.png){kind=icon}
.png){kind=icon}
Return
BladeYOLO: Wind Turbine Blade Defect Detection With Limited Annotations and Weak-Saliency Awareness
.png){kind=icon}
PRE
AI
Y
F
F
Z
H
魏
H
S
DOI：10.1109/tgrs.2026.3717985.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Wind turbine blade defect detection remains highly challenging in real-world inspection scenarios due to limited on-site data and the subtle visual characteristics of defects. In practice, blade defects are often small-scale, low-contrast, and difficult to distinguish from complex backgrounds, which significantly limits the robustness of existing detectors. To address these challenges, we propose BladeYOLO, a defect detection framework for wind turbine blades. Specifically, we integrate a Vision Transformer (ViT) backbone initialized with DINOv3 self-supervised pretrained weights into YOLOv12-L, enabling the transfer of large-scale generic visual priors to blade defect detection and improving feature representation under limited training annotations. To enhance the perception of subtle defects, we further develop a Mamba-guided weak-defect enhancement (MWE) module, which consists of a detail-enhanced multiscale branch for preserving high-frequency structural cues and a Cross-Mamba module for progressively propagating high-level semantic guidance to shallow features. In addition, we introduce a lightweight style-injector (SI) module that captures environment-related style information via Fourier decomposition and injects it into selected ViT self-attention layers, thereby improving robustness against environment-induced appearance variations. Extensive experiments demonstrate that BladeYOLO achieves superior performance on the WTBlade-Defect dataset, with additional annotation-budget experiments showing its favorable performance under reduced training annotations. Evaluation on the public Wind Surface Defect dataset further provides supportive evidence for the cross-dataset robustness of BladeYOLO. In particular, on this public dataset, BladeYOLO outperforms the best competing method by 3.5% in mean average precision (mAP)50 and 2.5% in mAP<inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">${}_{50-95}$ </tex-math></inline-formula>. The code is available at <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/zhangfangtao/BladeYOLO</uri>
Keywords:
DINOv3
limited annotations
Mamba
weak-saliency defects
wind turbine blade defect detection
YOLO
Journal
IF:
8.6
Papers:
2.1W
Citations:
10.7W
Organization
Cited Papers