Unsupervised Modular Adaptive Region Growing and RegionMix Classification for Wind Turbine Segmentation
This addresses the scalability challenge of requiring extensive annotated datasets for wind turbine inspections, though it is incremental as it builds on region-based methods.
The paper tackles the problem of wind turbine blade segmentation for automated inspections by reframing it as a binary region classification to reduce annotation needs, achieving state-of-the-art accuracy and strong cross-site generalization.
Reliable operation of wind turbines requires frequent inspections, as even minor surface damages can degrade aerodynamic performance, reduce energy output, and accelerate blade wear. Central to automating these inspections is the accurate segmentation of turbine blades from visual data. This task is traditionally addressed through dense, pixel-wise deep learning models. However, such methods demand extensive annotated datasets, posing scalability challenges. In this work, we introduce an annotation-efficient segmentation approach that reframes the pixel-level task into a binary region classification problem. Image regions are generated using a fully unsupervised, interpretable Modular Adaptive Region Growing technique, guided by image-specific Adaptive Thresholding and enhanced by a Region Merging process that consolidates fragmented areas into coherent segments. To improve generalization and classification robustness, we introduce RegionMix, an augmentation strategy that synthesizes new training samples by combining distinct regions. Our framework demonstrates state-of-the-art segmentation accuracy and strong cross-site generalization by consistently segmenting turbine blades across distinct windfarms.