基于计算机视觉的钢结构损伤检测综述

刘逸康; 张铭煊; 余倩倩

doi:10.3724/j.gyjzG26033109

基于计算机视觉的钢结构损伤检测综述

doi: 10.3724/j.gyjzG26033109

刘逸康^1,2,
张铭煊^1,2,
余倩倩^1,3, ,

1. 同济大学建筑工程系, 上海 200092;
2. 同济大学工程结构性能演化与控制教育部重点实验室, 上海 200092;
3. 同济大学土木工程防灾减灾全国重点实验室, 上海 200092

基金项目:

国家自然科学基金项目（52578239，52222803）。

详细信息

作者简介:
刘逸康,硕士研究生,主要从事钢结构性能检测方向研究,2430876@tongji.edu.cn。

通讯作者:
余倩倩,博士,教授,主要从事结构性能演化与控制方向研究,qianqian.yu@tongji.edu.cn。

计量
- 文章访问数: 7
- HTML全文浏览量: 1
- PDF下载量: 0
- 被引次数: 0
出版历程
- 收稿日期: 2026-03-31
- 网络出版日期: 2026-06-06

A Review of Computer Vision-Based Damage Detection in Steel Structures

LIU Yikang^1,2,
ZHANG Mingxuan^1,2,
YU Qianqian^{1,3
, ,}

1. Department of Structural Engineering, Tongji University, Shanghai 200092, China;
2. Key Laboratory of Performance Evolution and Control for Engineering Structures, Tongji University, Shanghai 200092, China;
3. State Key Laboratory of Disaster Reduction in Civil Engineering, Tongji University, Shanghai 200092, China

摘要

摘要: 高效可靠的钢结构健康监测是保证结构安全、延长服役寿命的关键。当前，计算机视觉（Computer Vision， CV）技术因其非接触、效率高和自动化程度高等优势，正逐渐成为钢结构运维检测的重要技术手段。围绕钢结构表面裂纹与腐蚀损伤，系统梳理了计算机视觉技术在钢结构损伤检测中的研究进展，归纳了图像分类、目标检测和图像分割等主要方法，重点总结了现有研究在微小目标识别、复杂背景抑制、小样本训练及工程现场部署等方面的关键优化策略。现有研究表明，计算机视觉技术有效提升了钢结构损伤检测的自动化、智能化和精细化水平，但在数据集规范化、模型抗干扰能力、跨场景泛化能力和轻量化实时推理等方面仍有进一步发展空间。
- 钢结构 /
- 损伤检测 /
- 计算机视觉 /
- 深度学习
Abstract: Efficient and reliable structural health monitoring is essential for ensuring the safety and extending the service life of steel structures. Owing to the advantages of non-contact nature， high efficiency， and a high degree of automation， computer vision （CV） has gradually become an important technology for the inspection and maintenance of steel structures. Focusing on surface cracks and corrosion damage of steel structures， this review systematically summarizes the recent research progress in CV-based damage detection and outlines the major approaches， including image classification， object detection， and image segmentation. Particular attention is paid to key optimization strategies for small object detection， robustness under complex backgrounds， few-shot learning， and on-site deployment. Existing studies indicate that CV has significantly improved the automation， intelligence， and precision of damage detection for steel structures. However， further advances are still required in dataset standardization， model robustness to interference， generalization capability across scenarios， and lightweight real-time inference.
- steel structure /
- damage detection /
- computer vision /
- deep learning

HTML全文

参考文献(158)

