Volume 15, Issue 5

AI-Based Road Surface Condition and Pothole Severity Estimation System

Author

Mr. Karunanidhi. P, Adhithya M, Adhithya M, Deepak G, Kathiravan T

Abstract

Road surface deterioration and pothole formation are major problems that affect transportation safety, vehicle operating cost, and passenger comfort. Traditional road inspection methods rely on manual surveys, public complaints, and periodic monitoring, which are time-consuming, expensive, and inefficient for large-scale road networks. Recent developments in Artificial Intelligence and computer vision enable automated road condition monitoring using image-based analysis. This paper presents an AI-based road surface condition and pothole severity estimation system that integrates deep learning–based detection, geometric parameter estimation, Road Quality Index (RQI) computation, and risk analysis. The proposed system uses a YOLO/CNN model to detect potholes from road images and video frames. The detected pothole region is analyzed to estimate its area using pixel-to-real-world conversion and its depth using intensity variation. Based on these parameters, RQI and a risk factor are calculated to evaluate road condition and prioritize maintenance. The system also extracts GPS coordinates to identify the exact location of potholes and generates automated email reports for authorities. The proposed approach reduces manual inspection effort, enables real-time monitoring, improves maintenance planning, and enhances road safety. The system can be integrated with intelligent transportation systems and smart city infrastructure.

REFERENCES

1. R. Maeda, H. Sekimoto, T. Seto, T. Kashiyama, and H. Omata, “Road damage detection and classification using deep neural networks with smartphone images,” Comput. Aided Civ. Infrastruct. Eng., vol. 33, no. 12, pp. 1127–1141, Dec. 2018.
2. S. Arya, T. Maeda, H. Sekimoto, and T. Seto, “Deep learning-based road damage detection using YOLO,” in Proc. IEEE Int. Conf. Image Process. (ICIP), 2020, pp. 1093–1097.
3. J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, “You Only Look Once: Unified, real-time object detection,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), 2016, pp. 779–788.
4. J. Redmon and A. Farhadi, “YOLOv3: An incremental improvement,” arXiv:1804.02767, 2018.
5. A. Bochkovskiy, C.-Y. Wang, and H.-Y. M. Liao, “YOLOv4: Optimal speed and accuracy of object detection,” arXiv:2004.10934, 2020.
6. K. Gopalakrishnan, S. Khaitan, A. Choudhary, and A. Agrawal, “Deep convolutional neural networks with transfer learning for computer vision-based pavement distress detection,” Constr. Build. Mater., vol. 157, pp. 322–330, Dec. 2017.
7. J. Kim and S. Ryu, “Pavement distress detection using convolutional neural networks,” IEEE Trans. Intell. Transp. Syst., vol. 21, no. 2, pp. 726–735, Feb. 2020.
8. M. Koch and I. Brilakis, “Pothole detection in asphalt pavement images,” Adv. Eng. Informat., vol. 25, no. 3, pp. 507–515, Aug. 2011.
9. H. Oliveira and P. L. Correia, “Automatic road crack detection and characterization,” IEEE Trans. Intell. Transp. Syst., vol. 14, no. 1, pp. 155–168, Mar. 2013.
10. S. Chambon and J.-M. Moliard, “Automatic road pavement assessment with image processing: Review and comparison,” Int. J. Geophys., vol. 2011, pp. 1–20, 2011.
11. S. R. Chandrasekhar, K. S. Reddy, and M. V. R. Prasad, “Automatic pothole detection using deep learning and image processing,” in Proc. IEEE Int. Conf. Adv. Comput. Commun. Syst. (ICACCS), 2021, pp. 1124–1129.
12. Y. Zhang, F. Zhang, and C. Liu, “Vision-based road surface condition monitoring using deep learning,” IEEE Access, vol. 9, pp. 120–132, 2021.
13. ASTM D6433-20, “Standard practice for roads and parking lots pavement condition index surveys,” ASTM Int., West Conshohocken, PA, USA, 2020.
14. D. G. Lowe, “Distinctive image features from scale-invariant keypoints,” Int. J. Comput. Vis., vol. 60, no. 2, pp. 91–110, Nov. 2004.
15. R. Szeliski, Computer Vision: Algorithms and Applications. London, U.K.: Springer, 2011.

DOI

https://doi.org/10.62226/ijarst20262659

PAGES : 1909-1914 | 10 VIEWS | 7 DOWNLOADS

Download Full Article