Computer Science

Computer Science ›› 2022, Vol. 49 ›› Issue (11A): 210800241-6.doi: 10.11896/jsjkx.210800241

• Image Processing & Multimedia Technology • Previous Articles     Next Articles

Rail Surface Defect Detection Model Based on Attention Module and Hybrid-supervised Learning

ZHAO Chen-yang1, ZHANG Hui2, LIAO De1, LI Chen1   

  1. 1 School of Electrical & Information Engineering,Changsha University of Science and Technology,Changsha 410114,China
    2 School of Robotics,Hunan University,Changsha 410012,China
  • Online:2022-11-10 Published:2022-11-21
  • About author:ZHAO Chen-yang,born in 1997,postgraduate.Her main research interests include covers image processing and deep learning.
    ZHANG Hui,born in 1983, Ph.D,professor,IEEE member.His main research interests include machine vision,sparse representation and vision tra-cking.
  • Supported by:
    National Key R & D Program of China(2018YFB1308200),National Natural Science Foundation of China(61971071,6202780012),Hunan Science Fund for Distinguished Young Scholars(2021JJ10025),Changsha Science and Technology Major Project(kh2003026),Joint Open Foundation of State Key Laboratory of Robotics(2021-KF-22-17) and China University Industry-University-Research Innovation Fund(2020HYA06006).

PDF (PC)

349

Abstract: Rail surface defect detection is an important part of ensuring railway safety.By analyzing the necessity of rail surface defect detection and the shortcomings of existing detection methods,a rail surface defect detection model based on attention mo-dule and hybrid-supervised learning is proposed.Aiming at the problem of a large number of parameters and high deployment cost of existing model,an end-to-end rail defect detection model is proposed.The attention module is used to guide the generation of feature clusters,which improves the speed of defect detection and reduces the cost of model deployment.In view of the problems of few abnormal samples and the high cost of labeling in practical applications,the influence of rough labeling and hybrid supervision is studied,and the pixel-level label data is processed to make different areas of the label get different attention and reduce the dependence of model on label.Finally,experiments are carried out on the actual rail datasets.and the results show that the performance of hybrid-supervised learning is equivalent to that of full supervised learning by adding a small amount of pixel-level label samples to image-level label samples,and the classification accuracy of the model reaches 99.7%.

Key words: Surface defect detection, Deep learning, Attention, Small-sized datasets, Rough label

CLC Number: 

