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.
出处
《计算机工程与应用》
CSCD
北大核心
2011年第24期202-204,210,共4页
Computer Engineering and Applications
关键词
立体视觉
摄像机标定
粒子群算法
畸变模型
stereo vision
camera calibration
Particle Swarm Optimization（PSO）
distortion model