[1]	袁宇峰. 我国钢结构产业发展现状及其用钢需求调查［J］. 冶金管理，2024（8）：10- 13.
[2]	中国建筑金属结构协会建筑钢结构行业可持续发展研究课题组. 中国建筑钢结构行业发展报告（2023—2024年度）［J］. 建筑，2025（7）：62- 68.
[3]	幸坤涛，赵晓青，郭小华，等. 工业建筑钢结构疲劳损伤检测、评估及加固关键技术研究［C］// 第十二届中国钢铁年会论文集. 北京：2019.
[4]	何润，周世康，张琦超，等. 桥梁钢结构的腐蚀与防护技术研究进展［J］. 钢铁研究学报，2025，37（5）：539- 556.
[5]	WU R K，ZHANG H，YANG R Z，et al. Nondestructive testing for corrosion evaluation of metal under coating［J］. Journal of Sensors，2021，2021（1）：1- 16.
[6]	VASAGAR V，HASSAN M K，ABDULLAH A M，et al. Non-destructive techniques for corrosion detection：a review［J］. Corrosion Engineering，Science and Technology，2024，59（1）：56- 85.
[7]	陈飞圻，薛江，逯鹏，等. 基于机器视觉的钢结构工程运维关键技术研究现状［J］. 工业建筑，2025，55（7）：131- 142.
[8]	朱洪洲，谭祺琦，范世平，等. 基于图像技术的沥青混合料细观结构研究进展［J］. 重庆交通大学学报（自然科学版），2021，40（10）：97- 110.
[9]	宋伟，左丹，邓邦飞，等. 高压输电线防震锤锈蚀缺陷检测［J］. 仪器仪表学报，2016，37（增刊1）：113- 117.
[10]	XU Y，LI H，LI S，et al. 3-D modelling and statistical properties of surface pits of corroded wire based on image processing technique［J］. Corrosion Science，2016，111：275- 287.
[11]	刘涛，艾军，张丽芳，等. 基于图像处理技术的钢箱梁防腐涂层寿命预测实验研究［J］. 中国腐蚀与防护学报，2013，33（5）：407- 412.
[12]	刘淼，薛建军，王玲，等. 基于数字图像分析的碳钢腐蚀等级评定方法［J］. 腐蚀与防护，2013，34（11）：997- 1000.
[13]	SHI T，KONG J Y，WANG X D，et al. Improved Sobel algorithm for defect detection of rail surfaces with enhanced efficiency and accuracy［J］. Journal of Central South University，2016，23（11）：2867- 2875．
[14]	姚志东，卢佳祁，熊梦雅，等. 基于计算机视觉的钢结构表面缺陷智能识别研究综述［J］. 建筑结构，2023，53（24）：126- 135.
[15]	逯鹏，赵天淞，王剑，等. 基于计算机视觉的钢结构表面损伤识别与健康监测综述［J］. 工业建筑，2022，52（10）：22- 27.
[16]	罗东亮，蔡雨萱，杨子豪，等. 工业缺陷检测深度学习方法综述［J］. 中国科学：信息科学，2022，52（6）：1002- 1039.
[17]	杨泽青，张明轩，陈英姝，等. 基于机器视觉的表面缺陷检测方法研究进展［J］. 现代制造工程，2023（4）：143- 156.
[18]	程锦锋，方贵盛，高惠芳. 表面缺陷检测的机器视觉技术研究进展［J］. 计算机应用研究，2023，40（4）：967- 977.
[19]	高艺平，王浩，李新宇，等. 基于深度智能视觉的表面缺陷检测研究进展［J］. 工业工程，2024，27（2）：27- 36.
[20]	邓志鹏，何施茗，杨根，等. 基于深度学习的纹理表面缺陷检测方法综述［J］. 计算机集成制造系统，2025，31（3）：721- 745.
[21]	AZIMI M，ESLAMLOU A D，PEKCAN G. Data-driven structural health monitoring and damage detection through deep learning：state-of-the-art review［J］. Sensors，2020，20（10）：2778.
[22]	刘颖，刘红燕，范九伦，等. 基于深度学习的小目标检测研究与应用综述［J］. 电子学报，2020，48（3）：590- 601.
[23]	ZHANG G，LIU Y，LIU J，et al. Causes and statistical characteristics of bridge failures:a review［J］. Journal of Traffic and Transportation Engineering（English Edition），2022，9（3）：388- 406.
[24]	IMAM B，CHRYSSANTHOPOULOS M K. A review of metallic bridge failure statistics［C］// Bridge Maintenance，Safety and Management：Proceedings of the Fifth International IABMAS Conference. Boca Raton：2010：3275- 3282.
[25]	HAMISHEBAHAR Y，GUAN H，SO S，et al. A comprehensive review of deep learning-based crack detection approaches［J］. Applied Sciences，2022，12（3）：1374.
[26]	YUAN Q，SHI Y，LI M. A review of computer vision-based crack detection methods in civil infrastructure：progress and challenges［J］. Remote Sensing，2024，16（16）：2910.
[27]	CUI C，ZHANG Q，ZHANG D，et al. Monitoring and detection of steel bridge diseases:a review［J］. Journal of Traffic and Transportation Engineering（English Edition），2024，11（2）：188- 208.
[28]	RIZHEVSKY A，SUTSKEVER I，HINTON G E. ImageNet classification with deep convolutional neural networks［C］// Proceedings of the 25th International Conference on Neural Information Processing Systems. New York：2012：1097- 1105.
[29]	SIMONYAN K，ZISSERMAN A. Very deep convolutional networks for large-scale image recognition［PP/OL］. V6. arXiv（2015-04-10）［2026-05-07］. https://doi.org/10.48550/arXiv.1409.1556.
[30]	SZEGEDY C，LIU W，JIA Y，et al. Going deeper with convolutions［C］// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Piscataway：2015：1- 9.
[31]	HE K，ZHANG X，REN S，et al. Deep residual learning for image recognition［C］// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Piscataway：2016：770- 778.
