Advances in concrete construction

Techno-Press (테크노프레스)
권호 표지
DOI QR코드

DOI QR Code

Automatic crack detection using quantum-inspired firefly algorithm with deep learning techniques

  • K.A. Vinodhini (Vel Tech High Tech Dr. Rangarajan Dr. Sakunthala Engineering College (An Autonomous Institution)) ;
  • K.R. Aswin Sidhaarth (Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology) ;
  • K.A. Varun Kumar (Department of Networking and Communications, School of Computing, SRM Institute of Science and Technology)
  • Received : 2024.01.18
  • Accepted : 2024.04.24
  • Published : 2024.08.25
⟨ Previous Next ⟩

Abstract

Detecting and quantifying cracks in bituminous (asphalt) road surfaces plays a crucial role in maintaining road infrastructure integrity and enabling cost-effective maintenance strategies. However, traditional manual inspections are laborious, time-intensive, and susceptible to inconsistencies due to factors like human fatigue, varying expertise levels, and subjective assessments. To address these challenges, this research proposes CrackNet, an innovative deep learning framework that harnesses state-of-the-art computer vision and object detection techniques for accurate and computationally efficient automated crack detection in bituminous road imagery. CrackNet introduces a novel hybrid neural network architecture that seamlessly integrates a cutting-edge Vision Transformer backbone with multi-scale convolutional feature fusion modules. The Vision Transformer component excels at capturing long-range structural dependencies and global contextual information, while the multi-scale fusion modules adeptly combine fine-grained crack details across various spatial resolutions. This unique design enables CrackNet to holistically model intricate crack topologies while preserving localized characteristics and intricate details. To further bolster robustness and generalization capabilities across diverse real-world scenarios, CrackNet incorporates self-supervised pre-training techniques that leverage unlabeled data and unsupervised pretext tasks. These strategies allow CrackNet to learn rich visual representations tailored specifically for crack detection. Additionally, an extensive data augmentation pipeline is employed, encompassing geometric, photometric, and adversarial transformations, to enhance model invariance to varying imaging conditions and environmental factors. The accuracy achieved by the newly proposed approach surpasses that of current state-of-the-art methodologies, reaching an impressive 97.8%.

