Techniques for the extraction of spatial and spectral information in the supervised classification of hyperspectral imagery for land-cover applications
- Álvaro Acción Montes
- Dora Blanco Heras Directora
- Francisco Argüello Pedreira Director
Universidad de defensa: Universidade de Santiago de Compostela
Fecha de defensa: 05 de mayo de 2023
- Raúl Celestino Guerra Fernández Presidente/a
- Natalia Seoane Iglesias Secretaria
- Javier Muro Martín Vocal
Tipo: Tesis
Resumen
The objective of this PhD thesis is the development of spatialspectral information extraction techniques for supervised classification tasks, both by means of classical models and those based on deep learning, to be used in the classification of land use or land cover (LULC) multi- and hyper-spectral images obtained by remote sensing. The main goal is the efficient application of these techniques, so that they are able to obtain satisfactory classification results with a low use of computational resources and low execution time.