IEEE Conference on Advanced Video and Signal Based Surveillance, 2005. (2005)
Sept. 16, 2005 to Sept. 16, 2005
V.D. Shet , Lab. of Comput. Vision, Maryland Univ., College Park, MD, USA
D. Harwood , Lab. of Comput. Vision, Maryland Univ., College Park, MD, USA
L.S. Davis , Lab. of Comput. Vision, Maryland Univ., College Park, MD, USA
This paper describes the architecture of a visual surveillance system that combines real time computer vision algorithms with logic programming to represent and recognize activities involving interactions amongst people, packages and the environments through which they move. The low level computer vision algorithms log primitive events of interest as observed facts, while the higher level Prolog based reasoning engine uses these facts in conjunction with predefined rules to recognize various activities in the input video streams. The system is illustrated in action on a multi-camera surveillance scenario that includes both security and safety violations.
multicamera surveillance scenario, video monitoring, visual surveillance system, computer vision algorithms, logic programming, video streams, activities recognition, higher level Prolog based reasoning engine
D. Harwood, L. Davis and V. Shet, "VidMAP: video monitoring of activity with Prolog," IEEE Conference on Advanced Video and Signal Based Surveillance, 2005.(AVSS), Como, 2005, pp. 224-229.