Hyperspectral Unmixing using a Structured Linear Mixing Model with Additive Spectral Variability
Abstract
Linear hyperspectral unmixing aims at retrieving pure material spectra present in an observed scene and their associated abundance fractions in each pixel. In most practical situations, hyperspectral images are affected by spectral variability (SV) also known as intra-class variability, which is caused by different physical phenomena including atmospheric effects, intrinsic variability of the pure materials and illumination or topographic changes. Nevertheless, the standard hyperspectral unmixing methods that rely on the Linear Mixing Model (LMM) do not consider these phenomena. Thus, neglecting them will spread errors throughout the linear hyperspectral unmixing process. To avoid this problem, this paper proposes two hyperspectral unmixing algorithms dedicated to a parametric model called Structured Additive Variability LMM (SAV-LMM). This mixing model handles SV in an additive manner by incorporating two terms into the standard LMM. Moreover, the designed algorithms are based on Nonnegative Matrix Factorization (NMF) and optimize a cost function which integrates additional penalization accounting for SV. Furthermore, a novel improved initialization scheme, which takes SV into account, is proposed. Experiments conducted on both synthetic and real datasets show the effectiveness of the proposed algorithms for linearly unmixing hyperspectral images with SV compared to the tested state-of-the-art methods.
Related
- Spatial-Spectral Trade-offs in Metasurface-Based Snapshot Hyperspectral Imaging
- RIS-based classification and EPR spectral variability of smartphone touchscreen glasses
- Robust acoustic representation of Japanese vowels under phonation variability using dynamic spectral analysis
- A Spectral Model for the Rainfall Variability Production
- From Variability to Spectral Energy Distribution Modeling: A Multiwavelength Study of the Neutrino Blazar TXS 0506+056
BibTeX
@misc{brezini2026hyperspectral,
title = {{Hyperspectral Unmixing using a Structured Linear Mixing Model with Additive Spectral Variability}},
author = {Salah Eddine Brezini and Yannick Deville and Moussa Sofiane Karoui and Fatima Zohra Benhalouche and Abdelaziz Ouamri},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.35580},
eprint = {2610.35580},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.35580},
}
RIS
TY - UNPB
TI - Hyperspectral Unmixing using a Structured Linear Mixing Model with Additive Spectral Variability
AU - Salah Eddine Brezini
AU - Yannick Deville
AU - Moussa Sofiane Karoui
AU - Fatima Zohra Benhalouche
AU - Abdelaziz Ouamri
PY - 2026
DA - 2026/10/26
PB - arXiv
DO - 10.48550/arxiv.2610.35580
UR - https://arxiv.org/abs/2610.35580
AB - Linear hyperspectral unmixing aims at retrieving pure material spectra present in an observed scene and their associated abundance fractions in each pixel. In most practical situations, hyperspectral images are affected by spectral variability (SV) also known as intra-class variability, which is caused by different physical phenomena including atmospheric effects, intrinsic variability of the pure materials and illumination or topographic changes. Nevertheless, the standard hyperspectral unmixing methods that rely on the Linear Mixing Model (LMM) do not consider these phenomena. Thus, neglecting them will spread errors throughout the linear hyperspectral unmixing process. To avoid this problem, this paper proposes two hyperspectral unmixing algorithms dedicated to a parametric model called Structured Additive Variability LMM (SAV-LMM). This mixing model handles SV in an additive manner by incorporating two terms into the standard LMM. Moreover, the designed algorithms are based on Nonnegative Matrix Factorization (NMF) and optimize a cost function which integrates additional penalization accounting for SV. Furthermore, a novel improved initialization scheme, which takes SV into account, is proposed. Experiments conducted on both synthetic and real datasets show the effectiveness of the proposed algorithms for linearly unmixing hyperspectral images with SV compared to the tested state-of-the-art methods.
ER -