计算机科学

计算机科学 ›› 2023, Vol. 50 ›› Issue (11A): 230200146-6.doi: 10.11896/jsjkx.230200146

• 图像处理&多媒体技术 • 上一篇    下一篇

基于深度学习的钢轨光带检测算法

张新峰1, 边浩南1, 张博2, 张嘉铭1, 梁玉清1   

  1. 1 北京工业大学信息学部 北京 100124
    2 中国铁道科学研究院集团有限公司基础设施检测研究所 北京 100081
  • 发布日期:2023-11-09
  • 通讯作者: 张博(zhangbojc@rails.cn)
  • 作者简介:(zxf@bjut.edu.cn)
  • 基金资助:
    中国铁道科学研究院集团有限公司基金(2022YJ179)

Rail Light Band Detection Algorithm Based on Deep Learning

ZHANG Xinfeng1, BIAN Haonan1, ZHANG Bo2, ZHANG Jiaming1, LIANG Yuqing1   

  1. 1 Faculty of Information Technology,Beijing University of Technology,Beijing 100124,China
    2 Institute of Infrastructure Testing,China Academy of Railway Sciences Group Co.,LTD.,Beijing 100081,China
  • Published:2023-11-09
  • About author:ZHANG Bo,born in 1988,Ph.D,asso-ciate researcher.His main research interests include inspection and monitoring of railway infrastructure,and so on.
  • Supported by:
    Foundation of China Academy of Railway Sciences Group Co. LTD.(2022YJ179).

PDF (PC)

202

摘要： 列车在轨道上行驶的过程中,车轮的轮缘会对钢轨轨面进行碾压,形成光带。钢轨光带的形状反映钢轨与车轮之间的位置关系,对异常光带形状的捕获可以有效预防列车运行的安全问题,并且提高列车乘坐的舒适程度。传统的人工检测光带方法存在效率低和专业性强等问题。早期的计算机视觉技术利用图像的边缘信息和灰度信息对钢轨区域进行定位,在此基础之上对光带区域进行分割,在效率和鲁棒性上差强人意。因此,对钢轨以及光带区域进行高效率、高精度分割是十分必要的。首先,使用ResNet分类网络区分道岔区和非道岔区图像。然后,针对两种图像,分别利用DeeplabV3+分割网络对图像的光带和钢轨区域进行分割。最后,针对钢轨边缘容易分割不清的问题,提出一种基于Douglas-Peucker算法的后处理算法,对钢轨边缘进行拟合。研究结果表明:相比于直接利用语义分割网络对两类图像一起分割,先分类再分割并对分割结果后处理的操作能够稳步提高分割准确率。该算法对非道岔区的图像的整体分割、铁轨分割、光带分割的交并比(IOU)分别为95.45%,87.48%,92.60%;对道岔区的图像的相应指标分别为90.20%,76.56%,85.42%。因此,所提算法对钢轨以及光带区域的分割精度较高,并且能够高效完成批量图像处理,具有较高的工程价值。

关键词: 深度学习, 图像处理, 损伤检测, 语义分割, 铁路轨道

Abstract: When the train is running on the track,the rim of the wheel will crush the rail surface to form a light band.The shape of the light band reflects the position relationship between the rail and the wheel.The capture of the abnormal light band shape can effectively prevent the safety problems of the train operation and improve the comfort of the train.The traditional light band detection method uses manual detection,which has some problems such as low efficiency and strong professionalism.The early computer vision technology used the edge information and gray information of the image to locate the rail region,and then segmented the light band region on this basis,which was not satisfactory in efficiency and robustness.Therefore,it is necessary to segment the rail and the light band with high efficiency and high precision.This paper firstly uses ResNet classification network to classify the image of the non-turnout and the image of turnout.Then,for the two kinds of images,DeeplabV3+ segmentation network is used to segment the light band and rail area of the image respectively.Finally,aiming at the problem that the edge of the rail is easy to be segmented unclearly,this paper proposes a post-processing algorithm based on the Douglas-Peucker algorithm to fit the edge of the rail.The research results show that,compared with the direct use of semantic segmentation network for the segmentation of two types of images,the segmentation accuracy can be improved steadily through the classification operation and the post-processing of the segmentation results.In addition,the intersection over union(IOU) of the overall segmentation,rail segmentation and light band segmentation of the non-turnout images are 95.45%,87.48% and 92.60%,respectively.For turnout images,the values are 90.20%,76.56% and 85.42%,respectively.The proposed algorithm has high precision for the segmentation of rail and light band region,and can efficiently complete batch image processing,which has high engineering value.

Key words: Deep learning, Image processing, Damage detection, Semantic segmentation, Railway track

中图分类号: 

  • TP391
[1]WANG Q D,YANG Y,LUO Y P,et al.Review on railway intrusion detection methods[J].Journal of Railway Science and Engineering,2019,16(12):3152-3159.
[2]ZUO Y L.Study on smoothness of high speed railway trackfrom unusualness of steel track light ribbon[J].Railway Stan-dard Design,2009(4):13-16.
[3]ZHOU Y,WANG S F,WANG F,et al.Analysis on abnormal running surface on the track top of urban mass transit[J].Urban Mass Transit,2012,15(10):49-52.
[4]LI W Y,FANG Y,JIANG S G,et al.Detection system of railway rail light band anomaly [J].Computer Engineering and Application,2017,53(9):246-252.
[5]TANG X N,WANG Y N.Visual Detection and Recognition Algorithm for Rail Surface Defects [J].Computer Engineering,2013,39(3):25-30.
[6]KRIZHEVSKY A,SUTSKEVER I,HINTON G E.Imagenetclassification with deep convolutional neural networks[J].Communications of the ACM,2017,60(6):84-90.
[7]SIMONYAN K,ZISSERMAN A.Very deep convolutional networks for large-scale image recognition[J].arXiv:1409.1556,2014.
[8]HE K,ZHANG X,REN S,et al.Deep residual learning for im-age recognition[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2016:770-778.
[9]LONG J,SHELHAMER E,DARRELL T.Fully Convolutional Networks for Semantic Segmentation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2017,39(4):640-651.
[10]RONNEBERGER O,FISCHER P,BROX T.U-net:Convolu-tional networks for biomedical image segmentation[C]//International Conference on Medical Image Computing and Computer-assisted Intervention.Cham:Springer,2015:234-241.
[11]ZHAO H,SHI J,QI X,et al.Pyramid scene parsing network[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2017:2881-2890.
[12]CHEN L C,PAPANDREOU G,KOKKINOS I,et al.Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs[C]//International Conference on Learning Representations.2015.
[13]CHEN L C,PAPANDREOU G,KOKKINOS I,et al.Deeplab:Semantic image segmentation with deep convolutional nets,atrous convolution,and fully connected crfs[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2017,40(4):834-848.
[14]CHEN L C,PAPANDREOU G,SCHROFF F,et al.Rethinking atrous convolution for semantic image segmentation[J].arXiv:1706.05587,2017.
[15]CHEN L C,ZHU Y,PAPANDREOU G,et al.Encoder-decoder with atrous separable convolution for semantic image segmentation[C]//Proceedings of the European Conference on Computer Vision(ECCV).2018:801-818.
[16]CHOLLET F.Xception:Deep learning with depthwise separable convolutions[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2017:1251-1258.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
渝ICP备16013121号-4
地址：重庆市渝北区洪湖西路18号    邮编：401121  
电话：023-63500828（编辑部） 023-67039612（会议/专题） 023-67039623（财务/发票）
E-mail：jsjkx12@163.com
本系统由北京玛格泰克科技发展有限公司设计开发