Analyzing Human Activities in Video




Professor Larry Davis

University of Maryland

Computer Vision Laboratory


Friday,  April 13, 2012

3:30 – 4:30p.m

Rm. 1500 EECS


Abstract:  One of the most important applications of computer vision is to monitor human activities in video (for example, in surveillance applications for safety and security violations).  There are a number of fundamental problems that must be addressed in developing such a video analysis system.  Algorithms are needed to detect people and to track them as they move through the field of view of the surveillance system.  While people move they perform various activities (carry things, exchange them, pick them up, put them down, open and close doors, desks, etc.) and these activities are typically determined by detailed modeling of human movement  and assessment of the side effects of the movement on the scene and other people.  Because of occlusion and field of view limitations, methods are needed to track even with gaps in observation.  This is referred to as the identity maintenance problem.  Approaches to solving the identity maintenance problem ordinarily rely on modeling appearance of people (clothing, face, gait), but identity maintenance can also take advantage of constraints derived from closed worlds, possession, and activity.  Finally,  there are various sources of context that constrain where, when and how people will be observed and act, and how their goals are related to  the time sequence of their individual activities and interactions with one another and the world.  The talk will describe and illustrate research on these problems conducted at the University of Maryland.


Biosketch: Larry S. Davis received his B.A. from Colgate University in 1970 and his M. S. and Ph. D. in Computer Science from the University of Maryland in 1974 and 1976 respectively. From 1977-1981 he was an Assistant Professor in the Department of Computer Science at the University of Texas, Austin. He returned to the University of Maryland as an Associate Professor in 1981. From 1985-1994 he was the Director of the University of Maryland Institute for Advanced Computer Studies. He is currently a Professor in the Institute and the Computer Science Department, as well as Chair of the Computer Science Department.   He was named a Fellow of the IEEE in 1997.