Research on the application of PSO algorithm in non-linear camera calibration

Camera calibration is an indispensable step for medical photogrammetry, augmented reality (AR) or image guided applications where quantitative information should be derived from the images. Non-linear optimization algorithms are widely used in camera calibration in order to obtain precise intrinsic and extrinsic parameters of camera. Due to the traditional optimization algorithms have such problems as being prone to get into local extrema and being susceptive to initial value, in camera calibration. The applications of an improved PSO algorithms used in non-linear camera calibration are studied and the calculation procedure of this method is provided in non-linear camera calibration. Calibration experiment shows that this method can overcome those defects and is an effective calibration method.

[1]  Zhengyou Zhang,et al.  A Flexible New Technique for Camera Calibration , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[2]  Marco Gori,et al.  Optimal Algorithms for Well-Conditioned Nonlinear Systems of Equations , 2001, IEEE Trans. Computers.

[3]  R. Eberhart,et al.  Comparing inertia weights and constriction factors in particle swarm optimization , 2000, Proceedings of the 2000 Congress on Evolutionary Computation. CEC00 (Cat. No.00TH8512).

[4]  Yue Shi,et al.  A modified particle swarm optimizer , 1998, 1998 IEEE International Conference on Evolutionary Computation Proceedings. IEEE World Congress on Computational Intelligence (Cat. No.98TH8360).

[5]  Wang She-yang.  Non-linear Camera Calibration Based on Genetic Algorithms , 2004 .