Dynamic Bayesian Networks for Visual Surveillance with Distributed Cameras

Abstract. This paper presents a surveillance system for tracking multiple people through a wide area with sparsely distributed cameras. The computational core of the system is an adaptive probabilistic model for reasoning about peoples' appearances, locations and identities. The system consists of two processing levels. At the low-level, individual persons are detected in the video frames and tracked at a single camera. At the high-level, a probabilistic framework is applied for estimation of identities and camera-to-camera trajectories of people. The system is validated in a real-world office environment with seven color cameras.

• Type: Conference
• Year: 2006
• Where: EUROSSC
• Authors: Wojciech Zajdel, Ali Taylan Cemgil, Ben J. A. Kröse
• Keywords: Adaptive Probabilistic Model, EUROSSC 2006, Information Management, Probabilistic, Real-world Office Environment