基于粒子群算法的双目立体视觉系统标定  

Camera calibration of stereo vision system based on PSO

作　　者：廉小磊[1] 贺利乐[1] 张颖[1] 

机构地区：[1]西安建筑科技大学机电学院,西安710055

出　　处：《计算机工程与应用》2011年第24期202-204,210,共4页Computer Engineering and Applications

摘　　要：摄像机标定是立体视觉系统研究的重要组成部分,针对双目立体视觉系统中摄像机标定这一多参数、复杂函数的优化问题,建立带有一阶径向畸变的摄像机模型,利用粒子群算法对模型中的参数进行优化处理,并同改进遗传算法的优化结果进行比较分析。实验结果表明该方法具有较高的精度,可满足工业机器视觉的要求。Camera calibration is the important part of the stereo vision system study.A camera model with radial distortion is established for the camera calibration,that is a complex nonlinear multi-parameter function optimization problem of the binocular stereo vision system.At the same time,the Particle Swarm Optimization（PSO）algorithm is used to optimize the pa-rameters,and then the genetic algorithm’s result is compared.The experimental results show that the method has high accura-cy,and can meet the requirements of industrial machine vision.

关 键 词：立体视觉 摄像机标定 粒子群算法 畸变模型 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]