Unmanned Aerial Vehicle-Based Road Damage Detection Using Convolutional Neural Networks

Using images taken by unmanned aerial vehicles (UAVs) and deep learning algorithms, this study introduces a novel method for detecting road damage and cracks. Maintaining sturdy roadways depends on regularly inspecting and repairing street foundations, but manual data collection is often hazardous and time-consuming. To address this, we leverage UAV technology and artificial intelligence (AI) to improve roadway hazard identification. Our approach utilizes YOLOv4, YOLOv5, and YOLOv7, which are advanced object detection models for processing UAV imagery. Experimental results on Chinese and Spanish datasets demonstrate that YOLOv7 achieves the highest accuracy in identifying road damage. Furthermore, we introduce YOLOv8, an improved method that enhances prediction precision, surpassing prior models when trained on road damage and crack detection datasets. This study paves the way for future advancements by showcasing the potential of UAV-based deep learning in automating and improving road condition assessments.