Publication

Abstract : The optimal placement of surveillance cameras to maximize the total coverage of camera networks is of significant research interest due to the proliferation of camera networks in diverse application scenarios. Existing camera placement algorithms are mostly designed to optimize coverage. In the event of failure of one or more cameras, these optimization algorithms reorient all the remaining cameras in the surveillance network to regain the lost coverage; and hence are not cost-effective. A simple and straightforward solution to regain the lost coverage is by reorienting the field of view of active cameras to overlap with those of the damaged cameras. In this paper, we propose the Visibility Graph Reduction (VGR) algorithm, a novel graph-based approach to select potential cameras amongst the active cameras, that can optimally alleviate the loss in coverage resulting from the failure of one or more cameras. We validate our algorithm on map images across diverse indoor and outdoor surveillance scenarios with existing camera networks. Experimental results show that our algorithm minimizes the number of cameras that need to be reoriented, and produces similar coverage results as that of reorientating all the available active cameras in the surveillance network. Our approach is both cost-effective and computationally efficient, and thus minimizes the human effort involved in reorienting cameras across practical scenarios.