Authors : Pravin Waghmare; Sapna Sonawane; Siva Kumar; Roopa Mulukutla; Indu Palam; Vallepu Dayakar; Harinee Ganapathy Subramani; Bharani Kumar Depuru

Volume/Issue : Volume 10 - 2025, Issue 3 - March

Google Scholar : https://tinyurl.com/5fzhwv4f

Scribd : https://tinyurl.com/4r27t9sa

DOI : https://doi.org/10.38124/ijisrt/25mar1262

Google Scholar

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

Note : Google Scholar may take 15 to 20 days to display the article.

Abstract : Indian road networks currently rely on manual safety audits that are costly, time-consuming, and pose safety risks to inspection personnel. This paper proposes an AI-driven road safety audit system that uses advanced object detection to automatically identify and evaluate critical road safety features (such as crash barriers, speed breakers,pavement marker insertions, road markings, and signboards) from highway images and video. By leveraging our client’s products in our analysis, the system is fully tailored to Indian road infrastructure, ensuring standard safety installations. (https://law.resource.org/pub/in/bis/irc/translate/irc.gov.in.sp.099.2013.html) The proposed approach addresses high inspection costs by minimizing the need for manual checks. Our AI system should increase Road Safety Awareness among an ordinary Indian citizen, resulting in lower risk of accidents on Indian National/State Highways. Expected outcomes include significant cost savings, lower chance of accidents,and Highway compliant safety features imposed at all high risk - medium risk zones. For example, targeting maintenance activities like repainting faded lane lines or repurposing signage and enhanced highway safety compliance through timely interventions. In conclusion, this AI-based road audit framework offers a scalable solution to improve road safety management in India, providing actionable insights for road contractors and authorities while emphasizing the importance of such data-driven audits in policymaking and infrastructure development. This Road Safety Audit System should also serve as a guideline for all Indian drivers who should be in a position to make effective suggestions for the overall road safety of India.

Keywords : Object Detection, Road Safety Audit, YNM Road Safety, Road Infrastructure, Road Markings, Signage, Barriers, Pavement Markers, Highway Safety, Road Contractors.

References :

1. D. Babić, D. Babić, M. Fiolic, and M. Ferko, "Road Markings and Signs in Road Safety," Encyclopedia, vol. 2, no. 4, pp. 1738–1752, Oct. 2022. doi: 10.3390/encyclopedia2040119.
2. D. Merolla, V. Latorre, A. Salis, and G. Boanelli, *Automated Road Safety: Enhancing Sign and Surface Damage Detection with AI*. 2024.
3. P. J. Carlson and M. S. Lupes, *Methods for Maintaining Traffic Sign Retroreflectivity*, Turner-Fairbank Highway Research Center, Federal Highway Administration, Texas Transportation Institute, Rep. No. FHWA-HRT-08-026, Jan. 2007. [Online]. Available: https://rosap.ntl.bts.gov/view/dot/41407
4. H. M. Eraqi, K. Soliman, D. Said, O. R. Elezaby, M. N. Moustafa, and H. Abdelgawad, "Automatic Roadway Features Detection with Oriented Object Detection," *Applied Sciences*, vol. 11, no. 8, p. 3531, Apr. 2021. doi: 10.3390/app11083531.
5. M. Flores-Calero, C. A. Astudillo, D. Guevara, J. Maza, B. S. Lita, B. Defaz, J. S. Ante, D. Zabala-Blanco, and J. M. Armingol Moreno, "Traffic Sign Detection and Recognition Using YOLO Object Detection Algorithm: A Systematic Review," *Mathematics*, vol. 12, no. 2, p. 297, Jan. 2024. doi: 10.3390/math12020297.
6. N. M. Alahdal, F. Abukhodair, L. Haj Meftah, and A. Cherif, "Real-time Object Detection in Autonomous Vehicles with YOLO," *Procedia Computer Science*, vol. 246, pp. 2792–2801, 2024. doi: 10.1016/j.procs.2024.09.392.
7. H. Loghashankar and H. Nguyen, "Real-Time Traffic Sign Detection: A Case Study in a Santa Clara Suburban Neighborhood," *arXiv preprint*, 2023. [Online]. Available: https://arxiv.org/abs/2310.09630
8. Z. Zhu, D. Liang, S. Zhang, X. Huang, B. Li, and S. Hu, "Traffic-Sign Detection and Classification in the Wild," in *Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR)*, 2016, pp. 2110–2121.
9. B. Pavani, A. K. Das, N. Grandhe, D. C. Mohanty, and B. K. Depuru, "Optimizing Construction Efficiency: AI-Powered Inventory Management for Steel Rods through Automated Counting and Image Processing," *Int. J. Innov. Sci. Res. Technol.*, vol. 9, no. 1, pp. 1494, Jan. 2024.
10. S. V. Kumar, S. Vidhya, P. S. Ramesh, R. Senthilkumar, and G. Ponnaian, "Augmented Road Safety in India Through Real-Time Detection of Road Hazards," *J. Comput. Anal. Appl.*, vol. 33, no. 2, pp. XX–YY, 2024.
11. S. MAHMUD, D. BABIĆ, and T. J. GATES, “A Comprehensive Review of Dynamic Speed Feedback Signs in Reducing Speed at Different Critical Locations”, PROMTT, vol. 36, no. 3, pp. 357–382, Jun. 2024.
12. Haris, M., & Glowacz, A. (2022). Retraction: Haris, M.; Glowacz, A. Road Object Detection: A Comparative Study of Deep Learning-Based Algorithms. Electronics 2021, 10, 1932. Electronics, 11(8), 1166.
13. Saillaja, V. & Mohammed, Rehaman & Krishnaveni, S. & Ravinder, Bathini & Srinivasan, S. & Nandagopal, V.. (2024). IoT-Embedded Traffic Cones with CNN-based Object Detection to Roadwork Safety. 120-125. 10.1109/IDCIoT59759.2024.10467 840.
14. Flores-Calero, M., Astudillo, C. A., Guevara, D., Maza, J., Lita, B. S., Defaz, B., Ante, J. S., Zabala-Blanco, D., & Armingol Moreno, J. M. (2024). Traffic Sign Detection and Recognition Using YOLO Object Detection Algorithm: A Systematic Review. Mathematics, 12(2), 297.
15. Zhao, R., Tang, S. H., Bin Supeni, E. E., Rahim, S. A., & Fan, L. (2024). Z-YOLOv8s-based approach for road object recognition in complex traffic scenarios. Alexandria Engineering Journal, 106, 298-311.