Progress on Large and Growing Video Surveillance Networks Dr Henry Detmold, University of Adealide Wed, 3 Sep, 2008, 10:10 Lecture Room 2060, Computer Science, Plaza Building AbstractThis talk will commence with a collection of demonstration videos. These demonstration videos will highlight overall progress in surveillance of 20 to 200 camera networks at the Australian Centre for Visual Technologies in the past year. These demonstrations motivate the technical part of the talk, which reports on a distributed implementation of the exclusion approach to estimation of camera overlap.
Large-scale intelligent video surveillance requires an accurate estimate of the relationships between the fields of view of the cameras in the network. The exclusion approach is the only method currently capable of performing online estimation of camera overlap for networks of more than 100 cameras, and implementations have demonstrated the capability to support networks of 1000 cameras. However, these implementations include a centralised processing component, with the practical result that the resources (in particular, memory) of the central processor limit the size of the network that can be supported.
In this talk, I'll present a new, partitioned, implementation of exclusion, suitable for deployment to a cluster of commodity servers. Results for this implementation demonstrate support for significantly larger camera networks than was previously feasible. Furthermore, the nature of the partitioning scheme enables incremental extension of system capacity through the addition of more servers, without interrupting the existing system. Finally, formulae for requirements of system memory and bandwidth resources, verified by experimental results, are presented to assist engineers seeking to implement the technique. |