一种高鲁棒性的钢轨表面缺陷检测算法
|
摘要
利用机器视觉技术检测钢轨表面缺陷时,存在背景光照复杂、车载检测设备与钢轨相对位置发生变化等情况,严重影响了缺陷检测的准确率,为此,提出基于灰度标准差与投影积分的钢轨表面区域定位算法和基于多尺度灰度对比度的增强算法。定位算法利用灰度标准差排除复杂背景的干扰,通过投影积分获取精确的钢轨表面区域;综合不同尺度空间的灰度对比度,将钢轨表面区域图像转化为灰度对比图,实现钢轨表面缺陷的增强;采用迭代阈值分割法提取钢轨表面的缺陷。实验结果表明:提出的钢轨表面缺陷检测算法在几种不同拍摄条件下漏检率均低于6%,准确率均高于93%,用于高速有砟轨道无缝钢轨表面缺陷检测时具有较高的鲁棒性。
When machine vision technology was used to detect the surface defects of rails,the background lighting was complex,the relative position of the on-board detection equipment and the rail changes,etc.,which seriously affected the defect detection accuracy.Therefore,a rail surface area localization algorithm was proposed based on gray standard deviation and projection integration,and an enhancement algorithm was also presented based on multi-scale gray-scale contrasts.The gray standard deviation was used to eliminate the interferences of complex backgrounds,and the precise positions of the orbital surfaces was obtained through the projection integral,then,the gray-scale contrasts in different scale spaces were obtained to convert the rail surface areas into a gray contrast maps for defect enhancements,finally,iterative threshold segmentation method was used to extract rail surface defects.Experiments show that,under several different shooting conditions,the missing detection rate of the rail surface defect detection algorithm proposed is less than 6%,and the accuracy rate is more than 93%.This algorithm has high robustness for the detection of surface defects on seamless rails in high-speed ballast tracks.
When machine vision technology was used to detect the surface defects of rails,the background lighting was complex,the relative position of the on-board detection equipment and the rail changes,etc.,which seriously affected the defect detection accuracy.Therefore,a rail surface area localization algorithm was proposed based on gray standard deviation and projection integration,and an enhancement algorithm was also presented based on multi-scale gray-scale contrasts.The gray standard deviation was used to eliminate the interferences of complex backgrounds,and the precise positions of the orbital surfaces was obtained through the projection integral,then,the gray-scale contrasts in different scale spaces were obtained to convert the rail surface areas into a gray contrast maps for defect enhancements,finally,iterative threshold segmentation method was used to extract rail surface defects.Experiments show that,under several different shooting conditions,the missing detection rate of the rail surface defect detection algorithm proposed is less than 6%,and the accuracy rate is more than 93%.This algorithm has high robustness for the detection of surface defects on seamless rails in high-speed ballast tracks.
引文
[1]中华人民共和国铁道部.铁运[2001]23号铁路线路维修规则[S].北京:中国铁道出版社,2001.Ministry of Railways of the Peoples Republic of China.Rules for Maintenance of Railway Lines[S].Beijing:China Railway Publishing House,2001.
[2] UTRATA D,CLARK R.Groundwork for Rail Flaw Detection Using Ultrasonic Phased Array Inspection[J].Review of Quantitative Nondestructive Evalution,2003,22(1):799-805.
[3] PAPAELIAS M P,LUGG M C,ROBERTS C,et al.High-speed Inspection of Rails Using ACFM Techniques[J].NDT&E International,2009,42(4):328-335.
[4] RUBINSZTEJN Y.Automatic Detection of Objects of Interest from Rail Track Images[D].Manchester:Manchester University,2011.
[5] MARINO F,DISTANTE A,MAZZEO P L,et al.A Real-time Visual Inspection System for Railway Maintenance:Automatic Hexagonal-headed Bolts Detection[J].IEEE Transactions on Systems Man&Cybernetics,Part C, Applications&Reviews,2007,37(3):418-428.
[6]任盛伟,李清勇,许贵阳,等.鲁棒实时钢轨表面擦伤检测算法研究[J].中国铁道科学,2011,32(1):25-29.REN Shengwei,LI Qingyong,XU Guiyang,et al.Research on Detection Algorithm of Robust Realtime Rail Surface Abrasion[J].China Railway Science,2011,32(1):25-29.
