BladeYOLO framework enhances wind turbine defect detection with limited data

Researchers have developed BladeYOLO, a new framework designed to improve the detection of defects on wind turbine blades, particularly in scenarios with limited annotated data. The system integrates a Vision Transformer (ViT) backbone with YOLOv12-L, leveraging self-supervised pre-training to enhance feature representation. BladeYOLO also incorporates a Mamba-guided module to better identify subtle defects and a Style-Injector module to increase robustness against environmental variations. Experiments show BladeYOLO outperforms existing methods on the WTBlade-Defect dataset and demonstrates cross-dataset robustness on the Wind Surface Defect dataset. AI

IMPACT This research could lead to more efficient and accurate wind turbine maintenance by improving automated defect detection systems.

RANK_REASON The item is an academic paper detailing a new computer vision model for a specific application. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.CV →

• BladeYOLO
• DINOv3
• Mamba
• Vision Transformer
• Wind Surface Defect
• WTBlade-Defect
• YOLOv12-L

• paper
• product
• other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →