End-to-End Convolutional Autoencoder for Nonlinear Hyperspectral Unmixing

Hyperspectral Unmixing is the process of decomposing a mixed pixel into its pure materials (endmembers) and estimating their corresponding proportions (abundances). Although linear unmixing models are more common due to their simplicity and flexibility, they suffer from many limitations in real worl...

Descripció completa

Dades bibliogràfiques

Autors principals:	Mohamad Dhaini, Maxime Berar, Paul Honeine, Antonin Van Exem
Format:	Artigo
Idioma:	Inglês
Publicat:	MDPI AG 2022-07-01
Col·lecció:	Remote Sensing
Matèries:	convolutional neural network autoencoder hyperspectral imaging nonlinear spectral unmixing
Accés en línia:	https://www.mdpi.com/2072-4292/14/14/3341
Etiquetes:	Afegir etiqueta Sense etiquetes, Sigues el primer a etiquetar aquest registre!