Robust Hyperspectral Unmixing with Correntropy based Metric

TL;DR

This paper introduces a robust hyperspectral unmixing model using a correntropy-based metric, which effectively handles noise and promotes sparsity in endmember abundances, outperforming existing methods.

Contribution

The paper proposes a novel correntropy-based unmixing model with sparsity constraints and a half-quadratic optimization approach, enhancing robustness to noise and improving unmixing accuracy.

Findings

Outperforms state-of-the-art unmixing models on synthetic data.

Effectively suppresses noise influence in hyperspectral unmixing.

Produces sparse and physically meaningful abundance estimates.

Abstract

Hyperspectral unmixing is one of the crucial steps for many hyperspectral applications. The problem of hyperspectral unmixing has proven to be a difficult task in unsupervised work settings where the endmembers and abundances are both unknown. What is more, this task becomes more challenging in the case that the spectral bands are degraded with noise. This paper presents a robust model for unsupervised hyperspectral unmixing. Specifically, our model is developed with the correntropy based metric where the non-negative constraints on both endmembers and abundances are imposed to keep physical significance. In addition, a sparsity prior is explicitly formulated to constrain the distribution of the abundances of each endmember. To solve our model, a half-quadratic optimization technique is developed to convert the original complex optimization problem into an iteratively re-weighted NMF with sparsity constraints. As a result, the optimization of our model can adaptively assign small weights to noisy bands and give more emphasis on noise-free bands. In addition, with sparsity constraints, our model can naturally generate sparse abundances. Experiments on synthetic and real data demonstrate the effectiveness of our model in comparison to the related state-of-the-art unmixing models.