International Journal of Scientific Research and Engineering Development

Road infrastructure maintenance is a critical aspect of ensuring transportation safety and efficiency. Traditional road inspection methods are manual, time-consuming, labor-intensive, and prone to human error. This paper presents an automated road damage detection system using Unmanned Aerial Vehicle (UAV) images and deep learning techniques. The proposed system utilizes a YOLOv8-based object detection model to identify various types of road damages, including cracks and potholes, from aerial images. The system processes input images through a web-based interface, detects damaged regions, and generates output with bounding boxes, confidence scores, and severity levels. Additionally, a road health score is calculated to assist authorities in prioritizing maintenance tasks. Experimental results demonstrate that the proposed approach improves detection efficiency and reduces the need for manual inspection. This system can be effectively applied in smart city infrastructure and road monitoring systems.

Sneha Pandurang Badhe,"Automated Road Damage Detection Using UAV Images and Deep Learning Techniques" International Journal of Scientific Research and Engineering Development, V9(2): Page(1730-1734) Mar-Apr 2026. ISSN: 2581-7175. www.ijsred.com. Published by Scientific and Academic Research Publishing.