[32]	HUANG G，LIU Z，VAN DER MAATEN L，et al. Densely connected convolutional networks［C］// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Piscataway：2017：4700- 4708.
[33]	VANNOCCI M，RITACCO A，CASTELLANO A，et al. Flatness defect detection and classification in hot rolled steel strips using convolutional neural networks［C］// International Work-Conference on Artificial Neural Networks. Cham：Springer International Publishing，2019：220- 234.
[34]	XU Y，BAO Y，CHEN J，et al. Surface fatigue crack identification in steel box girder of bridges by a deep fusion convolutional neural network based on consumer-grade camera images［J］. Structural Health Monitoring，2019，18（3）：653- 674.
[35]	REN S，HE K，GIRSHICK R，et al. Faster R-CNN：towards real-time object detection with region proposal networks［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence，2017，39（6）：1137- 1149.
[36]	王海云，王剑平，罗富华. 融合多层次特征Faster R-CNN的金属板带材表面缺陷检测研究［J］. 机械科学与技术，2021，40（2）：262- 269.
[37]	戴学丰，陈慧，朱成军. 基于改进Faster R-CNN的金属工件表面缺陷检测及实现［J］. 表面技术，2020，49（10）：362- 371.
[38]	REDMON J，DIVVALA S，GIRSHICK R，et al. You only look once：unified，real-time object detection［C］// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Piscataway：2016：779- 788.
[39]	REDMON J，FARHADI A. YOLO9000：better，faster，stronger［C］// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Piscataway：2017：7263- 7271.
[40]	WANG C Y，BOCHKOVSKIY A，LIAO H Y M. YOLOv7：trainable bag-of-freebies sets new state-of-the-art for real-time object detectors［C］// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Vancouver：2023：7462- 7475.
[41]	CHA Y J，CHOI W，SUH G，et al. Autonomous structural visual inspection using region-based deep learning for detecting multiple damage types［J］. Computer-Aided Civil and Infrastructure Engineering，2018，33（9）：731- 747.
[42]	SUH G，CHA Y J. Deep Faster R-CNN-based automated detection and localization of multiple types of damage［C］// Sensors and Smart Structures Technologies for Civil，Mechanical，and Aerospace Systems 2018. Bellingham：2018，10598：197- 204.
[43]	LONG J，SHELHAMER E，DARRELL T. Fully convolutional networks for semantic segmentation［C］// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Piscataway：2015：3431- 3440.
[44]	RONNEBERGER O，FISCHER P，BROX T. U-Net：convolutional networks for biomedical image segmentation［C］// International Conference on Medical Image Computing and Computer-Assisted Intervention. Cham：2015：234- 241.
[45]	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）. Cham：2018：801- 818.
[46]	JIA X，WANG Y，WANG Z. Fatigue crack detection based on semantic segmentation using DeepLabV3+ for steel girder bridges［J］. Applied Sciences，2024，14（18）：8132.
[47]	PAN Y，ZHANG L. Dual attention deep learning network for automatic steel surface defect segmentation［J］. Computer‐Aided Civil and Infrastructure Engineering，2022，37（11）：1468- 1487.
[48]	LIU Y，YAO J，LU X，et al. DeepCrack：a deep hierarchical feature learning architecture for crack segmentation［J］. Neurocomputing，2019，338：139- 153.
[49]	DONG C，LI L，YAN J，et al. Pixel-level fatigue crack segmentation in large-scale images of steel structures using an encoder-decoder network［J］. Sensors，2021，21（12）：4135.
[50]	ZHANG C，WAN L，WAN R Q，et al. Automated fatigue crack detection in steel box girder of bridges based on ensemble deep neural network［J］. Measurement，2022，202：111805.
[51]	KOMPANETS A，DUITS R，PAI G，et al. Loss function inversion for improved crack segmentation in steel bridges using a CNN framework［J］. Automation in Construction，2025，170：105896.
[52]	舒江鹏，李俊，马亥波，等. 基于特征金字塔网络的超大尺寸图像裂纹识别检测方法［J］. 土木与环境工程学报（中英文），2022，44（3）：29- 36.
[53]	LIN T Y，DOLLÁR P，GIRSHICK R，et al. Feature pyramid networks for object detection［C］// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2017：2117- 2125.
