High-Efficiency Hyperspectral Unmixing Based on Band Selection

Author

Yang Zhou ; Xiaorun Li ; Jiantao Cui

Author_Institution

Coll. of Electr. Eng., Zhejiang Univ., Hangzhou, China

fYear

2012

fDate

6-8 Nov. 2012

Firstpage

140

Lastpage

143

Abstract

Hyper spectral unmixing (HU) is important for ground objects identification. Due to the mass data hyper spectral sensors bring, band selection plays an important role in boosting efficiency of HU. This paper proposes a high-efficiency approach of HU that carries out two modified algorithms of band selection followed by nonnegative matrix factorization (NMF), which are linear prediction (LP) combined with K-L divergence and mutual information (MI). Experiment results based on simulated data and real hyper spectral imagery demonstrate that the proposed scheme is more efficient than initial NMF in HU.

Keywords

image processing; matrix decomposition; K-L divergence; NMF; boosting efficiency; ground objects identification; high-efficiency approach; hyperspectral imagery; hyperspectral unmixing band selection; linear prediction; mass data hyper spectral sensor; mutual information; nonnegative matrix factorization; Algorithm design and analysis; Hyperspectral imaging; Mathematical model; Mutual information; Runtime; band selection; hyperspectral unmixing; nonnegative matrix factorization;

fLanguage

English

Publisher

ieee

Conference_Titel

Intelligent Systems (GCIS), 2012 Third Global Congress on

Conference_Location

Wuhan

Print_ISBN

978-1-4673-3072-5

Type

conf

DOI

10.1109/GCIS.2012.39

Filename

6449503