Show simple item record

dc.contributor.advisorBeltrán Castañón, César Armando
dc.contributor.authorPineda Ancco, Ferdinand Edgardo
dc.description.abstractRecently, satellites in operation offering very high-resolution (VHR) images has experienced an important increase, but they remain as a smaller proportion against existing lower resolution (HR) satellites. Our work proposes an alternative to improve the spatial resolution of HR images obtained by Sentinel-2 satellite by using the VHR images from PeruSat1, a Peruvian satellite, which serve as the reference for the superresolution approach implementation based on a Generative Adversarial Network (GAN) model, as an alternative for obtaining VHR images. The VHR PeruSat-1 image dataset is used for the training process of the network. The results obtained were analyzed considering the Peak Signal to Noise Ratios (PSNR), the Structural Similarity (SSIM) and the Erreur Relative Globale Adimensionnelle de Synth`ese (ERGAS). Finally, some visual outcomes, over a given testing dataset, are presented so the performance of the model could be analyzed as well.
dc.publisherPontificia Universidad Católica del Perú
dc.sourcePontificia Universidad Católica del Perú
dc.sourceRepositorio de Tesis - PUCP
dc.subjectSatélites artificiales en telecomunicaciones
dc.subjectProcesamiento de imágenes digitales
dc.titleA generative adversarial network approach for super resolution of sentinel-2 satellite images
dc.typeinfo:eu-repo/semantics/masterThesisíster en Informática con mención en Ciencias de la Computaciónes_ESíaes_ES Universidad Católica del Perú. Escuela de Posgradoes_ESática con mención en Ciencias de la Computaciónes_ES
dc.type.otherTesis de maestría

Files in this item


There are no files associated with this item.

This item appears in the following Collection(s)

Show simple item record