Nonlinear unmixing of hyperspectral images: models and algorithms

TL;DR

This paper reviews recent advances in nonlinear unmixing models for hyperspectral images, addressing limitations of linear models in complex scenarios like multi-scattering effects.

Contribution

It provides a comprehensive overview of new nonlinear unmixing models and algorithms developed to improve hyperspectral image analysis.

Findings

Nonlinear models better handle multi-scattering effects.

Recent algorithms improve unmixing accuracy.

Overview of state-of-the-art nonlinear approaches.

Abstract

When considering the problem of unmixing hyperspectral images, most of the literature in the geoscience and image processing areas relies on the widely used linear mixing model (LMM). However, the LMM may be not valid and other nonlinear models need to be considered, for instance, when there are multi-scattering effects or intimate interactions. Consequently, over the last few years, several significant contributions have been proposed to overcome the limitations inherent in the LMM. In this paper, we present an overview of recent advances in nonlinear unmixing modeling.