Distributed video networks for incident detection and management
Mohan Manubhai Trivedi, Ivana Medvedec Mikić, G.T. Kogut · 2002
We describe a novel architecture for developing distributed video networks for incident detection and management. The networks utilize both rectilinear and omnidirectional cameras. It is recognized that robust and reliable segmentation of automobiles and shadows is critical in our application. We describe new segmentation procedure and present experimental results to support the basic feasibility and utility of the algorithms.