基于改进粒子群算法的煤矿井下相机参数优化  

Parameter Optimization of Underground Coal Mine Camera Based on Improved PSO

作　　者：乔佳伟 贾运红[1,2,3,4] 王强 QIAO Jiawei;JIA Yunhong;WANG Qiang(China Coal Research Institute,Beijing 100013,China;School of Mechatronics and Information Engineering,China University of Mining and Technology(Beijing),Beijing 100083,China;China Coal Technology and Engineering Group Taiyuan Research Institute Co.,Ltd.,Taiyuan 030006,China;National Engineering Laboratory,Coal Mining Machinery,Taiyuan 030006,China)

机构地区：[1]煤炭科学研究总院,北京100013 [2]中国矿业大学(北京)机电与信息工程学院,北京100083 [3]中国煤炭科工集团太原研究院有限公司,太原030006 [4]煤矿采掘机械国家工程实验室,太原030006

出　　处：《煤炭技术》2022年第4期119-122,共4页Coal Technology

基　　金：国家重点研发计划资助项目(2020YFB1314003);研究生教育基金(M2020-JY03);山西省重点研发计划(2020XXX001)。

摘　　要：煤矿井下视觉测量精度的关键在于相机参数的准确性,提出一种改进粒子群算法对张氏标定法所得参数进行优化,在迭代初期和后期分别使用e指数和粒子适应度函数值动态调节惯性权重。经过实验,优化后相机参数平均误差与标准差相比张氏标定法分别提高了23.65%、22.83%。且改进PSO算法与传统PSO算法、e指数调节惯性权重PSO相比,可以明显降低迭代次数,提高优化精度,是提高煤矿井下视觉测量准确性的一种有效方法。The key to the accuracy of visual measurement in underground coal mines lies in the accuracy of camera parameters.An improved particle swarm algorithm is proposed to optimize the parameters obtained by Zhang′s calibration method.In the early and late stages of the iteration,the eindex and the particle fitness function value are used to dynamically adjust the inertia weight.Through experiments,the average error of the camera parameters after optimization and the standard deviation are increased by 23.65% and 22.83% respectively compared with the Zhang′ s calibration method.Compared with the traditional PSO algorithm and the e-index adjustment inertia weight PSO,the improved PSO algorithm can significantly reduce the number of iterations and improve the optimization accuracy.It is an effective method to improve the accuracy of visual measurement in coal mines.

关 键 词：视觉测量 相机标定 惯性权重 改进粒子群算法 

分 类 号：TP242.62[自动化与计算机技术—检测技术与自动化装置] TP391.41[自动化与计算机技术—控制科学与工程]