Nonconvex-Sparsity and Nonlocal-Smoothness-Based Blind Hyperspectral Unmixing
Nonconvex-Sparsity and Nonlocal-Smoothness-Based Blind Hyperspectral Unmixing
复制标题
基于非凸稀疏性和非局部平滑性的盲高光谱解混
DOI：
10.1109/tip.2019.2893068
复制
发表时间：
2019-01
影响因子：
10.6
通讯作者：
Xu Zongben
中科院分区：
文献类型：
--
作者：
Yao Jing;Meng Deyu;Zhao Qian;Cao Wenfei;Xu Zongben
高光谱盲解混（HU）是高光谱数据开发的一项关键技术，其目的是将混合像元分解成由相应的分数丰度加权的组成物质集合。近年来，基于非负矩阵分解（NMF）的方法越来越受欢迎，并取得了良好的效果。在这些方法中，探索了丰度上的两类性质，即稀疏性和结构平滑性，并证明了它们对盲HU的重要性。然而，之前的所有方法都忽略了自然高光谱图像（HSI）所具有的另一个重要的深刻特性，即非局部平滑性，这意味着在更大的HSI区域内的相似斑块共享相似的平滑结构。基于之前对其他任务的尝试，这种先验结构反映了HSI的内在配置，因此有望在很大程度上提高所研究的HU问题的性能。在本文中，我们首先考虑了HSI中的这种先验，将其编码为非局部全变分（NLTV）正则化器。此外，通过充分探索HSI的内在结构，我们将NLTV推广到非局部HSI TV (NLHTV)，使模型更适合盲HU任务。通过将这两种正则化方法与描述丰度映射稀疏性的非凸对数和正则化方法结合到NMF模型中，我们提出了新的盲HU模型NLTV/NLHTV和对数和正则化NMF （NLTV- lsrnmf /NLHTV- lsrnmf）。为了求解所提出的模型，设计了一种基于备选优化策略（AOS）和乘法器交替方向法（ADMM）的高效算法。在模拟和真实高光谱数据集上进行的大量实验证实了该方法在盲HU任务中的优越性。
Blind hyperspectral unmixing (HU), as a crucial technique for hyperspectral data exploitation, aims to decompose mixed pixels into a collection of constituent materials weighted by the corresponding fractional abundances. In recent years, nonnegative matrix factorization (NMF)-based methods have become more and more popular for this task and achieved promising performance. Among these methods, two types of properties upon the abundances, namely, the sparseness and the structural smoothness, have been explored and shown to be important for blind HU. However, all of the previous methods ignore another important insightful property possessed by a natural hyperspectral image (HSI), non-local smoothness, which means that similar patches in a larger region of an HSI are sharing the similar smoothness structure. Based on the previous attempts on other tasks, such a prior structure reflects intrinsic configurations underlying an HSI and is thus expected to largely improve the performance of the investigated HU problem. In this paper, we first consider such prior in HSI by encoding it as the non-local total variation (NLTV) regularizer. Furthermore, by fully exploring the intrinsic structure of HSI, we generalize NLTV to non-local HSI TV (NLHTV) to make the model more suitable for the blind HU task. By incorporating these two regularizers, together with a non-convex log-sum form regularizer characterizing the sparseness of abundance maps, to the NMF model, we propose novel blind HU models named NLTV/NLHTV and log-sum regularized NMF (NLTV-LSRNMF/NLHTV-LSRNMF), respectively. To solve the proposed models, an efficient algorithm is designed based on an alternative optimization strategy (AOS) and alternating direction method of multipliers (ADMM). Extensive experiments conducted on both simulated and real hyperspectral data sets substantiate the superiority of the proposed approach over other competing ones for blind HU task.