Semi-Supervised Endmember Identification In Nonlinear Spectral Mixtures Via Semantic Representation

01/03/2017
by   Yuki Itoh, et al.
0

This paper proposes a new hyperspectral unmixing method for nonlinearly mixed hyperspectral data using a semantic representation in a semi-supervised fashion, assuming the availability of a spectral reference library. Existing semi-supervised unmixing algorithms select members from an endmember library that are present at each of the pixels; most such methods assume a linear mixing model. However, those methods will fail in the presence of nonlinear mixing among the observed spectra. To address this issue, we develop an endmember selection method using a recently proposed semantic spectral representation obtained via non-homogeneous hidden Markov chain (NHMC) model for a wavelet transform of the spectra. The semantic representation can encode spectrally discriminative features for any observed spectrum and, therefore, our proposed method can perform endmember selection without any assumption on the mixing model. Experimental results show that in the presence of sufficiently nonlinear mixing our proposed method outperforms dictionary-based sparse unmixing approaches based on linear models.

READ FULL TEXT

page 5

page 10

page 11

page 12

research
10/19/2021

Spectral Variability Augmented Sparse Unmixing of Hyperspectral Images

Spectral unmixing (SU) expresses the mixed pixels existed in hyperspectr...
research
12/04/2012

Unmixing of Hyperspectral Data Using Robust Statistics-based NMF

Mixed pixels are presented in hyperspectral images due to low spatial re...
research
04/30/2018

Hyperspectral unmixing with spectral variability using adaptive bundles and double sparsity

Spectral variability is one of the major issue when conducting hyperspec...
research
04/14/2016

Unsupervised Nonlinear Spectral Unmixing based on a Multilinear Mixing Model

In the community of remote sensing, nonlinear mixing models have recentl...
research
09/13/2016

Mapping the Similarities of Spectra: Global and Locally-biased Approaches to SDSS Galaxy Data

We apply a novel spectral graph technique, that of locally-biased semi-s...
research
02/08/2018

Archetypal Analysis for Sparse Representation-based Hyperspectral Sub-pixel Quantification

The estimation of land cover fractions from remote sensing images is a f...
research
03/01/2016

Technical Report: Band selection for nonlinear unmixing of hyperspectral images as a maximal clique problem

Kernel-based nonlinear mixing models have been applied to unmix spectral...

Please sign up or login with your details

Forgot password? Click here to reset