Towards Robust Cloud Detection in Satellite Images Using U-Nets

TytułTowards Robust Cloud Detection in Satellite Images Using U-Nets
Publication TypeConference Paper
Rok publikacji2021
AutorzyGrabowski B, Ziaja M, Kawulok M, Nalepa J
Conference Name2021 IEEE International Geoscience and Remote Sensing Symposium IGARSS
Date Published10/2021
Conference LocationBrussels, Belgium
ISBN Number978-1-6654-0369-6

Cloud detection is an important pre-processing step that allows us to significantly reduce the amount of satellite imagery which should undergo further processing. In this paper, we investigate the impact of training set selection on the abilities of fully-convolutional neural networks for this task. Our experiments, performed over a range of Landsat-8 satellite images, show that the performance of deep models can substantially vary for different training samples, especially in the case of challenging scenes, such as those capturing snowy areas.


Historia zmian

Data aktualizacji: 30/01/2022 - 14:59; autor zmian: Jarosław Miszczak (