2026-04-17T20:23:32Zhttps://recercat.cat/oai/request

oai:recercat.cat:2117/3751232026-02-07T09:08:14Zcom_2072_1033col_2072_452950

Comparative study of upsampling methods for super-resolution in remote sensing Salgueiro Romero, Luis Fernando Marcello Ruiz, Javier Vilaplana Besler, Verónica Àrees temàtiques de la UPC::Enginyeria de la telecomunicació::Radiocomunicació i exploració electromagnètica::Teledetecció Remote-sensing images Deep learning Super-resolution WorldView-2 Imatges satel·litàries Aprenentatge profund Many remote sensing applications require high spatial resolution images, but the elevated cost of these images makes some studies unfeasible. Single-image super-resolution algorithms can improve the spatial resolution of a lowresolution image by recovering feature details learned from pairs of low-high resolution images. In this work, several configurations of ESRGAN, a state-of-the-art algorithm for image super-resolution, are tested. We make a comparison between several scenarios, with different modes of upsampling and channels involved. The best results are obtained training a model with RGB-IR channels and using progressive upsampling. This work has been partially supported by the ARTEMISAT-2 (CTM2016-77733-R) and MALEGRA TEC2016-75976-R projects, funded by the Spanish AEI, FEDER funds,and by the Spanish Ministerio de Economía y Competitividad, respectively. L.S.R. would like to acknowledge the BECAL (Becas Carlos Antonio López) scholarship for the financial support. Peer Reviewed Postprint (author's final draft) 2019 Conference report https://www.spiedigitallibrary.org/conference-proceedings-of-spie/11433/2557357/Comparative-study-of-upsampling-methods-for-super-resolution-in-remote/10.1117/12.2557357.short info:eu-repo/grantAgreement/MINECO/Plan Estatal de Investigación Científica y Técnica y de Innovación 2013-2016/TEC2016-75976-R/Procesado de señales multimodales y aprendizaje automático en grafos Open Access International Society for Photo-Optical Instrumentation Engineers (SPIE)