Abstract:

Security is one of the major concerns in crowded places - airports, shopping malls and public gatherings. A possible mishap therein may be prevented if it can be predicted a bit early. It requires the knowledge of motion dynamics of the crowd for short term prediction. A crowd consists of interacting individuals and we believe this interaction to be guided by an underlying set of rules that depends highly on the place under observation and the undergoing event. We consider a medium density crowd where it is possible to track individuals. We are interested in modelling this crowd motion to predict individual trajectories. A linear cyclic pursuit model is proposed to define the crowd interaction. These trajectories of various individuals are then used in predicting personal space violation which might help in taking timely security actions, if needed. Further, we show that the model parameters can be used to study the motion of individuals forming groups among themselves. This would be useful in studying the behavior of individuals in social gatherings. The details of the technique will be presented in the seminar.

Bio:

Subhasis Chaudhuri received his B.Tech. degree from IIT Kharagpur and the Ph.D. degree from the University of California, San Diego. He joined the Electrical engineering department at IIT, Bombay in 1990 and is currently serving as an Institute Chair Professor and the Deputy Director (Academic and Infrastructure Affairs). He is a fellow of the science and engineering academies in India and IEEE. He is a co-author of several monographs, all published by Springer, NY. He has served as an associate editor for various journals including IEEE Transactions in Pattern Analysis and Machine Intelligence, and International Journal of Computer Vision. He has served as the program chair for International Conference on Computer Vision (ICCV) held in Beijing in 2005. His research interests include image processing,computer vision and computational haptics.

Host:

Dr. Anil Jain