CPS 296.1
Introduction to Computer Vision
Spring 2006

Course Mechanics

Project Guidelines

Project Information

General Resources

Places and Dates

•  Levine Science Research Center (LSRC) room A156, Tuesdays and Thursdays 10:05-11:20.
   A156 is across from the Blue Express Cafeteria.

Announcements

• Please watch this space for announcements.

Newsgroup

A newsgroup is available for this class. The group can be accessed as follows:

• Through the web at http://groups.google.com/group/duke_cs_cps296_1/

• By email at duke_cs_cps296_1@googlegroups.com

 Course Outline, Readings, and Software

This course explores some of the most successful ideas in computer vision at an introductory level. Linear algebra and probability are prerequisites. For each of the following topics, we will cover the basic concepts, look at one or two algorithms that work well, and discuss limitations and possible extensions. The numbers of lectures indicated for each topic are approximate.
 

Lectures	Module	Description	Readings	Samples and Software
1	Introduction	State of the art, fundamental challenges, IGVC competition		Powerpoint with examples
2	IGVC	Strategy. Project assignments. Hardware, software, logistics.	IGVC rules, DARPA tech papers
3, 4	Image Analysis	Convolution, smoothing, derivatives, median filtering, edge detection	[1], [2]	Convolution code, Edge samples
5	IGVC	IGVC status, issues, IGVC/DARPA tech papers
6	Image Formation	Relationship between world and image	[3]
7, 8, 9, 10	Stereo	Geometry, similarity metrics, rank and census transforms. Dynamic-programming, belief propagation	[4], [5], [6], [7], [8]	Stereo block matching browser.
11	IGVC	IGVC. Shashi and Stephen on Stanley, Whitespace
12, 13	Optical Flow	Definitions, issues, algorithms, with emphasis on Lucas and Kanade	[9], [10]	SSD motion software
14	IGVC	IGVC. Seda, Amber, Abishek on Prospect 11, planet traversability, collision avoidance, stereo obstacle avoidance
15, 16	Segmentation	For both images and flow. Split/merge methods, clustering	[11], [12], [13]	k-means and EM software
17	IGVC	IGVC. Sam, Christopher, Laura on Calculon, probabilistic algorithms for robotics, and Ion.
Spring Recess
18, 19, 20	Tracking	Appearance and motion models, Kalman filtering, particle filters	[14], [15], [16]	Kalman code for [14]
21	IGVC	IGVC. Monika and Joe on Blue Team and Team Caltech
22, 23, 24	Recognition	Generative models, discriminative classifiers. Features. Sample algorithms	[17], [18], [19]	k nearest neighbors on the plane. See also the OpenCV library
25, 26	IGVC	IGVC final project presentations

1. C. Tomasi. Convolution, smooting, and image derivatives. Class handout in PDF.
2. J. Canny. A computational approach to edge detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, 8(6):679-698, 1986. Class handout in paper form.
3. C. Tomasi. Image Formation. Class handout in PDF.
4. M. Z. Brown, D. Burschka, and G. D. Hager. Advances in computational stereo. IEEE Transactions on Pattern Analysis and Machine Intelligence, 25 (8) 993–1008, 2003. PDF.
5. R. Zabih and J. Woodfill. Non-parametric local transforms for computing visual correspondence. European Conference on Computer Vision, II:151–158, 2004. PDF.
6. J. I. Woodfill, G. Gordon, R. Buck. Tyzx DeepSea high speed stereo vision system. IEEE Conference on Computer Vision and Pattern Recognition Workshop, 3:41–45, 2004. PDF.
7. A. F. Bobick and S. S. Intille. Large occlusion stereo. International Journal of Computer Vision, 33(3):181-200, 1999. PDF.
8. J. Sun, N. Zheng and H. Shum. Stereo Matching Using Belief Propagation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 25 (7), 1–14, 2003. PDF.
9. J. L. Barron, D. J. Fleet and S. S. Beauchemin. Performance of optical flow techniques. International Journal of Computer Vision, 12(1), 43–77, 1994. The Postscript version is more legible on screen than the PDF version, but both print well.
10. C. Tomasi and T. Kanade.  Detection and tracking of point features. Technical Report CMU-CS-91-132, 1991. PDF.
11. C. Tomasi. Estimating Gaussian mixture densities with EM - A Tutorial. Class handout in PDF. See also tutorials on EM by Dellaert, Minka, Rennie, and Weiss.
12. S. L. Horowitz and T. Pavlidis. Picture segmentation by a tree traversal algorithm. Journal of the ACM 23(2):368–388, 1976. PDF.
13. J. Shi and J. Malik. Normalized cuts and image segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 22(8), 888–905, 2000. PDF.
14. C. Tomasi. Stochastic Estimation. Chapter 7 of the notes for mathematical methods class. PDF.
15. M. Isard and A. Blake CONDENSATION - Conditional density estimation for visual tracking. International Journal of Computer Vision, 29(1), 5–28, 1998. PDF.
16. A. Litvin, J. Konrad, W. C. Karl. Probabilistic video stabilization using Kalman filtering and mosaicking.IS&T/SPIE Symposium on Electronic Imaging, Image and Video Communications and Processing, 2003. PDF and videos.
17. Y. Freund and R. E. Schapire. Experiments with a New Boosting Algorithm. 13th International Conference on Machine Learning, 148–156, 1996. PDF.
18. P. Viola, M. J. Jones. Robust real-time face detection. International Journal of Computer Vision, 57(2), 137–154, 2004. PDF.
19. M. J. Jones and J. M. Rehg. Statistical color models with application to skin detection. International Journal of Computer Vision, 46(1):81–96, 2002. PDF.

Homework

• Homework 1, due on February 7. You will also need images circles.gif and lab.gif, and the Matlab function unwarp.m. All files for this homework assignment are also available as a single zip archive.

• Homework 2, due on March 9. You will also need the Matlab functions ssd.m, brute_force.m, window.m, and showStep.m, and image files hand.pgm and edges.pgm. All files for this homework assignment are also available as a single zip archive.

Teaching Staff

Carlo Tomasi, Instructor

E-mail address: tomasi@cs.duke.edu
Office Hours: By appointment
Office Location: D213 LSRC
Office Phone: (919) 660-6539
FAX: (919) 660-6519