Publication

Robust wind turbine blade segmentation from RGB images in the wild

Conference Article

Conference

IEEE International Conference on Image Processing (ICIP)

Edition

2023

Pages

1025-1029

Doc link

https://doi.org/10.1109/ICIP49359.2023.10223165

File

Download the digital copy of the doc pdf document

Abstract

With the relentless growth of the wind industry, there is an imperious need to design automatic data-driven solutions for wind turbine maintenance. As structural health monitoring mainly relies on visual inspections, the first stage in any automatic solution is to identify the blade region on the image. Thus, we propose a novel segmentation algorithm that strengthens the U-Net results by a tailored loss, which pools the focal loss with a contiguity regularization term. To attain top performing results, a set of additional steps are proposed to ensure a reliable, generic, robust and efficient algorithm. First, we leverage our prior knowledge on the images by filling the holes enclosed by temporarily-classified blade pixels and by the image boundaries. Subsequently, the mislead classified pixels are successfully amended by training an on-the-fly random forest. Our algorithm demonstrates its effectiveness reaching a non-trivial 97.39% of accuracy.


Categories

edge detection, image recognition, pattern recognition.

Author keywords

Blade Segmentation, Wind Turbine Inspections, BU-Net, Hole Filling

Scientific reference

R. Pérez, A. Espersen and A. Agudo. Robust wind turbine blade segmentation from RGB images in the wild, 2023 IEEE International Conference on Image Processing, 2023, Kuala Lumpur, Malaysia, pp. 1025-1029.