Sparse Linear Spectral Unmixing of Hyperspectral Images Using Expectation-Propagation
Sparse Linear Spectral Unmixing of Hyperspectral Images Using Expectation-Propagation
复制标题
基于期望传播的高光谱图像稀疏线性混合光谱分解
DOI：
10.1109/tgrs.2022.3147423
复制
发表时间：
2021-06
影响因子：
8.2
通讯作者：
Zeng Li;Y. Altmann;Jie Chen;S. Mclaughlin;S. Rahardja
中科院分区：
文献类型：
--
作者：
Zeng Li;Y. Altmann;Jie Chen;S. Mclaughlin;S. Rahardja
本文提出了一种新的贝叶斯方法的高光谱图像分解。观察到的像素被建模的材料签名加权其相应的丰度的线性组合。一个尖峰和板丰度先验被用来促进稀疏的混合物和伊辛先验模型被用来捕捉跨像素的混合物支持的空间相关性。我们近似的后验分布的丰度使用的期望传播（EP）方法。我们表明，它可以显着降低计算复杂性的解混阶段，同时提供不确定性的措施，相比传统上考虑的不确定性量化昂贵的蒙特卡罗策略。此外，每个EP因子内的许多变分参数可以以并行方式更新，这使得能够基于图形处理单元（GPU）映射有效的算法架构。在相同的近似贝叶斯框架下，我们将所提出的算法扩展到半监督解混，从而将丰度视为潜在变量，并使用期望最大化（EM）算法来细化端元矩阵。在合成数据和真实的高光谱数据上的实验结果表明，该框架优于现有的线性混合分解方法。
This article presents a novel Bayesian approach for hyperspectral image unmixing. The observed pixels are modeled by a linear combination of material signatures weighted by their corresponding abundances. A spike-and-slab abundance prior is adopted to promote sparse mixtures and an Ising prior model is used to capture spatial correlation of the mixture support across pixels. We approximate the posterior distribution of the abundances using the expectation-propagation (EP) method. We show that it can significantly reduce the computational complexity of the unmixing stage and meanwhile provide uncertainty measures, compared to expensive Monte Carlo strategies traditionally considered for uncertainty quantification. Moreover, many variational parameters within each EP factor can be updated in a parallel manner, which enables mapping of efficient algorithmic architectures based on graphics processing units (GPUs). Under the same approximate Bayesian framework, we then extend the proposed algorithm to semi-supervised unmixing, whereby the abundances are viewed as latent variables and the expectation-maximization (EM) algorithm is used to refine the endmember matrix. Experimental results on synthetic data and real hyperspectral data illustrate the benefits of the proposed framework over state-of-art linear unmixing methods.