Computers and Concrete

  • 제32권6호
  • /
  • Pages.615-623
  • /
  • 2023
  • /
  • 1598-8198(pISSN)
  • /
  • 1598-818X(eISSN)
테크노프레스 (Techno-Press)
권호 표지
DOI QR코드

DOI QR Code

Automatic crack detection of dam concrete structures based on deep learning

  • Zongjie Lv (The National Key Laboratory of Water Disaster Prevention, Hohai University) ;
  • Jinzhang Tian (National Dam Safety Research Center) ;
  • Yantao Zhu (The National Key Laboratory of Water Disaster Prevention, Hohai University) ;
  • Yangtao Li (The National Key Laboratory of Water Disaster Prevention, Hohai University)
  • 투고 : 2022.12.07
  • 심사 : 2023.08.14
  • 발행 : 2023.12.25
⟨ 이전 논문 다음 논문 ⟩

초록

Crack detection is an essential method to ensure the safety of dam concrete structures. Low-quality crack images of dam concrete structures limit the application of neural network methods in crack detection. This research proposes a modified attentional mechanism model to reduce the disturbance caused by uneven light, shadow, and water spots in crack images. Also, the focal loss function solves the small ratio of crack information. The dataset collects from the network, laboratory and actual inspection dataset of dam concrete structures. This research proposes a novel method for crack detection of dam concrete structures based on the U-Net neural network, namely AF-UNet. A mutual comparison of OTSU, Canny, region growing, DeepLab V3+, SegFormer, U-Net, and AF-UNet (proposed) verified the detection accuracy. A binocular camera detects cracks in the experimental scene. The smallest measurement width of the system is 0.27 mm. The potential goal is to achieve real-time detection and localization of cracks in dam concrete structures.

키워드

과제정보

This study was supported by the National Key R&D Program of China (No. 2022YFC3005404), the National Natural Science Foundation of China (52309152), the Fundamental Research Funds for the Central Universities (B230201013), the Natural Science Foundation of Jiangsu Province (BK20220978) and Open fund of National Dam Safety Research Center (Grant No. CX2023B03).

