Distributed Sensing and Perception via Sparse Representation

Event Status


The concept of sparse representation has been a hot topic in signal processing and statistics communities in the past few years, fueled by the emerging theory of compressive sensing. In this talk, I intend to further extend the scope of its applications to a new direction, called distributed sensing and perception. The research is motivated by the development of modern portable sensor devices that have become an integral part of our daily lives. We consider the confluence of sparse representation and efficient computer vision algorithms using a network of distributed smart camera sensors to recognize human faces and other general 3-D objects with high accuracy, and finally obtain the ability to fully reconstruct large-scale 3-D environments from just a few noisy images. Properly utilizing the special data structures imposed by real-world applications leads to superior results compared to existing methods.


Dr. Allen Y. Yang is a research scientist in the Department of EECS at UC Berkeley. His primary research areas include pattern analysis of geometric and statistical models in very high-dimensional data spaces and applications in motion segmentation, image segmentation, face recognition, and signal processing in heterogeneous sensor networks. He has published ten journal papers and more than 20 conference papers. He is the inventor of three US patents. He received his BEng degree in Computer Science from the University of Science and Technology of China (USTC) in 2001. From the University of Illinois at Urbana-Champaign (UIUC), he received two MS degrees in Electrical Engineering and Mathematics in 2003 and 2005, respectively, and a PhD in Electrical and Computer Engineering in 2006. Among the awards he received are a Best Bachelor's Thesis Award from USTC in 2001, a Henry Ford II Scholar Award from UIUC in 2003, a Best Paper Award from the International Society of Information Fusion and a Best Student Paper Award from Asian Conference on Computer Vision in 2009.

Date and Time
May 16, 2011, All Day