Distributed camera overlap estimation - Enabling large scale surveillance

Abstract

A key enabler for the construction of large-scale intelligent surveillance systems is the accurate estimation of activity topology graphs. An activity topology graph describes the relationships between the fields of view of the cameras in a surveillance network. An accurate activity topology estimate allows higher-level processing such as network-wide tracking to be localised within neighbourhoods defined by the topology, and thus to scale. The camera overlap graph is an important special case of the general activity topology, in which edges represent overlap between cameras' fields of view. We describe a family of pairwise occupancy overlap estimators, which are the only approaches proven to scale to networks with thousands of cameras. A distributed implementation is described, which enables the estimator to scale beyond the limits achievable by centralised implementations, and supports growth of the network whilst it remains online. Formulae are derived to describe the memory and network bandwidth requirements of the distributed implementation, which are verified by empirical results. Finally, the efficacy of the overlap estimators is demonstrated using results from their application in higher-level processing, specifically to network-wide tracking, which becomes feasible within the topology oriented architecture.