Cloud removal from satellite imagery using multispectral edge-filtered conditional generative adversarial networks

Hasan, Cengis and Horne, Ross and Mauw, Sjouke and Mizera, Andrzej (2022) Cloud removal from satellite imagery using multispectral edge-filtered conditional generative adversarial networks. International Journal of Remote Sensing, 43 (5). pp. 1881-1893. ISSN 0143-1161 (https://doi.org/10.1080/01431161.2022.2048915)

[thumbnail of Hasan-etal-IJRS-2022-Cloud-removal-from-satellite-imagery-using-multispectral-edge-filtered-conditional-generative-adversarial-networks]
Preview
 Text. Filename: Hasan-etal-IJRS-2022-Cloud-removal-from-satellite-imagery-using-multispectral-edge-filtered-conditional-generative-adversarial-networks.pdf
Final Published Version
License: Creative Commons Attribution 4.0 logo
Download (6MB)| Preview

Abstract

We propose a Generative Adversarial Network (GAN) based architecture for removing clouds from satellite imagery. Data used for training comprises of visible light RGB and near-infrared (NIR) band images. The novelty lies in the structure of the discriminator in the GAN architecture, which compares generated and target cloud-free RGB images concatenated with their edge-filtered versions. Experimental results show that our approach to removing clouds outperforms both visually and according to metrics, a benchmark solution that does not take edge filtering into account, and that improvements are robust when varying both training dataset size and NIR cloud penetrability.

CORE (COnnecting REpositories)