Chaotic particle swarm optimization for automatic surface or curve localization

In order to solve the automatic localization problem of the surface or curve detection, this paper presents a method for obtaining a global optimal solution, the method uses particle swarm algorithm to solve the position and orientation. To solve the problem of premature convergence and slow convergence in particle swarm algorithm, a chaotic mapping logistic model is presented to improve the performance of particle swarm algorithm and the shrinking chaotic mutation operator is applied into the method to increase the diversity and ergodicity of particle populations. In this paper, the objective matrix is separately described by quaternion and Euler angles, and the accuracy and convergence of the algorithm are analyzed taken into account these matrices. Simulation results demonstrate that two mentioned expressions can comply with the requirements of adaptive localization, and while Euler angles as optimization variables, chaotic particle swarm optimization have higher accuracy results. Finally, compared to Hong-Tan algorithms, the method is effective and reliable. © (2014) Trans Tech Publications, Switzerland.