摘要
为了较好地解决传统智能优化方法在摄像机标定中存在标定精度低、效率和鲁棒性差的问题,提出一种基于混沌天牛须搜索算法的摄像机标定方法。该方法使用MATLAB标定工具箱对摄像机非线性成像模型进行预标定,预标定结果作为混沌天牛须搜索算法的初始值;构造平均重投影误差适应度函数,建立混沌天牛须搜索算法优化模型对标定参数进行优化;与基于传统智能优化方法的摄像机标定方法进行实验对比。实验结果表明,该方法得到的平均重投影误差为0.00572像素,算法总的运行时间为46.15 s,可以有效提高摄像机标定的精度、鲁棒性与效率。
0x09In order to solve the problems of low precision,low efficiency and poor robustness in camera calibration of traditional intelligent optimization methods,a camera calibration method based on chaotic beetle antennae search algorithm is proposed.This method used MATLAB calibration toolbox to pre-calibrate the camera nonlinear imaging model,and the pre-calibration result was the initial value of the chaotic beetle antennae search algorithm.The average re-projection error fitness function was constructed,and the chaotic beetle antennae search algorithm optimization model was established to optimize the calibration parameters.The experiment was compared with the camera calibration method based on the traditional intelligent optimization method.The experimental results show that the average re-projection error obtained by this method is 0.00572 pixels,and the running time of the algorithm is 46.15 seconds,which can effectively improve the precision,robustness and efficiency of camera calibration.
作者
范山城
倪受东
张宏峰
Fan Shancheng;Ni Shoudong;Zhang Hongfeng(College of Mechanical and Power Engineering,Nanjing University of Technology,Nanjing 210000,Jiangsu,China)
出处
《计算机应用与软件》
北大核心
2023年第4期269-274,288,共7页
Computer Applications and Software
基金
江苏省科技厅政策引导类计划(产学研合作)/前瞻性联合研究项目(BY2016005-05)。
关键词
摄像机标定
摄像机标定参数
非线性成像
混沌天牛须搜索算法
Camera calibration
Camera calibration parameter
Nonlinear imaging
Chaotic beetle antennae search algorithm
