A Pavement Crack Detection and Evaluation Framework for a UAV Inspection System Based on Deep Learning
Source abstract
Abstract
Existing studies often lack a systematic solution for an Unmanned Aerial Vehicles (UAV) inspection system, which hinders their widespread application in crack detection. To enhance its substantial practicality, this study proposes a formal and systematic framework for UAV inspection systems, specifically designed for automatic crack detection and pavement distress evaluation. The framework integrates UAV data acquisition, deep-learning-based crack identification, and road damage assessment in a comprehensive and orderly manner. Firstly, a flight control strategy is presented, and road crack data are collected using DJI Mini 2 UAV imagery, establishing high-quality UAV crack image datasets with ground truth information. Secondly, a validation and comparison study is conducted to enhance the automatic crack detection capability and provide an appropriate deployment scheme for UAV inspection systems. This study develops automatic crack detection models based on mainstream deep learning algorithms (namely, Faster-RCNN, YOLOv5s, YOLOv7-tiny, and YOLOv8s) in urban road scenarios. The results demonstrate that the Faster-RCNN algorithm achieves the highest accuracy and is suitable for the online data collection of UAV and offline inspection at work stations. Meanwhile, the YOLO models, while slightly lower in accuracy, are the fastest algorithms and are suitable for the lightweight deployment of UAV with online collection and real-time inspection. Quantitative measurement methods for road cracks are presented to assess road damage, which will enhance the application of UAV inspection systems and provide factual evidence for the maintenance decisions made by road authorities.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Infrastructure Maintenance and Monitoring · Non-Destructive Testing Techniques · Image and Object Detection Techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Earth Sciences and Spatial Information Engineering, Hunan University of Sciences and Technology, Xiangtan 411201, China
Funding
China Postdoctoral Science Foundation · Hunan Provincial Natural Science Foundation · Chinese national college students innovation and entrepreneurship training program
References (34)
Show source-provided references
1. Automatic Road Crack Recognition Based on Deep Learning Networks from UAV Imagery10.5194/isprs-annals-X-4-W1-2022-685-2023 ↗
2. Pavement distress detection using convolutional neural networks with images captured via UAV10.1016/j.autcon.2021.103991 ↗
3. Pavement Crack Detection with Deep Learning Based on Attention Mechanism
4. Qi, S., Li, G., Chen, D., Chai, M., Zhou, Y., Du, Q., Cao, Y., Tang, L., and Jia, H. (2022). Damage Properties of the Block-Stone Embankment in the Qinghai–Tibet Highway Using Ground-Penetrating Radar Imagery. Remote Sens., 14.10.3390/rs14122950 ↗
5. Guo, S., Xu, Z., Li, X., and Zhu, P. (2022). Detection and Characterization of Cracks in Highway Pavement with the Amplitude Variation of GPR Diffracted Waves: Insights from Forward Modeling and Field Data. Remote Sens., 14.10.3390/rs14040976 ↗
6. Salman, M., Mathavan, S., Kamal, K., and Rahman, M. (2013, January 6–9). Pavement crack detection using the Gabor filter. Proceedings of the 16th international IEEE Conference on Intelligent Transportation Systems (ITSC 2013), The Hague, The Netherlands.10.1109/ITSC.2013.6728529 ↗
7. Evaluating pavement cracks with bidimensional empirical mode decomposition10.1155/2008/861701 ↗
8. Deep machine learning approach to develop a new asphalt pavement condition index10.1016/j.conbuildmat.2020.118513 ↗
9. ImageNet classification with deep convolutional neural networks10.1145/3065386 ↗
10. One stage detector (RetinaNet)-based crack detection for asphalt pavements considering pavement distresses and surface objects10.1007/s13349-020-00447-8 ↗
11. Pavement Crack Automatic Identification Method Based on Improved Mask R-CNN Model
12. Crack detection of asphalt pavement based on improved faster RCNN
13. Xu, X., Zhao, M., Shi, P., Ren, R., He, X., Wei, X., and Yang, H. (2022). Crack detection and comparison study based on faster R-CNN and mask R-CNN. Sensors, 22.10.3390/s22031215 ↗
14. Automated asphalt highway pavement crack detection based on deformable single shot multi-box detector under a complex environment10.1109/ACCESS.2021.3125703 ↗
15. Development of an automatic detector of cracks in concrete using machine learning10.1016/j.proeng.2017.01.418 ↗
16. Jiang, Y.T., Yan, H.T., Zhang, Y.R., Wu, K.Q., Liu, R.Y., and Lin, C.Y. (2023). RDD-YOLOv5: Road Defect Detection Algorithm with Self-Attention Based on Unmanned Aerial Vehicle Inspection. Sensors, 23.10.3390/s23198241 ↗
17. Road damage detection using UAV images based on multi-level attention mechanism10.1016/j.autcon.2022.104613 ↗
18. UAV vision detection method for crane surface cracks based on Faster R-CNN and image segmentation10.1007/s13349-022-00577-1 ↗
19. Xiang, X., Hu, H., Ding, Y., Zheng, Y., and Wu, S. (2023). GC-YOLOv5s: A Lightweight Detector for UAV Road Crack Detection. Appl. Sci., 13.10.3390/app131911030 ↗
20. Wang, X., Gao, H., Jia, Z., and Li, Z. (2023). BL-YOLOv8: An Improved Road Defect Detection Model Based on YOLOv8. Sensors, 23.10.3390/s23208361 ↗
21. An improved deep learning convolutional neural network for crack detection based on UAV images10.1007/s41062-023-01209-3 ↗
22. Zhao, Y., Zhou, L., Wang, X., Wang, F., and Shi, G. (2023). Highway Crack Detection and Classification Using UAV Remote Sensing Images Based on CrackNet and CrackClassification. Appl. Sci., 13.10.3390/app13127269 ↗
23. Liu, K. (2023). Learning-based defect recognitions for autonomous uav inspections. arXiv.
24. Object detection in 20 years: A survey10.1109/JPROC.2023.3238524 ↗
25. Bubbliiiing (2024, January 26). Faster-RCNN-PyTorch[CP]. Available online: https://github.com/bubbliiiing/faster-rcnn-pytorch.
26. UItralyics (2024, January 26). YOLOv5[CP]. Available online: https://github.com/ultralytics/yolov5.
27. Wong, K.Y. (2024, January 26). YOLOv7[CP]. Available online: https://github.com/WongKinYiu/yolov7.
28. Ultralytics (2024, January 26). YOLOv8[CP]. Available online: https://github.com/ultralytics/ultralytics.
29. Faster r-cnn: Towards real-time object detection with region proposal networks
30. A systematic study of the class imbalance problem in convolutional neural networks10.1016/j.neunet.2018.07.011 ↗
31. Sami, A.A., Sakib, S., Deb, K., and Sarker, I.H. (2023). Improved YOLOv5-Based Real-Time Road Pavement Damage Detection i-n Road Infrastructure Management. Algorithms, 16.10.3390/a16090452 ↗
32. Faramarzi, M. (2020). Road damage detection and classification using deep neural networks (YOLOv4) with smartphone images. SSRN.10.2139/ssrn.3627382 ↗
33. (2017). Technical Code of Maintenance for Urban Road (Standard No. CJJ36-2016). Available online: https://www.mohurd.gov.cn/gongkai/zhengce/zhengcefilelib/201702/20170228_231174.html.
34. (2018). Highway Performance Assessment Standards (Standard No. JTG 5210-2018). Available online: https://xxgk.mot.gov.cn/2020/jigou/glj/202006/t20200623_3313114.html.