[54]	ZHAO W，CHEN F，HUANG H，et al. A new steel defect detection algorithm based on deep learning［J］. Computational Intelligence and Neuroscience，2021，2021（1）：5592878.
[55]	LI G，LI X，ZHOU J，et al. Pixel-level bridge crack detection using a deep fusion about recurrent residual convolution and context encoder network［J］. Measurement，2021，176：109171.
[56]	QUQA S，MARTAKIS P，MOVSESSIAN A，et al. Two-step approach for fatigue crack detection in steel bridges using convolutional neural networks［J］. Journal of Civil Structural Health Monitoring，2022，12（1）：127- 140.
[57]	TONG T，LIN J，HUA J，et al. Crack identification for bridge condition monitoring using deep convolutional networks trained with a feedback-update strategy［J］. Maintenance，Reliability and Condition Monitoring，2021，1（2）：37- 51.
[58]	MENG S Q，GAO Z Y，ZHOU Y，et al. A three-stage deep-learning-based method for crack detection of high-resolution steel box girder image［J］. Smart Structures and Systems，2022，29（1）：29- 39.
[59]	ZHAI G H，NARAZAKI Y，WANG S，et al. Synthetic data augmentation for pixel-wise steel fatigue crack identification using fully convolutional networks［J］. Smart Structures and Systems，2022，29（1）：237- 250.
[60]	TA Q B，DANG N L，KIM Y C，et al. Semantic crack-image identification framework for steel structures using atrous convolution-based Deeplabv3+ Network［J］. Smart Structures and Systems，2022，30（1）：17- 34.
[61]	邓露，香超，王维，等. 基于改进编解码网络的钢箱梁疲劳裂纹分割［J］. 华中科技大学学报（自然科学版），2022，50（8）：66- 72.
[62]	朱劲松，李欢，王世芳. 基于卷积神经网络和迁移学习的钢桥病害识别［J］. 长安大学学报（自然科学版），2021，41（3）：52- 63.
[63]	DUNG C V，SEKIYA H，HIRANO S，et al. A vision-based method for crack detection in gusset plate welded joints of steel bridges using deep convolutional neural networks［J］. Automation in Construction，2019，102：217- 229.
[64]	YU Q Q，WANG J，GU X L，et al. An attention-based detection method of fatigue cracks on steel［J］. Structural Control and Health Monitoring，2025，2025（1）：7487687.
[65]	DAI A，CHANG A X，SAVVA M，et al. Scannet：Richly-annotated 3d reconstructions of indoor scenes［C］// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Piscataway：2017：5828- 5839.
[66]	HAN Q H，LIU X，XU J. Detection and location of steel structure surface cracks based on unmanned aerial vehicle images［J］. Journal of Building Engineering，2022，50：104098.
[67]	MENG S，GAO Z，ZHOU Y，et al. Real‐time automatic crack detection method based on drone［J］. Computer‐Aided Civil and Infrastructure Engineering，2023，38（7）：849- 872.
[68]	IANDOLA F N，HAN S，MOSKEWICZ M W，et al. SqueezeNet：alexNet-level accuracy with 50x fewer parameters and<0.5 MB model size［PP/OL］. V4. arXiv（2016-11-04）［2026-05-07］. https://doi.org/10.48550/arXiv.1602.07360.
[69]	HOWARD A G，ZHU M，CHEN B，et al. MobileNets:efficient convolutional neural networks for mobile vision applications［PP/OL］. V1. ArXiv（2017-04-17）［2026-05-07］. https://doi.org/10.48550/arXiv.1704.04861.
[70]	ZHANG X，ZHOU X，LIN M，et al. ShuffleNet：an extremely efficient convolutional neural network for mobile devices［C］// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Long Beach：2018：6848- 6856.
[71]	TAN M，LE Q V. EfficientNet：rethinking model scaling for convolutional neural networks［C］// Proceedings of the 36th International Conference on Machine Learning. 2019：6105- 6114.
[72]	WANG Y，WANG H，XIN Z. Efficient detection model of steel strip surface defects based on YOLO-V7［J］. IEEE Access，2022，10：133936- 133944.
[73]	LU N，WANG K，WANG H，et al. Real-time fatigue crack detection and prediction in steel structures based on an automated digital twin-driven framework［J］. Thin-Walled Structures，2025，218：114099.
[74]	GUO Z，ZHANG Y，ZHU Q. CSCP-YOLO：a lightweight and efficient algorithm for real-time steel surface defect detection［J］. Advanced Engineering Informatics，2022，54：101741.
