Faculty of Engineering and Natural Sciences
Object Tracking via a Collaborative Camera Network
Ali Özer Ercan
University of California, Berkeley
There is a growing need to develop low cost wireless networks of cameras with automated detection capabilities. The main challenge in building such networks is the high data rate of video cameras. On the one hand sending all the data, even after performing standard compression, is very costly in transmission energy, and on the other, performing sophisticated vision processing at each node to substantially reduce transmission rate requires high processing energy. To address these challenges, a task-driven approach has been proposed and demonstrated. In this approach, simple local processing is performed at each node to extract the essential information needed for the network to collaboratively perform the task and only this information is sent over the network.
In this talk, I will present such a task-driven approach for tracking a single object (e.g., a suspect) in a structured environment (e.g., an airport or a mall) in the presence of static and moving occluders using a wireless camera network. We assume the locations of the static occluders to be known, but only prior statistics on the positions of the moving occluders are available. Using simulations, will show the trade-offs between the tracker accuracy, occluder prior accuracy, number of cameras used and number of moving occluders. I will also present a camera subset selection algorithm that is suitable to implement with the tracker and demonstrate the possible energy and bandwidth savings by judicious selection of the cameras. Experimental results are also provided.
Ali Ozer Ercan received his B.S. degree from Bilkent University in 2000, the M.S. and the PhD degrees from Stanford University in 2002 and 2007, respectively; all in electrical engineering. Since 2007, he has been a post-doctoral researcher at the Berkeley Wireless Research Center at University of California at Berkeley. His research interests include the theory and applications of signal processing and wireless networks, and their system/circuit level implementations.
July 2, 2008, 10:30, FENS G035