ECE 893-5 Computer Vision Seminar

Fall 2005

In this course we review recent research publications related to visual detection, recognition, and tracking of people (or other objects), visual motion analysis, visual reconstruction, stereo vision, acoustic localization, robotic sensing, and other related topics. Each week we 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.  In addition, students are encouraged to volunteer to lead the discussion at least once during the semester.  All students are welcome to attend, whether or not they are signed up for the course. (For details on how to get credit, see the bottom of this page.)

Here are some miscellaneous computer vision resources.

Schedule

Week	Date	Paper	Discussion leader
1	8/24	Intro / overview	Stan Birchfield
2	8/31	Thomas Serre, Lior Wolf, Tomaso Poggio, Object recognition with features inspired by visual cortex, CVPR 2005.	Shrinivas Pundlik
3	9/7	Shai Avidan, Ensemble Tracking, CVPR 2005.	Sriram Rangarajan
4	9/14	Antonio Torralba, Kevin P. Murphy, William T. Freeman, Sharing features: efficient boosting procedures for multiclass object detection, CVPR 2004	Nikhil Rane
5	9/21	Dorin Comaniciu, Visvanathan Ramesh, Peter Meer, Kernel-Based Object Tracking, IEEE Trans. Pattern Analysis and Machine Intelligence, 25(5):564-577, May 2003	Xiao Wang
6	9/28	Kentaro Toyama, John Krumm, Barry Brumitt, Brian Meyers, Wallflower: Principles and Practice of Background Maintenance, ICCV 1999	Abhishek Aneja
7	10/5	[cancelled for departmental meeting]
8	10/12	M. Bleyer and M. Gelautz, A layered stereo matching algorithm using image segmentation and global visibility constraints, ISPRS Journal of Photogrammetry & Remote Sensing, 59:128-150, 2005.  (Earlier version in IEEE International Conference on Image Processing, pp. 2997-3000, 2004)	Brijesh Pillai
9	10/19	Y. Ivanov, A. Bobick, and J. Liu, Fast Lighting Independent Background Subtraction, IJCV 2000	Guang Zeng
10	10/26	[cancelled]
11	11/2	Zhang H., Huang W., Huang Z., Li L., Affine Object Tracking with Kernel-based Spatial-Color Representation, CVPR 2005.	Zhichao Chen
12	11/9	Kidron E., Schechner Y., Elad M., Pixels that Sound, CVPR 2005.	Prashant Oswal
13	11/16	Michael Siracusa, Louis-Philippe Morency, Kevin Wilson, John Fisher, and Trevor Darrell, A MultiModal Approach for Determining Speaker Location and Focus, ICMI 2003	Thomas Polon
14	11/23	[break]
15	11/30	Ahmed Elgammal, Ramani Duraiswami, and Larry S. Davis, Probabilistic Tracking in Joint Feature-Spatial Spaces, CVPR 2003	Pramod Potluri
16	12/7	Omar Javed, Zeeshan Rasheed, Orkun Alatas and Mubarak Shah, KNIGHTM:A Real Time Surveillance System for Multiple Overlapping and Non-Overlapping Cameras, The fourth International Conference on Multimedia and Expo (ICME 2003), Baltimore, Maryland, 2003.	Stan Birchfield

Potential future papers

• J. Xiao and M. Shah, Motion layer extraction in the presence of occlusion using graph cut, CVPR 2004
• Henele Adams, Sanjiv Singh, and Dennis Strelow. An empirical comparison of methods for image-based motion estimation. IEEE/RSJ International Conference on Intelligent Robots and Systems, October 2002. (PDF)
• A. Barbu, S.C. Zhu, Graph Partition By Swendsen-Wang Cuts, ICCV 2003
• S. Avidan, Support vector tracking, CVPR 2001
• Black and Jepson, Eigentracking:  Robust matching and tracking of articulated objects using a view-based representation, IJCV, 26(1), 1998
• Khan, Balch, Dellaert, A Rao-Blackwellized particle filter for eigentracking, CVPR 2004
• Freeman and Roth, Orientation histograms for hand gesture recognition, Workshop on AFGR, 1995
• Perez, Hue, Vermaak, Gangnet, Color-based probabilistic tracking, ECCV 2002
• Y. Wu, Robust visual tracking by integrating multiple cues based on co-inference learning, IJCV, 58(1), 2004
• Philomin, Duraiswami, Davis, Quasi-random sampling for condensation, ECCV 2000
• Brown, Burschka, and Hager, Advances in Computational Stereo, PAMI 2003.
• Tao Zhang, Daniel Freedman, Tracking Objects using Density Matching and Shape Priors, ICCV 2003
• Manifold learning web page
• Belkin, Niyogi, Laplacian eigenmaps for dimensionality reduction and data representation, Neural Comptuation, Vol. 15, Issue 6, June 2003
• Antonio Torralba Kevin P. Murphy William T. Freeman, Sharing features: efficient boosting procedures for multiclass object detection, CVPR 2004
• Baker and Matthews, Lucas-Kanade 20 years on:  A unifying framework, IJCV 56(3):221-255, 2004  webpage
• Molton, Davison, and Reid, Parameterisation and probability in image alignment, ACCV 2004.
• A. Davison, "3D Simultaneous Localisation and Map-Building Using Active Vision for a Robot Moving on Undulating Terrain", CVPR 2001
• Hammadi Nait-Charif & Stephen J. McKenna, Head Tracking and Action Recognition in a Smart Meeting Room, PETS 2003
• Yann, LeNet-5 convolutional neural networks -- homepage
• Kass, Witkin, and Terzopoulos, Snakes:  Active Contour Models, ICCV 1987
• Plumpe et al., Modeling of the Glottal Flow Derivative Waveform with Application to Speaker Identification, IEEE Transactions on speech and audio processing, 7(5), Sept. 1999
• Grimson et al., Using adaptive tracking to classify and monitor activities in a site, CVPR 1998
• M. J. Jones and J. M. Rehg, Statistical Color Models with Application to Skin Detection, Int. J. of Computer Vision, 46(1):81-96, Jan 2002.
• Morency, Rahimi, Darrell, Adaptive View-based Appearance Model, CVPR, 2003
• M. Irani, Multi-Frame Optical Flow Estimation Using Subspace Constraints, ICCV 1999
• Wu and Huang,  A Co-inference Approach to Robust Visual Tracking
• Sigal, Sclaroff, and Athitsos,  Estimation and prediction of evolving color distributions for skin segmentation under varying illumination, CVPR 2000
• Choo and Fleet.  People tracking using hybrid Monte Carlo filtering, ICCV 2001
• Elgammal and Davis, Probabilistic framework for segmenting people under occlusion, ICCV 2001
• Rui and Chen, Better proposal distributions:  Object tracking using unscented particle filter, CVPR 2001
• Toyama and Blake, Probabilistic Tracking in a Metric Space, ICCV 2001
• McKenna and Gong
• H. Schneiderman, T. Kanade. A Statistical Method for 3D Object Detection Applied to Faces and Cars, CVPR 2000
• Belhumeur, P.N., Hespanha, J.P., Kriegman, D.J., Eigenfaces vs. Fisherfaces: Recognition Using Class-Specific Linear Projection, PAMI(19), No. 7, July 1997, pp. 711-720. 
• Veksler, Fast Variable Window for Stereo Correspondence using Integral Images, CVPR 2003
• Sullivan, Blake, Isard, and MacCormick, Object Localization by Bayesian Correlation, ICCV 1999
• Horprasert, Harwood, Davis, A robust background subtraction and shadow detection,
• Javed, Shafique, Shah, A hierarchical approach to robust background subtraction using color and gradient information,
• Jianbo Shi, Serge Belongie, Thomas Leung, Jitendra Malik, Image And Video Segmentation: The Normalized Cut Framework, ICIP 1998
• Boykov, Veksler, Zabih, Markov Random fields with efficient approximations, CVPR 1998
• Chafik KERMAD, Christophe COLLEWET, Improving Feature Tracking by Robust Points of Interest Selection,
• Torresani and Bregler, Space-time tracking, ECCV 2002
• "The Template Update Problem", I. Matthews, T. Ishikawa, and S. Baker, BMCV, 2003

Administrivia

Instructor: Stan Birchfield, 207-A Riggs Hall, 656-5912, email: stb at clemson
Meetings: 4 - 5 pm Wednesdays, 223 Riggs Hall

To receive the 1-hour credit, students must

• sign up for the course at the beginning of the semester
• attend each week
• write a brief summary of each paper covered (five sentences minimum), answering
  • What did the authors do?
  • What are the strengths / weaknesses / potential improvements?
Summaries should be turned in via email to the instructor with a subject line of
    Paper summary: Author
where Author is replaced by the name of the first author of the paper. Non-conforming emails will be returned.  Summaries are due 15 minutes before the beginning of the seminar.
• lead the discussion at least once during the semester. You may select a paper either from the suggested list above or you may find one yourself. Either way, you should notify the instructor and get approval of the paper at least one week before your presentation.
  (Note:  A paper summary is not required for the week that you lead the discussion.)