YOLO Ensemble for UAV-based Multispectral Defect Detection in Wind Turbine Components
IDAACS 2025, pp. 11-16
Editorial summary
An ensemble combines a general YOLOv8 detector with a model specialised in thermal defects, then merges their bounding boxes. On the study’s evaluation data, mAP@0.5 increased from 0.91 for YOLOv8 alone to 0.93 for the ensemble, with F1 of 0.90.
Bibliographic reference
Use the publisher’s record for the citation format required by your journal or organisation.
Serhii Svystun, Pavlo Radiuk, Oleksandr Melnychenko, Oleg Savenko, Anatoliy Sachenko. "YOLO Ensemble for UAV-based Multispectral Defect Detection in Wind Turbine Components". IDAACS 2025, pp. 11-16, 2025. https://doi.org/10.1109/IDAACS68557.2025.11322062
Test a method against your business task.
Describe the decision your system needs to support and the data you have. We assess whether a method fits, define a prototype and agree how to measure its quality, response time and operating cost.