Adaptive scheduling of wireless video sensor nodes for surveillance applications

Traditional vision systems for surveillance applications are built essentially from distributed high resolution video cameras and powerful processing units which communicate in general with central servers via a high bandwidth network. Using autonomous and small wireless video sensor nodes can add a much higher level of flexibility, therefore extending the range of surveillance applications that could be considered and, more interestingly, can support dynamic deployment scenario. With such resource-constrained devices power conservation is an important issue but one must also ensure that the application's objectives are met. In this paper, we address the problem of adaptive scheduling of sensor node's activity to extend the network lifetime while fulfilling a critical surveillance application needs. We first present a distributed algorithm that ensures both coverage of the deployment area and network connectivity by providing multiple cover sets to manage Field of View redundancies. Then, we propose a multiple levels activity model that uses behavior functions modeled by modified Bezier curves to define application classes and allow for adaptive scheduling. Simulation results are presented to validate the performance of the proposed approach.