International Journal of
Advanced Multidisciplinary Application

Volume 3, Issue 5

• Author(s)Aiman R., Aisyah B., Wei U. Tan, Siti K.
• AffiliationFaculty of Electrical Engineering, Universiti Teknologi Malaysia (UTM), Johor Bahru , Malaysia,School of Computing, Universiti Teknologi Malaysia (UTM), Johor Bahru , Malaysia
• Page No.10-14
• Volume, Issue & YearVolume 3, Issue 5, May 2026
• Published On2026/05/02
• JournalInternational Journal of Advanced Multidisciplinary Application (IJAMA)
• ISSN No.3048-9350
• DOIhttps://doi.org/10.5281/zenodo.20006952

Abstract

Deteriorating Road Surfaces Remain A Major Contributor To Traffic Accidents, Vehicle Damage, And Rising Municipal Maintenance Costs In Fast-Urbanizing Cities Of South-East Asia. This Paper Presents The Design, Deployment, And Field Evaluation Of A Low-Cost, Real-Time Pothole Detection And Severity Assessment System Based On A Yolov8 Deep-Learning Model Running On An Edge Computing Platform (Nvidia Jetson Nano). Dash-Cam Video, Gps Coordinates, And Inertial Measurement Data Are Fused On-Board To Detect Potholes, Classify Their Severity Into Four Categories (Low, Medium, High, Critical), And Stream Geo-Tagged Reports To A Centralized Municipal Dashboard Via 4g. A Custom Dataset Of 12,400 Annotated Images Was Collected Across 8 Districts Of Johor Bahru And Used To Train And Validate The Model. Field Trials Over 480 Km Of Urban Roads Achieved A Mean Average Precision (Map@0.5) Of 0.93, An Inference Rate Of 27 Fps On The Edge Device, And A Severity Classification Accuracy Of 91.4%. The Proposed System Reduced Manual Road-Survey Effort By Approximately 78% And Enabled Prioritized Repair Scheduling, Demonstrating A Practical Pathway Toward Data-Driven Smart Road Maintenance For Medium-Sized Municipalities.

Keywords: Pothole detection, YOLOv8, Edge computing, Computer vision, Smart city, Road maintenance, Deep learning

References

1. [1] Public Works Department of Malaysia, "Annual Road Maintenance Report," Kuala Lumpur, 2025.
2. [2] World Bank, "Urban Mobility in South-East Asia: Trends and Challenges," Tech. Rep., 2024.
3. [3] J. Redmon and A. Farhadi, "YOLOv3: An incremental improvement," arXiv:1804.02767, 2018.
4. [4] G. Jocher et al., "Ultralytics YOLOv8," GitHub repository, 2023.
5. [5] S. Ren, K. He, R. Girshick, and J. Sun, "Faster R-CNN: Towards real-time object detection with region proposal networks," IEEE TPAMI, vol. 39, no. 6, pp. 1137–1149, 2017.
6. [6] A. Mednis et al., "Real-time pothole detection using Android smartphones with accelerometers," Proc. DCOSS, pp. 1–6, 2011.
7. [7] S. Koch and I. Brilakis, "Pothole detection in asphalt pavement images," Adv. Eng. Inform., vol. 25, no. 3, pp. 507–515, 2011.
8. [8] L. Wang et al., "Edge-AI based road defect monitoring using YOLOv5 on Jetson devices," Sensors, vol. 22, no. 14, 2022.
9. [9] H. Kim, J. Park, and S. Lee, "Real-time pavement crack detection using YOLOv7," IEEE Access, vol. 11, pp. 45521–45533, 2023.
10. [10] R. Bhatia and M. Singh, "Severity-aware pothole classification for smart cities," J. Intell. Transp. Syst., vol. 28, no. 4, pp. 612–627, 2024.
11. [11] NVIDIA Corporation, "Jetson Nano Developer Kit: Technical Specifications," 2023.
12. [12] OpenStreetMap Contributors, "OpenStreetMap Database," https://www.openstreetmap.org, accessed 2026.

Explore Our Related Journals

Looking for the right journal for your next manuscript? Explore our international peer-reviewed journals covering engineering, management, computer science, artificial intelligence and multidisciplinary research.