[75]	LIU R，ZENG W. Automatic detection of structural defects in tunnel lining via network pruning and knowledge distillation in YOLO［J］. Structural Health Monitoring，2026，25（2）：1165- 1181.
[76]	HUANG H，CAI Y，ZHANG C，et al. Crack detection of masonry structure based on thermal and visible image fusion and semantic segmentation［J］. Automation in Construction，2024，158：105213.
[77]	ALEXANDER Q G，HOSKERE V，NARAZAKI Y，et al. Fusion of thermal and RGB images for automated deep learning based crack detection in civil infrastructure［J］. AI in Civil Engineering，2022，1（1）：3.
[78]	WANG P，XIAO J，QIANG X，et al. An automatic building facade deterioration detection system using infrared-visible image fusion and deep learning［J］. Journal of Building Engineering，2024，95：110122.
[79]	ZHOU S，SONG W. Deep learning-based roadway crack classification with heterogeneous image data fusion［J］. Structural Health Monitoring，2021，20（3）：1274- 1293.
[80]	PARK S E，EEM S H，JEON H. Concrete crack detection and quantification using deep learning and structured light［J］. Construction and Building Materials，2020，252：119096.
[81]	WANG S，ZHAO X，GAO L，et al. Pixel-level crack segmentation and quantification enabled by multi-modality cross-fusion of RGB and depth images［J］. Automation in Construction，2024，160：105318.
[82]	XU W，CUI C，LUO C，et al. Fatigue crack monitoring of steel bridge with coating sensor based on potential difference method［J］. Construction and Building Materials，2022，350：128868.
[83]	MANU K C，MADHUSHREE C，CHANDINI M S，et al. Corrosion in steel structures:a review［J］. Journal of Mines，Metals and Fuels，2025，73（1）：189- 198.
[84]	ANWAR S，LI C. Diving deeper into underwater image enhancement：a survey［J］. Signal Processing：Image Communication，2020，89：115978.
[85]	DUY L D，ANH N T，SON N T，et al. Deep learning in semantic segmentation of rust in images［C］// Proceedings of the 2020 9th International Conference on Software and Computer Applications. Malaysia：2020：262- 266.
[86]	DAS A，DORAFSHAN S，KAABOUCH N. Autonomous image-based corrosion detection in steel structures using deep learning［J］. Sensors，2024，24（11）：3630.
[87]	中国国家标准化管理委员会. 金属基体上金属和其他无机覆盖层经腐蚀试验后的试样和试件的评级：GB/T 6461—2002［S］. 北京：中国标准出版社，2002.
[88]	ASTM International. Standard test method for evaluating degree of rusting on painted steel surfaces:ASTM D610-23［S］. West Conshohocken，PA：ASTM International，2023.
[89]	International Organization for Standardization. Paints and varnishes-evaluation of degradation of coatings-part 3：assessment of degree of rusting：ISO 4628-3 ∶2016［S］. Geneva，Switzerland：ISO，2016.
[90]	陆廷杰，刘东海，齐志龙. 基于深度学习的水下钢结构锈蚀识别与评价［J］. 天津大学学报（自然科学与工程技术版），2023，56（7）：713- 722.
[91]	PETRICCA L，MOSS T，FIGUEROA G，et al. Corrosion detection using AI：a comparison of standard computer vision techniques and deep learning model［C］// Proceedings of the Sixth International Conference on Computer Science，Engineering and Information Technology. Chennai：2016：91- 99.
[92]	ATHA D J，JAHANSHAHI M R. Evaluation of deep learning approaches based on convolutional neural networks for corrosion detection［J］. Structural Health Monitoring，2018，17（5）：1110- 1128.
[93]	HOLM E，TRANSETH A A，KNUDSEN O Ø，et al. Classification of corrosion and coating damages on bridge constructions from images using convolutional neural networks［C］// Twelfth International Conference on Machine Vision（ICMV 2019）. Bellingham：2020：549- 556.
[94]	BASTIAN B T，JASPREETH N，RANJITH S K，et al. Visual inspection and characterization of external corrosion in pipelines using deep neural network［J］. NDT & E International，2019，107：102134.
[95]	FORKAN A R M，KANG Y B，JAYARAMAN P P，et al. CorrDetector：a framework for structural corrosion detection from drone images using ensemble deep learning［J］. Expert Systems with Applications，2022，193：116461.
