Real-time Video Analysis at Siemens Corporate Research

Visvanathan Ramesh
Siemens Corporate Research

Time and Place

1305 Newell-Simon Hall
Refreshments 3:15 pm
Talk 3:30 pm

Abstract

The proliferation of cheap sensors and increased processing power has made real-time acquisition and processing of video information more feasible. Real-time video analysis tasks requiring object detection and tracking can increasingly be performed efficiently on standard PC's. Smart cameras are being designed that enable on-camera applications to directly output compressed data or meta-event information instead of raw video. These advances, along with major breakthroughs in communication and the Internet, are making possible real-time video monitoring for a variety of application sectors such as Industrial Automation, Transportation, Automotive Systems, Security/Surveillance, and Communications.

The real-time imaging group at SCR is focusing on the development of integrated, end-to-end solutions for video applications that require object detection, tracking and action/event analysis. This talk will present an overview of our research in statistical methods for real-time video surveillance systems, highlighting our solutions for subway/highway monitoring to provide emergency assistance and resource management, and our real-time tracking technologies for applications in video conferencing, intelligent video communications, and industrial automation.

Speaker Biography

Dr. Visvanathan Ramesh obtained his doctoral degree from the Department of EE at the University of Washington, where he defended his Ph.D dissertation titled "Performance Characterization of Image Understanding algorithms" in 1994. He has been actively involved in Image and Video Understanding research in low and mid level vision over the past 12 years and has published numerous publications in the topic. His primary objective is to build robust image and video analysis systems and to quantify robustness of IU algorithms.

Dr. Ramesh is currently a senior member of technical staff and project manager of the real-time imaging effort in the Imaging department at Siemens Corporate Research in Princeton NJ. At Siemens, he has focused on the research and development of statistical methods for real-time video analysis functions such as object detection, tracking, and action recognition. He is a co-author of a paper on real-time tracking that received the best paper award in CVPR 2000. His broad research interests are Pattern Recognition, Computer Vision, AI and Biomedical Engineering.

Speaker Appointments

For appointments, please contact Robert Collins(rcollins@cs.cmu.edu).