基于深度学习的混凝土缺陷检测方法综述

doi:10.11896/jsjkx.240900137

摘要/Abstract

摘要： 基于深度学习的混凝土缺陷检测通过提供结构状况的初始评估,可有效降低基础设施运营风险以及节约维护成本。文中归纳了近年来混凝土缺陷检测技术的研究进展,对相关研究的已有成果进行分析,讨论对比了各类检测方法的差异及优缺点。对可用于混凝土缺陷检测的图像数据集进行了梳理与介绍,再从实际应用出发,对混凝土缺陷检测中可能会存在的问题进行梳理,阐述与分析了能解决相应检测问题的相关研究。最后,针对该研究后续可能的发展方向进行展望。

关键词: 深度学习, 混凝土缺陷, 卷积神经网络, 目标检测, 语义分割, 实例分割

Abstract: Concrete defect detection based on deep learning can effectively reduce infrastructure operation risks and save maintenance costs by providing an initial assessment of structural conditions.This paper analyzes the research progress of concrete defect detection technologies in recent years,analyzes the existing achievements of related researches,and discusses and compares the differences,advantages and disadvantages of various detection methods.The image datasets that can be used for concrete defect detection are sorted out and introduced.Then,starting from the practical application,the possible problems in concrete defect detection are sorted out,and the related research that can solve the corresponding detection problems is expounded and analyzed.Finally,the possible future development directions of the research are prospected.

Key words: Deep learning, Concrete defect, Convolutional neural network, Target detection, Semantic segmentation, Instance segmentation

中图分类号:

TP391

王嘉敏, 武文红, 牛恒茂, 石宝, 乌尼尔, 郝旭, 张超, 付荣升. 基于深度学习的混凝土缺陷检测方法综述[J]. 计算机科学, 2025, 52(6A): 240900137-12. https://doi.org/10.11896/jsjkx.240900137

WANG Jiamin, WU Wenhong, NIU Hengmao, SHI Bao, WU Nier, HAO Xu, ZHANG Chao, FU Rongsheng. Review of Concrete Defect Detection Methods Based on Deep Learning[J]. Computer Science, 2025, 52(6A): 240900137-12. https://doi.org/10.11896/jsjkx.240900137

