Bayesian Unmixing using Sparse Dirichlet Prior with Polynomial Post-nonlinear Mixing Model

TL;DR

This paper introduces a Bayesian unmixing method for hyperspectral images using a sparse Dirichlet prior within a polynomial post-nonlinear mixing model, significantly improving estimation accuracy in semi-supervised scenarios.

Contribution

It proposes a novel sparse Dirichlet prior for nonlinear hyperspectral unmixing, enabling better abundance estimation without exact material knowledge.

Findings

Over 50% reduction in estimation error.

Effective in semi-supervised unmixing scenarios.

Improved accuracy over existing methods.

Abstract

A sparse Dirichlet prior is proposed for estimating the abundance vector of hyperspectral images with a nonlinear mixing model. This sparse prior is led to an unmixing procedure in a semi-supervised scenario in which exact materials are unknown. The nonlinear model is a polynomial post-nonlinear mixing model that represents each hyperspectral pixel as a nonlinear function of pure spectral signatures corrupted by additive white noise. Simulation results show more than 50% improvement in the estimation error.