Please use this identifier to cite or link to this item: http://hdl.handle.net/10553/75355
DC FieldValueLanguage
dc.contributor.authorRomero, Luis Salgueiroen_US
dc.contributor.authorMarcello, Javieren_US
dc.contributor.authorVilaplana, Verónicaen_US
dc.date.accessioned2020-11-11T08:04:03Z-
dc.date.available2020-11-11T08:04:03Z-
dc.date.issued2020en_US
dc.identifier.issn2072-4292en_US
dc.identifier.otherScopus-
dc.identifier.urihttp://hdl.handle.net/10553/75355-
dc.description.abstractSentinel-2 satellites provide multi-spectral optical remote sensing images with four bands at 10 m of spatial resolution. These images, due to the open data distribution policy, are becoming an important resource for several applications. However, for small scale studies, the spatial detail of these images might not be sufficient. On the other hand, WorldView commercial satellites offer multi-spectral images with a very high spatial resolution, typically less than 2 m, but their use can be impractical for large areas or multi-temporal analysis due to their high cost. To exploit the free availability of Sentinel imagery, it is worth considering deep learning techniques for single-image super-resolution tasks, allowing the spatial enhancement of low-resolution (LR) images by recovering high-frequency details to produce high-resolution (HR) super-resolved images. In this work, we implement and train a model based on the Enhanced Super-Resolution Generative Adversarial Network (ESRGAN) with pairs of WorldView-Sentinel images to generate a super-resolved multispectral Sentinel-2 output with a scaling factor of 5. Our model, named RS-ESRGAN, removes the upsampling layers of the network to make it feasible to train with co-registered remote sensing images. Results obtained outperform state-of-the-art models using standard metrics like PSNR, SSIM, ERGAS, SAM and CC. Moreover, qualitative visual analysis shows spatial improvements as well as the preservation of the spectral information, allowing the super-resolved Sentinel-2 imagery to be used in studies requiring very high spatial resolution.en_US
dc.languageengen_US
dc.relation.ispartofRemote Sensingen_US
dc.sourceRemote Sensing[EISSN 2072-4292],v. 12 (15), (Agosto 2020)en_US
dc.subject250616 Teledetección (Geología)en_US
dc.subject.otherDeep Learningen_US
dc.subject.otherGenerative Adversarial Networken_US
dc.subject.otherSentinel-2en_US
dc.subject.otherSuper-Resolutionen_US
dc.subject.otherWorldviewen_US
dc.titleSuper-resolution of Sentinel-2 imagery using generative adversarial networksen_US
dc.typeinfo:eu-repo/semantics/Articleen_US
dc.typeArticleen_US
dc.identifier.doi10.3390/RS12152424en_US
dc.identifier.scopus85089853089-
dc.contributor.authorscopusid57218455911-
dc.contributor.authorscopusid6602158797-
dc.contributor.authorscopusid23394280500-
dc.identifier.eissn2072-4292-
dc.identifier.issue15-
dc.relation.volume12en_US
dc.type2Artículoen_US
dc.utils.revisionen_US
dc.date.coverdateAgosto 2020en_US
dc.identifier.ulpgcen_US
dc.description.sjr1,285
dc.description.jcr4,848
dc.description.sjrqQ1
dc.description.jcrqQ1
dc.description.scieSCIE
item.fulltextCon texto completo-
item.grantfulltextopen-
crisitem.author.deptGIR IOCAG: Procesado de Imágenes y Teledetección-
crisitem.author.deptIU de Oceanografía y Cambio Global-
crisitem.author.deptDepartamento de Señales y Comunicaciones-
crisitem.author.orcid0000-0002-9646-1017-
crisitem.author.parentorgIU de Oceanografía y Cambio Global-
crisitem.author.fullNameMarcello Ruiz, Francisco Javier-
Appears in Collections:Artículos
Thumbnail
Adobe PDF (21,97 MB)
Show simple item record

SCOPUSTM   
Citations

56
checked on Mar 24, 2024

Page view(s)

163
checked on Sep 2, 2023

Download(s)

178
checked on Sep 2, 2023

Google ScholarTM

Check

Altmetric


Share



Export metadata



Items in accedaCRIS are protected by copyright, with all rights reserved, unless otherwise indicated.