

Road Guard: AI-Powered Road Damage Detection and Reporting System
Abstract
Potholes pose a significant challenge to road safety and infrastructure maintenance, demanding efficient solutions for detection and reporting. This paper presents an automated system for real-time pothole detection and reporting, leverag- ing the YOLOv8 object detection model and GPS integration for accurate location tracking. A Flask-based web application provides an organized platform to manage detected pothole data, classify severity levels such as Critical or Average, and store information in a JSON file for persistent access. Additionally, an interactive map feature enables authorities to filter, view, and manage pothole records efficiently. The proposed system demonstrates a practical approach to improve road condition monitoring and maintenance.
References
Ministry of Road Transport and Highways, ”Road Accidents in India - 2022,” Government of India, New Delhi, India, Oct. 2022.
Rana, P, Singh, R. R (2018). Impact of Rains on Road Transport. International Journal of Engineering Development and Research, 6(4),
https://rjwave.org/ijedr/papers/IJEDR1804018.pdf
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 Engineer- ing, vol. 33, no. 12, pp. 1127-1141, 2018.
Dong-Hoe Heo, Ji-Yoon Choi, Sang-Baeg Kim, Tae-Oh Tak, and Sheng- Peng Zhang, Image-Based Pothole Detection Using Multi-Scale Feature Network and Risk Assessment, Department of Mechanical and Biomedical Engineering, Kangwon National University, Chuncheon City, Gangwon- do, Republic of Korea and Kai Networks Corporation, Suwon City, Gyoenggi-do, Republic of Korea, 2023.
Grinberg, M. (2018). Flask Web Development: Developing Web Appli- cations with Python (2nd ed.). O’Reilly Media. Retrieved from https:
//coddyschool.com/upload/Flask Web Development Developing.pdf
Ngugi, S, Leaflet in Practice: Create webmaps using the JavaScript Leaflet library. University of Nairobi, 2023
R Sulistyowati , A Suryowinoto , H A Sujono, and I Iswahyudi, Monitoring of road damage detection systems using image processing methods and Google Map. Institut Teknologi Adhi Tama Surabaya, East Java, Indonesia, 2021.
Dr. Yusuf Perwej, Ankit Kumar, Neha Kulshrestha, Ashish Kumar Sri- vastava, and Chandan Mani Tripathi , The Assay of Potholes and Road Damage Detection, Ambalika Institute of Management and Technology, Lucknow, India, 2022.
Mostafa Hoseini , Stefano Puliti , Stephan Hoffmann , and Rasmus Astrup, Pothole detection in the woods: a deep learning approach for forest road surface monitoring with dashcams Division of Forest and Forest Resources, Department of Forest Operations and Digitalization, Norwegian Institute for Bioeconomy Research, A˚ s, Norway, 2023.
Bhavana N, Mallikarjun M Kodabagi, Muthu Kumar B, Ajay P, Muthukumaran N and Ahilan A, POT-YOLO: Real-Time Road Pot- holes Detection Using Edge Segmentation-Based Yolo V8 Network IEEE Sensors Journal ( Volume: 24, Issue: 15, 01 August 2024) DOI:
1109/JSEN.2024.3399008 Page(s): 24802 - 24809.
Refbacks
- There are currently no refbacks.