참고문헌

  1. Ali, R., Chuah, J.H., Talip, M.S.A., Mokhtar, N. and Shoaib, M.A. (2022), "Structural crack detection using deep convolutional neural networks", Automat. constr., 133, 103989. https://doi.org/10.1016/j.autcon.2021.103989.
  2. Cai, Y. and Wang, Y. (2022), "Ma-unet: An improved version of unet based on multi-scale and attention mechanism for medical image segmentation", Third International Conference on Electronics and Communication, Network and Computer Technology (ECNCT 2021), Harbin, China, December.
  3. Chen, L.C., Zhu, Y., Papandreou, G., Schroff, F. and Adam, H. (2018), "Encoder-decoder with atrous separable convolution for semantic image segmentation", Proceedings of the European Conference on Computer Vision (ECCV) 2018, Munich, Germany, September.
  4. Fu, J., Liu, J., Tian, H., Li, Y., Bao, Y., Fang, Z. and Lu, H. (2019), "Dual attention network for scene segmentation", Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition 2019, Long Beach, CA, USA, June.
  5. LeCun, Y., Bengio, Y. and Hinton, G. (2015), "Deep learning", Nature, 521(7553), 436-444. https://doi.org/10.1038/nature14539.
  6. Li, S., Zhao, X. and Zhou, G. (2019), "Automatic pixel-level multiple damage detection of concrete structure using fully convolutional network", Comput. Aided Civil Inf. Eng., 34(7), 616-634. https://doi.org/10.1111/mice.12433.
  7. Li, W., Qin, S., Li, F. and Wang, L. (2021), "MAD-UNet: A deep U-shaped network combined with an attention mechanism for pancreas segmentation in CT images", Med. Phys., 48(1), 329-341. https://doi.org/10.1002/mp.14617.
  8. Lin, T.Y., Goyal, P., Girshick, R., He, K. and Dollar, P. (2017), "Focal loss for dense object detection", Proceedings of the IEEE International Conference on Computer Vision 2017, Venice, Italy, October.
  9. Liu, Z., Cao, Y., Wang, Y. and Wang, W. (2019), "Computer vision-based concrete crack detection using U-net fully convolutional networks", Automat. Constr., 104, 129-139. https://doi.org/10.1016/j.autcon.2019.04.005.
  10. Ma, J., Chen, J., Ng, M., Huang, R., Li, Y., Li, C. and Martel, A.L. (2021), "Loss odyssey in medical image segmentation", Med. Image Anal., 71, 102035. https://doi.org/10.1016/j.media.2021.102035.
  11. Mostafaei, H., Ghamami, M. and Aghabozorgi, P. (2021), "Modal identification of concrete arch dam by fully automated operational modal identification", Struct., 32, 228-236. https://doi.org/10.1016/j.istruc.2021.03.028.
  12. Mostafaei, H., Mostofinejad, D., Ghamami, M. and Wu, C. (2023), "A new approach of ensemble learning in fully automated identification of structural modal parameters of concrete gravity dams: A case study of the Koyna dam", Struct., 50, 255-271. https://doi.org/10.1016/j.istruc.2023.02.034.
  13. Oktay, O., Schlemper, J., Folgoc, L.L., Lee, M., Heinrich, M., Misawa, K. and Rueckert, D. (2018), "Attention u-net: Learning where to look for the pancreas", arXiv preprint arXiv:1804.03999. https://doi.org/10.48550/arXiv.1804.03999.
  14. Ozgenel, C.F. and Gonenc Sorguc, A. (2018), "Performance comparison of pretrained convolutional neural networks on crack detection in buildings", 35th International Symposium on Automation and Robotics in Construction (ISARC 2018), Berlin, Germany, July.
  15. Pang J., Zhang, H., Feng, C. and Li, L. (2021), "U-Net-based segmentation of crack on dam surface using separable residual convolution and semantic compensation", Comput. Eng., 47(4), 306-312. https://doi.org/10.19678/j.issn.1000-3428.0057713.
  16. Ronneberger, O., Fischer, P. and Brox, T. (2015), "U-net: Convolutional networks for biomedical image segmentation", International Conference on Medical Image Computing and Computer-Assisted Intervention, Munich, Germany, October.
  17. Talab, A.M.A., Huang, Z., Xi, F. and HaiMing, L. (2016), "Detection crack in image using Otsu method and multiple filtering in image processing techniques", Optik, 127(3), 1030-1033. https://doi.org/10.1016/j.ijleo.2015.09.147.
  18. Turk, K., Kina, C. and Tanyildizi, H. (2022), "Predicting sorptivity and freeze-thaw resistance of self-compacting mortar by using deep learning and k-nearest neighbor", Comput. Concrete, 30(2), 99-111. https://doi.org/10.12989/cac.2022.30.2.099.
  19. Wang, G., Peter, W.T. and Yuan, M. (2018), "Automatic internal crack detection from a sequence of infrared images with a triple-threshold Canny edge detector", Measure. Sci. Technol., 29(2), 025403. https://doi.org/10.1088/1361-6501/aa9857.
  20. Wang, X. and Xie, M. (2022), "Integration of 3DGIS and BIM and its application in visual detection of concealed facilities", Geo. Spat. Inf. Sci., 2022, 1-10. https://doi.org/10.1080/10095020.2022.2054732.
  21. Woo, S., Park, J., Lee, J.Y. and Kweon, I.S. (2018), "Cbam: Convolutional block attention module", Proceedings of the European Conference on Computer Vision (ECCV) 2018, Munich, Germany, September.
  22. Xie, E., Wang, W., Yu, Z., Anandkumar, A., Alvarez, J.M. and Luo, P. (2021), "SegFormer: Simple and efficient design for semantic segmentation with transformers", Adv. Neural Inf. Pr. Syst., 34, 12077-12090.
  23. Zhang, L., Yang, F., Zhang, Y.D. and Zhu, Y.J. (2016), "Road crack detection using deep convolutional neural network", 2016 IEEE International Conference on Image Processing (ICIP), Phoenix, AZ, USA, September.
  24. Zhu, Y. and Tang, H. (2023), "Automatic damage detection and diagnosis for hydraulic structures using drones and artificial intelligence techniques", Remote Sens., 15(3), 615. https://doi.org/10.3390/rs15030615.