Camera Calibration Based on Particle Swarm Optimization

Abstract

A novel camera calibration approach based on Particle Swarm Optimization(PSO) is put forward in this paper. Firstly, we designed 35 sample points on the calibration box; Secondly, the 3D point and their corresponding 2D image coordi- nate of these sample points were obtained; In this approach, PSO algorithm was adopted to obtain the camera intrinsic parameters. Among the 35 sample points, 30 points were used for training, and other 5 points were mainly used to evaluate the effectiveness of camera calibration. The techniques presented in this paper have been implemented and tested with both synthetic and real data. Our experimental results show that the method can obtain satisfying calibration accuracy.