参考文献

[1]CHEN G.An investigation on the application of health monitoring technology for highway bridges[J].China Highway,2020(9):100-101.
[2]MOHAN A,POOBAL S.Crack detection using image processing:A critical review and analysis[J].Alexandria Engineering Journal,2018,57(2):787-798.
[3]HAN Y,SUN H,LI L,et al.Design and implementation of arapid inspection system for building exterior wall cracks based on drones [J].Courseof Civil Engineering and Management,2019,36(3):60-65.
[4]DU Q C,ZHONG W,ZHENG P Y.Crack detection technology of track beam based on digital image processing [J].Sichuan Architecture,2019,39(4):95-97.
[5]NI T Y,ZHANG W Y,YANG Y,et al.Research progress on bridge concrete crack detection basedon image processing [J].Urban Road and Bridge and Flood Control,2019(7):258-263,29-30.
[6]PAN X,YANG T Y.Postdisaster image-based damage detection and repair cost estimation of reinforced concrete buildings using dual convolutionalneural networks[J].Computer-Aided Civil and Infrastructure Engineering,2020,35(5):495-510.
[7]DUNG C V.Autonomous concrete crack detection using deepfully convolutional neural network[J].Automation in Construction,2019,99:52-58.
[8]ZHU L,LI D B,YAN X Z,et al.Intelligent detection method of tunnel cracks based on improvedMask R-CNN deep learning algorithm [J].Journal of Graphics,2023,44(1):177-183.
[9]GAI R L,CAI J R,WANG S Y,et al.An overview of the application of convolutional neuralnetworks in image recognition [J].Microcomputer System,2021,42(9):1980-1984.
[10]YANG S,XU Q F,WANGZ L.Research progress on structural damage identification based on convolutional neural networks [J].Journal ofBuilding Science and Engineering,2022,39(4):38-57.
[11]JIANG S H,JIANG X H.Review of concrete defect detectionbased on computer vision [J].Information Technology of Civil Engineering,2023,15(4):14-21.
[12]ZHOU Y,MENG S Q,KONG Q Z,et al.A review of research on intelligent detection of damageand intelligent prediction of response in building structures[J].Journal of Building Structures,2024,45(6):107-132.
[13]LECUN Y,BOTTOU L,BENGIO Y,et al.Gradient-basedlearning applied to document recognition[J].Proceedings of the IEEE,1998,86(11):2278-2324.
[14]KRIZHEVSKY A,SUTSKEVER I,HINTON G E.ImageNet classification with deep convolutional neural networks[J].Communications of the ACM,2017,60(6):84-90.
[15]SIMONYAN K,ZISSERMANA.Very deep convolutional net-works for large-scale image recognition[J].arXiv:1409.1556,2014.
[16]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.2016:770-778.
[17]SZEGEDY C,LIU W,JIA Y,et al.Going deeper with convolutions[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2015:1-9.
[18]HUANG G,LIU Z,VAN DER MAATEN L,et al.Densely connected convolutional networks[C]//Proceedings of the IEEE Conference on Computer Visionand Pattern Recognition.2017:4700-4708.
[19]IANDOLA F N,HAN S,MOSKEWICZ M W,et al.SqueezeNet:AlexNet-level accuracy with 50x fewer parameters and< 0.5 MB model size[J].arXiv:1602.07360,2016.
[20]HOWARD A G,ZHU M,CHEN B,et al.Mobilenets:Efficient convolutional neural networks for mobile vision applications[J].arXiv:1704.04861,2017.
[21]TAN M,LE Q.Efficientnet:Rethinking model scaling for convolutional neural networks[C]//International Conference on Machine Learning.PMLR,2019:6105-6114.
[22]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.2018:6848-6856.
[23]XU Y,ZHANG T R,JIN G.Corrosion crack identification of reinforced concrete based on deep learning SCNet [J].Journal of Hunan University(Natural Science Edition),2022,49(3):101-110.
[24]HUANG C P,GAN S K,TAN J J,et al.Intelligent classifier of concrete apparent disease based on deep learning [ J ].Journal of Huazhong University of Science and Technology(Natural Science Edition),2021,49(4):96-101,113.
[25]CHEN R.Migration learning-based bridge structure damage detection algorithm[J].Scientific Programming,2021,2021:1-10.
[26]CHEN L,CHEN W,WANG L,et al.Convolutional neural networks(CNNs)-based multi-category damage detection and recognition of high-speed rail(HSR) reinforced concrete(RC) bridges using test images[J].Engineering Structures,2023,276:115306.
[27]ZHANG Z H,LU J G.Crack detection of concrete bridges based on improved convolutional neural networks [J].Computer Simu-lation,2021,38(11):490-494.
[28]ZOUBIR H,RGUIG M,EL AROUSSI M,et al.Concrete bridge defects identification and localization based on classification deep convolutionalneural networks and transfer learning[J].Remote Sensing,2022,14(19):4882.
