Abstract

This paper presents a new Bayesian model and algorithm for nonlinear unmixing of hyperspectral images. The model proposed represents the pixel reflectances as linear combinations of the endmembers, corrupted by nonlinear (with respect to the endmembers) terms and additive Gaussian noise. Prior knowledge about the problem is embedded in a hierarchical model that describes the dependence structure between the model parameters and their constraints. In particular, a gamma Markov random field is used to model the joint distribution of the nonlinear terms, which are expected to exhibit significant spatial correlations. An adaptive Markov chain Monte Carlo algorithm is then proposed to compute the Bayesian estimates of interest and perform Bayesian inference. This algorithm is equipped with a stochastic optimisation adaptation mechanism that automatically adjusts the parameters of the gamma Markov random field by maximum marginal likelihood estimation. Finally, the proposed methodology is demonstrated through a series of experiments with comparisons using synthetic and real data and with competing state-of-the-art approaches.
Original languageEnglish
JournalIEEE Transactions on Computational Imaging
Early online date23 Sep 2015
DOIs
Publication statusPublished - 2015

Fingerprint

Markov chain
reflectance
pixel
analysis
methodology
experiment
parameter
distribution
state of the art
comparison

Keywords

  • stat.ME

Cite this

@article{9ad0dc0356ee4b15acbfc3d4f34d2337,
title = "Bayesian nonlinear hyperspectral unmixing with spatial residual component analysis",
abstract = "This paper presents a new Bayesian model and algorithm for nonlinear unmixing of hyperspectral images. The model proposed represents the pixel reflectances as linear combinations of the endmembers, corrupted by nonlinear (with respect to the endmembers) terms and additive Gaussian noise. Prior knowledge about the problem is embedded in a hierarchical model that describes the dependence structure between the model parameters and their constraints. In particular, a gamma Markov random field is used to model the joint distribution of the nonlinear terms, which are expected to exhibit significant spatial correlations. An adaptive Markov chain Monte Carlo algorithm is then proposed to compute the Bayesian estimates of interest and perform Bayesian inference. This algorithm is equipped with a stochastic optimisation adaptation mechanism that automatically adjusts the parameters of the gamma Markov random field by maximum marginal likelihood estimation. Finally, the proposed methodology is demonstrated through a series of experiments with comparisons using synthetic and real data and with competing state-of-the-art approaches.",
keywords = "stat.ME",
author = "Yoann Altmann and Marcelo Pereyra and Stephen McLaughlin",
note = "{"}This study was supported by the Direction Gen´ erale de l’armement, French Ministry of Defence, by the SuSTaIN program - EPSRC grant EP/D063485/1 - at the Department of Mathematics, University of Bristol, and the EPSRC via grant EP/J015180/1.{"}",
year = "2015",
doi = "10.1109/TCI.2015.2481603",
language = "English",
journal = "IEEE Transactions on Computational Imaging",
issn = "2333-9403",
publisher = "IEEE",

}

TY - JOUR

T1 - Bayesian nonlinear hyperspectral unmixing with spatial residual component analysis

AU - Altmann, Yoann

AU - Pereyra, Marcelo

AU - McLaughlin, Stephen

N1 - "This study was supported by the Direction Gen´ erale de l’armement, French Ministry of Defence, by the SuSTaIN program - EPSRC grant EP/D063485/1 - at the Department of Mathematics, University of Bristol, and the EPSRC via grant EP/J015180/1."

PY - 2015

Y1 - 2015

N2 - This paper presents a new Bayesian model and algorithm for nonlinear unmixing of hyperspectral images. The model proposed represents the pixel reflectances as linear combinations of the endmembers, corrupted by nonlinear (with respect to the endmembers) terms and additive Gaussian noise. Prior knowledge about the problem is embedded in a hierarchical model that describes the dependence structure between the model parameters and their constraints. In particular, a gamma Markov random field is used to model the joint distribution of the nonlinear terms, which are expected to exhibit significant spatial correlations. An adaptive Markov chain Monte Carlo algorithm is then proposed to compute the Bayesian estimates of interest and perform Bayesian inference. This algorithm is equipped with a stochastic optimisation adaptation mechanism that automatically adjusts the parameters of the gamma Markov random field by maximum marginal likelihood estimation. Finally, the proposed methodology is demonstrated through a series of experiments with comparisons using synthetic and real data and with competing state-of-the-art approaches.

AB - This paper presents a new Bayesian model and algorithm for nonlinear unmixing of hyperspectral images. The model proposed represents the pixel reflectances as linear combinations of the endmembers, corrupted by nonlinear (with respect to the endmembers) terms and additive Gaussian noise. Prior knowledge about the problem is embedded in a hierarchical model that describes the dependence structure between the model parameters and their constraints. In particular, a gamma Markov random field is used to model the joint distribution of the nonlinear terms, which are expected to exhibit significant spatial correlations. An adaptive Markov chain Monte Carlo algorithm is then proposed to compute the Bayesian estimates of interest and perform Bayesian inference. This algorithm is equipped with a stochastic optimisation adaptation mechanism that automatically adjusts the parameters of the gamma Markov random field by maximum marginal likelihood estimation. Finally, the proposed methodology is demonstrated through a series of experiments with comparisons using synthetic and real data and with competing state-of-the-art approaches.

KW - stat.ME

U2 - 10.1109/TCI.2015.2481603

DO - 10.1109/TCI.2015.2481603

M3 - Article

JO - IEEE Transactions on Computational Imaging

JF - IEEE Transactions on Computational Imaging

SN - 2333-9403

ER -