Abstract
Rail defects have long threatened the safety of railway vehicles. Existing inspection methods still have some problems and flaws that can not meet practical application. In this paper, we propose a rail surface defect inspection method based on bimodal structured light sensors, termed Rail Surface Defect Inspection Network (RSDINet), which can detect and measure defect in bimodal rail images. To verify effect of the method, we establish a bimodal image dataset of intensity and depth images collected by the constructed bimodal structured light sensors data acquisition system. To solve the irregularity of rail surface defect shape, we propose a feature extraction backbone network by introducing deformable convolution. Moreover, RSDINet adopts a parallel feature extraction strategy to process bimodal images respectively. Specifically, we apply different backbone networks to bimodal images respectively for different image characteristics to enhance the feature representation ability of network. Then, our RSDINet fuses multi-scale feature of bimodal images respectively and carries out multi-scale rail surface defect detection and measurement. It is worth noting that the proposed RSDINet can accomplish these two tasks end-to-end simultaneously. Experiments demonstrate that based on the established dataset, the method achieves 87.17 mAP and 39.07 mSAP for detection and measurement respectively at 6.2 FPS on a single GPU, which has a better performance than previous SOTA methods and shows a promising potential for application in high-speed railway.
Similar content being viewed by others
Data availability
Some or all data, models, or code generated or used during the study are available from the corresponding author by request (Shengchun Wang).
References
Dou Y, Huang Y, Li Q, Luo S (2014) A fast template matching-based algorithm for railway bolts detection. Int J Mach Learn Cybern 5(6):835–844
Li Q, Ren S (2012) A real-time visual inspection system for discrete surface defects of rail heads. IEEE Trans Instrum Meas 61(8):2189–2199
Huber-Mörk R, Nölle M, Oberhauser A, Fischmeister E (2010) Statistical rail surface classification based on 2d and 21/2d image analysis. In: International conference on advanced concepts for intelligent vision systems. Springer, Berlin, pp 50–61
Yu H, Li Q, Tan Y, Gan J, Wang J, Geng YA, Jia L (2019) A coarse-to-fine model for rail surface defect detection. IEEE Trans Instrum Meas 68(3):656–666
Li Q, Ren S (2012) A visual detection system for rail surface defects. IEEE Trans Syst Man Cybern Part C (Appl Rev) 42(6):1531–1542
Molodova M, Li Z, Núñez A, Dollevoet R (2014) Automatic detection of squats in railway infrastructure. IEEE Trans Intell Transp Syst 15(5):1980–1990
Wang J, Li Q, Gan J, Yu H, Yang X (2020) Surface defect detection via entity sparsity pursuit with intrinsic priors. IEEE Trans Ind Inform 16(1):141–150
Chen L, Liang Y, Wang K (2010) Inspection of rail surface defect based on machine vision system. In: The 2nd international conference on information science and engineering. IEEE, Hangzhou, China, pp 3793–3796
Molodova M, Li Z, Nunez A, Dollevoet R (2013) Monitoring the railway infrastructure: detection of surface defects using wavelets. In: International IEEE conference on intelligent transportation systems. IEEE, The Hague, pp 1316–1321
Gan J, Li Q, Wang J, Yu H (2017) A hierarchical extractor-based visual rail surface inspection system. IEEE Sens J 17(23):7935–7944
Xu K (2010) 3D detection technique of surface defects for steel rails based on linear lasers. Chin J Mech Eng. https://doi.org/10.3901/JME.2010.08.001
Ke X, Zhou P, Hu C (2012) 3D detection technique of surface defects for heavy rail based on binocular stereo vision. Proc SPIE Int Soc Opt Eng 8417:07
Ren S, Li Q, Xu G, Han Q, Feng Q (2011) Research on robust fast algorithm of rail surface defect detection. Zhongguo Tiedao Kexue/China Railw Fence 32(1):25–29
Zhao HW, Huang YP, Wang SC, Qing-Yong LI (2014) Rail surface defect detection algorithm based on spatial filtering. Comput Sci 41(1):130–137
Gao JQ, Liu GH (2017) 3D defect detection technology for rail surface with multi-camera line structure light. Mach Des Manuf 3:170–172
Li P, Wang P, Chen P, Xu H (2018) Rail corrugation detection based on 3D structured light and wavelet analysis. Railw Stand Des 62(8):33–38
