OPTIMAL CAMERA AND LIGHT SOURCE PLACEMENT FOR SURVEILLANCE APPLICATIONS

Abstract

Surveillance applications are gaining research importance day by day. Visual sensor arrays form the backbone of any surveillance applications. Correct visual sensor placement along with good lighting conditions is indispensable for the successful execution of such applications. For given application speci c restrictions, constraints, and visual occlusion it can be di cult to nd optimal positions for sensor placement. The complexity of these constraints suggests that automated methods for sensor placement are likely to be useful, particularly when the workspace is cluttered and application demands maximum coverage with minimum cost and good quality of service. Illuminating the space under surveillance is also equally important for good quality imaging. We present a novel approach for placement of both cameras and light sources for surveillance applications. Camera and light source placement depends on the geometry of the space under surveillance, considering the factors such as occlusion and shadowing e ect due to presence of objects in the environment, re ection, spatial resolution to assure better coverage of the most probable event locations, et cetera . The deployment strategy places cameras for maximum coverage of the multiple sensitive areas and light sources are placed for illuminating these areas to enhance the quality of the vision system. Since, constrained discrete optimization problems do not have e cient algorithmic solutions, use of evolutionary algorithms is preferred. Thus, solution to the problem of nding optimal camera and light source locations has been concluded using multi-objective genetic algorithm based optimization.