A Method for Detecting Pathologies in Concrete Structures Using Deep Neural Networks
Source abstract
Abstract
Pathologies in concrete structures, such as cracks, splintering, efflorescence, corrosion spots, and exposed steel bars, can be visually evidenced on the concrete surface. This paper proposes a method for automatically detecting these pathologies from images of the concrete structure. The proposed method uses deep neural networks to detect pathologies in these images. This method results in time savings and error reduction. The paper presents results in detecting the pathologies from wide-angle images containing the overall structure and also for the specific pathology identification task for cropped images of the region of the pathology. Identifying pathologies in cropped images, the classification task could be performed with 99.4% accuracy using cross-validation and classifying cracks. Wide images containing no, one, or several pathologies in the same image, the case of pathology detection, could be analyzed with the YOLO network to identify five pathology classes. The results for detection with YOLO were measured with mAP, mean Average Precision, for five classes of concrete pathology, reaching 11.80% for fissure, 19.22% for fragmentation, 5.62% for efflorescence, 27.24% for exposed bar, and 24.44% for corrosion. Pathology identification in concrete photos can be optimized using deep learning.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Infrastructure Maintenance and Monitoring · Concrete Corrosion and Durability · Geophysical Methods and Applications
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
UFMA/Computer Science Department, Universidade Federal do Maranhão, Campus do Bacanga, São Luís 65085-580, Brazil
UTAD/Engineering Department, Universidade de Trás-os-Montes e Alto Douro, 5000-801 Vila Real, Portugal
INESC-TEC—Institute for Systems and Computer Engineering, Technology and Science, 4200-465 Porto, Portugal
CMADE—Centre of Materials and Building Technologies, UTAD, 5000-801 Vila Real, Portugal
Funding
FCT (Portuguese Foundation for Science and Technology)
References (26)
Show source-provided references
1. James, K.W. (2016). Reinforced Concrete Mechanics and Design, Pearson Education Limited.
2. A review on five key sensors for monitoring of concrete structures10.1016/j.conbuildmat.2019.01.172 ↗
3. Safiuddin, M., Kaish, A.B.M.A., Woon, C.-O., and Raman, S.N. (2018). Early-Age Cracking in Concrete: Causes, Consequences, Remedial Measures, and Recommendations. Appl. Sci., 8.10.3390/app8101730 ↗
4. Deep Cascaded Neural Networks for Automatic Detection of Structural Damage and Cracks from Images10.5194/isprs-annals-V-2-2020-411-2020 ↗
5. Improved Crack Detection and Recognition Based on Convolutional Neural Network
6. Pal, M., Palevicius, P., Landauskas, M., Orinaite, U., Timofejeva, I., and Ragulskis, M. (2021). An Overview of Challenges Associated with Automatic Detection of Concrete Cracks in the Presence of Shadows. Appl. Sci., 11.10.3390/app112311396 ↗
7. Increasing the robustness of material-specific deep learning models for crack detection across different materials10.1016/j.engstruct.2019.110157 ↗
8. Kim, J.J., Kim, A.-R., and Lee, S.-W. (2020). Artificial Neural Network-Based Automated Crack Detection and Analysis for the Inspection of Concrete Structures. Appl. Sci., 10.10.3390/app10228105 ↗
9. Crack Detection on Concrete Images Using Classification Techniques in Machine Learning
10. A comparison of deep convolutional neural networks for image-based detection of concrete surface cracks
11. Autonomous Structural Visual Inspection Using Region-Based Deep Learning for Detecting Multiple Damage Types10.1111/mice.12334 ↗
12. Deep Learning-Based Crack Damage Detection Using Convolutional Neural Networks10.1111/mice.12263 ↗
13. Da Silva, W.R.L., and de Lucena, D.S. (2018). Concrete Cracks Detection Based on Deep Learning Image Classification. Proceedings, 2.10.3390/ICEM18-05387 ↗
14. Physical interpretation of machine learning-based recognition of defects for the risk management of existing bridge heritage10.1016/j.engfailanal.2023.107237 ↗
15. Machine-learning based vulnerability analysis of existing buildings10.1016/j.autcon.2021.103936 ↗
16. Classifying earthquake damage to buildings using machine learning10.1177/8755293019878137 ↗
17. (2022, March 01). Concrete Defect Bridge Image Dataset. Available online: https://zenodo.org/record/2620293#.YgLkC9_MKMo.
18. (2022, January 15). Concrete Crack Images for Classification. Available online: https://data.mendeley.com/datasets/5y9wdsg2zt/2.
19. Ozgenel, Ç.F., and Gonenç Sorguç, A. (2018, January 20–25). Performance Comparison of Pretrained Convolutional Neural Networks on Crack Detection in Buildings. Proceedings of the 35th ISARC, Berlin, Germany.10.22260/ISARC2018/0094 ↗
20. Zhang, L., Yang, F., Zhang, Y.D., and Zhu, Y.J. (2016, January 25–28). Road Crack Detection Using Deep Convolutional Neural Network. Proceedings of the 2016 IEEE International Conference on Image Processing (ICIP), Phoenix, AZ, USA.10.1109/ICIP.2016.7533052 ↗
21. Ai, S., and Kwon, J. (2020). Extreme Low-Light Image Enhancement for Surveillance Cameras Using Attention U-Net. Sensors, 20.10.3390/s20020495 ↗
22. Bochkovskiy, A., Wang, C.-Y., and Liao, H.-Y.M. (2020). YOLOv4: Optimal Speed and Accuracy of Object Detection. arXiv.
23. Redmon, J., Divvala, S., Girshick, R., and Farhadi, A. (2016). You Only Look Once: Unified, Real-Time Object Detection. arXiv.10.1109/CVPR.2016.91 ↗
24. Mundt, M., Majumder, S., Murali, S., Panetsos, P., and Ramesh, V. (2019, January 15–20). Meta-learning Convolutional Neural Architectures for Multi-target Concrete Defect Classification with the COncrete DEfect BRidge IMage Dataset. Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA.10.1109/CVPR.2019.01145 ↗
25. A deep learning-based approach for automatic detection of concrete cracks below the waterline10.21595/vp.2022.22845 ↗
26. Rasool, M., Ismail, N.A., Boulila, W., Ammar, A., Samma, H., Yafooz, W.M.S., and Emara, A.-H.M. (2022). A Hybrid Deep Learning Model for Brain Tumour Classification. Entropy, 24.10.3390/e24060799 ↗