Transformer for Multitemporal Hyperspectral Image Unmixing

TL;DR

This paper introduces MUFormer, a novel transformer-based model for multitemporal hyperspectral image unmixing, incorporating modules for global awareness and change enhancement to improve the analysis of surface dynamics.

Contribution

The paper presents MUFormer, an end-to-end unsupervised deep learning model with innovative modules for capturing global and local temporal changes in hyperspectral data.

Findings

Significantly improves unmixing accuracy on real and synthetic datasets.

Effectively captures semantic information of endmember and abundance changes.

Demonstrates superior performance over existing methods.

Abstract

Multitemporal hyperspectral image unmixing (MTHU) holds significant importance in monitoring and analyzing the dynamic changes of surface. However, compared to single-temporal unmixing, the multitemporal approach demands comprehensive consideration of information across different phases, rendering it a greater challenge. To address this challenge, we propose the Multitemporal Hyperspectral Image Unmixing Transformer (MUFormer), an end-to-end unsupervised deep learning model. To effectively perform multitemporal hyperspectral image unmixing, we introduce two key modules: the Global Awareness Module (GAM) and the Change Enhancement Module (CEM). The Global Awareness Module computes self-attention across all phases, facilitating global weight allocation. On the other hand, the Change Enhancement Module dynamically learns local temporal changes by comparing endmember changes between adjacent phases. The synergy between these modules allows for capturing semantic information regarding endmember and abundance changes, thereby enhancing the effectiveness of multitemporal hyperspectral image unmixing. We conducted experiments on one real dataset and two synthetic datasets, demonstrating that our model significantly enhances the effect of multitemporal hyperspectral image unmixing.