[96]	XU J，GUI C，HAN Q. Recognition of rust grade and rust ratio of steel structures based on ensembled convolutional neural network［J］. Computer-Aided Civil and Infrastructure Engineering，2020，35（10）：1160- 1174.
[97]	JIN LIM H，HWANG S，KIM H，et al. Steel bridge corrosion inspection with combined vision and thermographic images［J］. Structural Health Monitoring，2021，20（6）：3424- 3435.
[98]	ANDERSEN R，NALPANTIDIS L，RAVN O，et al. Investigating deep learning architectures towards autonomous inspection for marine classification［C］// 2020 IEEE International Symposium on Safety，Security，and Rescue Robotics（SSRR）. Abu Dhabi：2020：197- 204.
[99]	ZHOU Q，DING S，FENG Y，et al. Corrosion inspection and evaluation of crane metal structure based on UAV vision［J］. Signal，Image and Video Processing，2022，16（6）：1701- 1709.
[100]	JIA Z，FU M，ZHAO X，et al. Intelligent identification of metal corrosion based on Corrosion-YOLOv5s［J］. Displays，2023，76：102367.
[101]	NABIZADEH E，PARGHI A. Automated corrosion detection using deep learning and computer vision［J］. Asian Journal of Civil Engineering，2023，24（8）：2911- 2923.
[102]	AMELI Z，NESHELI S J，LANDIS E N. Deep learning-based steel bridge corrosion segmentation and condition rating using mask RCNN and YOLOv8［J］. Infrastructures，2023，9（1）：1- 16.
[103]	YU Q F，HAN Y D，LIN W G，et al. Detection and analysis of corrosion on coated metal surfaces using enhanced YOLOv5 algorithm for anti-corrosion performance evaluation［J］. Journal of Marine Science and Engineering，2024，12（7）：1090.
[104]	PIRIE C，MORENO-GARCIA C F. Image pre-processing and segmentation for real-time subsea corrosion inspection［C］// International Conference on Engineering Applications of Neural Networks. Cham：2021：220- 231.
[105]	王达磊，彭博，潘玥，等. 基于深度神经网络的锈蚀图像分割与定量分析［J］. 华南理工大学学报（自然科学版），2018，46（12）：121- 127.
[106]	FONDEVIK S K，STAHL A，TRANSETH A A，et al. Image segmentation of corrosion damages in industrial inspections［C］// 2020 IEEE 32nd International Conference on Tools with Artificial Intelligence（ICTAI）. Baltimore：2020：787- 792.
[107]	KATSAMENIS I，PROTOPAPADAKIS E，DOULAMIS A，et al. Pixel-level corrosion detection on metal constructions by fusion of deep learning semantic and contour segmentation［C］// International Symposium on Visual Computing. Cham：2020：160- 169.
[108]	AKHLAGHI B，MESGHALI H，EHTESHAMI M，et al. Predictive deep learning for pitting corrosion modeling in buried transmission pipelines［J］. Process Safety and Environmental Protection，2023，174：320- 327.
[109]	GAO R P，SHANG W J，ZHAO Y，et al. Research on fusion model method for corrosion damage detection of switch sliding baseplate［J］. Coatings，2024，14（12）：1552.
[110]	ZHANG Z W，LI S L，WANG H J，et al. A study of neural network-based evaluation methods for pipelines with multiple corrosive regions［J］. Reliability Engineering & System Safety，2025，253：110507.
[111]	秦荣杰．基于深度学习Transformer网络的钢板锈蚀类别识别方法研究［D］．西安：西安建筑科技大学，2023.
[112]	ALTABEY W A，NOORI M，WANG T，et al. Deep learning-based crack identification for steel pipelines by extracting features from 3D shadow modeling［J］. Applied Sciences，2021，11（13）：6063.
[113]	WANG B Q，LIU L A，CHENG X Q，et al. Advanced multi-image segmentation-based machine learning modeling strategy for corrosion prediction and rust layer performance evaluation of weathering steel［J］. Corrosion Science，2024，237：112334.
[114]	LI Y P，LI H G，GUAN Y，et al. Dense metal corrosion depth estimation［J］. Frontiers in Physics，2023，11：1277710.
[115]	SON E Y，JEONG D，OH M J. Corrosion area detection and depth prediction using machine learning［J］. International Journal of Naval Architecture and Ocean Engineering，2024，16：100617.
[116]	ARIAS F，GUEVARA E，JARAMILLO E，et al. Automated assessment of marine steel corrosion using visible-near-infrared hyperspectral imaging［J］. Coatings，2025，15（6）：645.
