Probabilistic Generative Model for Hyperspectral Unmixing Accounting for Endmember Variability

• Published in: IEEE transactions on geoscience and remote sensing Vol. 60; pp. 1 - 15
• Main Authors: Shi, Shuaikai, Zhao, Min, Zhang, Lijun, Altmann, Yoann, Chen, Jie
• Format: Journal Article
• Language: English
• Published: New York IEEE 2022; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Atmospheric modeling; Covariance matrices; Data models; Endmember variability; Environmental conditions; Estimates; Hyperspectral imaging; hyperspectral unmixing; Libraries; Methods; Modelling; Neural networks; Perturbation methods; probabilistic generative model; Probabilistic logic; Remote sensing; Spatial distribution; Spectra; Spectral signatures; Variability; variational inference (VI)
• ISSN: 0196-2892; 1558-0644
• DOI: 10.1109/TGRS.2021.3121799

The complex nature of hyperspectral images makes the analysis of spectral signatures a challenging task in remote sensing. For quantitative analysis, spectral unmixing is a well-established and effective tool to analyze the spectra and spatial distribution of substances in the scene. The classical unmixing algorithms usually fail to tackle spectral variability caused by variations in environmental conditions. Many variants based on the linear mixing process have been proposed to tackle this problem; however, the spectral variability modeling capacity of these algorithms is usually insufficient. In this article, we present a probabilistic generative model to address endmember variability and provide more accurate abundance and endmember estimates. The proposed model simultaneously extracts the endmembers and estimates abundances in an unsupervised manner. In particular, it allows fitting arbitrary endmember distributions through the nonlinear modeling capability of neural networks compared to other methods that use parametric endmember variability models. The performance of the proposed approach is evaluated on both synthetic and real datasets. Experimental results show its superiority in comparison with other state-of-the-art methods. The code of this work is available at https://github.com/shuaikaishi/PGMSU for the sake of reproducibility.