scholarly journals Sparse Nonnegative Matrix Factorization for Hyperspectral Unmixing Based on Endmember Independence and Spatial Weighted Abundance

2021 ◽  
Vol 13 (12) ◽  
pp. 2348
Author(s):  
Jingyan Zhang ◽  
Xiangrong Zhang ◽  
Licheng Jiao
Keyword(s):  
Matrix Factorization ◽  
Nonnegative Matrix Factorization ◽  
Hyperspectral Image ◽  
Nonnegative Matrix ◽  
Hyperspectral Data ◽  
Underlying Structure ◽  
Mixed Pixel ◽  
Hyperspectral Unmixing ◽  
Autocorrelation Matrix ◽  
Sparse Nonnegative Matrix Factorization

Hyperspectral image unmixing is an important task for remote sensing image processing. It aims at decomposing the mixed pixel of the image to identify a set of constituent materials called endmembers and to obtain their proportions named abundances. Recently, number of algorithms based on sparse nonnegative matrix factorization (NMF) have been widely used in hyperspectral unmixing with good performance. However, these sparse NMF algorithms only consider the correlation characteristics of abundance and usually just take the Euclidean structure of data into account, which can make the extracted endmembers become inaccurate. Therefore, with the aim of addressing this problem, we present a sparse NMF algorithm based on endmember independence and spatial weighted abundance in this paper. Firstly, it is assumed that the extracted endmembers should be independent from each other. Thus, by utilizing the autocorrelation matrix of endmembers, the constraint based on endmember independence is to be constructed in the model. In addition, two spatial weights for abundance by neighborhood pixels and correlation coefficient are proposed to make the estimated abundance smoother so as to further explore the underlying structure of hyperspectral data. The proposed algorithm not only considers the relevant characteristics of endmembers and abundances simultaneously, but also makes full use of the spatial-spectral information in the image, achieving a more desired unmixing performance. The experiment results on several data sets further verify the effectiveness of the proposed algorithm.

A Review of the Hyperspectral Unmixing Methods that Based on Constrained NMF and Constrained Sparse Regression

2015 ◽  
Vol 713-715 ◽  
pp. 1540-1545
Author(s):  
Cheng Yong Zheng
Keyword(s):  
Image Analysis ◽  
Matrix Factorization ◽  
Nonnegative Matrix Factorization ◽  
Hyperspectral Image ◽  
Nonnegative Matrix ◽  
The Other ◽  
Research Topics ◽  
Sparse Regression ◽  
Hyperspectral Unmixing ◽  
Hyperspectral Image Analysis

Hyperspectral unmixing (HSU) plays an important role in hyperspectral image analysis, and most of the current HSU algorithms are base on linear mixing model (LMM). This paper gives a review of two linear HSU methods that have been drawn great attention recently: one is constrained nonnegative matrix factorization (CNMF) based method, the other is constrained sparse regression (CSR) based method. We carried on the systematic summary to these two types of methods, based on which, we point out some potential research topics.

Nonnegative matrix factorization with region sparsity learning for hyperspectral unmixing

2017 ◽  
Vol 15 (06) ◽  
pp. 1750063
Author(s):  
Bin Qian ◽  
Lei Tong ◽  
Zhenmin Tang ◽  
Xiaobo Shen
Keyword(s):  
Matrix Factorization ◽  
Nonnegative Matrix Factorization ◽  
Spatial Information ◽  
State Of The Art ◽  
Nonnegative Matrix ◽  
Hyperspectral Data ◽  
Optimization Scheme ◽  
Hyperspectral Unmixing ◽  
Relationship Of ◽  
The Relationship

Hyperspectral unmixing is one of the most important techniques in the remote sensing image analysis tasks. In recent decades, nonnegative matrix factorization (NMF) has been shown to be effective for hyperspectral unmixing due to the strong discovery of the latent structure. Most NMFs put emphasize on the spectral information, but ignore the spatial information, which is very crucial for analyzing hyperspectral data. In this paper, we propose an improved NMF method, namely NMF with region sparsity learning (RSLNMF), to simultaneously consider both spectral and spatial information. RSLNMF defines a new sparsity learning model based on a small homogeneous region that is obtained via the graph cut algorithm. Thus RSLNMF is able to explore the relationship of spatial neighbor pixels within each region. An efficient optimization scheme is developed for the proposed RSLNMF, and its convergence is theoretically guaranteed. Experiments on both synthetic and real hyperspectral data validate the superiority of the proposed method over several state-of-the-art unmixing approaches.

scholarly journals Maximum Likelihood Estimation Based Nonnegative Matrix Factorization for Hyperspectral Unmixing

2021 ◽  
Vol 13 (13) ◽  
pp. 2637
Author(s):  
Qin Jiang ◽  
Yifei Dong ◽  
Jiangtao Peng ◽  
Mei Yan ◽  
Yi Sun
Keyword(s):  
Maximum Likelihood ◽  
Maximum Likelihood Estimation ◽  
Objective Function ◽  
Least Squares ◽  
Matrix Factorization ◽  
Nonnegative Matrix Factorization ◽  
Nonnegative Matrix ◽  
Likelihood Estimation ◽  
Hyperspectral Data ◽  
Hyperspectral Unmixing

Hyperspectral unmixing (HU) is a research hotspot of hyperspectral remote sensing technology. As a classical HU method, the nonnegative matrix factorization (NMF) unmixing method can decompose an observed hyperspectral data matrix into the product of two nonnegative matrices, i.e., endmember and abundance matrices. Because the objective function of NMF is the traditional least-squares function, NMF is sensitive to noise. In order to improve the robustness of NMF, this paper proposes a maximum likelihood estimation (MLE) based NMF model (MLENMF) for unmixing of hyperspectral images (HSIs), which substitutes the least-squares objective function in traditional NMF by a robust MLE-based loss function. Experimental results on a simulated and two widely used real hyperspectral data sets demonstrate the superiority of our MLENMF over existing NMF methods.

Nonnegative matrix factorization with entropy regularization for hyperspectral unmixing

2021 ◽  
Vol 42 (16) ◽  
pp. 6362-6393
Author(s):  
Junmin Liu ◽  
Shuai Yuan ◽  
Xuehu Zhu ◽  
Yifan Huang ◽  
Qian Zhao
Keyword(s):  
Matrix Factorization ◽  
Nonnegative Matrix Factorization ◽  
Nonnegative Matrix ◽  
Hyperspectral Unmixing
Sign in / Sign up

Export Citation Format

Share Document