Modeling and Recognition of Dynamic Events in A Camera Network

Amit K. Roy-Chowdhury

Professor of Electrical Engineering

UC Riverside

Date: Friday, November 3, 2006
Place: Buchanan 1930
Time: 2:00 pm — 3:00 pm


Abstract:

As cameras get cheaper, large numbers of them are being installed in many applications. However, most of them transmit their videos to a central location where they are interpreted by human observers. This is infeasible with large networks and extracts a heavy toll on the available bandwidth for transmission. Therefore, it is very important to automatically extract meaningful patterns of dynamic events from the video sequences observed over the network. This will require integration of knowledge from a variety of disciplines including image processing, computer vision, machine learning, and statistics among others.

In this talk, we will start with a high-level presentation of the multi-camera (including some non-imaging sensors also) networks we are building at UCR. Thereafter, I will highlight the main issues that need to be addressed for this endeavor to be successful. Finally, we will focus on some of those issues and describe our current work and present some results. The detailed presentations will be on tracking, modeling and recognition of dynamic events, robustness issues especially in relation to illumination, fusion of imaging and non-imaging sensors and finally, on multi-terminal video compression. The presentation will be at a relatively high-level with the goal of providing an overview of the variety of research in image analysis being conducted in our group.

AMIT K. ROY-CHOWDHURY has been an Assistant Professor of Electrical Engineering at the University of California, Riverside since January 2004. He completed his PhD in 2002 from the University of Maryland, College Park, where he also worked as a Research Associate in 2003. His research interests are in the broad areas of image processing and analysis, computer vision, video communications and machine learning. Currently, he is working on problems of pose and illumination invariant video-based object recognition, event analysis in large video networks, and multi-terminal video compression. Dr. Roy-Chowdhury has over fifty papers in peer-reviewed journals, conferences and edited books. He is an author of the book titled Recognition of Humans and Their Activities Using Video. He is a PI on a number of research grants from Federal and private agencies. He is on the program committee of many major conferences in computer vision and image/signal processing, is a regular reviewer for the main journals in these areas, and is on the organizing committees of CVPR 2008 and ICIP 2008.

Host: Professor B.S. Manjunath, Electrical and Computer Engineering