Detecting Road Depressions Based on Deep Learning Techniques

Mohammed Basim Omar
International Journal of Computational and Electronic Aspects in Engineering
Volume 6: Issue 3, July 2025, pp 153-167


Author's Information
Mohammed Basim Omar1 
Corresponding Author
1Department of Computer Science, College of Computer Science and Mathematics, Tikrit University, Tikrit, Iraq
mohammed.b@tu.edu.iq

Research Paper -- Peer Review
First online on – 12 July 2025

Open Access article under Creative Commons License

Cite this article –Mohammed Basim Omarl, “Detecting Road Depressions Based on Deep Learning Techniques”, International Journal of Computational and Electronic Aspects in Engineering, RAME Publishers, Volume 6, Issue 3, pp. 153-167, 2025.
https://doi.org/10.26706/ijceae.6.3.20250606


Abstract:-
Road infrastructure sustainability and public safety require monitoring and detection of potholes. Traditional methods of human-based traffic monitoring and pothole inspections are expensive, time-consuming and prone to human error. In this paper the usability of the YOLOv12 deep learning model to perform automated pothole detection in real-world conditions was examined. The authors generated a custom dataset consisting of 65 annotated video frames showcasing puddles or potholes which was used to train and validate the YOLOv12-based pothole detection model to determine its ability to accurately detect potholes and puddles. The YOLO series of models (you only look once) has shown success in real-time object detection in previous versions and YOLOv12 model is an advanced model with better detection capabilities. In this study, we have utilized the contextual workflow of preparing and preprocessing dataset, manual data annotation, and then training the YOLOv12 model to improve pothole detection. The experiments were analyzed using precision-recall curves, confusion matrices and F1-scores demonstrated YOLOv12's overall performance had high detection rates with minimal false positives. Visual confirmation of bounding box predictions provided additional assurance of accuracy and reliability in the model predictions. Overall the results demonstrate YOLOv12 is a promising solution for automated pothole detection with opportunities to reduce inspection expenses and add efficiency to road maintenance. Future work will evaluate scalability, possibilities in conjunction with sensor technologies and deploying for real-time applications on edge devices. The work contributes towards continued contributions to computer vision methods for road condition monitoring and supports growing transitions to smart infrastructure management systems.
Index Terms:-
Deep Learning; YOLO; Object Detection; Pothole Detection
REFERENCES
  1. K. R. Ahmed, "Smart pothole detection using deep learning based on dilated convolution," Sensors, vol. 21, no. 24, p. 8406, 2021.

  2. Y. Safyari, M. Mahdianpari, and H. Shiri, "A review of vision-based pothole detection methods using computer vision and machine learning," Sensors, vol. 24, no. 17, p. 5652, 2024.

  3. N. Ma et al., "Computer vision for road imaging and pothole detection: a state-of-the-art review of systems and algorithms," Transportation safety and Environment, vol. 4, no. 4, p. tdac026, 2022.

  4. N. Waisi, "Deep Feature Fusion Method for Images Classification," International Journal of Computational & Electronic Aspects in Engineering (IJCEAE), vol. 5, no. 4, 2024.

  5. M. H. Asad, S. Khaliq, M. H. Yousaf, M. O. Ullah, and A. Ahmad, "Pothole detection using deep learning: A real‐time and AI‐on‐the‐edge perspective," Advances in Civil Engineering, vol. 2022, no. 1, p. 9221211, 2022.

  6. S. F. M. Radzi, M. A. Abd Rahman, M. K. A. M. Yusof, N. S. M. Haniff, and R. F. Rahmat, "Computationally Enhanced UAV-based Real-Time Pothole Detection using YOLOv7-C3ECA-DSA algorithm," IEEE Access, 2025.

  7. H. M. Kanoosh, A. F. Abbas, N. N. Kamal, Z. M. Khadim, D. A. Majeed, and S. Algburi, "Image-Based CAPTCHA Recognition Using Deep Learning Models," in Proceedings of the Cognitive Models and Artificial Intelligence Conference, 2024, pp. 273-278.