[29]CAI T C,LIU C,ZHOU X T,et al.UAV-based building facade crack detection [J].Engineering Survey,2022,50(4):45-51.
[30]AKGÜL İ.Mobile-DenseNet:Detection of building concretesurface cracks using a new fusion technique based on deep lear-ning[J].Heliyon,2023,9(10).
[31]PALEVIČIUS P,PAL M,LANDAUSKAS M,et al.Automatic detection of cracks on concrete surfaces in the presence of shadows[J].Sensors,2022,22(10):3662.
[32]GIRSHICK R,DONAHUE J,DARRELL T,et al.Rich feature hierarchies for accurate object detection and semantic segmentation[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2014:580-587.
[33]HE K,ZHANG X,REN S,et al.Spatial pyramid pooling in deep convolutional networks for visual recognition[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2015,37(9):1904-1916.
[34]GIRSHICK R.Fast r-cnn[C]//Proceedings of the IEEE International Conference on Computer Vision.2015:1440-1448.
[35]REN S,HE K,GIRSHICK R,et al.Faster R-CNN:Towardsreal-time object detection with region proposal networks[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2016,39(6):1137-1149.
[36]REDMON J,DIVVALA S,GIRSHICK R,et al.You only lookonce:Unified,real-time object detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2016:779-788.
[37]REDMON J,FARHADI A.YOLO9000:better,faster,stronger[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2017:7263-7271.
[38]REDMON J,FARHADI A.Yolov3:An incremental improve-ment[J].arXiv:1804.02767,2018.
[39]BOCHKOVSKIY A,WANG C Y,LIAO H Y M.Yolov4:Optimal speed and accuracy of object detection[J].arXiv:2004.10934,2020.
[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.2023:7464-7475.
[41]LIU W,ANGUELOV D,ERHAN D,et al.Ssd:Single shotmultibox detector[C]//Computer Vision-ECCV 2016:14th European Conference,Amsterdam,The Netherlands,October 11-14,2016,Proceedings,Part I 14.Springer International Publishing,2016:21-37.
[42]KUMAR S S,WANG M,ABRAHAM D M,et al.Deep learning-based automated detection of sewer defects in CCTV videos[J].Journal of Computing in Civil Engineering,2020,34(1):04019047.
[43]CUI X N,WANG Q C,LI S,et al.Intelligent identification of double-block sleeper cracks based on YOLO-v5 [J].Railway Journal,2022,44(4):104-111.
[44]ZHU Z W,ZHU D B,ZHU T.Intelligent detection of highway bridge cracks based on drones and deep learning [J].China Water Transport(Second Half Month),2024,24(2):122-124.
[45]WU H H,WANG A H,WANG H D.Tunnel image crack detection based on Faster R-CNN [J].Journal of Taiyuan University of Science and Technology,2019,40(3):165-168.
[46]LI C,XU P,NIU L,et al.Tunnel crack detection using coarse-to-fine region localization and edge detection[J].Wiley Interdisciplinary Reviews:Data Mining and Knowledge Discovery,2019,9(5):e1308.
[47]KIM B,NATARAJAN Y,PREETHAA K R S,et al.Real-time assessment of surface cracks in concrete structures using integrated deep neural networks with autonomous unmanned aerial vehicle[J].Engineering Applications of Artificial Intelligence,2024,129:107537.
[48]HUANG B,KANG F,TANG Y.Real-time detection method of concrete dam cracks based on target detection [J].Journal of Tsinghua University(Natural Science Edition),2023,63(7):1078-1086.
[49]ZOU D,ZHANG M,BAI Z,et al.Multicategory damage detection and safety assessment of post-earthquake reinforced concrete structures using deep learning[J].Computer-Aided Civil and Infrastructure Engineering,2022,37(9):1188-1204.
[50]XU G,YUE Q,LIU X.Real-time monitoring of concrete crack based on deep learning algorithms and image processing techniques[J].Advanced Engineering Informatics,2023,58:102214.
[51]LONG J,SHELHAMER E,DARRELL T.Fully convolutional networks for semantic segmentation[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2015:3431-3440.
[52]BADRINARAYANAN V,KENDALL A,CIPOLLA R.Segnet:A deep convolutional encoder-decoder architecture for image segmentation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2017,39(12):2481-2495.
[53]RONNEBERGER O,FISCHER P,BROX T.U-net:Convolu-tional networks for biomedical image segmentation[C]//Medical Image Computing and Computer-assisted Intervention-MICCAI 2015:18th international conference,Munich,Germany,October 5-9,2015,proceedings,part III 18.Springer International Publishing,2015:234-241.
[54]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.
[55]HE K,GKIOXARI G,DOLLÁR P,et al.Mask r-cnn[C]//Proceedings of the IEEE International Conference on Computer Vision.2017:2961-2969.
[56]LI S,ZHAO X,ZHOU G.Automatic pixel-level multiple damage detection of concrete structure using fully convolutional network[J].Computer-Aided Civil and Infrastructure Engineering,2019,34(7):616-634.
