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)
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: 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.
-
-
Item type: Article ID code: 87233 Dates: DateEvent24 March 2022Published24 February 2022Accepted7 June 2021SubmittedSubjects: Science > Mathematics > Electronic computers. Computer science
Geography. Anthropology. Recreation > Physical geographyDepartment: Faculty of Science > Computer and Information Sciences Depositing user: Pure Administrator Date deposited: 08 Nov 2023 12:37 Last modified: 09 Apr 2024 04:19 URI: https://strathprints.strath.ac.uk/id/eprint/87233