In hyperspectral data, mixed pixels are frequent due to the low-medium spatial resolution of the imaging spectrometer, or to intimate mixing effects. Hence the process of blind hyperspectral unmixing, which separates the pixel spectra into a collection of spectral signatures and a set of fractional abundances, is a mandatory task in hyperspectral image processing. In this study, among models capable of performing linear spectral unmixing, we present a comparative analysis performed on real data acquired from the PRISMA (PRecursore IperSpettrale della Missione Applicativa) hyperspectral satellite between deep nonnegative matrix factorization and artificial neural network autoencoder based methods.
Deep NMF and Autoencoder: A Comparative Analysis for Hyperspectral Unmixing Using Prisma Real Images
Gaetano Settembre
;Nicoletta Del Buono;Flavia Esposito;
2024-01-01
Abstract
In hyperspectral data, mixed pixels are frequent due to the low-medium spatial resolution of the imaging spectrometer, or to intimate mixing effects. Hence the process of blind hyperspectral unmixing, which separates the pixel spectra into a collection of spectral signatures and a set of fractional abundances, is a mandatory task in hyperspectral image processing. In this study, among models capable of performing linear spectral unmixing, we present a comparative analysis performed on real data acquired from the PRISMA (PRecursore IperSpettrale della Missione Applicativa) hyperspectral satellite between deep nonnegative matrix factorization and artificial neural network autoencoder based methods.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.