กก

CE 290V: Advanced Topics in Visual Computing

CE 290V is advanced course in image analysis and computer vision. Topics include motion analysis, video registration, stereo, image-based rendering, object detection, object recognition, object tracking, and event detection. Mathematical tools including the variational method, belief propagation in Bayesian net, graph cut, the hidden Markov model, and various techniques in statistical machine learning.

Text Books

As a growing research area, there is no single good textbook. The suggested reference book is กฐComputer Vision -- A modern approach,กฑ by David Forsyth and Jean Ponce, Prentice Hall, 2002. A collection of papers will be assigned to student for reading and discussion. A high quality course project is expected by the end of the course.

Prerequisites

EE264 and CE 264 are recommended but not required. Good background in linear algebra is expected.

Presentation and Lecture Schedule

Papers will be assigned and students will make presentations on the papers and their project. The instructor will complement the presentation with more insights and references.

Assessment

Paper presentation 40%

Project 60%

Week	Topic and Papers
1	Motion analysis: (TBD) กค S. S. Beauchemin and J. L. Barron. The computation of optical flow. ACM Computing Surveys, 27(3):433--467, 1995. กค J.R. Bergen, P. Anandan, K.J. Hanna, and R. Hingorani. Hierarchical model-based motion estimation. In Proc. ECCV, pages 237--252, 1992. Course presentations: 3/30 - Motion analysis
2	Video registration: (TBD) Steve Hsu's talk at the Workshop on Video Registration on July 13, 2001 . Download here. Steve Hsu, S. Samarasekera, R. Kumar, H.S. Sawhney, กฐPose Estimation, Model Refinement, and Enhanced Visualization Using Video,กฑ in Proc. CVPR 00, Hilton Head Is., SC, vol. I, 488--495, June 2000 Course presentations 4/1 - Video Registratio (Steve Hsu).
3	Stereo computation: กค C. L. Zitnick and T. Kanade, กฐA cooperative algorithm for stereo and occlusion detection,กฑ CMU-RI-TR-99-35, October 1999. กค K. N. Kutulakos and S. M. Seitz, กฐA theory of shape by space carving,กฑ in Proc. Seventh International Conference on Computer Vision (ICCVกฏ99) , pp. 307-314, 1999 กค Y. Boykov, O. Veksler, and R. Zabih, กฐFast approximate energy minimization via graph cuts,กฑ in Proc. Int. Conf. on Computer Vision, September 1999
4	Image based rendering (TBD) กค M. Levoy and P. Hanrahan. กฐLight field renderingกฑ. In Computer Graphics Proceedings, Annual Conference Series, Proc. SIGGRAPHกฏ96, August 1996. ACM SIGGRAPH. กค Wojciech Matusik , Chris Buehler , Ramesh Raskar , Steven J. Gortler , Leonard McMillan, Image-based visual hulls, Proceedings of the 27th annual conference on Computer graphics and interactive techniques, p.369-374, July 2000. กค Andrew Fitzgibbon , Yonatan Wexler , Andrew Zisserman, Image-based rendering using image-based priors, Proceedings of the Ninth IEEE International Conference on Computer Vision, p.1176, October 13-16, 2003.
5	Object detection (TBD) กค Schneiderman H., and T. Kanade. "A Statistical Method for 3D Object Detection Applies to Faces and Cars," Proc. IEEE Conference on Computer Vision and Pattern Recognition, pages 746-751, 2000. กค P. Viola and M. Jones, กฐRapid object detection using a boosted cascade of simple features,กฑ in IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Dec. 2001. กค Y. LeCun, L. Bottou, Y. Bengio, and P. Haffner, "Gradient-based learning applied to document recognition, " Proceedings of the IEEE, vol. 86, pp. 2278--2324, November 1998.
6	Object recognition (TBD) M. Turk and A. Pentland, กฐEigenfaces for recognition,กฑ J. Cognitive Neuroscience, vol. 3, no. 1, 1991. W. Y. Zhao, R. Chellappa, A. Rosenfeld, and P. J. Phillips. Face recognition: A literature survey. UMD CfAR Technical Report CAR-TR-948, 2000.
7	Visual tracking (TBD) กค D. B. Reid, An algorithm for tracking multiple targets, IEEE Trans. Automatic Control, vol. 24, no. 6, pp. 843-854, Dec. 1979. กค M. Isard and A. Blake, "Condensation -- conditional density propagation for visual tracking," International Journal of Computer Vision 29(1), pp. 5--28, 1998. กค D. Comaniciu, V. Ramesh, and P. Meer, กฐReal-time tracking of non-rigid objects using mean shift,กฑ in Proc. Computer Vision and Pattern Recognition, volume 2, pages 142-149, Hilton Head, SC, 2000.
8	Event Detection: (TBD) กค F. Porikli, T. Haga กฐEvent Detection by Eigenvector Decomposition Using Object and Frame Featuresกฑ, IEEE Int. Conference on Computer Vision and Pattern Recognition, Maryland , 2004 กค Shaogang Gong, Tao Xiang: Recognition of Group Activities using Dynamic Probabilistic Networks. ICCV 2003: 742-749.
9	Final Project
10	Final Presentation

Project Topics:

(More to come)

กก