Spectral Unmixing with Multiple Dictionaries

TL;DR

This paper introduces M2PALS, a novel algorithm for spectral unmixing that leverages multiple spectral dictionaries and allows user-guided or segmentation-based selection of pure pixels, improving flexibility and accuracy.

Contribution

It proposes a multiple-dictionary constrained low-rank matrix approximation model and an algorithm to implement it, addressing limitations of existing spectral unmixing methods.

Findings

Effective on synthetic hyperspectral data

Demonstrated improved unmixing accuracy on real images

Flexible in handling multiple spectral libraries

Abstract

Spectral unmixing aims at recovering the spectral signatures of materials, called endmembers, mixed in a hyperspectral or multispectral image, along with their abundances. A typical assumption is that the image contains one pure pixel per endmember, in which case spectral unmixing reduces to identifying these pixels. Many fully automated methods have been proposed in recent years, but little work has been done to allow users to select areas where pure pixels are present manually or using a segmentation algorithm. Additionally, in a non-blind approach, several spectral libraries may be available rather than a single one, with a fixed number (or an upper or lower bound) of endmembers to chose from each. In this paper, we propose a multiple-dictionary constrained low-rank matrix approximation model that address these two problems. We propose an algorithm to compute this model, dubbed M2PALS, and its performance is discussed on both synthetic and real hyperspectral images.