[117]	EGODAWELA S，GOSTAR A K，BUDDIKA H A D S，et al. Metal loss defect detection and depth estimation using multi-spectral image analysis of cooling excited steel specimen with corrosion［J］. Scientific Reports，2025，15（1）：23894.
[118]	LIU L，TAN E，ZHEN Y，et al. AI-facilitated coating corrosion assessment system for productivity enhancement［C］// 2018 13th IEEE Conference on Industrial Electronics and Applications（ICIEA）. Wuhan：2018：606- 610.
[119]	YAO Y，YANG Y，WANG Y，et al. Artificial intelligence-based hull structural plate corrosion damage detection and recognition using convolutional neural network［J］. Applied Ocean Research，2019，90：101823.
[120]	LUO C，YU L，YAN J，et al. Autonomous detection of damage to multiple steel surfaces from 360 panoramas using deep neural networks［J］. Computer‐Aided Civil and Infrastructure Engineering，2021，36（12）：1585- 1599.
[121]	YU L J，YANG E F，LUO C，et al. AMCD：an accurate deep learning-based metallic corrosion detector for MAV-based real-time visual inspection［J］. Journal of Ambient Intelligence and Humanized Computing，2023，14：8087- 8098.
[122]	HUANG M，ZHANG J，LI J，et al. Damage identification of steel bridge based on data augmentation and adaptive optimization neural network［J］. Structural Health Monitoring，2024，24：1674- 1699.
[123]	BIANCHI E，HEBDON M. Visual structural inspection datasets［J］. Automation in Construction，2022，139：104299.
[124]	梁俊杰，韦舰晶，蒋正锋. 生成对抗网络GAN综述［J］. 计算机科学与探索，2020，14（1）：1- 17.
[125]	RADFORD A，METZ L，CHINTALA S. Unsupervised representation learning with deep convolutional generative adversarial networks［PP/OL］. V2. arXiv（2016-01-07）［2026-05-07］. https://doi.org/10.48550/arXiv.1511.06434.
[126]	GULRAJANI I，AHMED F，ARJOVSKY M，et al. Improved training of Wasserstein GANs［C］// Neural Information Processing Systems. Long Beach：2017：5769- 5779.
[127]	LEI X，SUN L，XIA Y. Lost data reconstruction for structural health monitoring using deep convolutional generative adversarial networks［J］. Structural Health Monitoring，2022，20（4）：2069- 2087.
[128]	GAO Y，KONG B，MOSALAM K M. Deep leaf-bootstrapping generative adversarial network for structural image data augmentation［J］. Computer-Aided Civil and Infrastructure Engineering，2019，34（9）：755- 773.
[129]	MAEDA H，KASHIYAMA T，SEKIMOTO Y，et al. Generative adversarial network for road damage detection［J］. Computer-Aided Civil and Infrastructure Engineering，2021，36（1）：47- 60.
[130]	XU Y Z，WU H，LIU Y L，et al. Automated surface defect detection based on CycleGAN model［C］// Journal of Physics:Conference Series. Bristol：2024，2890：012036.
[131]	WANG Y，LIAO X，CUI W，et al. Defending against and generating adversarial examples together with generative adversarial networks［J］. Scientific Reports，2025，15（1）：12994.
[132]	ZHOU H Y，JIANG F，LU H T，et al. SSDA-YOLO：semi-supervised domain adaptive YOLO for cross-domain object detection［J］. Computer Vision and Image Understanding，2023，229：103649.
[133]	牟宗涵. 基于无人机图像的铁路桥梁钢结构表面缺陷智能识别方法研究［D］. 北京：北京交通大学，2023.
[134]	钱企豪，郑战光，梁钊，等. 基于颜色特征的半监督聚类算法在铜片腐蚀等级识别中的应用［J］. 腐蚀与防护，2023，44（5）：34- 40.
[135]	FENG J J，TIAN L F，LI X X，et al. Adaptive adversarial self-training for semi-supervised object detection in complex maritime scenes［J］. Mathematics，2024，12（15）：2348.
[136]	WANG S Y，NGUYEN H D，WILSON R，et al. Deep CNN-based semi-supervised learning approach for identifying and segmenting corrosion in hydraulic steel and water resources infrastructure［J］. Structural Health Monitoring，2025，24：2229- 2249.
[137]	GUO M H，XU T X，LIU J J，et al. Attention mechanisms in computer vision：a survey［J］. Computational Visual Media，2022，8（3）：331- 368.
[138]	DUAN Z，HUANG X H，HOU J，et al. Research on intelligent diagnosis of corrosion in the operation and maintenance stage of steel structure engineering based on U-Net attention［J］. Buildings，2024，14（12）：3972.
