Translator Disclaimer
29 January 2007 A trajectory based video segmentation for surveillance applications
Author Affiliations +
Proceedings Volume 6506, Multimedia Content Access: Algorithms and Systems; 65060A (2007)
Event: Electronic Imaging 2007, 2007, San Jose, CA, United States
Video segmentation for content based retrieval has traditionally been done using shot cut detection algorithms that search for abrupt changes in scene content. Surveillance videos however, usually use still cameras, and do not contain any shots. Hence, a novel high level semantic change detection algorithm is proposed in this paper that uses object trajectory features to segment surveillance footage. These trajectory features are extracted automatically, using background subtraction and a multiple blob tracking algorithm. The trajectory features are first used to remove false object detections from background subtraction. Semantics extracted from the remaining object trajectories are then used to segment the video. The results of the algorithm when applied to surveillance data are compared with hand labeled segmentation to obtain precision recall curves and harmonic mean. Comparisons with traditional background subtraction and video segmentation algorithms show a drastic improvement in performance.
© (2007) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Naveen M. Thomas and Nishan Canagarajah "A trajectory based video segmentation for surveillance applications", Proc. SPIE 6506, Multimedia Content Access: Algorithms and Systems, 65060A (29 January 2007);

Back to Top