Semi-Supervised Cloud Detection with Weakly Labeled RGB Aerial Images using Generative Adversarial Networks

Toon Stuyck, Axel-Jan Rousseau, Mattia Vallerio, Eric Demeester

2022

Abstract

Despite extensive efforts, it is still very challenging to correctly detect clouds automatically from RGB images. In this paper, an automated and effective cloud detection method is proposed based on a semi-supervised generative adversarial networks that was originally designed for anomaly detection in combination with structural similarity. By only training the networks on cloudless RGB images, the generator network is able to learn the distribution of normal input images and is able to generate realistic and contextually similar images. If an image with clouds is introduced, the network will fail to recreate a realistic and contextually similar image. Using this information combined with the structural similarity index, we are able to automatically and effectively segment anomalies, which in this case are clouds. The proposed method compares favourably to other commonly used cloud detection methods on RGB images.

Paper Citation

in Harvard Style

Stuyck T., Rousseau A., Vallerio M. and Demeester E. (2022). Semi-Supervised Cloud Detection with Weakly Labeled RGB Aerial Images using Generative Adversarial Networks. In Proceedings of the 11th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM, ISBN 978-989-758-549-4, pages 630-635. DOI: 10.5220/0010871500003122

in Bibtex Style

@conference{icpram22,
author={Toon Stuyck and Axel-Jan Rousseau and Mattia Vallerio and Eric Demeester},
title={Semi-Supervised Cloud Detection with Weakly Labeled RGB Aerial Images using Generative Adversarial Networks},
booktitle={Proceedings of the 11th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,},
year={2022},
pages={630-635},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010871500003122},
isbn={978-989-758-549-4},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 11th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,
TI - Semi-Supervised Cloud Detection with Weakly Labeled RGB Aerial Images using Generative Adversarial Networks
SN - 978-989-758-549-4
AU - Stuyck T.
AU - Rousseau A.
AU - Vallerio M.
AU - Demeester E.
PY - 2022
SP - 630
EP - 635
DO - 10.5220/0010871500003122