Unsupervised Modular Adaptive Region Growing and RegionMix Classification for Wind Turbine Segmentation

TL;DR

This paper presents an annotation-efficient, unsupervised segmentation method for wind turbine blades that combines adaptive region growing, region merging, and a novel augmentation strategy called RegionMix, achieving high accuracy and generalization.

Contribution

It introduces a fully unsupervised, interpretable region growing technique and a new augmentation method, RegionMix, for robust wind turbine blade segmentation.

Findings

Achieves state-of-the-art segmentation accuracy.

Demonstrates strong cross-site generalization.

Reduces reliance on extensive annotated datasets.

Abstract

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.