[7]袁小翠,吴禄慎,陈华伟.钢轨表面缺陷检测的图像预处理改进算法[J].计算机辅助设计与图形学学报,2014,26(5):800-805.YUAN Xiaocui,WU Lushen,CHEN Huawei.Improved Image Preprocessing Algorithm for Rail Surface Defect Detection[J].Journal of Computer-aided Design&Computer Graphics,2014,26(5):800-805.
[8]丁锐.铁路图像分类和轨顶边缘定位算法研究[D].成都:西南交通大学,2013.DING Rui.Research on Railway Image Classification and Track Top Edge Localization Algorithm[D].Chengdu:Southwest Jiaotong University,2013.
[9] GORDON R,RANGAYYAN R M.Feature Enhancement of Film Mammograms Using Fixed and Adaptive Neighborhoods:Correction[J].Applied Optics,1984,23(13):2055.
[10]宋翠玉,李培军,杨锋杰.运用多尺度图像纹理进行城市扩展变化检测[J].国土资源遥感,2006,18(3):37-42.SONG Cuiyu,LI Peijun,YANG Fengjie.Detection of Urban Expansion Change Using Multiscale Image Texture[J].Remote Sensing for Land&Resources,2006,18(3):37-42.
[11] MOHAN S, RAVISHANKAR M.Optimized Histogram Based Contrast Limited Enhancement for Mammogram Images[J].American Council for an Energy-efficient Economy International Journal on Information Technology,2013,1(3):66-71.
[2] UTRATA D,CLARK R.Groundwork for Rail Flaw Detection Using Ultrasonic Phased Array Inspection[J].Review of Quantitative Nondestructive Evalution,2003,22(1):799-805.
[3] PAPAELIAS M P,LUGG M C,ROBERTS C,et al.High-speed Inspection of Rails Using ACFM Techniques[J].NDT&E International,2009,42(4):328-335.
[4] RUBINSZTEJN Y.Automatic Detection of Objects of Interest from Rail Track Images[D].Manchester:Manchester University,2011.
[5] MARINO F,DISTANTE A,MAZZEO P L,et al.A Real-time Visual Inspection System for Railway Maintenance:Automatic Hexagonal-headed Bolts Detection[J].IEEE Transactions on Systems Man&Cybernetics,Part C, Applications&Reviews,2007,37(3):418-428.
[6]任盛伟,李清勇,许贵阳,等.鲁棒实时钢轨表面擦伤检测算法研究[J].中国铁道科学,2011,32(1):25-29.REN Shengwei,LI Qingyong,XU Guiyang,et al.Research on Detection Algorithm of Robust Realtime Rail Surface Abrasion[J].China Railway Science,2011,32(1):25-29.
[7]袁小翠,吴禄慎,陈华伟.钢轨表面缺陷检测的图像预处理改进算法[J].计算机辅助设计与图形学学报,2014,26(5):800-805.YUAN Xiaocui,WU Lushen,CHEN Huawei.Improved Image Preprocessing Algorithm for Rail Surface Defect Detection[J].Journal of Computer-aided Design&Computer Graphics,2014,26(5):800-805.
[8]丁锐.铁路图像分类和轨顶边缘定位算法研究[D].成都:西南交通大学,2013.DING Rui.Research on Railway Image Classification and Track Top Edge Localization Algorithm[D].Chengdu:Southwest Jiaotong University,2013.
[9] GORDON R,RANGAYYAN R M.Feature Enhancement of Film Mammograms Using Fixed and Adaptive Neighborhoods:Correction[J].Applied Optics,1984,23(13):2055.
[10]宋翠玉,李培军,杨锋杰.运用多尺度图像纹理进行城市扩展变化检测[J].国土资源遥感,2006,18(3):37-42.SONG Cuiyu,LI Peijun,YANG Fengjie.Detection of Urban Expansion Change Using Multiscale Image Texture[J].Remote Sensing for Land&Resources,2006,18(3):37-42.
[11] MOHAN S, RAVISHANKAR M.Optimized Histogram Based Contrast Limited Enhancement for Mammogram Images[J].American Council for an Energy-efficient Economy International Journal on Information Technology,2013,1(3):66-71.