Browse > Article
http://dx.doi.org/10.12989/smm.2022.9.3.289

Pixel-based crack image segmentation in steel structures using atrous separable convolution neural network  

Ta, Quoc-Bao (Department of Ocean Engineering, Pukyong National University)
Pham, Quang-Quang (Department of Ocean Engineering, Pukyong National University)
Kim, Yoon-Chul (Department of Civil Engineering, Yonsei University)
Kam, Hyeon-Dong (Department of Ocean Engineering, Pukyong National University)
Kim, Jeong-Tae (Department of Ocean Engineering, Pukyong National University)
Publication Information
Structural Monitoring and Maintenance / v.9, no.3, 2022 , pp. 289-303 More about this Journal
Abstract
In this study, the impact of assigned pixel labels on the accuracy of crack image identification of steel structures is examined by using an atrous separable convolution neural network (ASCNN). Firstly, images containing fatigue cracks collected from steel structures are classified into four datasets by assigning different pixel labels based on image features. Secondly, the DeepLab v3+ algorithm is used to determine optimal parameters of the ASCNN model by maximizing the average mean-intersection-over-union (mIoU) metric of the datasets. Thirdly, the ASCNN model is trained for various image sizes and hyper-parameters, such as the learning rule, learning rate, and epoch. The optimal parameters of the ASCNN model are determined based on the average mIoU metric. Finally, the trained ASCNN model is evaluated by using 10% untrained images. The result shows that the ASCNN model can segment cracks and other objects in the captured images with an average mIoU of 0.716.
Keywords
atrous convolution; crack identification; Deeplabv3+ network; semantic segmentation; steel structure; vision image;
Citations & Related Records
Times Cited By KSCI : 3  (Citation Analysis)
연도 인용수 순위
1 Bao, Y., Li, J., Nagayama, T., Xu, Y., Spencer, B.F. and Li, H. (2021), "The 1st international project competition for structural health monitoring (IPC-SHM, 2020): A summary and benchmark problem", Struct. Health Monitor., 20(4), 2229-2239. https://doi.org/10.1177/14759217211006485   DOI
2 Barbedo, J.G.A. (2018), "Impact of dataset size and variety on the effectiveness of deep learning and transfer learning for plant disease classification", Comput. Electron Agric., 153, 46-53. https://doi.org/10.1016/j.compag.2018.08.013   DOI
3 Battista, R. and Pfeil, M. (1999), "Fatigue cracks induced by traffic loading on steel bridges' slender orthotropic decks", The Ninth International Conference on Computational Methods and Experimental Measurements", WIT Transact. Modell. Simul., 21, 37-46. https://www.witpress.com/elibrary/wit-transactions-on-modelling-and-simulation/22/4967
4 Campbell, L.E., Connor, R.J., Whitehead, J.M. and Washer, G.A. (2021), "Human factors affecting visual inspection of fatigue cracking in steel bridges", Struct. Infrastruct. Eng., 17(11), 1447-1458. https://doi.org/10.1080/15732479.2020.1813783   DOI
5 Chen, L.C., Papandreou, G., Kokkinos, I., Murphy, K. and Yuille, A.L. (2018), "Deeplab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs", IEEE Trans. Pattern. Anal. Mach. Intell., 40(4), 834-848. Doi: 10.1109/TPAMI.2017.2699184   DOI
6 Dong, C., Li, L., Yan, J., Zhang, Z., Pan, H. and Catbas, F.N. (2021), "Pixel-level fatigue crack segmentation in large-scale images of steel structures using an encoder-decoder network", Sensors, 21(12). https://doi.org/10.3390/s21124135   DOI
7 Alzubaidi, L., Zhang, J., Humaidi, A.J., Al-Dujaili, A., Duan, Y., Al-Shamma, O., Santamaria, J., Fadhel, M.A., Al-Amidie, M. and Farhan, L. (2021), "Review of deep learning: concepts, CNN architectures, challenges, applications, future directions", J. Big Data, 8 (1), 1-74. https://doi.org/10.1186/s40537-021-00444-8   DOI
8 Bailly, A., Blanc, C., Francis, E., Guillotin, T., Jamal, F., Wakim, B. and Roy, P. (2022), "Effects of dataset size and interactions on the prediction performance of logistic regression and deep learning models", Comput. Methods Programs Biomed., 213, 106504. https://doi.org/10.1016/j.cmpb.2021.106504   DOI
