Deep learning-based concrete defect detection has emerged as a promising technology to overcome the limitations of manual visual inspection, which is often subjective, laborious, and time-consuming. However, most existing methods rely heavily on manual labels and adopt a fully supervised learning approach, which hinders their practical application in engineering. To tackle these concerns, we proposed a semi-supervised learning model, termed Semi-SegDefect. Our proposal utilizes a mean teacher architecture to assign pseudo-labels to the pixels of unlabeled images and performs pixel-level contrastive learning on a sparse set of hard negative pixels to achieve segmentation boundaries with the highest possible accuracy. Test results demonstrate that Semi-SegDefect outperforms fully supervised models significantly, especially when trained with limited labeled data. This method shows great promise for enhancing the accuracy and scalability of concrete defect segmentation and can contribute to the advancement of the construction industry.
FlahMNunezIBen ChaabeneW, et al. Machine learning algorithms in civil structural health monitoring: a systematic review. Arch Comput Methods Eng2021; 28: 2621–2643.
2.
ReaganDSabatoANiezreckiC.Feasibility of using digital image correlation for unmanned aerial vehicle structural health monitoring of bridges. Struct Health Monit2018; 17: 1056–1072.
3.
TaheriS.A review on five key sensors for monitoring of concrete structures. Constr Build Mater2019; 204: 492–509.
SpencerBFJrHoskereVNarazakiY.Advances in computer vision-based civil infrastructure inspection and monitoring. Engineering2019; 5: 199–222.
7.
BaoYLiH.Machine learning paradigm for structural health monitoring. Struct Health Monit2021; 20: 1353–1372.
8.
ZhangQBarriKBabanajadSK, et al. Real-time detection of cracks on concrete bridge decks using deep learning in the frequency domain. Engineering2020; 7: 1786–1796.
9.
ZhouSSongW.Deep learning–based roadway crack classification with heterogeneous image data fusion. Struct Health Monit2021; 20: 1274–1293.
10.
PalevičiusPPalMLandauskasM, et al. Automatic detection of cracks on concrete surfaces in the presence of shadows. Sensors-Basel2022; 22: 3662.
11.
LiCXuPNiuL, et al. Tunnel crack detection using coarse-to-fine region localization and edge detection. Wiley Interdiscip Rev Data Min Knowl Discovery2019; 9: e1308.
12.
MunawarHSUllahFHeraviA, et al. Inspecting buildings using drones and computer vision: a machine learning approach to detect cracks and damages. Drones2021; 6: 5.
13.
ZouDZhangMBaiZ, et al. Multicategory damage detection and safety assessment of post-earthquake reinforced concrete structures using deep learning. Comput-Aided Civ Infrastruct Eng2022; 37: 1188–1204.
14.
SantosRRibeiroDLopesP, et al. Detection of exposed steel rebars based on deep-learning techniques and unmanned aerial vehicles. Automat Constr2022; 139: 104324.
15.
ZhangXRajanDStoryB.Concrete crack detection using context-aware deep semantic segmentation network. Comput-Aided Civ Infrastruct Eng2019; 34: 951–971.
16.
HanXZhaoZChenL, et al. Structural damage-causing concrete cracking detection based on a deep-learning method. Constr Build Mater2022; 337: 127562.
17.
LiYYuMWuD, et al. Automatic pixel-level detection method for concrete crack with channel-spatial attention convolution neural network. Struct Health Monit. Epub ahead of print 5July2022. DOI: 10.1177/14759217221109496.
18.
KangDHChaY-J.Efficient attention-based deep encoder and decoder for automatic crack segmentation. Struct Health Monit2022; 21: 2190–2205.
19.
CuiXWangQDaiJ, et al. Intelligent crack detection based on attention mechanism in convolution neural network. Adv Struct Eng2021; 24: 1859–1868.
20.
HoskereVNarazakiYHoangTA, et al. MaDnet: multi-task semantic segmentation of multiple types of structural materials and damage in images of civil infrastructure. J Civ Struct Health Monit2020; 10: 757–773.
21.
XuYBaoYChenJ, 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. Struct Health Monit2019; 18: 653–674.
22.
XuYWeiSBaoY, et al. Automatic seismic damage identification of reinforced concrete columns from images by a region-based deep convolutional neural network. Struct Control Health Monit2019; 26: e2313.
