International conference on construction engineering and project management (국제학술발표논문집)

  • 2024.07a
  • /
  • Pages.152-159
  • /
  • 2024
  • /
  • 2508-9048(eISSN)
Korea Institute of Construction Engineering and Management (한국건설관리학회)
권호 표지
DOI QR코드

DOI QR Code

Enhancement of concrete crack detection using U-Net

  • Molaka Maruthi (School of Architecture, Civil, Environment and Energy Engineering, Kyungpook National University) ;
  • Lee, Dong Eun (School of Architecture, Civil, Environment and Energy Engineering, Kyungpook National University) ;
  • Kim Bubryur (Department of Robot and smart system engineering, Kyungpook National University)
  • Published : 2024.07.29
Download PDF
⟨ Previous Next ⟩

Abstract

Cracks in structural materials present a critical challenge to infrastructure safety and long-term durability. Timely and precise crack detection is essential for proactive maintenance and the prevention of catastrophic structural failures. This study introduces an innovative approach to tackle this issue using U-Net deep learning architecture. The primary objective of the intended research is to explore the potential of U-Net in enhancing the precision and efficiency of crack detection across various concrete crack detection under various environmental conditions. Commencing with the assembling by a comprehensive dataset featuring diverse images of concrete cracks, optimizing crack visibility and facilitating feature extraction through advanced image processing techniques. A wide range of concrete crack images were collected and used advanced techniques to enhance their visibility. The U-Net model, well recognized for its proficiency in image segmentation tasks, is implemented to achieve precise segmentation and localization of concrete cracks. In terms of accuracy, our research attests to a substantial advancement in automated of 95% across all tested concrete materials, surpassing traditional manual inspection methods. The accuracy extends to detecting cracks of varying sizes, orientations, and challenging lighting conditions, underlining the systems robustness and reliability. The reliability of the proposed model is measured using performance metrics such as, precision(93%), Recall(96%), and F1-score(94%). For validation, the model was tested on a different set of data and confirmed an accuracy of 94%. The results shows that the system consistently performs well, even with different concrete types and lighting conditions. With real-time monitoring capabilities, the system ensures the prompt detection of cracks as they emerge, holding significant potential for reducing risks associated with structural damage and achieving substantial cost savings.

Keywords

Acknowledgement

This work was supported by the National Research Foundation of Korea (NRF) grant funded by the Korea government (MSIT) (No. 2022R1C1C1005409). This work is supported by the Korea Agency for Infrastructure Technology Advancement (KAIA) grant funded by the Ministry of Land, Infrastructure and Transport (Grant RS-2023-00251002). This work was supported by the National Research Foundation of Korea (NRF) grant funded by the Korea government (MSIT) (No. NRF-2018R1A5A1025137).

References

  1. J. Y. Lee et al., "Adaptive decision-making for civil infrastructure systems and communities exposed to evolving risks," Struct. Saf., vol. 75, pp. 1-12, 2018, Nov..
  2. B. Kim et al, "Surface crack detection using deep learning with shallow CNN architecture for enhanced computation," Neural Comput. Applic., vol. 33, no. 15, pp. 9289-9305, 2021.
  3. L. Tian et al., "Image-range stitching and semantic-based crack detection methods for tunnel inspection vehicles," Remote Sens., vol. 15, no. 21, p. 5158, 2023, Oct. 28.
  4. N. Yuvaraj et al., "Transfer learning based real-time crack detection using unmanned aerial system," Int. J. High-Rise Build., vol. 9, no. 4, pp. 351-360, 2020.
  5. Z. H. Hoylman et al., "Drought assessment has been outpaced by climate change: Empirical arguments for a paradigm shift," Nat. Commun., vol. 13, no. 1, 2715, 2022, May 17.
  6. Y. Fujita et al., "Classification model based on U-net for crack detection from asphalt pavement images," J. Image Graph., pp. 121-126, 2023, Jun..
  7. M. U. Saeed et al., "3D MRU-Net: A novel mobile residual U-Net deep learning model for spine segmentation using computed tomography images," Biomed. Signal Process. Control, vol. 86, p. 105153, 2023, Sept..
  8. C. Yu et al., "An improved U-Net model for concrete crack detection," Mach. Learn. Appl., vol. 10, p. 100436, 2022.
  9. Q. Song et al., "Two-stage framework with improved U-Net based on self-supervised contrastive learning for pavement crack segmentation," Expert Syst. Appl., vol. 238, p. 122406, 2024.
  10. Y. Zhang and L. Zhang, 2023, Detection of pavement cracks by deep learning models of transformer and UNet. arXiv preprint arXiv:2304.12596.
  11. T. Lee et al., "Improvement of concrete crack segmentation performance using stacking ensemble learning," Appl. Sci., vol. 13, no. 4, p. 2367, 2023.
  12. P. Padmapoorani and S. Senthilkumar, "Application of machine learning for crack detection on concrete structures using CNN architecture," Mater. (Rio Janeiro), vol. 28, no. 1, p. e20230010, 2023.
  13. F. Elghaish et al., "Multi-layers deep learning model with feature selection for automated detection and classification of highway pavement cracks," Smart Sustain. Built Environ., 2024.
  14. T. Liu et al., "BC-DUnet-based segmentation of fine cracks in bridges under a complex background," PLOS ONE, vol. 17, no. 3, p. e0265258, 2022.
  15. S. F. Mahenge et al., "A modified U-net architecture for road surfaces cracks detection" in Proc. 8th International Conference on Computing and Artificial Intelligence, 2022, Mar., pp. 464-471.
  16. F. Lin et al., "Crack semantic segmentation using the U-net with full attention strategy. arXiv 2021," arXiv Preprint ArXiv:2104.14586.