Road Hazards Monitoring and Reporting System Implementing YOLOv8 Algorithm

Road hazards are one of the most significant risks to public safety, leading to numerous accidents and fatalities annually. This research is an AI-driven web application that uses a camera or image uploaded by the user to monitor roads and street lanes to create a safer environment for riders and commuters. The web-based user-friendly system involved training datasets with the YOLOv8 (You Only Look Once version 8) algorithm to recognize road hazards like potholes and sinkholes. It also allows users to capture and record road conditions and details of issues, including date, time, and location. enables seamless reporting of road-related concerns to the relevant authorities. The system can effectively identify and detect road hazards, classifying them into categories such as potholes and sinkholes with an accuracy of 90.2%, an F1-score of 81.3%, precision at 92%, and a recall of 79.4%. The evaluation of the system was conducted following ISO/IEC 25010, which measures the quality of the system implementation and its design. Also, this research adds to the United Nations Sustainable Development 11: Make cities and human settlements inclusive, safe, resilient, and sustainable.