Nonlinear Hyperspectral Unmixing based on Multilinear Mixing Model using Convolutional Autoencoders

TL;DR

This paper introduces a novel autoencoder-based neural network for nonlinear hyperspectral unmixing using the multilinear mixing model, explicitly modeling endmembers, abundances, and transition probabilities, with spectral and spatial modes.

Contribution

It proposes a new deep learning framework that explicitly incorporates the multilinear mixing model into an autoencoder architecture for unsupervised spectral unmixing.

Findings

Achieves competitive performance on synthetic datasets.

Effectively models spectral-spatial correlations.

Outperforms traditional methods in nonlinear unmixing tasks.

Abstract

Unsupervised spectral unmixing consists of representing each observed pixel as a combination of several pure materials called endmembers with their corresponding abundance fractions. Beyond the linear assumption, various nonlinear unmixing models have been proposed, with the associated optimization problems solved either by traditional optimization algorithms or deep learning techniques. Current deep learning-based nonlinear unmixing focuses on the models in additive, bilinear-based formulations. By interpreting the reflection process using the discrete Markov chain, the multilinear mixing model (MLM) successfully accounts for the up to infinite-order interactions between endmembers. However, to simulate the physics process of MLM by neural networks explicitly is a challenging problem that has not been approached by far. In this article, we propose a novel autoencoder-based network for unsupervised unmixing based on MLM. Benefitting from an elaborate network design, the relationships among all the model parameters {\em i.e.}, endmembers, abundances, and transition probability parameters are explicitly modeled. There are two modes: MLM-1DAE considers only pixel-wise spectral information, and MLM-3DAE exploits the spectral-spatial correlations within input patches. Experiments on both the synthetic and real datasets demonstrate the effectiveness of the proposed method as it achieves competitive performance to the classic solutions of MLM.