<![CDATA[This study presents a novel approach to the automated detection of road surface defects using Unmanned Aerial Vehicles (UAVs) and advanced image processing. The research background highlights the critical need for efficient and safe road infrastructure maintenance. Traditional methods, which rely on manual visual inspections, are often time-consuming, expensive, and expose inspectors to traffic risks. The primary objective is to design and validate an automated system for identifying and classifying various road surface defects, such as potholes, cracks, and rutting. The system aims to leverage aerial imagery captured by UAVs and process it with a Convolutional Neural Network (CNN). The research seeks to demonstrate a solution that is faster, more accurate, and safer than manual inspection methods, paving the way for proactive road maintenance. The research methodology involves three key stages: data acquisition, model development, and validation. High-resolution images of various road defects are captured using a UAV. These images are then used to train a custom-designed CNN model. The model is trained to recognize and classify different types of defects with high precision. The results indicate that the combination of UAVs and CNNs is a robust and effective solution for road monitoring. The conclusion is that this automated system provides a scalable, safe, and highly accurate method for road surface defect detection. ]]>
Copyrights © 2025
