Video Surveillance and Activity Monitoring Detection and Tracking of Moving Objects
Approach:	The proposed method relies on a graph representation of moving objects which allows to derive and maintain a dynamic template of each moving object by enforcing their temporal coherence. This inferred template along with the graph representation used in our approach allows us to characterize objects trajectories as an optimal path in a graph.
Publications:	Detection and Tracking of Objects in Airborne Video Imagery, Interpretation of Visual Motion Workshop, CVPR98, Santa Barbara, June 1998. Detecting and Tracking Objects in Video Surveillance, Proc. of the IEEE Computer Vision and Pattern Recognition 99, Fort Collins, June 1999.
Results: VSAM Project	Image sequence Tracking Trajectories Image sequence Tracking Trajectories Image sequence Mosaic and Tracking Image sequence Mosaic and Tracking Tracks
Last modified: November 2006 USC Computer Vision