Application of Various YOLO Models for Computer Vision-Based Real-Time Pothole Detection
Source abstract
Abstract
Pothole repair is one of the paramount tasks in road maintenance. Effective road surface monitoring is an ongoing challenge to the management agency. The current pothole detection, which is conducted image processing with a manual operation, is labour-intensive and time-consuming. Computer vision offers a mean to automate its visual inspection process using digital imaging, hence, identifying potholes from a series of images. The goal of this study is to apply different YOLO models for pothole detection. Three state-of-the-art object detection frameworks (i.e., YOLOv4, YOLOv4-tiny, and YOLOv5s) are experimented to measure their performance involved in real-time responsiveness and detection accuracy using the image set. The image set is identified by running the deep convolutional neural network (CNN) on several deep learning pothole detectors. After collecting a set of 665 images in 720 × 720 pixels resolution that captures various types of potholes on different road surface conditions, the set is divided into training, testing, and validation subsets. A mean average precision at 50% Intersection-over-Union threshold (mAP_0.5) is used to measure the performance of models. The study result shows that the mAP_0.5 of YOLOv4, YOLOv4-tiny, and YOLOv5s are 77.7%, 78.7%, and 74.8%, respectively. It confirms that the YOLOv4-tiny is the best fit model for pothole detection.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Infrastructure Maintenance and Monitoring · Advanced Neural Network Applications · Vehicle License Plate Recognition
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Civil Engineering, Kyungpook National University, Daegu 41566, Korea
Department of Architectural Engineering, Kyungpook National University, Daegu 41566, Korea
Funding
National Research Foundation of Korea
References (35)
Show source-provided references
1. Harvey, J., Al-Qadi, I.L., Ozer, H., and Flintsch, G. (2020, January 3–6). Pavement, Roadway, and Bridge Life Cycle Assessment 2020. Proceedings of the International Symposium on Pavement. Roadway, and Bridge Life Cycle Assessment 2020, LCA 2020, Sacramento, CA, USA.10.1201/9781003092278 ↗
2. Feasibility study of asphalt pavement pothole properties measurement using 3D line laser technology10.1016/j.ijtst.2020.07.004 ↗
3. Wang, H.W., Chen, C.H., Cheng, D.Y., Lin, C.H., and Lo, C.C. (2015). A real-time pothole detection approach for intelligent transportation system. Math. Probl. Eng., 2015.10.1155/2015/869627 ↗
4. Li, W., Shen, Z., and Li, P. (2019, January 14–15). Crack detection of track plate based on YOLO. Proceedings of the 12th International Symposium on Computational Intelligence and Design (ISCID), Hangzhou, China.10.1109/ISCID.2019.10086 ↗
5. Automatic road defect detection by textural pattern recognition based on AdaBoost10.1111/j.1467-8667.2011.00736.x ↗
6. Autonomous structural visual inspection using region-based deep learning for detecting multiple damage types10.1111/mice.12334 ↗
7. Unsupervised approach for autonomous pavement-defect detection and quantification using an inexpensive depth sensor10.1061/(ASCE)CP.1943-5487.0000245 ↗
8. Autonomous pothole detection using deep region-based convolutional neural network with cloud computing
9. Silva, L.A., Sanchez San Blas, H., Peral García, D., Sales Mendes, A., and Villarubia González, G. (2020). An architectural multi-agent system for a pavement monitoring system with pothole recognition in UAV images. Sensors, 20.10.3390/s20216205 ↗
10. Assistive intelligent transportation systems: The need for user localization and anonymous disability identification10.1109/MITS.2017.2666579 ↗
11. Imagenet classification with deep convolutional neural networks
12. Redmon, J., and Farhadi, A. (2017, January 21–26). YOLO9000: Better, Faster, Stronger. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.10.1109/CVPR.2017.690 ↗
13. Redmon, J., and Farhadi, A. (2018). Yolov3: An incremental improvement. arXiv.
14. Bochkovskiy, A., Wang, C.Y., and Liao HY, M. (2020). Yolov4: Optimal speed and accuracy of object detection. arXiv.
15. Malta, A., Mendes, M., and Farinha, T. (2021). Augmented Reality Maintenance Assistant Using YOLOv5. Appl. Sci., 11.10.3390/app11114758 ↗
16. Jiang, Z., Zhao, L., Li, S., and Jia, Y. (2020). Real-time object detection method based on improved YOLOv4-tiny. arXiv.
