改进Canny算子在列车车轮踏面损伤检测中的应用
|
摘要
高速列车车轮踏面剥离、擦伤等损伤的检测主要以效率低下的人工巡检为主,为了提高检测效率设计一种基于机器视觉的高速列车车轮踏面损伤的动态检测系统,提出使用改进Canny算子对车轮踏面损伤进行边缘检测。改进的Canny算子在平滑图像时采用自适应加权中值滤波算法来代替高斯滤波,采用添加45°和135°方向梯度模板的Sobel算子来计算梯度幅值,以大津法(Otsu法)来确定最佳高低阈值。仿真实验结果表明:基于自适应加权中值滤波和大津法的改进Canny算子可以有效地检测车轮踏面损伤的边缘,同时也实现了自动检测。
The detection of damage such as scratch and stripping of the wheel tread of high-speed train is mainly based on inefficient artificial inspection. In order to improve detection efficiency, a dynamic detection system based on machine vision high-speed train wheel tread damage was designed. This paper put forward the edge detection of wheel tread damage by using improved Canny algorithm. The improved Canny algorithm uses an adaptive weighted median filter algorithm to replace the Gaussian filter in smoothing the image. This method added 45° and 135° gradient templates on the basis of the existing Sobel algorithm when calculating the gradient amplitude, and uses the Otsu method to determine optimal high and low thresholds. The experimental results show that the improved Canny algorithm based on adaptive weighted median filter and Otsu method can effectively detect the edge of wheel tread damage and also achieve automatic detection.
The detection of damage such as scratch and stripping of the wheel tread of high-speed train is mainly based on inefficient artificial inspection. In order to improve detection efficiency, a dynamic detection system based on machine vision high-speed train wheel tread damage was designed. This paper put forward the edge detection of wheel tread damage by using improved Canny algorithm. The improved Canny algorithm uses an adaptive weighted median filter algorithm to replace the Gaussian filter in smoothing the image. This method added 45° and 135° gradient templates on the basis of the existing Sobel algorithm when calculating the gradient amplitude, and uses the Otsu method to determine optimal high and low thresholds. The experimental results show that the improved Canny algorithm based on adaptive weighted median filter and Otsu method can effectively detect the edge of wheel tread damage and also achieve automatic detection.
引文
[1]Condier J F,Fodiman P.Experimental characterization of wheel and rail surface roughness[J].Journal of Sound and Vibration,2000,231(3):667-672.
[2]赵勇,方宗德,田丽丽.列车车轮踏面缺陷的图像区域提取[J].光学精密工程,2009,17(4):901-908.ZHAO Yong,FANG Zongde,TIAN Lili.Defect region extraction in images of train wheel tread[J].Optics and Precision Engineering,2009,17(4):901-908.
[3]张渝,王黎,高晓蓉,等.国内外车轮踏面损伤检测技术综述[J].机车车辆工艺,2002(1):1-4.ZHANG Yu,WANG Li,GAO Xiaorong,et al.A review of wheel tread damage detection technologies in and out China[J].Locomotive&Rolling Stock Technology,2002(1):1-4.
[4]张志腾,侯涛.基于改进Canny算法的列车车轮踏面损伤边缘提取[J].铁道标准设计,2018,62(1):148-150.ZHANG Zhiteng,HOU Tao.Edge extraction of train wheel tread damage based on improved Canny algorithm[J].Railway Standard Design,2018,62(1):148-150.
[5]陈静,禹建伟,谭志忠.地铁车辆轮对动态检测系统研究[J].城市轨道交通研究,2014(7):82-84.CHEN Jing,YU Jianwei,TAN Zhizhong.On dynamic testing system of metro vehicle wheelset[J].Urban Mass Transit,2014(7):82-84.
[6]Panetta K A,Wharton E J,Agaian S S.Logarithmic edge detection with applications[J].Journal of Computers,2008,3(9):3346-3351.
[7]Canny J.A computational approach to edge detection[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1986,8(6):679-698.
[8]许宏科,秦严严,陈会茹.一种基于改进Canny的边缘检测算法[J].红外技术,2014,36(3):210-214.XU Hongke,QIN Yanyan,CHEN Huiru.An improved algorithm for edge detection based on Canny[J].Infrared Technology,2014,36(3):210-214.
[9]吴翔,于微波,马艳辉,等.一种新的改进Canny图像边缘检测算法[J].影像科学与光化学,2016,34(1):116-121.WU Xiang,YU Weibo,MA Yanhui,et al.A new improved Canny image edge detection algorithm[J].Imaging Science and Photochemistry,2016,34(1):116-121.
[10]吉玲,杨亚,付珊珊,等.一种改进的Canny边缘检测算法[J].微处理机,2015(1):40-43.JI Ling,YANG Ya,FU Shanshan,et al.An improved Canny edge detection algorithm[J].Microprocessors,2015(1):40-43.
