“WTA/TLA: A UAV-captured Dataset for Semantic Segmentation of Energy Infrastructure” was virtually presented in the 2022 International Conference on Unmanned Aircraft Systems (ICUAS), that took place in Dubrovnik, Croatia on 21-24 June 2022. This research has been conducted in the context of the AUTOPSY project, concerning the scene semantic segmentation for the use cases of Power Transmission Networks and Wind Turbine Farms.
A public dataset has also been published and is available in the following link:
https://github.com/gzamps/wta_tla_dataset.
Specifically, the proposed dataset refers to the development of state-of-the-art deep neural networks for the semantic segmentation of energy infrastructures using image data captured from UAVs. In addition, a deep learning architecture focused on the specific use cases was employed.
The paper is available in the following link:
https://ieeexplore.ieee.org/abstract/document/9836096