ECE 893: Computer Vision Seminar
Fall 2003
3:00-3:50pm F, 223 Riggs
Objective
In this course, we will review recent research publications related to
visual detection, recognition, and tracking of people (or other objects)
visual motion analysis
stereo vision
etc.
Plan
Each week we will meet to discuss one paper from the recent literature. Students should read the paper beforehand and prepare questions and comments in order to participate fully in the discussion. Additionally, students should volunteer to lead the discussion at least once during the semester (don't worry: it's okay if you don't understand the paper!). To get 1 hour credit for the course, students must
attend each week
write a summary of one paper each week (four or five sentences), answering
What did they do?
What are the strengths / weaknesses / potential improvements?
lead the discussion once during the semester
Instructor
Prof. Stan Birchfield
207A Riggs Hall
656-5912
stb clemson.edu (insert @ symbol)
Schedule
Date | Paper(s) | Discussion leader(s) |
8/29/03 | intro / overview | Stan Birchfield |
9/5/03 |
Rowley, Baluja, and Kanade,
Neural-network based face detection, CVPR, 1996; or Rowley, Baluja, and Kanade, Neural-network based face detection, PAMI, 20(1):23-38, 1998 |
Bragad Natarajan |
9/12/03 | Viola and Jones,
Rapid Object Detection using a Boosted Cascade of Simple Features,
CVPR 2001; [optional background reading: Freund and Schapire, A short introduction to boosting, JJSAI, 1999] |
Amar Subramanya |
9/19/03 | Shi and Tomasi,
Good features to track, CVPR 1994; [optional background reading: Lucas and Kanade, An iterative image registration technique with an application to stereo vision , IJCAI 1981 |
Stan Birchfield |
9/26/03 | Wang and Adelson, Representing moving images with layers, TIP, 3(5):625-637, 1994 | Raghu Kumaran |
10/3/03 | Brostow and Essa, Motion Based Decompositing of Video, ICCV 1999 | Guang Zeng |
10/10/03 | Schodl and Essa,
Depth layers from occlusions, CVPR 2001; [optional background reading: minimum description length (MDL) web site] |
Yi Jiang |
10/17/03 | C. Tomasi and T. Kanade, Shape and Motion from Image Streams
under Orthography: a Factorization Method, IJCV, 9(2): 137-154, 1992; or C. Tomasi and T. Kanade, Factoring Image Sequences into Shape and Motion, Proceedings of IEEE Workshop on Visual Motion, 1991; or C. Tomasi and T. Kanade, Shape and Motion Without Depth, ICCV 1990 |
Stan Birchfield |
10/24/03 | Haritaoglu, Harwood, and Davis, W4: Who? When? Where? What? A real time system for detecting and tracking people, FAGR 1998 | Sunil Guduru |
10/31/03 | Jepson, Fleet, and El-Maraghi, Robust Online Appearance Models for Visual Tracking, CVPR 2001 | Shrinivas Pundlik |
11/7/03 | Birchfield and Tomasi,
Multiway cut for stereo and motion with slanted surfaces, ICCV 1999; [optional background reading: Boykov, Veksler, Zabih, Markov random fields with efficient approximations, CVPR 1998] |
Stan Birchfield |
11/14/03 | W. T. Freeman and E. H. Adelson, The design and use of steerable filters, PAMI 13(9):891-906, 1991 | Sriram Rangarajan |
11/21/03 | Tommasini et al., Making Good Features Track Better, CVPR 1998 | Vikram Iyengar |
Resources
Computer vision books
Abbreviations
Potential papers to cover in the future
Toyama et al. Wallflower: Principles and Practice of Background Maintenance, ICCV 1999
Ivanov et al., Fast Lighting Independent Background Subtraction, IEEE Workshop on Visual Surveillance, 1998
Chafik KERMAD, Christophe COLLEWET, Improving Feature Tracking by Robust Points of Interest Selection,
Torresani and Bregler, Space-time tracking, ECCV 2002
M. J. Black and D. J. Fleet, Probabilistic Detection and Tracking of Motion Boundaries Int. J. of Computer Vision, 38(3):231-245, July 2000 Or Probabilistic detection and tracking of motion discontinuities in ICCV 1999