  • TP391
[1]ZHANG H,SONG Y N,WANG Y N,et al.Nondestructive Testing and Evaluation of Rail Defects:A Review [J].Chinese Journal of Scientific Instrument,2019,40(2):11-25.
[2]MIN Y Z,YUE B,MA H F,et al.Rail Surface Defect Detection Based on Image Gray Gradient Feature [J].Chinese Journal of Scientific Instrument,2018,39(4):220-229.
[3]TAO G M,WANG R F,ZHU H L,et al.Development and Application of Automatic Detection Technology for Rail Surface Quality[J].Steel Rolling,2016,33(6):59-62.
[4]PARK J K,KWON B K,PARK J H,et al.Machine learning-based imaging system for surface defect inspection[J].International Journal of Precision Engineering and Manufacturing-Green Technology,2016,3(3):303-310.
[5]TAO X,ZHANG D,MA W,et al.Automatic metallic surface defect detection and recognition with convolutional neural networks[J].Applied Sciences,2018,8(9):1575.
[6]JIN X T,WANG Y N,ZHANG H,et al.Rail Surface Defect Detection System Based on Bayesian CNN and Attention Network[J].Acta Automatica Sinica,2019,45(12):2312-2327.
[7]ZHANG H,SONG Y,CHEN Y,et al.MRSDI-CNN:Multi-Model Rail Surface Defect Inspection System Based on Convolutional Neural Networks[J].IEEE Transactions on Intelligent Transportation Systems,2022,23(8):1162-1177.
[8]WANG L,ZHUANG L,ZHANG Z.Automatic detection of rail surface cracks with a superpixel-based data-driven framework[J].Journal of Computing in Civil Engineering,2019,33(1):04018053.
[9]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,2018,68(3):656-666.
[10]NI X,MA Z,LIU J,et al.Attention Network for Rail Surface Defect Detection via CASIoU-Guided Center-Point Estimation[J].IEEE Transactions on Industrial Informatics,2022,18(3):1694-1705.
[11]YUAN H,CHEN H,LIU S W,et al.A deep convolutional neural network for detection of rail surface defect[C]//2019 IEEE Vehicle Power and Propulsion Conference(VPPC).IEEE,2019:1-4.
[12]RACKI D,TOMAZEVIC D,SKOCAJ D.A compact convolutional neural network for textured surface anomaly detection[C]//2018 IEEE Winter Conference on Applications of Computer Vision(WACV).IEEE,2018:1331-1339.
[13]TABERNIK D,ŠELA S,SKVARČ J,et al.Segmentation-based deep-learning approach for surface-defect detection[J].Journal of Intelligent Manufacturing,2020,31(3):759-776.
[14]BOŽIČ J,TABERNIK D,SKOČAJ D.End-to-end training of a two-stage neural network for defect detection[C]//2020 25th International Conference on Pattern Recognition(ICPR).IEEE,2021:5619-5626.
[15]XU L,LV S,DENG Y,et al.A weakly supervised surface defect detection based on convolutional neural network[J].IEEE Access,2020,8:42285-42296.
[16]BOŽIČ J,TABERNIK D,SKOČAJ D.Mixed supervision for surface-defect detection:from weakly to fully supervised lear-ning[J].Computers in Industry,2021,129:103459.
[17]LIU H,LIU F,FAN X,et al.Polarized Self-Attention:Towards High-quality Pixel-wise Regression[J].arXiv:2107.00782,2021.
[1] RAO Zhi-shuang, JIA Zhen, ZHANG Fan, LI Tian-rui. Key-Value Relational Memory Networks for Question Answering over Knowledge Graph [J]. Computer Science, 2022, 49(9): 202-207.
[2] WU Zi-yi, LI Shao-mei, JIANG Meng-han, ZHANG Jian-peng. Ontology Alignment Method Based on Self-attention [J]. Computer Science, 2022, 49(9): 215-220.
[3] TANG Ling-tao, WANG Di, ZHANG Lu-fei, LIU Sheng-yun. Federated Learning Scheme Based on Secure Multi-party Computation and Differential Privacy [J]. Computer Science, 2022, 49(9): 297-305.
[4] ZHOU Fang-quan, CHENG Wei-qing. Sequence Recommendation Based on Global Enhanced Graph Neural Network [J]. Computer Science, 2022, 49(9): 55-63.
[5] DAI Yu, XU Lin-feng. Cross-image Text Reading Method Based on Text Line Matching [J]. Computer Science, 2022, 49(9): 139-145.
[6] ZHOU Le-yuan, ZHANG Jian-hua, YUAN Tian-tian, CHEN Sheng-yong. Sequence-to-Sequence Chinese Continuous Sign Language Recognition and Translation with Multi- layer Attention Mechanism Fusion [J]. Computer Science, 2022, 49(9): 155-161.
[7] XU Yong-xin, ZHAO Jun-feng, WANG Ya-sha, XIE Bing, YANG Kai. Temporal Knowledge Graph Representation Learning [J]. Computer Science, 2022, 49(9): 162-171.
[8] XIONG Li-qin, CAO Lei, LAI Jun, CHEN Xi-liang. Overview of Multi-agent Deep Reinforcement Learning Based on Value Factorization [J]. Computer Science, 2022, 49(9): 172-182.
[9] WANG Jian, PENG Yu-qi, ZHAO Yu-fei, YANG Jian. Survey of Social Network Public Opinion Information Extraction Based on Deep Learning [J]. Computer Science, 2022, 49(8): 279-293.
[10] HAO Zhi-rong, CHEN Long, HUANG Jia-cheng. Class Discriminative Universal Adversarial Attack for Text Classification [J]. Computer Science, 2022, 49(8): 323-329.
[11] JIANG Meng-han, LI Shao-mei, ZHENG Hong-hao, ZHANG Jian-peng. Rumor Detection Model Based on Improved Position Embedding [J]. Computer Science, 2022, 49(8): 330-335.
[12] LI Rong-fan, ZHONG Ting, WU Jin, ZHOU Fan, KUANG Ping. Spatio-Temporal Attention-based Kriging for Land Deformation Data Interpolation [J]. Computer Science, 2022, 49(8): 33-39.
[13] WANG Ming, PENG Jian, HUANG Fei-hu. Multi-time Scale Spatial-Temporal Graph Neural Network for Traffic Flow Prediction [J]. Computer Science, 2022, 49(8): 40-48.
[14] FANG Yi-qiu, ZHANG Zhen-kun, GE Jun-wei. Cross-domain Recommendation Algorithm Based on Self-attention Mechanism and Transfer Learning [J]. Computer Science, 2022, 49(8): 70-77.
[15] ZHU Cheng-zhang, HUANG Jia-er, XIAO Ya-long, WANG Han, ZOU Bei-ji. Deep Hash Retrieval Algorithm for Medical Images Based on Attention Mechanism [J]. Computer Science, 2022, 49(8): 113-119.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
渝ICP备16013121号-4
Add:18# Honghu West Rd., Yubei ,Chongqing,China    Post Code: 401121
Tel: 023-63500828/023-67039612/023-67039623
E-mail: jsjkx12@163.com
Powered by Beijing Magtech Co., Ltd.