Real-Time Pothole Detection Using Deep Learning and YOLO Variants

References

[1] C. Koch and I. Brilakis, "Pothole detection in asphalt pavement images using edge detection and thresholding," IEEE Transactions on Intelligent Transportation Systems, vol. 12, no. 4, pp. 1256–1264, 2011.

[2] H. Ryu, Y. Kim, and S. Y. Shin, "Road anomaly and pothole detection using classical image processing and edge detection," International Journal of Computer and Communication Engineering, vol. 4, no. 3, pp. 182–189, 2015.

[3] S. K. Ryu, T. Kim, and Y. R. Kim, "Image-based pothole detection system using grayscale texture gradient evaluation for intelligent transportation," Mathematical Problems in Engineering, vol. 15, no. 1, pp. 112–120, 2015.

[4] T. Kim and S. K. Ryu, "Review and analysis of the limitations of classical image processing methodologies for continuous road monitoring," Journal of Emerging Trends in Computing and Information Sciences, vol. 5, no. 8, pp. 603–608, 2014.

[5] P. P. Prasad and S. R. Ram, "Road defect classification and pothole detection using HOG features combined with SVM," IEEE Transactions on Intelligent Transportation Systems, vol. 18, no. 5, pp. 1215–1225, 2017.

[6] E. Salari and X. Yu, "Pavement distress detection and severity classification using LBP feature extraction and random forest," Journal of Transportation Engineering, vol. 140, no. 1, pp. 58–66, 2014.

[7] Y. LeCun, Y. Bengio, and G. Hinton, "Deep learning," Nature, vol. 521, no. 7553, pp. 436–444, 2015.

[8] M. I. Jordan and T. M. Mitchell, "Machine learning: Trends, perspectives, and prospects," Science, vol. 349, no. 6245, pp. 255–260, 2015.

[9] A. Zhang, K. C. P. Wang, B. Li, and Y. Liu, "Automated pixel-level pavement defect detection on asphalt surfaces using a deep convolutional neural network," Computer-Aided Civil and Infrastructure Engineering, vol. 32, no. 10, pp. 805–819, 2017.

[10] Y. V. Silva and M. C. Oliveira, "Robust pothole and road surface defect detection using deep convolutional neural networks," IEEE Transactions on Intelligent Vehicles, vol. 3, no. 2, pp. 185–194, 2018.

[11] M. U. Ali, S. Saleem, and M. A. Khan, "Road surface pothole anomaly detection using transfer learning with ImageNet pre-trained backbones," IEEE Access, vol. 8, pp. 114383–114393, 2020.

[12] L. Jiao, F. Zhang, and F. Liu, "A survey of deep learning-based object detection," IEEE Access, vol. 7, pp. 128837–128868, 2019.

[13] 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.

[14] C. Y. Wang, A. Bochkovskiy, and H. Y. M. Liao, "YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors," in Proc. IEEE Conf. Computer Vision and Pattern Recognition (CVPR), pp. 7464–7475, 2023.

[15] Z. Zou, K. Chen, Z. Shi, Y. Guo, and J. Ye, "Object detection in 20 years: A survey," Proceedings of the IEEE, vol. 111, no. 3, pp. 257–276, 2023.

[16] A. R. R. Singh and V. K. Singh, "Real-time automated pothole detection framework using the YOLOv8 deep learning architecture," IEEE Transactions on Intelligent Transportation Systems, vol. 25, no. 4, pp. 3125–3135, 2023.

[17] M. H. F. Rahman and M. M. H. Shuvo, "Road defect severity classification and pothole identification utilizing the YOLOv8 object detection model," Journal of Computer Vision, vol. 18, no. 2, pp. 112–128, 2023.

[18] X. Wang, Y. Han, and X. Chen, "Convergence of edge computing and deep learning: A comprehensive survey," IEEE Communications Surveys and Tutorials, vol. 22, no. 2, pp. 869–904, 2020.

[19] J. Chen and X. Ran, "Deep learning with edge computing: A review," Proceedings of the IEEE, vol. 107, no. 8, pp. 1655–1674, 2019.

[20] H. R. Kumar, S. S. Patil, and K. M. Raj, "Cross-platform Flutter mobile application architecture for real-time deep learning model deployment at the edge," IEEE Access, vol. 9, pp. 45210–45222, 2021.

@article{1715445,
      author = {Jothivasan M, Revathi D},
      title = {Real-Time Pothole Detection Using Deep Learning and YOLO Variants},
      journal = {Iconic Research And Engineering Journals},
      year = {2026},
      volume = {9},
      number = {9},
      pages = {2040-2049},
      issn = {2456-8880},
      url = {https://www.irejournals.com/formatedpaper/1715445.pdf},
      abstract = {Road infrastructure deterioration, particularly in the form of potholes, poses a significant threat to global road safety, causing severe traffic accidents and substantial vehicle damage. Traditional methods for identifying road anomalies rely heavily on manual inspections and citizen reporting, which are inherently inefficient, labor-intensive, and prone to human error. To overcome these limitations, this research proposes an automated real-time pothole detection system leveraging deep learning architectures. Specifically, this study evaluates and compares the performance of YOLO variants, including YOLOv5, YOLOv7, YOLOv8, and YOLOv11, alongside the proposed YOLOv26n model. The models were trained and fine-tuned on an annotated, augmented dataset of diverse road-surface images to ensure robustness across varying environmental and lighting conditions. Experimental results demonstrate the efficacy of the proposed approach, with YOLOv26n achieving a mean Average Precision (mAP) of 89.1%, an overall detection accuracy of 87.4%, and a real-time inference speed of 42 FPS. This intelligent detection framework empowers municipalities to proactively prioritize road maintenance and enhance overall vehicular safety.},
      keywords = {Deep Learning, Object Detection, Pothole Detection, Road Safety, YOLOv26n},
      month = {March},
      doi = {https://doi.org/10.64388/IREV9I9-1715445}
  }