Skip to Main content Skip to Navigation
Conference papers

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

Yoann Altmann 1 Nicolas Dobigeon 1 Jean-Yves Tourneret 1
1 IRIT-SC - Signal et Communications
IRIT - Institut de recherche en informatique de Toulouse
Abstract : 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 contaminated by an additive white Gaussian noise. The nonlinear effects are approximated by a polynomial leading to a polynomial post-nonlinear mixing model. A Bayesian algorithm is proposed to estimate the parameters involved in the model yielding an unsupervised nonlinear unmixing algorithm. Due to the large number of parameters to be estimated, an efficient constrained Hamiltonian Monte Carlo algorithm is investigated. The performance of the unmixing strategy is finally evaluated on synthetic data.
Complete list of metadatas

Cited literature [15 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01239743
Contributor : Open Archive Toulouse Archive Ouverte (oatao) <>
Submitted on : Tuesday, December 8, 2015 - 10:50:53 AM
Last modification on : Tuesday, October 13, 2020 - 1:58:03 PM
Long-term archiving on: : Wednesday, March 9, 2016 - 1:20:24 PM

File

altmann_12547.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01239743, version 1
  • OATAO : 12547

Citation

Yoann Altmann, Nicolas Dobigeon, Jean-Yves Tourneret. Bayesian algorithm for unsupervised unmixing of hyperspectral images using a post-nonlinear model. 21st European Signal and Image Processing Conference (EUSIPCO 2013), Sep 2013, Marrakech, Morocco. pp. 1-5. ⟨hal-01239743⟩

Share

Metrics

Record views

228

Files downloads

65