YOLO Ensemble for UAV-based Multispectral Defect Detection in Wind Turbine Components
arXiv:2509.04156
Abstract
This paper proposes an ensemble approach integrating a general-purpose YOLOv8 model with a specialized thermal model for wind turbine defect detection. Using a sophisticated bounding box fusion algorithm, the ensemble achieves a mean Average Precision of 0.93 and F1-score of 0.90, outperforming standalone models.
Citation
Serhii Svystun, Pavlo Radiuk, Oleksandr Melnychenko, Oleg Savenko, Anatoliy Sachenko. "YOLO Ensemble for UAV-based Multispectral Defect Detection in Wind Turbine Components". arXiv:2509.04156, 2025.