|
|
Target Tracking and Monitoring across Multiple Cameras
Dr. Yi-Ping Hung
Tuesday, March 25, 2008
2:00PM ~ 3:00PM, Harris Center 101
Abstract
Camera networks are widely used in visual surveillance because they can monitor the activities of targets over a large area. In this talk, I will present our research on three topics concerning target tracking and monitoring in a multi-camera system. First, we propose an adaptive learning method for tracking targets across multiple cameras with disjoint views. There are usually two visual cues employed for tracking targets across cameras: spatio-temporal cue and appearance cue. To learn the relationships among cameras, traditional methods used batch-learning procedures or hand-labeled correspondence, which can work well only within a short period of time. Here, we propose an unsupervised method which learns both spatio-temporal relationships and appearance relationships adaptively and can be applied to long-term monitoring. For the second topic, we introduce a method for generating smooth view transition when monitoring a target across multiple cameras. The sudden view change occurred when switching the monitoring view between cameras may give the viewer an uncomfortable flash. More importantly, with such sudden view change, it is difficult for the viewer to understand the spatial relationship between cameras. We have developed a simple and efficient technique that can render smooth view transition in real time, which also works for transition between disjoint views. The third topic concerns a multi-resolution monitoring system, called e-Fovea. In this system, we use a fixed camera and a fixed projector to cover a wide-angle field of view with lower resolution while integrating a pan-tilt-zoom camera and a steerable projector to focus on a foveal view, which provides high-resolution details.
Short Bio
Yi-Ping Hung received his B.S. in Electrical Engineering from the National Taiwan
University in 1982. He received an M.S. from the Division of Engineering, an M.S.
from the Division of Applied Mathematics, and a Ph.D. from the Division of
Engineering, all at Brown University, in 1987, 1988 and 1990, respectively. He is currently a professor in the Graduate Institute of Networking and Multimedia, and in the Department of Computer Science and Information Engineering, both at the National Taiwan University. From 1990 to 2002, he was with the Institute of
Information Science, Academia Sinica, Taiwan, where he became a tenured research
fellow in 1997 and is now an adjunct research fellow. He has served as a deputy
director of the Institute of Information Science, Academia Sinica, and is now the director of the Graduate Institute of Networking and Multimedia, National Taiwan University. He received the Young Researcher Publication Award from Academia
Sinica in 1997, and has served as the program co-chairs of ACCV2000, ICAT2000,
IVR2004, as the workshop co-chair of ICCV2003, and as a member in the editorial
board of the International Journal of Computer Vision since 2004. He is the keynote speaker for PSIVT 2007 in Santiago, Chile. His current research interests include computer vision, pattern recognition, image processing, virtual reality, multimedia and human-computer interaction.
|
|