23.
ShimSKimJChoG-C, et al. Multiscale and adversarial learning-based semi-supervised semantic segmentation approach for crack detection in concrete structures. IEEE Access2020; 8: 170939–170950.
24.
ShimSKimJLeeS-W, et al. Road damage detection using super-resolution and semi-supervised learning with generative adversarial network. Automat Constr2022; 135: 104139.
25.
LiGWanJHeS, et al. Semi-supervised semantic segmentation using adversarial learning for pavement crack detection. IEEE Access2020; 8: 51446–51459.
26.
ZhangGPanYZhangL.Semi-supervised learning with GAN for automatic defect detection from images. Automat Constr2021; 128: 103764.
27.
GaoZPengBLiT, et al. Generative adversarial networks for road crack image segmentation. In: 2019 International joint conference on neural networks (IJCNN), Budapest, Hungary, 2019, pp. 1–8. IEEE.
XuYBaoYZhangY, et al. Attribute-based structural damage identification by few-shot meta learning with inter-class knowledge transfer. Struct Health Monit2021; 20: 1494–1517.
30.
XuYFanYBaoY, et al. Task-aware meta-learning paradigm for universal structural damage segmentation using limited images. Eng Struct2023; 284: 115917.
ChenHJinYJinG, et al. Semisupervised semantic segmentation by improving prediction confidence. IEEE Trans Neural Networks Learn Syst2021; 33: 4991–5003.
33.
ChenXYuanYZengG, et al. Semi-supervised semantic segmentation with cross pseudo supervision. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, Nashville, TN, USA, 2021, pp. 2613–2622.
34.
TarvainenAValpolaH.Mean teachers are better role models: weight-averaged consistency targets improve semi-supervised deep learning results. Adv Neural Inf Process Syst2017; 30: 1195–1204.
35.
LiuZMaoHWuC-Y, et al. A convnet for the 2020s. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, New Orleans, LA, USA, 2022, pp. 11976–11986.
36.
ChenL-CPapandreouGSchroffF, et al. Rethinking atrous convolution for semantic image segmentation. arXiv preprint arXiv:170605587, 2017.
37.
Le-KhacPHHealyGSmeatonAF.Contrastive representation learning: a framework and review. IEEE Access2020; 8: 193907–193934.
38.
JaiswalABabuARZadehMZ, et al. A survey on contrastive self-supervised learning. Technologies2020; 9: 2.
39.
LiSZhaoXZhouG.Automatic pixel-level multiple damage detection of concrete structure using fully convolutional network. Comput Aided Civ Infrastruct Eng2019; 34: 616–634.
40.
YangLLiBLiW, et al. Semantic metric 3d reconstruction for concrete inspection. In: Proceedings of the IEEE conference on computer vision and pattern recognition workshops, Salt Lake City, UT, USA, 2018, pp. 1543–1551.
41.
YangXLiHYuY, et al. Automatic pixel-level crack detection and measurement using fully convolutional network. Comput Aided Civ Infrastruct Eng2018; 33: 1090–1109.
42.
ZhangCChangC-CJamshidiM.Simultaneous pixel-level concrete defect detection and grouping using a fully convolutional model. Struct Health Monit2021; 20: 2199–2215.
43.
YunSHanDOhSJ, et al. Cutmix: Regularization strategy to train strong classifiers with localizable features. In: Proceedings of the IEEE/CVF international conference on computer vision, Seoul, Korea (South), 2019, pp. 6023–6032.
YangLQiLFengL, et al. Revisiting weak-to-strong consistency in semi-supervised semantic segmentation. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, Vancouver, BC, Canada, 2023, pp. 7236–7246.
46.
PeirisHChenZEganG, et al. Duo-SegNet: adversarial dual-views for semi-supervised medical image segmentation. In: Medical image computing and computer assisted intervention–MICCAI 2021, Strasbourg, France, September 27–October 1, 2021, pp. 428–438. Springer.
47.
KirillovAGirshickRHeK, et al. Panoptic feature pyramid networks. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, Long Beach, CA, USA, 2019, pp. 6399–6408.
48.
ChenL-CZhuYPapandreouG, et al. Encoder-decoder with atrous separable convolution for semantic image segmentation. In: Proceedings of the European conference on computer vision (ECCV), Munich, Germany, 2018, pp. 801–818.
