Method and Research of Concrete Pavement Crack Detection Based on Convolution Neural Network
DOI:
https://doi.org/10.54097/hset.v56i.10105Keywords:
Concrete Pavement, Mendeley Data, Convolution Neural Network, Crack Detection, Civil EngineeringAbstract
Being essential to civil engineering, concrete pavement is prone to cracks in the process of use, which affects the bearing capacity and driving safety of concrete roads. In this paper, a convolution neural network (CNN) is used to identify concrete pavement cracks, with the Concrete Crack Images for Classification of Mendeley Data utilized to test the CNN performance. Mendeley Data is used to compare the performance of concrete pavement crack detection between CNN and other three classical network models. The experimental results show that Accuracy, Precision, Recall, and F1-Score are 0.97, 0.98, 0.96, and 0.97 respectively. Compared with image recognition methods such as RNN-LSTM, Contour Threshold, and ResMLP, the Accuracy of CNN is the highest in this paper, which proves that CNN has high recognition performance in concrete pavement crack recognition. Besides, it is of high reference value for the behavior and decision-making of concrete pavement crack recognition.
Downloads
References
Cha, Y. J., Choi, W. & Buyukozturk, O. (2017). Deep learning-based crack damage detection using convolutional neural networks. Computer-Aided Civil and Infrastructure Engineering. 32. 361-378. 10.1111/mice.12263.
Koch, C., Doycheva, K., Kasi, V., Akinci, B. & Fieguth, P. (2015). A review on computer vision based defect detection and condition assessment of concrete and asphalt civil infrastructure. Advanced Engineering Informatics. 29. 10.1016/j.aei.201 5. 01.008.
Shanaka, K. B., Thilakarathna, S., Perera, J., Arashpour, M., Sharafi, P., Teodosio, B., Shringi, A. & Mendis, P. (2022). Artificial intelligence and smart vision for building and construction 4.0: Machine and deep learning methods and applications. Automation in Construction. 141. 104440. 10.1016/j.autcon.2022.104440.
Wu, X. Y., Ma, J. F., Sun, Y., Zhao, C. Q. & Basu, A. (2021). Multi-scale deep pixel distribution learning for concrete crack detection. 6577-6583. 10.1109/ICPR488 06.2021.9413312.
Eslam, M. A., Abobakr, A. S. & Alfalah, G. (2021). Analyzing concrete cracks’ characteristics using meta-heuristic computing. 10.1109/DASA53625.2021.9682352.
Gupta, S., Lin, Y. A., Lee, H. J., Buscheck, J., Wu, R. Z., Lynch, J., Garg, N. & Loh, K. (2021). In situ crack mapping of large-scale self-sensing concrete pavements using electrical resistance tomography. Cement and Concrete Composites. 122. 104154. 10.1016/j.cemconcomp.2021.104154.
Qu, Z., Chen, W., Wang, S. Y., Yi, T. M. & Liu, L. (2021). A crack detection algorithm for concrete pavement based on attention mechanism and multi-features fusion. IEEE Transactions on Intelligent Transportation Systems. pp. 1-10. 10.1109/ TITS.2021.3106647.
Yu, Y., Samali, B., Rashidi, M., Mohammadi, M., Nguyen, T. & Zhang, G. (2022). Vision-based concrete crack detection using a hybrid framework considering noise effect. Journal of Building Engineering. 61. 105246. 10.1016/j.jobe.2022.105246.
Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z. H., Karpathy, A., Khosla, A., Bernstein, M., Berg, A. & Li, F. F. (2014). ImageNet large scale visual recognition challenge. International Journal of Computer Vision. 115. 10.1007/s11263-015-0816-y.
Yue, Z. Y., Gao, F., Xiong, X., Wang, J., Huang, T., Yang, E. F. & Zhou, H. Y. (2021). A novel semi-supervised convolutional neural network method for synthetic aperture radar image recognition. Cognitive Computation. 13. 10.1007/s12559-019-0 9639-x.
Wang, J. J., Zhong, Y. F., Zheng, Z., Ma, A. L. & Zhang, L. P. (2020). RSNet: The search for remote sensing deep neural networks in recognition tasks. 10.1109/TGRS.2020.3001401.
Mujahid, A., Awan, M., Yasin, A., Mohammed, M., Damaševičius, R., Maskeliunas, R. & Hameed, K. (2021). Real-time hand gesture recognition based on deep learning YOLOv3 model. Applied Sciences. 11. 4164. 10.3390/app11094164.
Wu, D., Zhang, C. J., Li, J., Rong, R., Wu, H. Y. & Xu, Y. M. (2021). Forest fire recognition based on feature extraction from multi-view images. Traitement du Signal. 38. 775-783. 10.18280/ts.380324.
Özgenel, Ç. & Sorguc, A. (2018). Performance comparison of pretrained convolutional neural networks on crack detection in buildings. 10.22260/ISARC2018 /0094.
Zhang, L. F., Yang, Y., Zhang, D. & Zhu, Y. J. (2016). Road crack detection using deep convolutional neural network. 2016 IEEE International Conference on Image Processing (ICIP), Phoenix, AZ, USA, pp. 3708-3712, doi: 10.1109/ICIP.2016.75330 52.
Abdolrasol, M., Hussain, S., Ustun, T. S., Sarker, M., Hannan, M. A., Mohamed, R., Ali, J., Mekhilef, S. & Milad, A. (2021). Artificial neural networks based optimization techniques: A review. Electronics. 10. 2689. 10.3390/electronics102126 89.
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
