基于缺陷比例限制的背景差分钢轨表面缺陷检测方法

doi:10.11772/j.issn.1001-9081.2020030337

计算机应用 ›› 2020, Vol. 40 ›› Issue (10): 3066-3074.DOI: 10.11772/j.issn.1001-9081.2020030337

• 虚拟现实与多媒体计算 • 上一篇下一篇

基于缺陷比例限制的背景差分钢轨表面缺陷检测方法

曹义亲, 刘龙标

华东交通大学软件学院, 南昌 330013

收稿日期:2020-03-23 修回日期:2020-04-30 出版日期:2020-10-10 发布日期:2020-05-19
通讯作者: 刘龙标
作者简介:曹义亲(1964-),男,江西都昌人,教授,硕士,CCF会员,主要研究方向:图像处理、模式识别;刘龙标(1995-),男,江西赣州人,硕士研究生,主要研究方向:图像处理。
基金资助:
国家自然科学基金资助项目（61663009）；江西省科技支撑计划重点项目（20161BBE50081）。

Rail surface defect detection method based on background differential with defect proportion limitation

CAO Yiqin, LIU Longbiao

School of Software, East China Jiaotong University, Nanchang Jiangxi 330013, China

Received:2020-03-23 Revised:2020-04-30 Online:2020-10-10 Published:2020-05-19
Supported by:
This work is partially supported by the National Natural Science Foundation of China (61663009), the Key Program of the Science and Technology Supporting Plan of Jiangxi Province (20161BBE50081).

摘要/Abstract

摘要： 针对钢轨表面图像具有的光照不均匀、可识别特征有限、对比度低、反射特性易变等特性，提出基于缺陷比例限制的背景差分钢轨表面缺陷检测方法。该方法主要包括轨面图像预处理、背景建模与差分、缺陷比例限制滤波、缺陷比例限制最大熵阈值分割和连通区域标记5个步骤。首先结合轨面图像列灰度均值和列灰度中值进行快速背景建模，将预处理后的图像与背景图像进行差分操作；其次利用轨面图像缺陷占比较低的特征对差分图进行缺陷比例上限的阈值截断，以增强差分图的对比度；随后利用此特征改进最大熵阈值分割，采用自适应加权因子对目标熵进行全局可变加权，并选择出一个合适的阈值使熵值最大化，使得在保留真实缺陷的同时减弱诸如阴影、锈迹等噪声的干扰；最后利用连通区域标记法对阈值分割后的二值图像中的缺陷区域进行统计，并把缺陷面积低于钢轨损伤标准的区域判定为噪声并进行去除，以实现钢轨表面缺陷检测。仿真实验结果表明，新方法可以对钢轨表面缺陷进行很好的检测，其检测结果的召回率、精确率和加权调和平均值分别达到94.19%、88.34%和92.96%，平均错误分类误差值为0.006 4，具有一定的实用价值。

关键词: 钢轨表面图像, 背景差分, 缺陷比例限制, 阈值分割, 缺陷检测

Abstract: Aiming at the characteristics of rail surface images such as uneven illumination, limited discernible features, low contrast and changeable reflection characteristics, a background differential rail surface defect detection method based on defect proportion limitation was proposed. The method mainly includes five steps:pre-processing of rail surface images, background modeling and difference, defect proportion limitation filtering, maximum entropy threshold segmentation of defect proportion limitation and connected area labeling. Firstly, the column grayscale mean and median of the rail surface image were combined to perform the rapid background modeling, and the difference operation was carried out to the pre-processed image and the background image. Secondly, the feature with low defect proportion in the rail surface image was used to truncate the upper threshold limit of the defect proportion in order to enhance the contrast of the difference image. Thirdly, the maximum entropy threshold segmentation was improved by using this feature, the global variable weighting of the target entropy was carried out by using the adaptive weighting factor, and an appropriate threshold was selected to maximize the entropy value, so as to reduce the interference of noises such as shadow and rust while retaining the real defects. Finally, the connected area labeling method was used to perform the statistics of the defect areas in the segmented binary image, and the area with defect area lower than the rail damage standard was determined as the noise and removed, so as to realize the rail surface defect detection. Simulation results show that the new method can detect rail surface defects well, and its results have the recall rate, precision rate and weighted harmonic mean of 94.19%, 88.34% and 92.96% respectively, and the average mis-classification error of 0.006 4, so that the method has certain practical value.

Key words: rail surface image, background difference, defect proportion limitation, threshold segmentation, defect detection

中图分类号:

TN391.41

曹义亲, 刘龙标. 基于缺陷比例限制的背景差分钢轨表面缺陷检测方法[J]. 计算机应用, 2020, 40(10): 3066-3074.

CAO Yiqin, LIU Longbiao. Rail surface defect detection method based on background differential with defect proportion limitation[J]. Journal of Computer Applications, 2020, 40(10): 3066-3074.