  8. B. Bučko, E. Lieskovská, K. Zábovská, and M. Zábovský, "Computer vision based pothole detection under challenging conditions," Sensors, vol. 22, no. 22, p. 8878, 2022.

  9. B. Patel and A. Singhadia, "Automatic Number Plate Recognition System Using Improved Segmentation Method," International Journal of Engineering Trends and Technology, vol. 16, pp. 386-389, 10/25 2014, doi: 10.14445/22315381/IJETT-V16P277.

  10. M. Kamalesh, B. Chokkalingam, J. Arumugam, G. Sengottaiyan, S. Subramani, and M. A. Shah, "An intelligent real time pothole detection and warning system for automobile applications based on IoT technology," Journal of Applied Science and Engineering, vol. 24, no. 1, pp. 77-81, 2021.

  11. S.-K. Ryu, T. Kim, and Y.-R. Kim, "Image‐based pothole detection system for its service and road management system," Mathematical Problems in Engineering, vol. 2015, no. 1, p. 968361, 2015.

  12. N. Bhavana, M. M. Kodabagi, B. M. Kumar, P. Ajay, N. Muthukumaran, and A. Ahilan, "POT-YOLO: Real-Time Road Potholes Detection using Edge Segmentation based Yolo V8 Network," IEEE Sensors Journal, 2024.

  13. A. A. Hadi, "The Impact of Artificial Neural Network (ANN) on the Solar Energy Cells: A Review," International Journal of Computational & Electronic Aspects in Engineering (IJCEAE), vol. 5, no. 1, 2024.

  14. A. Naaman, "Using Machine Learning Models to Evaluate the Performance of Website in Iraqi Universities," International Journal of Computational and Electronic Aspects in Engineering, vol. 3, 12/09 2022, doi: 10.26706/ijceae.3.4.2211496.

  15. P. Gupta and M. Dixit, "Image-based road pothole detection using deep learning model," in 2022 14th International Conference on Computational Intelligence and Communication Networks (CICN), 2022: IEEE, pp. 59-64.

  16. Z. Haimer, K. Mateur, Y. Farhan, and A. Ait Madi, "Pothole detection: A performance comparison between YOLOv7 and YOLOv8," in 2023 9th International Conference on Optimization and Applications (ICOA), 2023: IEEE, pp. 1-7.

  17. D. S. Cherian, "Image Caption Generator Using CNN and LSTM," International Journal of Computational & Electronic Aspects in Engineering (IJCEAE), vol. 3, no. 2, 2022.

  18. W. Razzaq, "Categorization of Carcinogenic Abnormalities in Digital Mastography Using Deep Learning Algorithms," International Journal of Computational & Electronic Aspects in Engineering (IJCEAE), vol. 4, no. 4, 2023.

  19. A. Lincy, G. Dhanarajan, S. S. Kumar, and B. Gobinath, "Road pothole detection system," in ITM Web of Conferences, 2023, vol. 53: EDP Sciences, p. 01008.

  20. V. S. Bidve et al., "Pothole detection model for road safety using computer vision and machine learning," Int J Artif Intell ISSN, vol. 2252, no. 8938, p. 4481.

  21. R. Fan, U. Ozgunalp, B. Hosking, M. Liu, and I. Pitas, "Pothole detection based on disparity transformation and road surface modeling," IEEE Transactions on Image Processing, vol. 29, pp. 897-908, 2019.

  22. N. K. Rout, G. Dutta, V. Sinha, A. Dey, S. Mukherjee, and G. Gupta, "Improved pothole detection using YOLOv7 and ESRGAN," arXiv preprint arXiv:2401.08588, 2023.

  23. M. A. Ahmed et al., "Taxonomy, Open Challenges, Motivations, and Recommendations in Driver Behavior Recognition: A Systematic Review," Iraqi Journal for Computer Science and Mathematics, vol. 5, no. 3, p. 17, 2024.

  24. To view full paper, Download here


Publishing with