[139]	KATSAMENIS I，DOULAMIS N，DOULAMIS A，et al. Simultaneous precise localization and classification of metal rust defects for robotic-driven maintenance and prefabrication using residual attention U-Net［J］. Automation in Construction，2022，137：104182.
[140]	MA S B，ZHAO X，WAN L，et al. A lightweight algorithm for steel surface defect detection using improved YOLOv8［J］. Scientific Reports，2025，15：93469.
[141]	FU M J，JIA Z T，WU L Z，et al. Detection and recognition of metal surface corrosion based on CBG-YOLOv5s［J］. PloS One，San Francisco，2024，19（4）：1932- 6203.
[142]	ZHANG G H，LIU S X，NIE S Q，et al. YOLO-RDP：lightweight steel defect detection through improved YOLOv7-tiny and model pruning［J］. Symmetry，2024，16（4）：1- 12.
[143]	TAN L，CHEN X H，YUAN D J，et al. DSNet：a Computer vision-based detection and corrosion segmentation network for corroded bolt detection in tunnel［J］. Structural Control and Health Monitoring，2024，2024（1）：1- 16.
[144]	YU V F，SANTIYUDA G，LIN S W，et al. Neural network pruning for lightweight metal corrosion image segmentation models［J］. IEEE Access，2025，13：71673- 71687.
[145]	HAN Q H，ZHAO N，XU J. Recognition and location of steel structure surface corrosion based on unmanned aerial vehicle images［J］. Journal of Civil Structural Health Monitoring，2021，11（5）：1375- 1392.
[146]	ELTOUNY K，SAJEDI S，LIANG X. Dmg2Former-AR：vision transformers with adaptive rescaling for high-resolution structural visual inspection［J］. Sensors，2024，24（18）：6007.
[147]	YE X W，JIN T，LI Z X，et al. Structural crack detection from benchmark data sets using pruned fully convolutional networks［J］. Journal of Structural Engineering，2021，147（11）：04721008.
[148]	BIANCHI E，HEBDON M. Corrosion condition state semantic segmentation dataset［DS］. Blacksburg，VA，USA：Virginia Tech，2021.
[149]	HOSKERE V，NARAZAKI Y，HOANG T A，et al. MaDnet：multi-task semantic segmentation of multiple types of structural materials and damage in images of civil infrastructure［J］. Journal of Civil Structural Health Monitoring，2020，10（5）：757- 773.
[150]	DONG H，SONG K，HE J，et al. PGA-Net：pyramid feature fusion and global context attention network for automated surface defect detection［J］. IEEE Transactions on Industrial Informatics，2020，16（12）：7448- 7458.
[151]	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.
[152]	SONG K C，HU S P，YAN Y H，et al. Surface defect detection method using saliency linear scanning morphology for silicon steel strip under oil pollution interference［J］. ISIJ International，2014，54（11）：2598- 2607.
[153]	SONG K，YAN Y H. Micro surface defect detection method for silicon steel strip based on saliency convex active contour model，mathematical problems in engineering［J］. Mathematical Problems in Engineering，2013（1）：429094.
[154]	ZHANG S，ZHANG Q，GU J，et al. Visual inspection of steel surface defects based on domain adaptation and adaptive convolutional neural network［J］. Mechanical Systems and Signal Processing，2021，153：107541.
[155]	HU X，YANG J，JIANG F，et al. Steel surface defect detection based on self-supervised contrastive representation learning with matching metric［J］. Applied Soft Computing，2023，145：110578.
[156]	YANG X CA 1，FAN Y L，BAO Y Q，et al. Task-aware meta-learning paradigm for universal structural damage segmentation using limited images［J］. Engineering Structures，2023，284：115917.
[157]	LI Y，CHEN Z，ZHA D，et al. Automated anomaly detection via curiosity-guided search and self-imitation learning［J］. IEEE Transactions on Neural Networks and Learning Systems，2022，33（6）：2365- 2377.
[158]	RIPPEL O，MERTENS P，MERHOF D. Modeling the distribution of normal data in pre-trained deep features for anomaly detection［C］// 2020 25th International Conference on Pattern Recognition（ICPR）. Milan：2021：6726- 6733.