参考文献

[1] LI Q,ZHONG Z,LIANG Z,et al. Rail inspection meets big data:methods and trends[C]//Proceedings of the 18th International Conference on Network-Based Information Systems. Piscataway:IEEE,2015:302-308.
[2] 张辉, 宋雅男, 王耀南, 等. 钢轨缺陷无损检测与评估技术综述[J]. 仪器仪表学报,2019,40(2):11-25.(ZHANG H,SONG Y N,WANG Y N,et al. Review of rail defect non-destructive testing and evaluation[J]. Chinese Journal of Scientific Instrument,2019, 40(2):11-25.)
[3] ZHANG H,JIN X,JONATHAN Q M,et al. Automatic visual detection system of railway surface defects with curvature filter and improved Gaussian mixture model[J]. IEEE Transactions on Instrumentation and Measurement,2018,67(7):1593-1608.
[4] MOHAMMADI R,HE Q,GHOFRANI F,et al. Exploring the impact of foot-by-foot track geometry on the occurrence of rail defects[J]. Transportation Research Part C:Emerging Technologies, 2019,102:153-172.
[5] KISHORE M B,PARK J W,SONG S J,et al. Characterization of defects on rail surface using eddy current technique[J]. Journal of Mechanical Science and Technology,2019,33(9):4209-4215.
[6] ANTIPOV A G,MARKOV A A. Detectability of rail defects by magnetic flux leakage method[J]. Russian Journal of Nondestructive Testing,2019,55(4):277-285.
[7] MARKOV A A,MAKSIMOVA E A,ANTIPOV A G. Analyzing the development of rail defects based on results of multichannel periodic testing[J]. Russian Journal of Nondestructive Testing,2019,55(12):875-886.
[8] TRINH H,HAAS N,LI Y,et al. Enhanced rail component detection and consolidation for rail track inspection[C]//Proceedings of the 2012 IEEE Workshop on the Applications of Computer Vision. Piscataway:IEEE,2012:289-295.
[9] DUBEY A K,JAFFERY Z A. Maximally stable extremal region marking-based railway track surface defect sensing[J]. IEEE Sensors Journal,2016,16(24):9047-9052.
[10] MIN Y,XIAO B,DANG J,et al. Real time detection system for rail surface defects based on machine vision[J]. EURASIP Journal on Image and Video Processing,2018,2018:No. 3.
[11] ABBAS M A. Improving deep learning performance using random forest HTM cortical learning algorithm[C]//Proceedings of the 1st International Workshop on Deep and Representation Learning. Piscataway:IEEE,2018:13-18.
[12] ZHANG X,WANG K,WANG Y,et al. An improved method of rail health monitoring based on CNN and multiple acoustic emission events[C]//Proceedings of the 2017 IEEE International Instrumentation and Measurement Technology Conference. Piscataway:IEEE,2017:1-6.
[13] SHANG L,YANG Q,WANG J,et al. Detection of rail surface defects based on CNN image recognition and classification[C]//Proceedings of the 20th International Conference on Advanced Communication Technology. Piscataway:IEEE,2018:45-51.
[14] 赵永强, 饶元, 董世鹏, 等. 深度学习目标检测方法综述[J]. 中国图象图形学报,2020,25(4):629-654.(ZHAO Y Q,RAO Y,DONG S P,et al. Survey on deep learning object detection[J]. Journal of Image and Graphics,2020,25(4):629-654.)
[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 X C,WU L S,CHEN H W. Rail image segmentation based on Otsu threshold method[J]. Optics and Precision Engineering,2016,24(7):1772-1781.)
[16] OTSU N. A threshold selection method from gray-level histograms[J]. IEEE Transactions on Systems, Man, and Cybernetics, 1979,9(1):62-66.
[17] YU H,LI Q,TAN Y,et al. A coarse-to-fine model for rail surface defect detection[J]. IEEE Transactions on Instrumentation and Measurement,2019,68(3):656-666.
[18] 贺振东, 王耀南, 刘洁, 等. 基于背景差分的高铁钢轨表面缺陷图像分割[J]. 仪器仪表学报,2016,37(3):640-649.(HE Z D,WANG Y N,LIU J,et al. Background differencing-based high-speed rail surface defect image segmentation[J]. Chinese Journal of Scientific Instrument,2016,37(3):640-649.)
[19] 闵永智, 岳彪, 马宏锋, 等. 基于图像灰度梯度特征的钢轨表面缺陷检测[J]. 仪器仪表学报,2018,39(4):220-229.(MIN Y Z,YUE B,MA H F,et al. Rail surface defects detection based on gray scale gradient characteristics of image[J]. Chinese Journal of Scientific Instrument,2018,39(4):220-229.)
[20] GAN J,LI Q,WANG J,et al. A hierarchical extractor-based visual rail surface inspection system[J]. IEEE Sensors Journal, 2017,17(23):7935-7944.
[21] PARIS S,DURAND F. A fast approximation of the bilateral filter using a signal processing approach[J]. International Journal of Computer Vision,2009,81(1):24-52.
[22] ROSIN P L,ELLIS T. Image difference threshold strategies and shadow detection[C]//Proceedings of the 1995 British Machine Vision Conference. Durham:BMVA Press,1995:347-356.
[23] 郭会文, 吴新宇, 苏士娟, 等. 移动相机下基于三维背景估计的运动目标检测[J]. 仪器仪表学报,2017,38(10):2573-2580. (GUO H W,WU X Y,SU S J,et al. 3D background estimation for moving object detection using a single moving camera[J]. Chinese Journal of Scientific Instrument,2017,38(10):2573-2580.)
[24] KAPUR J N,SAHOO P K,WONG A K C. A new method for graylevel picture thresholding using the entropy of the histogram[J]. Computer Vision,Graphics,and Image Processing,1985,29(3):273-285.
[25] PAPAELIAS M,ROBERTS C,DAVIS C L. A review on nondestructive evaluation of rails:state-of-the-art and future development[J]. Proceedings of the Institution of Mechanical Engineers,Part F:Journal of Rail and Rapid Transit,2008,222(4):367-384.
[26] YASNOFF W A,MUI J K,BACUS J W. Error measures for scene segmentation[J]. Pattern Recognition,1977,9(4):217-231.
[27] LI Q,SHI Z,ZHANG H,et al. A cyber-enabled visual inspection system for rail corrugation[J]. Future Generation Computer Systems,2018,79(Pt 1):374-382.