Keywords

References

  1. Basalamah, S.M. (2017), "Concrete crack detection using deep learning", In: 2017 IEEE International Conference.
  2. Cha, Y.J. and Choi, W. (2017), "Deep learning-based crack damage detection using convolutional neural networks", Comput.‐Aided Civil Infrastr. Eng., 32(5), 361-378. https://doi.org/10.1111/mice.12263
  3. Chen, F., Jahanshahi, M.R., Wu, R.T. and Joffe, C. (2017), "A texture-based video processing methodology using Bayesian data fusion for autonomous crack detection on metallic surfaces", Comput.‐Aided Civil Infrastr. Eng., 32(4), 271-287. https://doi.org/10.1111/mice.12256
  4. 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 Transact. Pattern Anal. Mach. Intell., 40(4), 834-848. https://doi.org/10.1109/TPAMI.2017.2699184
  5. Choi, B., Kim, H., Jung, J. and Kim, J. (2019), "Deep learning-based concrete crack detection using a region-based convolutional neural network", Struct. Concrete, 20(5), 1596-1604. https://doi.org/10.1002/suco.201800138
  6. Dey, N., Ashour, A.S., Borra, S. and Samui, P. (2018), "Rehabilitation of flexural members using deep learning-based crack detection", Neural Comput. Applicat., 30(9), 2773-2787.
  7. Dong, Z. and Fang, S. (2018), "Automated bridge crack detection using deep convolutional neural networks", In: 2018 International Conference on Intelligent Transportation, Big Data & Smart City (ICITBS), pp. 260-263.
  8. Dong, Z., Wu, Y., Pei, M. and Jia, Y. (2015), "Vehicle type classification using a semisupervised convolutional neural network", IEEE Transact. Intell. Transport. Syst., 16(4), 2247-2256. https://doi.org/10.1109/TITS.2015.2402438
  9. Dorafshan, S., Thomas, R.J. and Maguire, M. (2018), "Comparison of deep learning and edge detection algorithms for crack detection in concrete structures", Constr. Build. Mater., 186, 1031-1045. https://doi.org/10.1016/j.conbuildmat.2018.08.011
  10. Dung, C.V. and Anh, L.D. (2019), "Autonomous concrete crack detection using deep fully convolutional neural network", Automat. Constr., 99, 52-58. https://doi.org/10.1016/j.autcon.2018.11.028
  11. Gopalakrishnan, K., Khaitan, S.K., Choudhary, A. and Agrawal, A. (2017), "Deep convolutional neural networks with transfer learning for computer vision-based data-driven pavement distress detection", Constr. Build. Mater., 157, 322-330. https://doi.org/10.1016/j.conbuildmat.2017.09.110
  12. Hoang, N.D. and Nguyen, Q.L. (2018), "A novel method for asphalt pavement crack detection using image processing and artificial neural network", Adv. Civil Eng., 2018.
  13. Khattak, M.J., Khattab, A. and Zhang, J. (2018), "Automated detection of cracks on concrete bridge deck surfaces using a convolution neural network", J. Comput. Civil Eng., 32(3), p. 04018008.
  14. Kumawat, R., Verma, A.K., Rathore, A.S. and Thakur, N. (2021), "Defect detection in concrete structures using deep learning-based semantic segmentation", Automat. Constr., 124, p. 103566.
  15. Li, Z., Jiang, Y., Guo, Q., Peng, Q. and Chen, C. (2018), "A weakly supervised solution for concrete cover crack detection based on adversarial training", Automat. Constr., 92, 255-269.
  16. Lim, J.H. and Lim, J.T. (2020), "Concrete crack detection algorithm using deep learning-based segmentation", Adv. Civil Eng., 2020.
  17. 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
  18. Ni, F., Yuan, Y. and Wang, Y. (2019), "Automatic detection of concrete cracks on a bridge deck using deep neural networks", J. Comput. Civil Eng., 33(3), p.04019007.
  19. Vinodhini, K.A. and Sidhaarth, K.R.A. (2022), "Automatic crack detection in the pavement with lion optimization algorithm using deep learning techniques", Int. J. Adv. Manuf. Technol., pp. 1-10. https://doi.org/10.1007/s00170-022-10724-z
  20. Vinodhini, V. and Sidhaarth, A. (2023), "An investigation study on automatic crack detection using image processing techniques", In: AIP Conference Proceedings, Vol. 2766, No. 1. https://doi.org/10.1063/5.0139421
  21. Vinodhini, K.A. and Sidhaarth, K.R.A. (2024), "Pothole detection in bituminous road using CNN with transfer learning", Measurement: Sensors, 31, p. 100940. https://doi.org/10.1016/j.measen.2023.100940
  22. Xu, Y., Bao, Y., Chen, J., Zheng, H. and Li, S.T. (2019), "Surface defect detection in welded joints using deep learning", Struct. Health Monitor., 18(3), 653-666. https://doi.org/10.1177/1475921718764873
  23. Ye, X.W., Jin, T. and Yun, C.B. (2019), "A deep learning-based approach for crack detection using convolutional neural network", Struct. Control Health Monitor., 26(11), p. e2416.
  24. You, Z., Li, Q. and Jiao, L. (2020), "Crack detection in images of concrete structures using a deep convolutional neural network", J. Comput. Civil Eng., 34(2), p. 04019051.
  25. Zhao, H., Shi, J., Qi, X., Wang, X. and Jia, J. (2017), "Pyramid scene parsing network", Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2881-2890.
  26. Zou, Q., Zhang, Z., Li, Q., Qi, X., Wang, Q. and Wang, S. (2018), "DeepCrack: Learning hierarchical convolutional features for crack detection", IEEE Transact. Image Process., 28(3), 1498-1512. https://doi.org/10.1109/TIP.2018.2878966