Deep Generative Endmember Modeling: An Application to Unsupervised Spectral Unmixing

Abstract

Endmember (EM) spectral variability can greatly impact the performance of standard hyperspectral image analysis algorithms. Extended parametric models have been successfully applied to account for the EM spectral variability. However, these models still lack the compromise between flexibility and low-dimensional representation that is necessary to properly explore the fact that spectral variability is often confined to a low-dimensional manifold in real scenes. In this paper we propose to learn a spectral variability model directly form the observed data, instead of imposing it \emph{a priori}. This is achieved through a deep generative EM model, which is estimated using a variational autoencoder (VAE). The encoder and decoder that compose the generative model are trained using pure pixel information extracted directly from the observed image, what allows for an unsupervised formulation. The proposed EM model is applied to the solution of a spectral unmixing problem, which we cast as an alternating nonlinear least-squares problem that is solved iteratively with respect to the abundances and to the low-dimensional representations of the EMs in the latent space of the deep generative model. Simulations using both synthetic and real data indicate that the proposed strategy can outperform the competing state-of-the-art algorithms.

References in corpus (8)

• Nonlinear unmixing of hyperspectral images: models and algorithms
• Hyperspectral unmixing with spectral variability using a perturbed linear mixing model
• Tech Report: A Fast Multiscale Spatial Regularization for Sparse Hyperspectral Unmixing
• A Blind Multiscale Spatial Regularization Framework for Kernel-based Spectral Unmixing
• Nonparametric Detection of Nonlinearly Mixed Pixels and Endmember Estimation in Hyperspectral Images
• Technical Report: Band selection for nonlinear unmixing of hyperspectral images as a maximal clique problem
• A Low-rank Tensor Regularization Strategy for Hyperspectral Unmixing
• Improved Hyperspectral Unmixing With Endmember Variability Parametrized Using an Interpolated Scaling Tensor

Cited by in corpus (12)

• Spectral Variability in Hyperspectral Data Unmixing: A Comprehensive Review
• Deep Hyperspectral Unmixing using Transformer Network
• Integration of Physics-Based and Data-Driven Models for Hyperspectral Image Unmixing
• Hyperspectral Unmixing via Deep Autoencoder Networks for a Generalized Linear-Mixture/Nonlinear-Fluctuation Model
• Image Processing and Machine Learning for Hyperspectral Unmixing: An Overview and the HySUPP Python Package
• SSCU-Net: Spatial-Spectral Collaborative Unmixing Network for Hyperspectral Images
• Model-Based Deep Autoencoder Networks for Nonlinear Hyperspectral Unmixing
• A Data Dependent Multiscale Model for Hyperspectral Unmixing With Spectral Variability
• Dynamical Hyperspectral Unmixing with Variational Recurrent Neural Networks
• Deep Generative Models for Library Augmentation in Multiple Endmember Spectral Mixture Analysis
• Kalman Filtering and Expectation Maximization for Multitemporal Spectral Unmixing
• Learning Interpretable Deep Disentangled Neural Networks for Hyperspectral Unmixing