基于缺陷比例限制的背景差分钢轨表面缺陷检测方法

Rail surface defect detection method based on background differential with defect proportion limitation

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	吴则举, 焦翠娟, 陈亮. 基于改进Faster R-CNN的轮胎缺陷检测方法[J]. 计算机应用, 2021, 41(7): 1939-1946.
[2]	高钦泉, 黄炳城, 刘文哲, 童同. 基于改进CenterNet的竹条表面缺陷检测方法[J]. 计算机应用, 2021, 41(7): 1933-1938.
[3]	史杨潇, 章军, 陈鹏, 王兵. 基于轻量级网络的钢铁表面缺陷分类[J]. 计算机应用, 2021, 41(6): 1836-1841.
[4]	贾鹤鸣, 李瑶, 姜子超, 孙康健. 基于改进共生生物搜索算法的林火图像多阈值分割[J]. 计算机应用, 2021, 41(5): 1465-1470.
[5]	卓禹心, 韩素雅, 张榆锋, 李支尧, 董毅峰. 基于超声谐波包络Nakagami参数图像的微波消融区域自动分割方法[J]. 计算机应用, 2021, 41(10): 3089-3096.
[6]	张京爱, 王江涛. 基于多尺度卷积神经网络和类内mixup操作的磁瓦表面质量识别[J]. 计算机应用, 2021, 41(1): 275-279.
[7]	王思宇, 高炜欣, 李璐. 环口焊X射线焊缝图像质量评定模型[J]. 计算机应用, 2020, 40(9): 2748-2753.
[8]	付磊, 任德均, 吴华运, 郜明, 邱吕, 胡云起. 基于改进Fast-SCNN的塑瓶气泡缺陷实时分割算法[J]. 计算机应用, 2020, 40(6): 1824-1829.
[9]	张亚洲, 卢先领. 基于改进相干增强扩散与纹理能量测度和高斯混合模型的导光板表面缺陷检测方法[J]. 计算机应用, 2020, 40(5): 1545-1552.
[10]	王理顺, 钟勇, 李振东, 贺宜龙. 基于深度学习的织物缺陷在线检测算法[J]. 计算机应用, 2019, 39(7): 2125-2128.
[11]	陈本智, 方志宏, 夏勇, 张灵, 兰守忍, 王利生. 基于X射线图像的厚钢管焊缝中气孔缺陷的自动检测[J]. 计算机应用, 2017, 37(3): 849-853.
[12]	杨婷, 李博, 石雯婧, 张成飞. 基于DSP的单车道车流量实时监测算法[J]. 计算机应用, 2017, 37(2): 593-596.
[13]	张蕾, 朱义鑫, 徐春, 于凯. 基于字典学习的软件缺陷检测算法[J]. 计算机应用, 2016, 36(9): 2486-2491.
[14]	孟令江, 王挺, 姚辰. 野外环境下图像中坑区域的提取方法[J]. 计算机应用, 2016, 36(4): 1132-1136.
[15]	甘玲, 李瑞. 基于自适应虚拟线圈的多车道车流量检测算法[J]. 计算机应用, 2016, 36(12): 3511-3514.