El sistema se apagará debido a tareas habituales de mantenimiento. Por favor, guarde su trabajo y desconéctese.
A generative adversarial network approach for super resolution of sentinel-2 satellite images
Abstract
Recently, 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.
Temas
Satélites artificiales en telecomunicaciones
Procesamiento de imágenes digitales
Procesamiento de imágenes digitales
Para optar el título de
Maestro en Informática con mención en Ciencias de la Computación