Safeguarding Mobility: YOLOv8n-Enabled Road Surface Detection and Classification

In an era marked by continual technological advancement, road safety emerges as a critical global concern, with potholes posing persistent threats to commuters and vehicles alike. This research paper explores the realm of road surface classification, with a particular emphasis on automating pothole detection through innovative technological integration. Leveraging the state-of-the-art object detection algorithm YOLOv8n, we aim to revolutionize the identification and mitigation of road imperfections. Our proposed methodology seamlessly processes video data, transforming it into an accessible and optimized format, while utilizing YOLOv8n for real-time pothole detection and labeling. This automated classification expedites identification processes and enhances maintenance efficiency, facilitating timely interventions to rectify road defects and bolster safety measures. Through this research, we contribute to the discourse on road safety and infrastructure management, showcasing the transformative potential of AI-driven solutions to forge a safer and more resilient transportation network, one pothole at a time.