17. LeCun, Y., Kavukcuoglu, K., and Farabet, C. (June, January 30). Convolutional networks and applications in vision. Proceedings of the 2010 IEEE International Symposium on Circuits and Systems, Paris, France.10.1109/ISCAS.2010.5537907 ↗
18. A 3D-CNN model with CT-based parametric response mapping for classifying COPD subjects10.1038/s41598-020-79336-5 ↗
19. Park, S.S., Tran, V.T., Doan, N.P., and Hwang, K.B. (2021). Evaluation of Damage Level for Ground Settlement Using the Convolutional Neural Network. CIGOS 2021, Emerging Technologies and Applications for Green Infrastructure, Springer.10.1007/978-981-16-7160-9_128 ↗
20. Ho, T.T., Park, J., Kim, T., Park, B., Lee, J., Kim, J.Y., and Choi, S. (2021). Deep learning models for predicting severe progression in COVID-19-infected patients: Retrospective study. JMIR Med. Inform., 9.10.2196/24973 ↗
21. Forecasting damage mechanics by deep learning
22. Do, D.T., Lee, J., and Nguyen-Xuan, H. (2019). Fast evaluation of crack growth path using time series forecasting. Eng. Fract. Mech., 218.10.1016/j.engfracmech.2019.106567 ↗
23. Transfer learning for vehicle detection using two cameras with different focal lengths10.1016/j.ins.2019.11.034 ↗
24. Dinh, V.Q., Nguyen, T.D., and Nguyen, P.H. (2020, January 26–27). Stereo Domain Translation for Denoising and Super-Resolution Using Correlation Loss. Proceedings of the 7th NAFOSTED Conference on Information and Computer Science (NICS), Ho Chi Minh City, Vietnam.10.1109/NICS51282.2020.9335830 ↗
25. Girshick, R., Donahue, J., Darrell, T., and Malik, J. (2014, January 23–28). Rich feature hierarchies for accurate object detection and semantic segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Columbus, OH, USA.10.1109/CVPR.2014.81 ↗
26. Girshick, R. (2015, January 7–13). Fast r-cnn. Proceedings of the IEEE International Conference on Computer Vision, Santiago, Chile.10.1109/ICCV.2015.169 ↗
27. Faster r-cnn: Towards real-time object detection with region proposal networks
28. He, K., Gkioxari, G., Dollár, P., and Girshick, R. (2017, January 22–29). Mask r-cnn. Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy.10.1109/ICCV.2017.322 ↗
29. Cai, Z., and Vasconcelos, N. (2018, January 18–23). Cascade r-cnn: Delving into high quality object detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.10.1109/CVPR.2018.00644 ↗
30. Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.Y., and Berg, A.C. (2016, January 11–14). Ssd: Single shot multibox detector. Proceedings of the European Conference on Computer Vision, Amsterdam, The Netherlands.10.1007/978-3-319-46448-0_2 ↗
31. Redmon, J., Divvala, S., Girshick, R., and Farhadi, A. (2016, January 11–14). You only look once: Unified, real-time object detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Amsterdam, The Netherlands.10.1109/CVPR.2016.91 ↗
32. Lin, T.Y., Dollár, P., Girshick, R., He, K., Hariharan, B., and Belongie, S. (2017, January 21–26). Feature pyramid networks for object detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.10.1109/CVPR.2017.106 ↗
33. Tinier-YOLO: A real-time object detection method for constrained environments10.1109/ACCESS.2019.2961959 ↗
34. Pavement distress detection and classification based on YOLO network10.1080/10298436.2020.1714047 ↗
35. Rahman, A., and Patel, S. (2021, November 21). Annotated Potholes Image Dataset. Kaggle. Available online: https://www.kaggle.com/chitholian/annotated-potholes-dataset.