Bayesian unsupervised unmixing of hyperspectral images using a post-nonlinear model

Yoann Altmann, Nicolas Dobigeon, Jean-Yves Tourneret

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)


This paper presents a nonlinear mixing model for hyperspectral image unmixing. The proposed model assumes that the pixel reflectances are post-nonlinear functions of unknown pure spectral components (referred to as endmembers) contaminated by an additive white Gaussian noise. The nonlinear effects affecting endmembers are approximated by polynomial functions leading to a polynomial post-nonlinear mixing model. A Bayesian strategy is used to estimate the parameters of this model yielding an unsupervised nonlinear unmixing algorithm. Due to the large number of parameters to be estimated, an efficient constrained HamiltonianMarkov chain Monte Carlo method is developed to sample according to the posterior of the Bayesian model. The performance of the resulting unmixing strategy is evaluated on synthetic data.

Original languageEnglish
Title of host publication21st European Signal Processing Conference (EUSIPCO 2013)
ISBN (Print)9780992862602
Publication statusPublished - 8 May 2014
Event21st European Signal Processing Conference 2013 - Morocco, Marrakech, Morocco
Duration: 9 Sept 201313 Sept 2013

Publication series

NameEuropean Signal Processing Conference
ISSN (Print)2219-5491
ISSN (Electronic)2076-1465


Conference21st European Signal Processing Conference 2013
Abbreviated titleEUSIPCO 2013


  • Hamiltonian Monte Carlo
  • Hyperspectral imagery
  • post-nonlinear model
  • spectral unmixing

ASJC Scopus subject areas

  • Signal Processing
  • Electrical and Electronic Engineering


Dive into the research topics of 'Bayesian unsupervised unmixing of hyperspectral images using a post-nonlinear model'. Together they form a unique fingerprint.

Cite this