Unmixing of Hyperspectral Data Using Robust Statistics-based NMF

TL;DR

This paper introduces a robust statistics-based nonnegative matrix factorization method for spectral unmixing in hyperspectral images, effectively handling outliers and improving unmixing accuracy.

Contribution

The paper presents a novel RNMF approach that enhances spectral unmixing by incorporating robust cost functions and iterative updates, outperforming traditional NMF methods.

Findings

RNMF effectively handles outliers in hyperspectral data.

Compared to traditional NMF, RNMF shows improved unmixing accuracy.

Method validated on simulated and real datasets.

Abstract

Mixed pixels are presented in hyperspectral images due to low spatial resolution of hyperspectral sensors. Spectral unmixing decomposes mixed pixels spectra into endmembers spectra and abundance fractions. In this paper using of robust statistics-based nonnegative matrix factorization (RNMF) for spectral unmixing of hyperspectral data is investigated. RNMF uses a robust cost function and iterative updating procedure, so is not sensitive to outliers. This method has been applied to simulated data using USGS spectral library, AVIRIS and ROSIS datasets. Unmixing results are compared to traditional NMF method based on SAD and AAD measures. Results demonstrate that this method can be used efficiently for hyperspectral unmixing purposes.