[11]雷超阳,刘军华,张敏.一种基于自适应的新型中值滤波算法[J].计算机工程与应用,2008,44(12):60-62.LEI Chaoyang,LIU Junhua,ZHANG Min.New median filter algorithm based on adaption[J].Computer Engineering and Applications,2008,44(12):60-62.
[12]Meher S K,Singhawat B.An improved recursive and adaptive median filter for high density impulse noise[J].AEU-International Journal of Electronics and Communications,2014,68(12):1173-1179.
[13]Otsu N.A threshold selection method from gray-level histograms[J].IEEE Transaction on System,Man and Cybernetics,1979,9(1):62-66.
[14]杨丹,赵海滨,龙哲.MATLAB图像处理实例详解[M].北京:清华大学出版社,2013:238-239.YANG Dan,ZHAO Haibin,LONG Zhe.MATLAB image processing examples detailed[M].Beijing:Tsinghua University Press,2013:238-239.
[15]袁小翠,吴禄慎,陈华伟.基于Otsu方法的钢轨图像分割[J].光学精密工程,2016,24(7):1772-1781.YUAN Xiaocui,WU Lushen,CHEN Huawei.Rail image segmentation based on Otsu threshold method[J].Optics and Precision Engineering,2016,24(7):1772-1781.
[2]赵勇,方宗德,田丽丽.列车车轮踏面缺陷的图像区域提取[J].光学精密工程,2009,17(4):901-908.ZHAO Yong,FANG Zongde,TIAN Lili.Defect region extraction in images of train wheel tread[J].Optics and Precision Engineering,2009,17(4):901-908.
[3]张渝,王黎,高晓蓉,等.国内外车轮踏面损伤检测技术综述[J].机车车辆工艺,2002(1):1-4.ZHANG Yu,WANG Li,GAO Xiaorong,et al.A review of wheel tread damage detection technologies in and out China[J].Locomotive&Rolling Stock Technology,2002(1):1-4.
[4]张志腾,侯涛.基于改进Canny算法的列车车轮踏面损伤边缘提取[J].铁道标准设计,2018,62(1):148-150.ZHANG Zhiteng,HOU Tao.Edge extraction of train wheel tread damage based on improved Canny algorithm[J].Railway Standard Design,2018,62(1):148-150.
[5]陈静,禹建伟,谭志忠.地铁车辆轮对动态检测系统研究[J].城市轨道交通研究,2014(7):82-84.CHEN Jing,YU Jianwei,TAN Zhizhong.On dynamic testing system of metro vehicle wheelset[J].Urban Mass Transit,2014(7):82-84.
[6]Panetta K A,Wharton E J,Agaian S S.Logarithmic edge detection with applications[J].Journal of Computers,2008,3(9):3346-3351.
[7]Canny J.A computational approach to edge detection[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1986,8(6):679-698.
[8]许宏科,秦严严,陈会茹.一种基于改进Canny的边缘检测算法[J].红外技术,2014,36(3):210-214.XU Hongke,QIN Yanyan,CHEN Huiru.An improved algorithm for edge detection based on Canny[J].Infrared Technology,2014,36(3):210-214.
[9]吴翔,于微波,马艳辉,等.一种新的改进Canny图像边缘检测算法[J].影像科学与光化学,2016,34(1):116-121.WU Xiang,YU Weibo,MA Yanhui,et al.A new improved Canny image edge detection algorithm[J].Imaging Science and Photochemistry,2016,34(1):116-121.
[10]吉玲,杨亚,付珊珊,等.一种改进的Canny边缘检测算法[J].微处理机,2015(1):40-43.JI Ling,YANG Ya,FU Shanshan,et al.An improved Canny edge detection algorithm[J].Microprocessors,2015(1):40-43.
[11]雷超阳,刘军华,张敏.一种基于自适应的新型中值滤波算法[J].计算机工程与应用,2008,44(12):60-62.LEI Chaoyang,LIU Junhua,ZHANG Min.New median filter algorithm based on adaption[J].Computer Engineering and Applications,2008,44(12):60-62.
[12]Meher S K,Singhawat B.An improved recursive and adaptive median filter for high density impulse noise[J].AEU-International Journal of Electronics and Communications,2014,68(12):1173-1179.
[13]Otsu N.A threshold selection method from gray-level histograms[J].IEEE Transaction on System,Man and Cybernetics,1979,9(1):62-66.
[14]杨丹,赵海滨,龙哲.MATLAB图像处理实例详解[M].北京:清华大学出版社,2013:238-239.YANG Dan,ZHAO Haibin,LONG Zhe.MATLAB image processing examples detailed[M].Beijing:Tsinghua University Press,2013:238-239.
[15]袁小翠,吴禄慎,陈华伟.基于Otsu方法的钢轨图像分割[J].光学精密工程,2016,24(7):1772-1781.YUAN Xiaocui,WU Lushen,CHEN Huawei.Rail image segmentation based on Otsu threshold method[J].Optics and Precision Engineering,2016,24(7):1772-1781.