[57]ZHANG H L,LI D H,DING Y.Research on cascaded neural network algorithm for concretecrack detection [J].Journal of Hydroelectric Power,2022,41(8):134-143.
[58]DENG L,SUN T,YANG L,et al.Binocular video-based 3D reconstruction and length quantification of cracks in concrete structures[J].Automation in Construction,2023,148:104743.
[59]SUI H G,HUANG L H,LIU C X.Using the attention-grabbing Mask R-CNN to detect facade damage of earthquake-damaged buildings [J].Journal of Wuhan University(Information Science Edition),2020,45(11):1660-1668.
[60]WOO S,PARK J,LEEJ Y,et al.Cbam:Convolutional block attention module[C]//Proceedings of the European Conference on Computer Vision(ECCV).2018:3-19.
[61]MENG Q C,LI M J,WAN D,et al.Real-time segmentation algorithm for concrete cracks basedon M-Unet [J].Journal of Civil and Environmental Engineering,2024,46(1):215-222.
[62]ZHAO X B,WANG J J.Bridge crack detection based on im-proved DeeplabV3＋and transfer learning [J].Computer Engineering and Application,2023,59(5):262-269.
[63]XIA X H,SU J G,WANG Y Y,et al.Lightweightpavement crack detection model based on DeepLabv3＋[J].Progress of Laser and Optoelectronics,2024,61(8):182-191.
[64]LIAO Y N,DOU D Y.Design and research of bridge crack detection method based on Mask RCNN [J].Application Optics,2022,43(1):100-105,118.
[65]NIU H Y,BAO T F,LI Y T,et al.A pixel-level detection methodfor cracks in concrete dams based on improved Mask R-CNN [J].Advances in Water Conservancy and Hydropower Science and Technology,2023,43(1):87-92,98.
[66]LI Y,WANG H,DANGL M,et al.A robust instance segmentation framework for underground sewer defect detection[J].Measurement,2022,190:110727.
[67]HANG J,WU Y,LI Y,et al.A deep learning semantic segmentation network with attention mechanism for concrete crack detection[J].Structural Health Monitoring,2023,22(5):3006-3026.
[68]WANG Q,WU B,ZHU P,et al.ECA-Net:Efficient channel attention for deep convolutional neural networks[C]//Procee-dings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2020:11534-11542.
[69]D V C S.Concrete crack detection with handwriting script interferences using faster region-based convolutional neural network[J].Computer-Aided Civil and Infrastructure Engineering,2020,35(4):373-388.
[70]JIANG Y,PANG D,LI C,et al.Two-step deep learning ap-proach for pavement crack damage detection and segmentation[J].International Journal of Pavement Engineering,2023,24(2):2065488.
[71]LIU S,QI L,QIN H,et al.Path aggregation network for instance segmentation[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2018:8759-8768.
[72]HAN K,WANG Y,TIAN Q,et al.Ghostnet:More featuresfrom cheap operations[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2020:1580-1589.
[73]ZHAO S,KANG F,LI J.Concrete dam damage detection and localisation based on YOLOv5s-HSC and photogrammetric 3D reconstruction[J].Automation in Construction,2022,143:104555.
[74]LONG T,DONG A G,LIU L J.Pavement crack detection based on attention mechanism and deformable convolution [J].Computer Science,2023,50(S1):402-407.
[75]PAN Y,ZHANG G,ZHANG L.A spatial-channel hierarchical deep learning network for pixel-level automated crack detection[J].Automation in Construction,2020,119:103357.
[76]QU Z,LI M.Pavement crack detection with hybrid dilated convolution and attention mechanism [J].Computer Engineering and Design,2023,44(8):2425-2431.
[77]XUE Y,LI Y.A fast detection method via region-based fully convolutional neural networks for shield tunnel lining defects[J].Computer-Aided Civil and Infrastructure Engineering,2018,33(8):638-654.
[78]QU Z,MEI J,LIU L,et al.Crack detection of concrete pavement with cross-entropy loss function and improved VGG16 network model[J].IEEE Access,2020,8:54564-54573.
[79]LIANG S J.Crack identification of concrete bridges based on improved ResNet-14 and RS-Unet models [J].Journal of Beijing Jiaotong University,2023,47(3):10-18.
[80]DENG L,ZHANG A,GUO J,et al.An integrated method for road crack segmentation and surface feature quantification under complex backgrounds[J].Remote Sensing,2023,15(6):1530.
[81]HOU H,YANG P Z,CAO J J,et al.Improved concrete crack detection method based on U-Net network [J].Computer Knowledge and Technology,2022,18(16):8-11.
[82]HU J,SHEN L,SUN G.Squeeze-and-excitation networks[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2018:7132-7141.
[83]SHI J,MA W Q,WU H J.Improved YOLOv4 concrete building crack detection algorithm [J].Microelectronics and Computer,2023,40(3):56-66.
