A Low-rank Tensor Regularization Strategy for Hyperspectral Unmixing

TL;DR

This paper proposes a flexible low-rank tensor regularization method for hyperspectral unmixing that improves results by better capturing the underlying structure without losing important fine-scale information.

Contribution

It introduces a novel low-rank tensor regularization strategy that balances low-rank constraints with solution flexibility in hyperspectral unmixing.

Findings

Enhanced unmixing accuracy on synthetic data

Improved results on real hyperspectral datasets

Flexibility preserves fine-scale abundance details

Abstract

Tensor-based methods have recently emerged as a more natural and effective formulation to address many problems in hyperspectral imaging. In hyperspectral unmixing (HU), low-rank constraints on the abundance maps have been shown to act as a regularization which adequately accounts for the multidimensional structure of the underlying signal. However, imposing a strict low-rank constraint for the abundance maps does not seem to be adequate, as important information that may be required to represent fine scale abundance behavior may be discarded. This paper introduces a new low-rank tensor regularization that adequately captures the low-rank structure underlying the abundance maps without hindering the flexibility of the solution. Simulation results with synthetic and real data show that the the extra flexibility introduced by the proposed regularization significantly improves the unmixing results.