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

Cengis Hasan, Ross Horne, Sjouke Mauw, Andrzej Mizera

Research output: Contribution to journalArticlepeer-review

10 Citations (Scopus)
24 Downloads (Pure)

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.
Original languageEnglish
Pages (from-to)1881-1893
Number of pages13
JournalInternational Journal of Remote Sensing
Volume43
Issue number5
DOIs
Publication statusPublished - 24 Mar 2022

Keywords

  • generative adversarial network
  • satellite imagery
  • cloud removal

Fingerprint

Dive into the research topics of 'Cloud removal from satellite imagery using multispectral edge-filtered conditional generative adversarial networks'. Together they form a unique fingerprint.

Cite this