Krizhevsky A, Sutskever I, Hinton G (2017) Imagenet classification with deep convolutional neural networks. Commun ACM 60(6):84–90
Faghih-Roohi S, Siamak H, Núez A, Babuska R, Schutter BD (2016) Deep convolutional neural networks for detection of rail surface defects. In: International joint conference on neural networks (IJCNN 2016). IEEE, Vancouver, pp 2584–2589
Shang L, Yang Q, Wang J, Li S, Lei W (2018) Detection of rail surface defects based on CNN image recognition and classification. In: 2018 20th International conference on advanced communication technology (ICACT). IEEE, Chuncheon, pp 45–51
Song Y, Zhang H, Liu L, Zhang H (2019) Rail surface defect detection method based on YOLOv3 deep learning networks. In: 2018 Chinese automation congress (CAC). IEEE, Xi’an, pp 1563–1568
He Y, Song K, Meng Q, Yan Y (2020) An end-to-end steel surface defect detection approach via fusing multiple hierarchical features. IEEE Trans Instrum Meas 69(4):1493–1504
Yi L, Li G, Jiang M (2017) An end-to-end steel strip surface defects recognition system based on convolutional neural networks. Steel Res Int 88(2):176–187
Chen LC, Papandreou G, Kokkinos I, Murphy K, Yuille AL (2018) DeepLab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs. IEEE Trans Pattern Anal Mach Intell 40(4):834–848
Dai J, Qi H, Xiong Y, Li Y, Zhang G, Hu H, Wei Y (2017) Deformable convolutional networks. In: 2017 IEEE international conference on computer vision (ICCV). IEEE, Venice, pp 764–773
Everingham M, Gool LV, Williams CKI, Zisserman WA (2010) The Pascal visual object classes (VOC) challenge. Int J Comput Vis 88(2):303–338
Girshick R, Donahue J, Darrell T, Malik J (2014) Rich feature hierarchies for accurate object detection and semantic segmentation. In: 2014 IEEE conference on computer vision and pattern recognition. IEEE, Columbus, pp 580–587
Girshick R (2015) Fast R-CNN. In: 2015 IEEE international conference on computer vision (ICCV). IEEE, Santiago, pp 1440–1448
Ren S, He K, Girshick R, Sun J (2017) Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans Pattern Anal Mach Intell 39(6):1137–1149
Redmon J, Divvala S, Girshick R, Farhadi A (2016) You only look once: unified, real-time object detection. In: 2016 IEEE conference on computer vision and pattern recognition (CVPR). IEEE, Las Vegas, pp 779–788
Redmon J, Farhadi A (2018) Yolov3: an incremental improvement. arXiv e-prints. arXiv:1804.02767 [cs.CV]
Bochkovskiy A, Wang CY, Liao HYM (2020) Yolov4: optimal speed and accuracy of object detection. arXiv e-prints. arXiv:2004.10934 [cs.CV]
Redmon J, Farhadi A (2017) Yolo9000: better, faster, stronger. In: 2017 IEEE conference on computer vision and pattern recognition (CVPR). IEEE, Honolulu, pp 6517–6525
Liu W, Anguelov D, Erhan D, Szegedy C, Reed S, Fu CY, Berg AC (2016) SSD: single shot multibox detector. In: Computer vision—ECCV 2016. Springer, Cham, pp 21–23
Li B, Ouyang W, Sheng L, Zeng X, Wang X (2019) Gs3d: an efficient 3d object detection framework for autonomous driving. In: 2019 IEEE/CVF conference on computer vision and pattern recognition (CVPR). IEEE, Long Beach
Chen X, Kundu K, Zhu Y, Ma H, Fidler S, Urtasun R (2018) 3D object proposals using stereo imagery for accurate object class detection. IEEE Trans Pattern Anal Mach Intell 40(5):1259–1272
Qi CR, Liu W, Wu C, Su H, Guibas LJ (2018) Frustum pointnets for 3D object detection from RGB-D data. In: 2018 IEEE/CVF conference on computer vision and pattern recognition (CVPR). IEEE, Salt Lake City
Zhou Y, Tuzel O (2018) Voxelnet: End-to-end learning for point cloud based 3D object detection. In: 2018 IEEE/CVF conference on computer vision and pattern recognition (CVPR). IEEE, Salt Lake City
Acknowledgements
Work described in this paper was supported by National Natural Science Foundation of China—China National Railway Group Co., LTD. High-speed Railway Basic Research Fund under Grant no. U1934215, Research and Development Plan of China Academy of Railway Sciences Co. LTD under Grant no. 2021IMXM04.
Author information
Authors and Affiliations
Corresponding authors
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Zheng, J., Wang, L., Liu, J. et al. An inspection method of rail head surface defect via bimodal structured light sensors. Int. J. Mach. Learn. & Cyber. 14, 1903–1920 (2023). https://doi.org/10.1007/s13042-022-01736-y
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s13042-022-01736-y