Joint Colloquium Distinguished Lecture Series
Looking for Patterns in Videos
Wednesday, April 21, 2010
In this talk, I will first discuss some of the general principles for designing robust video-based pattern recognition systems. I will then present many examples of statistical techniques for video-based modeling and recognition of actions involving single and multiple humans using motion, shape and behavior as features. Methods based on dynamic texture models, landmarks and special manifolds will be discussed. Methods for addressing variations due to time warping and viewpoints will be illustrated for action recognition and unsupervised clustering of video sequences.
Rama Chellappa received the B.E. (Hons.) degree from the University of Madras, India, in 1975 and the M.E. (Distinction) degree from the Indian Institute of Science, Bangalore, in 1977. He received the M.S.E.E. and Ph.D. Degrees in electrical engineering from Purdue University, West Lafayette, IN, in 1978 and 1981 respectively. Since 1991, he has been a Professor of electrical engineering and an affiliate Professor of computer science at the University of Maryland, College Park. He is also affiliated with the Center for Automation Research (Director) and the Institute for Advanced Computer Studies (Permanent member). He also holds a Minta Martin Professorship in the College of Engineering. Prior to joining the University of Maryland, he was an Assistant (1981-1986) and Associate Professor (1986-1991) and Director of the Signal and Image Processing Institute (1988-1990) with the University of Southern California, Los Angeles.
|Return to EECS Joint Colloquium|