.uwatleroo.ca/~mannr

Prerequisites: There are no formal prerequisites for this course, however, it is advisable to have some exposure to numerical computation, especially linear algebra (eg., CS370), and some basic programming experience (Matlab).

References: All required material will be provided in lectures. The following recommended books will be on reserve in the library:

• E. Trucco and A. Verri, Introductory Techniques for 3D Computer Vision, Prentice-Hall, 1998 (ISBN 0-13-261108-2).
• K. R. Castleman, Digital Image Processing, Prentice Hall, 1996.
• B. K. P. Horn, Robot vision, MIT Press, 1986.
•  Selected journal articles

Grading (tentative): The lecture material will be same for undergrad and grad students. The grading will be: four assignments (50%), Project (50%). The project could include a literature review, an experimental analysis of some algorithm, an implementation of a new algorithm, or any other topic of mutual interest to the student and instructor. Graduate students will be given additional questions on the assignments and/or will be required to undertake a larger project.

General Information:

• Course outline(includes list of readings)
  

Assigments:

• Assignment #1.  Image formation and Lighting.
• Out: 12 Jan, 2006.  Due: 11:30am (start of class), 31 Jan, 2006.
• Assignment #2. Linear Systems and Feature Detection.  Additional (Matlab) software (for Q1(b)).
  
• Out: 31 Jan, 2006.  Due: 11:30am, 14 Feb, 2006.
• Assignment #3. Mixture models for optical flow.
  
• Out: 14 Feb, 2006.  Due: 11:30am, Tues 7 Mar, 2006.
• Assignment #4.  Stereo vision: block matching and dynamic programming.
• Out: 2 Mar, 2006.  Due: 11:30am, Thurs 16 Mar, 2006.
  

Lectures:

• Tues Jan 3. Vision overview (half of first lecture); Image formation, optics. Radiometry (Horn Ch10, Trucco and Verri Ch2)
• Thur Jan 5. Combining images of different exposure. References: Mann S. and Picard W., "IS\&T's 48th annual conference, Cambridge, MA. May 1995.; Debevec P.E. and Malik J., Siggraph 1997.
• Tues Jan 10. Image formation, shading, gradient space, photometric stereo. (Horn Ch10)
• Thur Jan 12. Linear systems and filtering. (Horn Ch6)
• Tues Jan 17. Fourier theory. (Castleman Ch10)
• Thur Jan 19. Fourier theory (Part 2). (Castleman Ch10, 11)
• Tues Jan 24. Feature detection, Edges (Trucco and Verri, Sect. 4.2)
• Thur Jan 26. Feature detection, part 2.  Corners (Trucco and Verri, Sect. 4.3), SIFT featrues (David Lowe, UBC).
• Tues Jan 31. Data fitting: Least squares.
  
• Thur Feb 2.  Data fitting: Robust models.
  
• Tues Feb 7. Data fitting: Mixture models.
• Thur Feb 9. Optical flow.
• Tues Feb 14. Mixture models for optical flow.
• Thur Feb 16. *class cancelled* ("snow day")
  
• Tues Feb 21. Optical snow
• Thur Feb 23. *class cancelled* ("reading days")
• Tues Feb 28. Stereo, baseline case.
• Thur Mar 2. Stereo, dynamic programming.  Begin Epipolar geometry
• Tues Mar 7. Epipolar geometry
• Thus Mar 9. Structure from motion (continuous methods)
• Tues Mar 14. Structure from motion (discrete methods)
• Thus Mar 16. Object recognition: PCA
  
• Tues Mar 21. Object recognition: Alignment methods
  
• Thurs Mar 23.
• Tues Mar 28.
• Wed Mar 29. Last day of classes.  Projects due!

Reference material:

Course software:

Project ideas:

• Implementation and/or further study of algorithms described in class
  • Mixture models,
  • Optical flow,
  • Image alignment for composites,
  • Structure from motion, etc.
• Literature review (a brief review of a current research area)
  • vision applications (eg., medical image processing, robot control, etc.)
  • current subfield (eg., object recognition, stereo, etc)
  • related areas (eg., psychophysics)
• Any other vision-related topic:
  • Note: I recommend specifying a small, well-defined, problem, even if you plan an ambitious project. You can always add to it later.

Additional References (not required for course):