Title:Distributed Multi-Camera Networks: Graphical Models, Tensor Representation, and Plenoptic Functions

　　Speaker: Dan Schonfeld（Fellow, IEEE; Deputy EiC of IEEE T-CSVT）

　　Time: 2010-11-20 9:30

　　Venue: the Conference Room of Optical Image Analysis and Learning Center (OPTIMAL), 3rd Floor, Building 3

　　Abstract:

　　Tremendous efforts have been made over the past few years to install large camera networks in sensitive facilities and metropolitan areas. The aim of the deployed camera networks is to enhance surveillance, security, traffic monitoring, and emergency management. The critical limitation of camera networks is the enormous volume of video data generated, rendering large-scale real-time imaging efforts ineffective. The massive volume of visual data poses an increasingly formidable barrier for effective use of real-time networked multi-camera systems. In this talk, we transform the collection of networked cameras into a single imaging device by introducing a new design methodology for distributed signal processing over complex-structure representation of multi-camera visual data. We demonstrate the proposed approach to distributed multi-camera systems in target tracking, pose estimation, event detection, and image rendering and reconstruction.

　　Speaker Profile:

　　Dan Schonfeld received the B.S. degree in Electrical Engineering and Computer Science from the University of California at Berkeley, and the M.S. and Ph.D. degrees in Electrical and Computer Engineering from The Johns Hopkins University, in 1986, 1988, and 1990, respectively. In 1990, he joined the University of Illinois at Chicago, where he is currently a Professor in the Departments of Electrical and Computer Engineering, Computer Science, and Bioengineering. Dr. Schonfeld has authored over 170 technical papers in various journals and conferences. He was co-author of papers that won the Best Student Paper Awards in Visual Communication and Image Processing 2006 and IEEE International Conference on Image Processing 2006 and 2007. Dr. Schonfeld has been elevated to the rank of IEEE Fellow “for contributions to image and video analysis.” He is currently serving as Deputy Editor-in-Chief of the IEEE Transactions on Circuits and Systems for Video Technology and Special Sections Area Editor for the IEEE Signal Processing Magazine. His current research interests are in multi-dimensional signal processing; image and video analysis; computer vision; and genomic signal processing.

　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　 Optical Image Analysis and Learning Center

　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　 Tel: 029 - 8888 9302

　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　 E-mail: OPTIMAL@opt.ac.cn