Optimizing Camera Placements for Overlapped Coverage with 3D Camera Projections
This addresses the practical problem of efficient camera placement for surveillance or monitoring in specific domains like retail, representing an incremental improvement over prior methods.
The paper tackles the problem of optimally placing cameras to achieve user-defined coverage in real environments, proposing a method that formulates camera selection as a mixed integer linear programming problem using 3D voxel projections. Experimental results in two retail stores show it outperforms existing methods in coverage and overlap for triangulation.
This paper proposes a method to compute camera 6Dof poses to achieve a user defined coverage. The camera placement problem is modeled as a combinatorial optimization where given the maximum number of cameras, a camera set is selected from a larger pool of possible camera poses. We propose to minimize the squared error between the desired and the achieved coverage, and formulate the non-linear cost function as a mixed integer linear programming problem. A camera lens model is utilized to project the cameras view on a 3D voxel map to compute a coverage score which makes the optimization problem in real environments tractable. Experimental results in two real retail store environments demonstrate the better performance of the proposed formulation in terms of coverage and overlap for triangulation compared to existing methods.