基于注意力机制与混合监督学习的钢轨表面缺陷检测模型

doi:10.11896/jsjkx.210800241

计算机科学 ›› 2022, Vol. 49 ›› Issue (11A): 210800241-6.doi: 10.11896/jsjkx.210800241

• 图像处理&多媒体技术 • 上一篇下一篇

基于注意力机制与混合监督学习的钢轨表面缺陷检测模型

赵晨阳¹, 张辉², 廖德¹, 李晨¹

1 长沙理工大学电气与信息工程学院长沙 410114
2 湖南大学机器人学院长沙 410012

出版日期:2022-11-10 发布日期:2022-11-21
通讯作者: 张辉(zhanghuihby@126.com)
作者简介:(zhaochenyang920@163.com)
基金资助:
国家重点研发计划(2018YFB1308200),国家自然科学基金(61971071,6202780012);湖南省杰出青年科学基金(2021JJ10025);长沙市科技重大专项(kh2003026),机器人学国家重点实验室联合开放基金(2021-KF-22-17);中国高校产学研创新基金(2020HYA06006)

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

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

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).

摘要/Abstract

摘要： 钢轨表面缺陷检测是保障铁路安全运行的重要一环,通过分析钢轨表面缺陷检测的必要性和现有检测方法的不足,提出了一种基于注意力机制与混合监督学习的钢轨表面缺陷检测模型。针对现有模型参数量大、部署成本高的问题,提出了端到端的钢轨缺陷检测模型,利用注意力模块引导特征丛的生成,提高缺陷检测速度,降低模型部署成本;针对实际应用中存在的异常样本少、标注成本高等问题,研究粗糙标签与混合监督对模型的影响,对像素级标签进行数据处理,使标签的不同区域获得不同的关注,降低模型对标签的依赖性。最终在实际钢轨数据集上进行实验验证,结果表明在图像级标签样本中加入少量像素级标签样本的混合监督学习可获得与全监督学习相当的性能,模型的分类准确率达99.7%。

关键词: 表面缺陷检测, 深度学习, 注意力, 小样本, 粗糙标签

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

中图分类号:

TP391

赵晨阳, 张辉, 廖德, 李晨. 基于注意力机制与混合监督学习的钢轨表面缺陷检测模型[J]. 计算机科学, 2022, 49(11A): 210800241-6. https://doi.org/10.11896/jsjkx.210800241

ZHAO Chen-yang, ZHANG Hui, LIAO De, LI Chen. Rail Surface Defect Detection Model Based on Attention Module and Hybrid-supervised Learning[J]. Computer Science, 2022, 49(11A): 210800241-6. https://doi.org/10.11896/jsjkx.210800241

参考文献

[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.

相关文章 15

[1]	周芳泉, 成卫青. 基于全局增强图神经网络的序列推荐 Sequence Recommendation Based on Global Enhanced Graph Neural Network 计算机科学, 2022, 49(9): 55-63. https://doi.org/10.11896/jsjkx.210700085
[2]	戴禹, 许林峰. 基于文本行匹配的跨图文本阅读方法 Cross-image Text Reading Method Based on Text Line Matching 计算机科学, 2022, 49(9): 139-145. https://doi.org/10.11896/jsjkx.220600032
[3]	周乐员, 张剑华, 袁甜甜, 陈胜勇. 多层注意力机制融合的序列到序列中国连续手语识别和翻译 Sequence-to-Sequence Chinese Continuous Sign Language Recognition and Translation with Multi- layer Attention Mechanism Fusion 计算机科学, 2022, 49(9): 155-161. https://doi.org/10.11896/jsjkx.210800026
[4]	徐涌鑫, 赵俊峰, 王亚沙, 谢冰, 杨恺. 时序知识图谱表示学习 Temporal Knowledge Graph Representation Learning 计算机科学, 2022, 49(9): 162-171. https://doi.org/10.11896/jsjkx.220500204
[5]	熊丽琴, 曹雷, 赖俊, 陈希亮. 基于值分解的多智能体深度强化学习综述 Overview of Multi-agent Deep Reinforcement Learning Based on Value Factorization 计算机科学, 2022, 49(9): 172-182. https://doi.org/10.11896/jsjkx.210800112
[6]	饶志双, 贾真, 张凡, 李天瑞. 基于Key-Value关联记忆网络的知识图谱问答方法 Key-Value Relational Memory Networks for Question Answering over Knowledge Graph 计算机科学, 2022, 49(9): 202-207. https://doi.org/10.11896/jsjkx.220300277
[7]	吴子仪, 李邵梅, 姜梦函, 张建朋. 基于自注意力模型的本体对齐方法 Ontology Alignment Method Based on Self-attention 计算机科学, 2022, 49(9): 215-220. https://doi.org/10.11896/jsjkx.210700190
[8]	汤凌韬, 王迪, 张鲁飞, 刘盛云. 基于安全多方计算和差分隐私的联邦学习方案 Federated Learning Scheme Based on Secure Multi-party Computation and Differential Privacy 计算机科学, 2022, 49(9): 297-305. https://doi.org/10.11896/jsjkx.210800108
[9]	黎嵘繁, 钟婷, 吴劲, 周帆, 匡平. 基于时空注意力克里金的边坡形变数据插值方法 Spatio-Temporal Attention-based Kriging for Land Deformation Data Interpolation 计算机科学, 2022, 49(8): 33-39. https://doi.org/10.11896/jsjkx.210600161
[10]	汪鸣, 彭舰, 黄飞虎. 基于多时间尺度时空图网络的交通流量预测模型 Multi-time Scale Spatial-Temporal Graph Neural Network for Traffic Flow Prediction 计算机科学, 2022, 49(8): 40-48. https://doi.org/10.11896/jsjkx.220100188
[11]	方义秋, 张震坤, 葛君伟. 基于自注意力机制和迁移学习的跨领域推荐算法 Cross-domain Recommendation Algorithm Based on Self-attention Mechanism and Transfer Learning 计算机科学, 2022, 49(8): 70-77. https://doi.org/10.11896/jsjkx.210600011
[12]	朱承璋, 黄嘉儿, 肖亚龙, 王晗, 邹北骥. 基于注意力机制的医学影像深度哈希检索算法 Deep Hash Retrieval Algorithm for Medical Images Based on Attention Mechanism 计算机科学, 2022, 49(8): 113-119. https://doi.org/10.11896/jsjkx.210700153
[13]	魏恺轩, 付莹. 基于重参数化多尺度融合网络的高效极暗光原始图像降噪 Re-parameterized Multi-scale Fusion Network for Efficient Extreme Low-light Raw Denoising 计算机科学, 2022, 49(8): 120-126. https://doi.org/10.11896/jsjkx.220200179
[14]	刘冬梅, 徐洋, 吴泽彬, 刘倩, 宋斌, 韦志辉. 基于边框距离度量的增量目标检测方法 Incremental Object Detection Method Based on Border Distance Measurement 计算机科学, 2022, 49(8): 136-142. https://doi.org/10.11896/jsjkx.220100132
[15]	陈坤峰, 潘志松, 王家宝, 施蕾, 张锦. 基于双目叠加仿生的微换衣行人再识别 Moderate Clothes-Changing Person Re-identification Based on Bionics of Binocular Summation 计算机科学, 2022, 49(8): 165-171. https://doi.org/10.11896/jsjkx.210600140

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

基于注意力机制与混合监督学习的钢轨表面缺陷检测模型

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

PDF (PC)

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

Metrics

本文评价

推荐阅读 0