Paper Info
Title
Bayesian Estimation of Linear Mixtures Using the Normal Compositional Model. Application to Hyperspectral Imagery
Abstract
This paper studies a new Bayesian unmixing algorithm for hyperspectral images. Each pixel of the image is modeled as a linear combination of so-called endmembers. These endmembers are supposed to be random in order to model uncertainties regarding their knowledge. More precisely, we model endmembers as Gaussian vectors whose means have been determined using an endmember extraction algorithm such as the famous N-finder (N-FINDR) or Vertex Component Analysis (VCA) algorithms. This paper proposes to estimate the mixture coefficients (referred to as abundances) using a Bayesian algorithm. Suitable priors are assigned to the abundances in order to satisfy positivity and additivity constraints whereas conjugate priors are chosen for the remaining parameters. A hybrid Gibbs sampler is then constructed to generate abundance and variance samples distributed according to the joint posterior of the abundances and noise variances. The performance of the proposed methodology is evaluated by comparison with other unmixing algorithms on synthetic and real images.
Year
DOI
Venue
2010
10.1109/TIP.2010.2042993
IEEE Transactions on Image Processing
Keywords
Field
DocType
Bayes methods,geophysical image processing,Bayesian estimation,N-flnder,endmembers,hybrid Gibbs sampler,hyperspectral imagery,linear mixtures,normal compositional model,vertex component analysis,Bayesian inference,Monte Carlo methods,hyperspectral images,normal compositional model,spectral unmixing
Endmember,Linear combination,Bayesian inference,Pattern recognition,Linear model,Artificial intelligence,Prior probability,Bayes estimator,Conjugate prior,Gibbs sampling,Mathematics
Journal
Volume
Issue
ISSN
19
6
1057-7149
Citations 
PageRank 
References 
54
2.35
10
Authors
4
Name
Order
Citations
PageRank
Olivier Eches1542.35
Nicolas Dobigeon22070108.02
Corinne Mailhes3542.35
Jean-Yves Tourneret483564.32