Semi-Supervised Endmember Identification In Nonlinear Spectral Mixtures Via Semantic Representation

TL;DR

This paper introduces a semi-supervised hyperspectral unmixing method that uses semantic spectral representations to identify endmembers in nonlinear mixtures without assuming a linear mixing model, outperforming traditional approaches.

Contribution

The paper presents a novel endmember selection technique leveraging NHMC-based semantic spectral representations, enabling nonlinear unmixing without linear model assumptions.

Findings

Outperforms linear dictionary-based unmixing in nonlinear scenarios

Uses semantic spectral features for robust endmember selection

Effective in highly nonlinear spectral mixing conditions

Abstract

This paper proposes a new hyperspectral unmixing method for nonlinearly mixed hyperspectral data using a semantic representation in a semi-supervised fashion, assuming the availability of a spectral reference library. Existing semi-supervised unmixing algorithms select members from an endmember library that are present at each of the pixels; most such methods assume a linear mixing model. However, those methods will fail in the presence of nonlinear mixing among the observed spectra. To address this issue, we develop an endmember selection method using a recently proposed semantic spectral representation obtained via non-homogeneous hidden Markov chain (NHMC) model for a wavelet transform of the spectra. The semantic representation can encode spectrally discriminative features for any observed spectrum and, therefore, our proposed method can perform endmember selection without any assumption on the mixing model. Experimental results show that in the presence of sufficiently nonlinear mixing our proposed method outperforms dictionary-based sparse unmixing approaches based on linear models.