Hyperspectral Unmixing Overview: Geometrical, Statistical, and Sparse Regression-Based Approaches

TL;DR

This paper provides a comprehensive overview of hyperspectral unmixing methods, covering geometrical, statistical, and sparse regression approaches, highlighting their models, challenges, and experimental characteristics.

Contribution

It offers a detailed survey of unmixing techniques from foundational to recent methods, emphasizing their models, mathematical issues, and experimental insights.

Findings

Geometrical and statistical methods effectively estimate endmembers.

Sparse regression approaches improve unmixing accuracy.

Spatial-contextual algorithms enhance robustness in noisy conditions.

Abstract

Imaging spectrometers measure electromagnetic energy scattered in their instantaneous field view in hundreds or thousands of spectral channels with higher spectral resolution than multispectral cameras. Imaging spectrometers are therefore often referred to as hyperspectral cameras (HSCs). Higher spectral resolution enables material identification via spectroscopic analysis, which facilitates countless applications that require identifying materials in scenarios unsuitable for classical spectroscopic analysis. Due to low spatial resolution of HSCs, microscopic material mixing, and multiple scattering, spectra measured by HSCs are mixtures of spectra of materials in a scene. Thus, accurate estimation requires unmixing. Pixels are assumed to be mixtures of a few materials, called endmembers. Unmixing involves estimating all or some of: the number of endmembers, their spectral signatures, and their abundances at each pixel. Unmixing is a challenging, ill-posed inverse problem because of model inaccuracies, observation noise, environmental conditions, endmember variability, and data set size. Researchers have devised and investigated many models searching for robust, stable, tractable, and accurate unmixing algorithms. This paper presents an overview of unmixing methods from the time of Keshava and Mustard's unmixing tutorial [1] to the present. Mixing models are first discussed. Signal-subspace, geometrical, statistical, sparsity-based, and spatial-contextual unmixing algorithms are described. Mathematical problems and potential solutions are described. Algorithm characteristics are illustrated experimentally.