Computer Vision-Based Automated Detection of Road Surface Defects for Intelligent Transportation Infrastructure

Authors

  • Asmitha Kumari, H. Sarker Author

Keywords:

: Computer vision, road surface defects, deep learning, YOLO, pavement crack detection, pothole detection, object detection, intelligent transportation systems, road infrastructure monitoring

Abstract

Road surface defects such as cracks, potholes and pavement deterioration are important factors affecting road safety, transportation efficiency and infrastructure maintenance. Conventional road inspection methods generally depend on manual observation and periodic field surveys, which may require considerable time, labour and financial resources. Recent developments in computer vision and deep learning provide opportunities for automating road condition assessment through digital images captured using vehicle-mounted cameras and mobile devices. This paper presents a computer vision-based framework for automated detection and classification of road surface defects for intelligent transportation infrastructure. The proposed framework uses image preprocessing, deep-learning-based object detection and defect localization to identify common pavement damages, including longitudinal cracks, transverse cracks, alligator cracks and potholes. A YOLO-based detection architecture is considered to support efficient image analysis and potential real-time deployment. The proposed approach also incorporates image enhancement, data augmentation, multi-scale feature extraction and confidence-based detection filtering to improve robustness under varying environmental and road conditions. The RDD2022 dataset is considered for model development and evaluation because of its multi-national road image collection and annotated pavement damage categories. Detection performance is intended to be evaluated using precision, recall, mean average precision, inference time and model size. The framework provides a basis for integrating automated pavement inspection with intelligent transportation systems, supporting road maintenance prioritization, infrastructure monitoring and data-driven maintenance planning.

References

1. H. 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, doi: 10.1111/mice.12387.

2. D. Arya, H. Maeda, S. K. Ghosh, D. Toshniwal, and Y. Sekimoto, “RDD2020: An annotated image dataset for automatic road damage detection using deep learning,” Data in Brief, vol. 36, Art. no. 107133, 2021, doi: 10.1016/j.dib.2021.107133.

3. D. Arya et al., “RDD2022: A multi-national image dataset for automatic road damage detection,” Geoscience Data Journal, vol. 11, no. 4, pp. 846–862, 2024, doi: 10.1002/gdj3.260.

4. X. Chen, S. Yongchareon, and M. Knoche, “A review on computer vision and machine learning techniques for automated road surface defect and distress detection,” Semantic Computing, vol. 1, no. 4, 2023, doi: 10.3233/SCS-230001.

5. H. Yao, Y. Fan, X. Wei et al., “Research and optimization of YOLO-based method for automatic pavement defect detection,” Electronic Research Archive, vol. 32, no. 3, pp. 1708–1730, 2024, doi: 10.3934/era.2024078.

6. D. Arya, H. Maeda, S. K. Ghosh, D. Toshniwal, H. Omata, T. Kashiyama, and Y. Sekimoto, “Crowdsensing-based Road Damage Detection Challenge (CRDDC'2022),” in Proc. 2022 IEEE International Conference on Big Data (Big Data), Osaka, Japan, 2022, pp. 6378–6386, doi: 10.1109/BigData55660.2022.10021040.

7. Bajarang Bhagwat, V. (2023). Optimizing Payroll to General Ledger Reconciliation: Identifying Discrepancies and Enhancing Financial Accuracy. JOURNAL OF ADVANCE AND FUTURE RESEARCH, 1 (4).

8. Koneni, C., & Lokula, S. (2026, June). Silent Data Corruption in Distributed Genai-Augmented Data Pipelines: an Empirical Study of Hallucination-Induced Failure Propagation. In 2026 IEEE 46th International Conference on Distributed Computing Systems Workshops (ICDCSW) (pp. 137-143). IEEE.

9. Addepalli, D. N. V. (2026). An Autonomous Agentic Ai Framework For Coverage-Guided Chaos Engineering And Resilience Optimisation In Cloud-Native Distributed Systems. International Journal of Artificial Intelligence and Computer Electronics, 2(1), 80-89.

10. Addepalli, D. N. V. (2026). An Autonomous Agentic Ai Framework For Coverage-Guided Chaos Engineering And Resilience Optimisation In Cloud-Native Distributed Systems. International Journal of Artificial Intelligence and Computer Electronics, 2(1), 80-89.

11. Koneni, C., & Lokula, S. (2026, June). Silent Data Corruption in Distributed Genai-Augmented Data Pipelines: an Empirical Study of Hallucination-Induced Failure Propagation. In 2026 IEEE 46th International Conference on Distributed Computing Systems Workshops (ICDCSW) (pp. 137-143). IEEE.

12. Pal, A. (2026). Productivity vs. Compliance: The New Engineering Challenge of AI Coding Assistants in Regulated Codebases. International Journal of Computer Information Systems & Industrial Management Applications, 18, 1248.

13. Rashy, R. A. (2026). Empirical Validation of Predictive Project Controls for Early Schedule-Risk Detection: Analysis of CPM Float Erosion and Milestone Performance in Construction Projects. International Journal of Artificial Intelligence and Computer Electronics, 2(4), 17-24.

14. Chayka, D. P. (2026). An intelligent framework for customer-centric packaging optimization and operational efficiency across industries. International Journal of Production Research (IJPR), 3(2), 1-19.

15. Chayka, D. P. (2026). The Role of Packaging Automation in Improving Operational Efficiency, Productivity, and Manufacturing Performance in Corrugated Packaging Operations. International Journal of Innovation in Electronics and Computer Information Technology, 3(4), 1-8.

Downloads

Published

30-09-2026

How to Cite

Computer Vision-Based Automated Detection of Road Surface Defects for Intelligent Transportation Infrastructure. (2026). Innovative Journal of Computing, Security and Digital Technologies, 1(3), 25-43. https://ijcdst.in/index.php/about/article/view/16

Similar Articles

11-15 of 15

You may also start an advanced similarity search for this article.