An Optimised Indoor Deployment of Visual Sensor Networks

This paper deals with the problem of deploying a sensor network to monitor an area. More specifically, we consider sensor nodes that are equipped with smart cameras. We refer to this network as visual sensor network (VSN). The cameras used in this study are directional and must be placed along the walls to ensure better coverage in an indoor environment. The optimisation problem has two objective functions: (i) maximise the overall coverage of the study area and (ii) maximise the coverage of some spots called areas of interest. To deal with this problem, we propose an approach based on a genetic algorithm and a simulation tool to measure the cameras' fields of view (based on ray tracing). The results obtained show that the algorithm adapts well to the presence of obstacles and/or areas of interest. Moreover, the algorithm succeeds in simultaneously optimising the two objective functions without being trapped by local optima.