Master Thesis

Machine Learning-based Segmentation applied to Wind Turbines Images: Loss exploration

Work default illustration


  • If you are interested in the proposal, please contact with the supervisors.


The goal of the project is developing an image segmentation algorithm on wind turbine blade imagery, obtained during drone inspections. Hence, given an image of a blade, we would like to obtain a binary image of the same size, which indicates whether each pixel belongs to the blade or the background region. This project proposes to improve current Artificial Intelligence networks by designing customized loss functions that include our prior knowledge of blade images.

Requisites: Candidates with a background in optimization, machine learning and good programming skills (Matlab/Python/C++) are particularly encouraged to apply. This project will be supervised by Raül Perez i Gonzalo and Antonio Agudo.

This industrial project will be executed in collaboration with the company Wind Power Lab, who will provide the video data.