[UCI-Calit2] Presentation 3 pm Today "Visual Analysis of Crowded Scenes"

[Shellie Nazarenus]

REMINDER: Presentation TODAY (Wed. 5/30/07) at 3 p.m. in Calit2 Building, Room 3008.

TITLE: "Visual Analysis of Crowded Scenes"

PRESENTER: Dr. Mubarak Shah
Computer Vision Lab (http://www.cs.ucf.edu/~vision/)
School of Electrical Engineering & Computer Science
University of Central Florida

ABSTRACT: Automatic segmentation and learning of dominant motion patterns or activities from a video is an important visual surveillance problem. Most of the current approaches assume that the observed scene is not crowded, and that reliable tracks of objects are available over longer durations. Therefore, these approaches are not extendable to more challenging surveillance videos of crowded environments like markets, subways, religious festivals, parades, concerts, football matches etc, where tracking of individual objects is very hard, if not impossible.
The talk will include a framework for modeling scenes involving high density crowds in which Lagrangian particle dynamics are used to segment crowd flows and detect any flow instability. For this purpose flow fields generated by moving crowds are treated as an aperiodic dynamical system which is manifested in terms of time dependent optical flow. A grid of particles is overlaid on the flow field, and particles are advected using a numerical integration scheme. This is followed by the quantification of the amount by which the neighboring particles have diverged using a Cauchy-Green deformation tensor. The maximum eigenvalue of this tensor is used to construct a Finite Time Lyapunov Exponent (FTLE) field, which reveals the Lagrangian Coherent Structures (LCS) present in the underlying flow. The LCS divides the flow into regions of qualitatively different dynamics and therefore can be used to locate flow segment boundaries. This is done by segmenting the FTLE field using a normalized cuts framework. 
Shah will also present an algorithm for detecting global motion patterns that exploits the instantaneous motion information present in a video instead of long-term motion tracks. A motion pattern is then defined as a group of flow vectors that are part of the same physical process or motion. Algorithmically, this is accomplished by first detecting the representative modes (sinks) of motion patterns, followed by the generation of super tracks, which coherently represent the discovered motion patterns. 
  
ABOUT THE SPEAKER: Dr. Mubarak Shah, Agere Chair Professor of Computer Science, and the founding director of the Computer Visions Lab at the University of Central Florida, is a researcher in a number of computer vision areas. Dr. Shah is a fellow of IEEE and IAPR. In 2006, he was awarded a Pegasus Professor award, the highest award at UCF, given to a faculty member who has made a significant impact on the university, has made an extraordinary contribution to the university community, and has demonstrated excellence in teaching, research and service. He was an IEEE Distinguished Visitor speaker for 1997-2000 and received IEEE Outstanding Engineering Educator Award in 1997. He received the Harris  Corporation's Engineering Achievement Award in 1999, the TOKTEN awards from UNDP in 1995, 1997, and 2000; Teaching Incentive Program award in 1995 and 2003, Research Incentive Award in 2003, Millionaires' Club  awards in 2005 and 2006, University Distinguished Researcher award in 2007,  honorable mention for the ICCV 2005 Where Am I? Challenge Problem, and was nominated for the best paper award in ACM Multimedia Conference in 2005.  He is an editor of international book series on Video Computing; editor in chief of Machine Vision and Applications journal, and an associate editor of ACM Computing Surveys journal. He was an associate editor of the IEEE Transactions on PAMI, and a guest editor of the special issue of International Journal of Computer Vision on Video Computing.

FACULTY HOST: Ramesh Jain, Bren Distinguished Professor, UCI Donald Bren School of Information and Computer Sciences