International Research Journal of Innovations in Engineering and Technology - IRJIET International Open Access, Monthly, Peer Reviewed, Reputed Journal ISSN (online): 2581-3048

Impact Factor (2025): 6.9

DOI Prefix: 10.47001/IRJIET

AI Powered Pothole Detection Severity Analysis and Reporting System

Abstract

Road infrastructure plays a vital role in ensuring safe and efficient transportation. Potholes are one of the major causes of road accidents, vehicle damage, and traffic congestion, particularly in urban and semi-urban areas. Conventional pothole detection and reporting methods rely on manual inspection and public complaints, which are time-consuming, inefficient, and often lack proper severity assessment. To address these limitations, this paper proposes an AI Powered Pothole Detection Severity Analysis and Reporting System designed to automate the identification, classification, and reporting of potholes using artificial intelligence techniques.

The proposed system is designed to analyze road surface images captured through cameras or mobile devices and detect potholes using AI-based image processing models. Once detected, the system is intended to evaluate the severity of potholes based on visual features such as size, area, and depth indicators. The analyzed information is structured into reports and associated with location data to support effective road maintenance planning.

The primary objective of the proposed system is to enhance road safety, reduce dependency on manual inspection, and enable severity-based prioritization of pothole repairs. The system is expected to provide a scalable and efficient solution for smart road infrastructure monitoring. Future work includes full-scale implementation, real-time processing, integration with GPS-based location tracking, and deployment through web or mobile platforms.

Country : India

1 Aditya Kale2 Omkar Ankush3 Abhishek Wankhede4 Rajvardhan Somase5 Prof. Mayuri Narudkar

  1. Student, Department of Artificial Intelligence & Machine Learning Engineering, Ajeenkya D.Y. Patil School of Engineering Polytechnic, Pune, Maharashtra, India
  2. Student, Department of Artificial Intelligence & Machine Learning Engineering, Ajeenkya D.Y. Patil School of Engineering Polytechnic, Pune, Maharashtra, India
  3. Student, Department of Artificial Intelligence & Machine Learning Engineering, Ajeenkya D.Y. Patil School of Engineering Polytechnic, Pune, Maharashtra, India
  4. Student, Department of Artificial Intelligence & Machine Learning Engineering, Ajeenkya D.Y. Patil School of Engineering Polytechnic, Pune, Maharashtra, India
  5. Guide, Professor, Department of Artificial Intelligence & Machine Learning Engineering, Ajeenkya D.Y. Patil School of Engineering Polytechnic, Pune, Maharashtra, India

IRJIET, Volume 10, Issue 3, March 2026 pp. 24-28

doi.org/10.47001/IRJIET/2026.103005

Full Paper
Download

References

  1. S. Maeda, Y. Sekimoto, T. Seto, T. Kashiyama, and H. Omata, “Road damage detection and classification using deep neural networks with smartphone images,” Computer-Aided Civil and Infrastructure Engineering, vol. 33, no. 12, pp. 1127–1141, 2018.
  2. J. Arya, A. Pratap, and S. Tiwari, “Pothole detection using image processing and machine learning,” International Journal of Engineering Research and Technology (IJERT), vol. 9, no. 6, pp. 120–124, 2020.
  3. M. Jahanshahi, S. F. Masri, G. S. Sukhatme, and B. F. Spencer Jr., “Automated damage detection and classification of civil infrastructure using computer vision,” Structural Control and Health Monitoring, vol. 18, no. 7, pp. 806–825, 2011.
  4. R. Amhaz, S. Chambon, J. Idier, and V. Baltazart, “Automatic road crack detection using random structured forests,” IEEE Transactions on Intelligent Transportation Systems, vol. 17, no. 12, pp. 3434–3445, Dec. 2016.
  5. Zhang, K. C. P. Wang, Y. Fei, Y. Liu, and G. Chen, “Automated pixel-level pavement crack detection on 3D asphalt surfaces using a deep-learning network,” Computer-Aided Civil and Infrastructure Engineering, vol. 32, no. 10, pp. 805–819, 2017.
  6. J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, “You only look once: Unified, real-time object detection,” in Proc. IEEE Conf. Computer Vision and Pattern Recognition (CVPR), pp. 779–788, 2016.
  7. K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” in Proc. IEEE Conf. Computer Vision and Pattern Recognition (CVPR), pp. 770–778, 2016.
  8. Kochhar, S. Kumar, and R. Gupta, “Smart pothole detection system using image processing and GPS,” International Journal of Computer Applications, vol. 182, no. 44, pp. 1–5, 2019.

Copyright @ 2026-2017 IRJIET. All Right Reserved.

Developed by Byzero Technologies