CS 787 - Computational Vision

Winter 2003
Department of Computer Science
University of Waterloo

Instructor: Richard Mann, DC2510, x3006, mannr@uwaterloo.ca

Lectures: Mondays 2:30-5:00, Room DC3313.
First class: Monday 6 Jan, 2003.

Grades

Please come and see me if you want to discuss grades. I also have detailed comments on your projects.

         A1(25)  A2(17)  A3(20) Asst(%)  Proj(%) Grade(%)

96127845  25.0    17.0    19.0   98.33      96      97
98204645  23.0    17.0    18.0   94.00      92      93
00237239  23.0    13.0    13.0   77.82      78      78
98166305  11.0    10.5    11.0   53.59      74      64

98170875  23.0    17.0    16.0   90.67      87      89
20105626  23.0    12.0    16.0   80.86      83      82
97142203  21.0    16.0    19.0   91.04      94      93
20096923  20.0    14.0    13.0   75.78      90      83

92800139  25.0    13.5    19.0   91.47     INC     INC
99801223  21.0    14.5    16.0   83.10      80      82
97097097  25.0    17.0    19.0   98.33      91      95
95124981  24.0    16.5    19.0   96.02      92      94

20114144  25.0    17.0    17.0   95.00      90      93
99178686  24.0    17.0    19.0   97.00      83      90
97029368  18.0    15.0    15.0   78.41      88      83
20105579  20.0    16.0    15.0   83.04      86      85

99801648  23.0    11.5    19.0   84.88      87      86
98113680  23.0    15.0    16.0   86.75      81      84

News:

Project deadline EXTENDED. Due: Tuesday 22 April, 2003
This is the last day of the Undergraduate exam period. There will be no further extensions.

Project help: Email me to arrange a meeting and/or send me a URL to your material.

Last Class: Mon 31 March. Topic: "Computational Perceivers".

"Old" News:

Assignment #3 is ready. Details below. Due: Wed 12 Mar., 5pm

Assignment #2 is ready. See details below. Due: Wed 26 Feb, 5pm

Project proposals, due Monday 17 Feb. Original ideas, research or otherwise, are welcome! Feel free to contact me by Email or after the lectures...

Matlab access: Please use undergraduate environment (bacon, etc). Graduate students may get a course account (bring your Watcard to MC3011).

Assignment #1 is ready. See below details below. Due: Wed 12 Feb, 5pm

Undergrad students can register with Quest. But you need to fill out an "override form", get it signed, and return to "CS Undergrad Office". (Location?)

Books (Trucco & Verri, Forsyth & Ponce, and Horn) on reserve in DC library. 3hr loan period.

Please check newsgroup (uw.cs.cs787). I've just answered some questions about the project.

Summary

Computational vision is concerned with the automatic processing of image and video data for scene reconstruction, object recognition, navigation, and activity detection.

The objective of this course is to provide a concise treatment of some fundamental problems in computational vision. This course will focus on a core set of problems where efficient and robust algorithms can be applied. Students will be required to implement several algorithms using real datasets. In addition to providing practical approaches and algorithms, this course will provide the foundation required to pursue research computational vision.

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. Programming will be done in Matlab.
Note: this course is open to undergraduates, with permission of the instructor.

Marking (tentative)

Assignments: 50%

Four assignments. Handwritten + small programming component.

Final project: 50%

Implementation or literature review.

References

All required material will be provided in lectures. Possible references include:

Introductory Techniques for 3D Computer Vision, E. Trucco and A. Verri, Prentice-Hall, 1998.

A concise treatment, focussing on geometric approaches to vision.
The course closely follows this book.
Computer Vision, A modern approach, D. A. Forsyth and J. Ponce, Prentice Hall, 2003.

Comprehensive treatment of most areas of vision. A good resource
for background reading and choosing project ideas.

Robot vision, B. K. P. Horn, MIT Press, 1986.

Vision, D. Marr. Freeman, 198x.

Three-Dimensional Computer Vision, O. Faugeras, MIT Press, 1993.

Digital Image Processing, K. R. Castleman, Prentice Hall, 1996.

I will put all of these books on reserve in the library. You may also purchase Trucco and Verri's book in the University bookstore.

Lecture Schedule (preliminary)

Lecture	Topic	References
1. (Jan 6)	Vision Overview; Image formation	Horn Ch2, Trucco and Verri Ch2 Related link: - Combining images of varying exposure (S. Mann, Toronto)
2. (Jan 13)	Lighting and reflectance models Application: Photometric stereo	Horn Ch10 Related links: - Lightness and shading illusions (E. Adelson, MIT) - Shape from shading (M. Langer, McGill)
3. (Jan 20)	Filtering: Linear systems, Fourier theory Note: did not cover discrete case (finite size images, sampling). This will be covered in Lecture #4.	Horn Ch6, Castleman Ch 10
4. (Jan 27)	Edge and Feature detection. Application: good features to track (corners)	Trucco and Verri Ch4
5. (Feb 3)	Parameterized features and model fitting. Application: fitting lines to data using robust and mixture models.
6. (Feb 10)	Optical flow Application: mixture models for optical flow	Trucco and Verri Ch8, Horn Ch12 References: - Mixture models for optical flow (A. Jepson, Toronto) - Optical Snow
7. (Feb 17)	Structure from motion	Trucco and Verri Ch8
8. (Feb 24)	Stereo (Baseline case)	Trucco and Verri Ch7; Faugeras Sect 6.6
9. (Mar 3)	Stereo (Epipolar geometry) Application: 3d scene reconstruction	Trucco and Verri Ch7; Faugeras Ch7
10. (Mar 10)	Object Recognition: View-based approaches. Application: PCA for object recognition	Trucco and Verri Ch9,
11. (Mar 17)	Object Recognition: Model-based approaches. Application: Object search	Trucco and Verri Ch9
12. (Mar 24)	Computational perceivers. Applications: Scene labelling, perception of scene dynamics
13. (Mar 31)	Reserved.

Assignments

Assignment #1: Lighting, Fourier analysis, Feature detection.

Assignment text (PDF), complete package (tar, zipped).

Due: Wed, 12 Feb, 2003, 5:00pm

Notes:

To do the assignments you will need access to Matlab. This is available on the Undergrad computing environment. Graduate students may get course accounts by visiting MC3011 (bring your "Watcard").

You will need to install the following course software (tar, zipped) in your home directory.

Assignment #2: Robust and Mixture Models for Optical Flow.

Assignment text (PDF), complete package (tar, zipped)

Due: Wed, 26 Feb, 2003, 5:00pm

Assignment #3: Stereo Vision: Block matching and Dynamic programming.

Assignment text (PDF), complete package (tar, zipped)

Due: Wed, 12 Mar, 2003, 5:00pm