Unsupervised unmixing of hyperspectral images accounting for endmember variability

Abderrahim Halimi (1) , Nicolas Dobigeon (1) , Jean-Yves Tourneret (2)

1 IRIT-SC - Signal et Communications
2 IRIT-MINDS - CoMputational imagINg anD viSion

This paper presents an unsupervised Bayesian algorithm for hyperspectral image unmixing, accounting for endmember variability. The pixels are modeled by a linear combination of endmembers weighted by their corresponding abundances. However, the endmembers are assumed random to consider their variability in the image. An additive noise is also considered in the proposed model, generalizing the normal compositional model. The proposed algorithm exploits the whole image to benefit from both spectral and spatial information. It estimates both the mean and the covariance matrix of each endmember in the image. This allows the behavior of each material to be analyzed and its variability to be quantified in the scene. A spatial segmentation is also obtained based on the estimated abundances. In order to estimate the parameters associated with the proposed Bayesian model, we propose to use a Hamiltonian Monte Carlo algorithm. The performance of the resulting unmixing strategy is evaluated through simulations conducted on both synthetic and real data.

Mots clés: MCMC methods; Hyperspectral imagery; endmember variability; image classification; spectral unmixing; Bayesian algorithm; Hamiltonian Monte-Carlo

Domaines: Informatique [cs]

Abderrahim Halimi, Nicolas Dobigeon, Jean-Yves Tourneret. Unsupervised unmixing of hyperspectral images accounting for endmember variability. IEEE Transactions on Image Processing, 2015, 24 (12), pp.4904--4917. ⟨10.1109/TIP.2015.2471182⟩. ⟨hal-03198231⟩