Detection of Road Defects from Unmanned Aerial Vehicles Using Machine Learning
Light & Engineering · 25.06.2026 · 4
DOI: 10.33383/2025-075 ↗Kurz gefasst
Fachartikel in der Zeitschrift Light & Engineering, online erschienen am 19.06.2026. Verfasst von Ahsan Mustafa und 2 weiteren Autor:innen. Die Arbeit nennt 17 Literaturangaben.
Abstract (Originalsprache)
The timely detection of road surface deterioration is a critical factor in infrastructure maintenance and traffic safety. Conventional inspection methods remain labour-intensive, costly, and prone to human error. In contrast, unmanned aerial vehicles (UAVs) combined with advanced computer vision techniques provide a scalable and cost-effective alternative. In this study, we propose a neural network model based on the YOLOv12 object detection framework for identifying road surface defects. The model is trained on a UAV-PDD2023 dataset containing over 2400 high-resolution aerial images annotated across six categories of road defects. Two model configurations with varying preprocessing steps and hyperparameters are evaluated to assess robustness and generalization. The evaluation of the model efficiency was performed when RGB imagery is replaced with single-channel counterparts. Results show that the accuracy of defect detection remains largely unaffected: over 90 percent of the defects detected in RGB imagery were also correctly identified in single-channel images, with a performance variation of less than ±5 %. This indicates that a single trained model can be effectively applied to images with different spectral characteristics.
Zitieren
APA
Mustafa, A., Kataev, M. Y., & Efremenko, D. S. (2026). Detection of Road Defects from Unmanned Aerial Vehicles Using Machine Learning. Light & Engineering, 4. https://doi.org/10.33383/2025-075
Vancouver
Mustafa A, Kataev MY, Efremenko DS. Detection of Road Defects from Unmanned Aerial Vehicles Using Machine Learning. Light & Engineering. 2026:4. doi:10.33383/2025-075
BibTeX
@article{Mustafa2026,
author = {Mustafa, Ahsan and Kataev, Michael Yu. and Efremenko, Dmitry S.},
title = {Detection of Road Defects from Unmanned Aerial Vehicles Using Machine Learning},
journal = {Light & Engineering},
year = {2026},
pages = {4},
doi = {10.33383/2025-075}
}
EUVIMED