Distributed Interactive Video Arrays for Event Based Analysis of Incidents

The Distributed Interactive Video Array (DIVA) system is developed to provide a large-scale, redundant cluster ofvideo streams to observe a remote scene and to supply automatic focus-of-attention with event-driven servoing to capture desired events at appropriate resolutions and perspectives. Installing multiple sensors introduces several new research issues related to the system design, including handoff schemes for passing tracked objects between sensors and clusters, methods for determining the "best view" given the context of the traffic scene, and sensor fusion algorithms to best employ the strengths of a given sensor or sensor modality. This paper describes our research focused on the development of DIVA system for traffic and incident monitoring. The paper describes the overall architecture of the DIVA system, algorithms for vehicle and platoon tracking using multiple cameras, and experimental results using novel distributed video networks deployed on the campus and the interstate I-5.