A Hierarchical Bayesian Model Accounting for Endmember Variability and Abrupt Spectral Changes to Unmix Multitemporal Hyperspectral Images

TL;DR

This paper introduces a hierarchical Bayesian model for multitemporal hyperspectral unmixing that effectively handles both smooth spectral variability and abrupt spectral changes, improving accuracy in complex scenarios.

Contribution

The paper presents a novel hierarchical Bayesian unmixing model that accounts for both spectral variability and outliers in multitemporal hyperspectral images, using MCMC inference.

Findings

The proposed model outperforms existing methods on synthetic data.

It effectively captures both gradual and abrupt spectral changes.

Results demonstrate improved unmixing accuracy in real datasets.

Abstract

Hyperspectral unmixing is a blind source separation problem which consists in estimating the reference spectral signatures contained in a hyperspectral image, as well as their relative contribution to each pixel according to a given mixture model. In practice, the process is further complexified by the inherent spectral variability of the observed scene and the possible presence of outliers. More specifically, multi-temporal hyperspectral images, i.e., sequences of hyperspectral images acquired over the same area at different time instants, are likely to simultaneously exhibit moderate endmember variability and abrupt spectral changes either due to outliers or to significant time intervals between consecutive acquisitions. Unless properly accounted for, these two perturbations can significantly affect the unmixing process. In this context, we propose a new unmixing model for multitemporal hyperspectral images accounting for smooth temporal variations, construed as spectral variability, and abrupt spectral changes interpreted as outliers. The proposed hierarchical Bayesian model is inferred using a Markov chain Monte-Carlo (MCMC) method allowing the posterior of interest to be sampled and Bayesian estimators to be approximated. A comparison with unmixing techniques from the literature on synthetic and real data allows the interest of the proposed approach to be appreciated.