Self-calibration of heterogeneous sensors based on particle swarm optimization

A new approach to the extrinsic calibration of a camera and 3D laser range finder in complex industrial workplace is presented in this paper. This calibration approach is based on line correspondences and does not need any calibration pattern. With the constraints of projection line produced by laser scanning points in intensity image, the nonlinear optimization function of the extrinsic parameters between a camera and 3D laser range finder is established. The proposed approach which adopts the particle swarm optimization (PSO) algorithm to optimize the extrinsic parameters is insensitive to the initial value of extrinsic parameters. The effectiveness of the proposed algorithm is verified by the experimental results on synthetic and real scene.