9 Cha, Y.-J., Choi, W. and Buyukozturk, O. (2017), "Deep learning-based crack damage detection using convolutional neural networks", Comput.-Aided Civ. Infrastruct. Eng., 32(5), 361-378. https://doi.org/10.1111/mice.12263   DOI
10 Dung, C.V., Sekiya, H., Hirano, S., Okatani, T. and Miki, C. (2019), "A vision-based method for crack detection in gusset plate welded joints of steel bridges using deep convolutional neural networks", Autom. Constr., 102, 217-229. https://doi.org/10.1016/j.autcon.2019.02.013   DOI
11 Gallwey, T.J. (1998b), "Evaluation and control of industrial inspection: Part II-The scientific basis for the guide", Int. J. Ind. Ergon., 22(1-2), 51-65. https://doi.org/10.1016/S0169-8141(97)00067-X   DOI
12 Lee, J.K., Bae, D.S., Lee, S.P. and Lee, J.H. (2014), "Evaluation on defect in the weld of stainless steel materials using nondestructive technique", Fusion Eng. Des., 89(7-8), 1739-1745. https://doi.org/10.1016/j.fusengdes.2013.12.026   DOI
13 Yao, L., Dong, Q., Jiang, J. and Ni, F. (2020), "Deep reinforcement learning for long-term pavement maintenance planning", Comput.-Aided Civ. Infrastruct. Eng., 35(11), 1230-1245. https://doi.org/10.1111/mice.12558   DOI
14 Ruder, S. (2016), "An overview of gradient descent optimization algorithms", arXiv preprint, arXiv:1609.04747. https://doi.org/10.48550/arXiv.1609.04747   DOI
15 Zhao, Z.Q., Zheng, P., Xu, S.T. and Wu, X. (2019), "Object detection with deep learning: a review", IEEE Trans. Neural Netw. Learn. Syst., 30(11), 3212-3232. Doi: 10.1109/TNNLS.2018.2876865   DOI
16 Zhu, X.P., Rizzo, P., Marzani, A. and Bruck, J. (2010), "Ultrasonic guided waves for nondestructive evaluation/structural health monitoring of trusses", Meas. Sci. Technol., 21(4). https://doi.org/10.1088/0957-0233/21/4/045701   DOI
17 Dung, C.V. and Anh, L.D. (2019), "Autonomous concrete crack detection using deep fully convolutional neural network", Autom. Constr., 99, 52-58. https://doi.org/10.1016/j.autcon.2018.11.028   DOI
18 Gallwey, T.J. (1998a), "Evaluation and control of industrial inspection: Part I-Guidelines for the practitioner", Int. J. Ind. Ergon., 22(1-2), 37-49. https://doi.org/10.1016/S0169-8141(97)00066-8   DOI
19 Mutlib, N.K., Baharom, S.B., El-Shafie, A. and Nuawi, M.Z. (2016), "Ultrasonic health monitoring in structural engineering: buildings and bridges", Struct. Control Health Monit., 23(3), 409-422. https://doi.org/10.1002/stc.1800   DOI
20 Ronneberger, O., Fischer, P. and Brox, T. (2015), "U-net: Convolutional networks for biomedical image segmentation", Proceedings of International Conference on Medical Image Computing and ComputerAssisted Intervention, Munich, Germany, October. https://doi.org/10.1007/978-3-319-24574-4_28   DOI
21 See, J.E. (2012), "Visual inspection: a review of the literature", Report SAND2012-8590; Accessed on 2022.03.04. https://www.osti.gov/servlets/purl/1055636
22 Spencer, B.F., Hoskere, V. and Narazaki, Y. (2019), "Advances in computer vision-based civil infrastructure inspection and monitoring", Engineering, 5(2), 199-222. https://doi.org/10.1016/j.eng.2018.11.030   DOI
23 Wang, X. and Wu, N. (2019), "Crack identification at welding joint with a new smart coating sensor and entropy", Mech. Syst. Signal Process., 124, 65-82. https://doi.org/10.1016/j.ymssp.2019.01.044   DOI
24 Wang, Y., Fu, Z., Ge, H., Ji, B. and Hayakawa, N. (2019), "Cracking reasons and features of fatigue details in the diaphragm of curved steel box girder", Eng. Struct., 201, 109767. https://doi.org/10.1016/j.engstruct.2019.109767   DOI
25 Xu, Y., Bao, Y., Chen, J., Zuo, W. and Li, H. (2018), "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 Monitor., 18(3), 653-674. https://doi.org/10.1177/1475921718764873   DOI
26 Yang, X., Li, H., Yu, Y., Luo, X., Huang, T. and Yang, X. (2018), "Automatic pixel-level crack detection and measurement using fully convolutional network", Comput.-Aided Civ. Infrastruct. Eng., 33(12), 1090-1109. https://doi.org/10.1111/mice.12412   DOI
27 Ye, X., Jin, T. and Yun, C. (2019), "A review on deep learning-based structural health monitoring of civil infrastructures", Smart Struct. Syst., Int. J., 24 (5), 567-585. https://doi.org/10.12989/sss.2019.24.5.567   DOI