Multilayer Structured NMF for Spectral Unmixing of Hyperspectral Images

TL;DR

This paper introduces a multilayer NMF approach with sparseness constraints for spectral unmixing in hyperspectral images, improving accuracy over existing methods by decomposing mixed pixels into endmembers and abundances.

Contribution

The paper presents a novel multilayer NMF method with sparseness constraints that enhances spectral unmixing performance in hyperspectral data analysis.

Findings

Outperforms previous spectral unmixing methods

Reduces spectral and abundance angle distances

Effective on both synthetic and real datasets

Abstract

One of the challenges in hyperspectral data analysis is the presence of mixed pixels. Mixed pixels are the result of low spatial resolution of hyperspectral sensors. Spectral unmixing methods decompose a mixed pixel into a set of endmembers and abundance fractions. Due to nonnegativity constraint on abundance fraction values, NMF based methods are well suited to this problem. In this paper multilayer NMF has been used to improve the results of NMF methods for spectral unmixing of hyperspectral data under the linear mixing framework. Sparseness constraint on both spectral signatures and abundance fractions matrices are used in this paper. Evaluation of the proposed algorithm is done using synthetic and real datasets in terms of spectral angle and abundance angle distances. Results show that the proposed algorithm outperforms other previously proposed methods.