The Community for Technology Leaders
Proceedings of the IEEE Conference on Advanced Video and Signal Based Surveillance, 2003. (2003)
Miami, Florida
July 21, 2003 to July 22, 2003
ISBN: 0-7695-1971-7
pp: 221
Michael D. Beynon , Massachusetts Institute of Technology
Daniel J. Van Hook , Massachusetts Institute of Technology
Michael Seibert , Massachusetts Institute of Technology
Alen Peacock , Massachusetts Institute of Technology
Dan Dudgeon , Massachusetts Institute of Technology
ABSTRACT
We describe a video surveillance system that detects abandoned packages automatically. In this system, multiple cameras locate objects in space and time despite occlusions and distracting lighting effects observed by subsets of the cameras. A multiple-state model of an abandoned package provides the ability to detect realistic abandoned package events. This paper outlines the system by describing the modules for camera view segmentation, object classification, view-object association, 3D object tracking, and finally detection of the event of a package being abandoned, which highlights object association using multiple cameras and the multiple-state abandoned package model.
INDEX TERMS
null
CITATION

M. Seibert, D. Dudgeon, D. J. Van Hook, M. D. Beynon and A. Peacock, "Detecting Abandoned Packages in a Multi-Camera Video Surveillance System," Proceedings of the IEEE Conference on Advanced Video and Signal Based Surveillance, 2003.(AVSS), Miami, Florida, 2003, pp. 221.
doi:10.1109/AVSS.2003.1217925
94 ms
(Ver 3.3 (11022016))