基于单目视觉的悬臂式掘进机定位方法  

Positioning method of boomed roadheader based on monocular vision

作　　者：李英娜[1] 安博烁 崔彦平[2] 刘百健 孔瑞 LI Yingna;AN Boshuo;CUI Yanping;LIU Baijian;KONG Rui(Shijiazhuang Coal Mining Machinery Co.,Ltd.,Shijiazhuang 050000,Hebei,China;School of Mechanical Engineering,Hebei University of Science and Technology,Shijiazhuang 050018,Hebei,China;School of Material Science and Engineering,Hebei University of Science and Technology,Shijiazhuang 050018,Hebei,China)

机构地区：[1]石家庄煤矿机械有限责任公司,河北石家庄050000 [2]河北科技大学机械工程学院,河北石家庄050018 [3]河北科技大学材料科学与工程学院,河北石家庄050018

出　　处：《矿山机械》2025年第2期1-7,共7页Mining & Processing Equipment

基　　金：中央引导地方科技发展资金项目(226Z1906G);河北省教育厅科学研究项目资助(CXY2024038);石家庄市驻冀高校基础研究项目(241791157A)。

摘　　要：为了解决煤矿井下掘进机定位过程中干扰强、振动大、低照度和难以实时跟踪等问题,提出了基于视觉测量的定位方法,构建了悬臂式掘进机单目位姿测量系统。以4个红外光斑为点特征,利用限制对比度自适应直方图均衡化算法进行去雾,同时采用改进的自适应双边滤波算法进行去噪。通过PnP单目视觉的定位方法,解算出掘进机机身的位姿,最后搭建了掘进机静态和动态试验台进行位姿检测。结果表明:定位误差在x、y、z 3个方向上的误差均在8 mm内,同时在动态试验测试中最大误差不超过68 mm。In order to solve the problems of strong interference,large vibration,low illumination and difficulty in real-time tracking in the positioning process of roadheaders in the coal mine,a positioning method based on visual measurement was proposed,and a monocular pose measurement system of the boomed roadheader was constructed.Then,four infrared spots were used as point features,and the contrast limited adaptive histogram equalization algorithm was used for defogging.At the same time,the improved adaptive bilateral filtering algorithm was used for denoising.Through the positioning method of PnP monocular vision,the pose of the roadheader body was calculated.Finally,the static and dynamic test bench of the roadheader was built for its pose detection test.The results showed that the positioning errors in the three directions of x,y and z were within 8 mm,and the maximum error in the dynamic test was not more than 68 mm.

关 键 词：悬臂式掘进机 单目视觉 图像预处理 光斑特征提取 PNP 视觉测量 

分 类 号：TD421.5[矿业工程—矿山机电]