Low-Rank Tensor Modeling for Hyperspectral Unmixing Accounting for Spectral Variability

Traditional hyperspectral unmixing methods neglect the underlying variability of spectral signatures often observed in typical hyperspectral images (HI), propagating these mismodeling errors throughout the whole unmixing process. Attempts to model material spectra as members of sets or as random var...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	IEEE transactions on geoscience and remote sensing Ročník 58; číslo 3; s. 1833 - 1842
Hlavní autoři:	Imbiriba, Tales, Borsoi, Ricardo Augusto, Bermudez, Jose Carlos Moreira
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	New York IEEE 01.03.2020 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:	Additives Algorithms Computer simulation Electrical engineering Endmember (EM) variability Environmental management hyperspectral data Hyperspectral imaging Ill posed problems low rank Parametric statistics Random variables Regularization Spectra Spectral signatures tensor decomposition Tensors ULTRA accounting for EM variability (ULTRA-V) unmixing with low-rank tensor regularization algorithm (ULTRA) Variability
ISSN:	0196-2892, 1558-0644
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Buďte první, kdo okomentuje tento záznam!