[84]XIANG C,WANG W,DENG L,et al.Crack detection algorithm for concrete structures based on super-resolution reconstruction and segmentation network[J].Automation in Construction,2022,140:104346.
[85]ZHANG J,LU C,WANG J,et al.Concrete cracks detectionbased on FCN with dilated convolution[J].Applied Sciences,2019,9(13):2686.
[86]REN Y,HUANG J,HONG Z,et al.Image-based concrete crack detection in tunnels using deep fully convolutional networks[J].Construction and Building Materials,2020,234:117367.
[87]QU Z,CAO C,LIU L,et al.A deeply supervised convolutional neural network for pavement crack detection with multiscale feature fusion[J].IEEE Transactions on Neural Networks and Learning Systems,2021,33(9):4890-4899.
[88]ZHU W,ZHANG H,EASTWOOD J,et al.Concrete crack detection using lightweight attention feature fusion single shot multibox detector[J].Knowledge-Based Systems,2023,261:110216.
[89]HE T J,LI H E.Pavement disease detection model based on improved YOLOv5 [J].Journalof Civil Engineering,2024,57(2):96-106.
[90]LI Y,MA R,LIU H,et al.Real-time high-resolution neural network with semantic guidance for crack segmentation[J].Automation in Construction,2023,156:105112.
[91]KIM J,SHIM S,KANG S J,et al.Learning Structure for Concrete Crack Detection Using Robust Super-Resolution with Generative Adversarial Network[J].Structural Control and Health Monitoring,2023,2023(1):8850290.
[92]MUNDT M,MAJUMDER S,MURALI S,et al.Meta-learningconvolutional neural architectures for multi-target concrete defect classification with the concrete defect bridge image dataset[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2019:11196-11205.
[93]ZHANG L,YANG F,ZHANG Y D,et al.Road crack detection using deep convolutional neural network[C]//2016 IEEE International Conferenceon Image Processing(ICIP).IEEE,2016:3708-3712.
[94]DORAFSHAN S,THOMAS R J,MAGUIRE M.SDNET2018:An annotated image dataset for non-contact concrete crack detection using deep convolutional neural networks[J].Data in Brief,2018,21:1664-1668.
[95]YANG L,LI B,LI W,et al.Deep concrete inspection using unmanned aerial vehicle towardscssc database[C]//Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems.2017:24-28.
[96]XU H,SU X,WANG Y,et al.Automatic bridge crack Detection Using A convolutional neural network[J].Applied Sciences,2019,9(14):2867.
[97]ZOUBIR H,RGUIG M,ELAROUSSI M.Crack recognition automation in concrete bridges using Deep Convolutional Neural Networks[C]//MATEC Web of Conferences.EDP Sciences,2021,349:03014.
[98]SHI Y,CUI L,QI Z,et al.Automatic road crack detection using random structured forests[J].IEEE Transactions on Intelligent Transportation Systems,2016,17(12):3434-3445.
[99]ZOU Q,CAO Y,LI Q,et al.CrackTree:Automatic crack detection from pavement images[J].Pattern Recognition Letters,2012,33(3):227-238.
[100]LIU Y,YAO J,LU X,et al.DeepCrack:A deep hierarchical feature learning architecture for crack segmentation[J].Neurocomputing,2019,338:139-153.
[101]LI J,WANG Q,MA J,et al.Multi-defect segmentation fromfaçade images using balanced copy-paste method[J].Computer-Aided Civil andInfrastructure Engineering,2022,37(11):1434-1449.
[102]LI B,GUO H,WANG Z.Data augmentation using CycleGAN-based methods for automatic bridge crack detection[C]//Structures.Elsevier,2024,62:106321.
[103]LI Y,BAO T,HUANG X,et al.Underwater crack pixel-wiseidentification and quantification for dams via lightweight semantic segmentationand transfer learning[J].Automation in Construction,2022,144:104600.
[104]PEREZ H,TAH J H M.Deep learning smartphone application for real-time detection of defects in buildings[J].Structural Control and Health Monitoring,2021,28(7):e2751.
[105]LEE K,LEE S,KIMH Y.Bounding-box object augmentationwith random transformations for automated defect detection in residential building façades[J].Automation in Construction,2022,135:104138.
[106]LI S,ZHAO X.High-resolution concrete damage image synthesis using conditional generative adversarial network[J].Automation in Construction,2023,147:104739.
[107]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.
[108]DING W,MA H B,SHU J P,et al.Research onclassification and identification of concrete structure diseases based on residual network [J].Journal of Building Science and Engineering,2022,39(4):127-136.
[109]XU Z Y,QIANS R.Research on concrete crack identificationbased on transfer learning and Xception network [J].Software ngineering,2022,25(7):15-18.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed