         
|
GRASP Lab Seminar 2003-2004
September 12, 1:00 PM, Levine Hall 307, hosted by Jianbo Shi.
Sudeep
Sarkar
University of South Florida
The Human ID Gait Challenge Problem
Abstract: Identification of people by analysis of gait patterns extracted from video has recently become a popular research problem. However, the conditions under which the problem is solvable are not understood or characterized. To provide a means for measuring progress and characterizing the properties of gait recognition, we introduce the HumanID Gait Challenge Problem. The challenge problem consists of a baseline algorithm, a set of twelve experiments, and a large data set. The baseline algorithm estimates silhouettes by background subtraction, and performs recognition by temporal correlation of silhouettes. The twelve experiments are of increasing difficulty and examine the effects of five covariates on performance. The covariates are: change in viewing angle, change in shoe type, change in walking surface, carrying or not carrying a briefcase, and temporal differences. Identification rates for the twelve experiments range from 78% on the easiest experiment to 3% on the hardest. All five covariates had statistically significant effects on performance, with walking surface and time difference having the greatest impact. We found that the lower 30% of the silhouette accounts for about 75% of the identification rates. The dataset consists of 1870 sequences from 122 subjects spanning 5 covariates (1.2 Gigabytes of data). The gait data, the source code of the baseline algorithm, and scripts to run, score, and analyze the challenge experiments are available at www.GaitChallenge.org. This infrastructure supports further development of gait recognition algorithms, and additional experiments to understand the strengths and weaknesses of new algorithms.
Biography: Sudeep Sarkar received the B.Tech degree in Electrical Engineering from the Indian Institute of Technology, Kanpur, in 1988 where he was judged the best graduating Electrical Engineer. He received the M.S. and Ph.D. degrees in electrical engineering, on a University Presidential Fellowship, from The Ohio State University, Columbus, in 1990 and 1993, respectively. Since 1993, he has been with the Computer Science and Engineering Department at the University of South Florida, Tampa, where he is currently an Associate Professor.
He is the recipient of the National Science Foundation CAREER award in 1994, the USF Teaching Incentive Program Award for undergraduate teaching excellence in 1997 and the Outstanding Undergraduate Teaching Award in 1998. He is the co-author of the book "Computing Perceptual Organization in Computer Vision," published by World Scientific. He also the co-editor of the book "Perceptual Organization for Artificial Vision Systems" published by Kluwer Publishers. He was the guest co-editor of the Computer Vision and Image Understanding (CVIU) Journal Special Issue on Perceptual Organization in Computer Vision, Oct 1999. He is presently serving on the editorial boards for the IEEE Transactions on Pattern Analysis and Machine Intelligence, Journal of Pattern Recognition. He served on the editorial board of Pattern Analysis and Applications Journal during 2000-2001. He has published 75 journal papers and refereed conference or workshop papers. His research interests include perceptual organization in single images and multiple image sequences, probabilistic reasoning, Bayesian Networks, low level image segmentation, color-texture analysis of burn scars, non-rigid modeling of impact of burn scars, and performance evaluation of vision systems.
