计算机工程与应用 ›› 2011, Vol. 47 ›› Issue (14): 200-203.

• 工程与应用 • 上一篇    下一篇

量子粒子群优化算法在摄像机标定中的应用

郁 钱,孙 俊,须文波   

  1. 江南大学 信息工程学院,江苏 无锡 214122
  • 收稿日期:1900-01-01 修回日期:1900-01-01 出版日期:2011-05-11 发布日期:2011-05-11

Application of Quantum-Behaved Particle Swarm Optimization in camera calibration

YU Qian,SUN Jun,XU Wenbo   

  1. School of Information Engineering,Jiangnan University,Wuxi,Jiangsu 214122,China
  • Received:1900-01-01 Revised:1900-01-01 Online:2011-05-11 Published:2011-05-11

摘要: 摄像机标定是三维重构中最关键的一步,它的精度直接决定了三维重构结果的逼真程度。为了能够提高摄像机标定的精度,克服传统优化算法易陷入局部最小,反投影误差大等缺点,首次将量子粒子群优化算法(Quantum-Behaved Particle Swarm Optimization,QPSO)应用于摄像机标定中。该方法利用传统的线性方法求得初始值,利用QPSO对初始值进行优化。实验数据表明,基于QPSO的摄像机标定的平均反投影误差小于一个像素,是一种可行的方法,且与智能优化算法PSO相比,基于QPSO的摄像机标定具有更小的误差。

关键词: 三维重构, 最子粒子群优化算法(QPSO), 量子粒子群优化算法, 摄像机标定

Abstract: Camera calibration is a key step in three-dimensional reconstruction,which directly determines the accuracy of 3D reconstruction.This paper firstly applies the Quantum-Behaved Particle Swarm Optimization to camera calibration in order to improve the accuracy and overcome the drawbacks of traditional optimization algorithm,such as local-optima inclination and poor back-projection error.Firstly,this method uses the traditional linear method to achieve the initial value,and then optimizes the initial value with QPSO.Experimental data show that camera calibration based on QPSO has less average back-projection error than a pixel and is an effective and reliable method.Experiment also shows that this approach has lower error than the one based on PSO.

Key words: three-dimensional reconstruction, Quantum-Behaved Particle Swarm Optimization(QPSO), Quantum-Behaved Particle Swarm Optimization, camera calibration