重加权稀疏和全变差约束下的深度非负矩阵分解高光谱解混
Reweighted sparsity regularized deep nonnegative matrix factorization with total variation toward hyperspectral unmixing
- 2020年24卷第4期 页码:401-416
纸质出版日期: 2020-04-07
DOI: 10.11834/jrs.202019193
扫 描 看 全 文
浏览全部资源
扫码关注微信
纸质出版日期: 2020-04-07 ,
扫 描 看 全 文
祝伟,王雪,黄岩,杜培军,谭琨.2020.重加权稀疏和全变差约束下的深度非负矩阵分解高光谱解混.遥感学报,24(4): 401-416Zhu W,Wang X,Huang Y,Du P J and Tan K. 2020. Reweighted sparsity regularized deep nonnegative matrix factorization with total variation toward hyperspectral unmixing. Journal of Remote Sensing(Chinese), 24(4): 401-416[DOI:10.11834/jrs.20209193]
ZHU Wei,WANG Xue,HUANG Yan,DU Peijun,TAN Kun. 2020. Reweighted sparsity regularized deep nonnegative matrix factorization with total variation toward hyperspectral unmixing. Journal of Remote Sensing(Chinese). 24(4): 401-416
近年来,非负矩阵分解NMF(Nonnegative Matrix Factorization)由于其简单有效的特点,已被广泛应用于解混。由于传统的NMF只有单层结构,不能获取隐藏层的信息,其解混效果受到制约,为了研究影像的深度空谱特征,本文在深度NMF结构的基础上,提出了一种基于全变差和重加权稀疏约束的深度非负矩阵分解(RSDNMF-TV)算法。首先,使用深度NMF模型代替传统单层NMF模型,在预训练阶段进行逐层预训练,而在微调阶段减少分解误差。其次,由于丰度矩阵是稀疏的,本文在深度NMF模型中加入重加权稀疏正则化项,其权值则根据丰度矩阵自适应更新。最后,进一步引入全变差正则化项,以利用空间信息并促进丰度图的分段平滑性。论文采用梯度下降法推导出乘性迭代规则,为验证所提出的RSDNMF-TV算法的有效性,利用模拟数据集、Cuprite数据集以及高分五号数据集进行实验,并与其他经典方法作对比,结果发现本方法具有更好的解混效果,同时具有一定的去噪能力。
Hyperspectral unmixing
as a crucial preprocessing step for many hyperspectral applications
refers to the process of decomposing an image into a set of endmembers and corresponding abundance matrices. Nonnegative Matrix Factorization (NMF) has been widely utilized in hyperspectral unmixing because of its simplicity and effectiveness
whereas traditional NMF exits the local minimum problem. Various modified NMFs have been proposed to address such problem. Deep NMF has shown good performance in feature extraction using a multilayer NMF model.
A novel deep NMF algorithm called reweighted sparsity regularized deep NMF with total variation (RSDNMF-TV) is proposed in this study by integrating the total variation and reweighted sparsity with deep layers. First
the deep NMF is obtained by extending the traditional single-layer NMF to the multilayer with pretraining and fine-tuning stages. The former stage pretrains all factors layer by layer
and the latter reduces the decomposition error. Second
a weighted sparse regularizer is integrated into the deep NMF model by sparing the abundance matrix
and its weights are adaptively updated in accordance with the abundance matrix. Finally
the total variation is introduced to improve the piecewise smoothness of abundance maps. In this study
gradient descent method is implemented for the multiplicative update.
The experimental results obtained on simulated and real data sets confirm the effectiveness of the proposed method. For real data sets
we utilized the well-known AVIRIS Cuprite and GF-5 data sets. Six other algorithms
namely
total variation regularized reweighted sparse NMF
spatial group sparsity regularized NMF
minimum-volume CNMF
L
1/2
sparsity CNMF
multilayer NMF
and VCA-FCLS
were used for comparison. The results on the three hyperspectral datasets show that the proposed unmixing method can outperform other algorithms.
In summary
the proposed algorithm achieves improved performance with strong robustness and denoising ability
especially on images with low signal-to-noise ratio. However
RSDNMF-TV has several limitations
which are summarized as follows: (1) the deep NMF has higher computational complexity compared with the traditional NMF. (2) The proposed method only utilizes the prior knowledge of abundance and ignores the constraints on endmembers
such as spectral variability. (3) Parameter
β
is relevant to image’s spatial autocorrelation
and the adaptive selection of the parameter remains challenging. Future work will focus on solving these problems.
遥感高光谱解混深度学习深度非负矩阵分解重加权稀疏全变差
remote sensinghyperspectral unmixingdeep learningdeep nonnegative matrix factorizationreweighted sparsitytotal variation
Adams J B, Smith M O and Johnson P E. 1986. Spectral mixture modeling: a new analysis of rock and soil types at the Viking Lander 1 Site. Journal of Geophysical Research, 91(B8): 8098-8112 [DOI: 10.1029/jb091ib08p08098http://dx.doi.org/10.1029/jb091ib08p08098]
Bayliss J D, Gualtieri J A and Cromp R F. 1997. Analyzing hyperspectral data with independent component analysis//Proceedings of SPIE 3240, 26th AIPR Workshop: Exploiting New Image Sources and Sensors. Washington, DC, United States: SPIE: 3240 [DOI: 10.1117/12.300050http://dx.doi.org/10.1117/12.300050]
Beck A and Teboulle M. 2009. Fast gradient-based algorithms for constrained total variation image denoising and deblurring problems. IEEE Transactions on Image Processing, 18(11): 2419-2434 [DOI: 10.1109/TIP.2009.2028250http://dx.doi.org/10.1109/TIP.2009.2028250]
Bioucas-Dias J M and Nascimento J M P. 2008. Hyperspectral subspace identification. IEEE Transactions on Geoscience and Remote Sensing, 46(8): 2435-2445 [DOI: 10.1109/TGRS.2008.918089http://dx.doi.org/10.1109/TGRS.2008.918089]
Bioucas-Dias J M, Plaza A, Dobigeon N, Parente M, Du Q, Gader P and Chanussot J. 2012. Hyperspectral unmixing overview: geometrical, statistical, and sparse regression-based approaches. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 5(2): 354-379 [DOI: 10.1109/JSTARS.2012.2194696http://dx.doi.org/10.1109/JSTARS.2012.2194696]
Candès E J, Wakin M B and Boyd S P. 2008. Enhancing sparsity by reweighted ℓ1 minimization. Journal of Fourier Analysis and Applications, 14(5/6): 877-905 [DOI: 10.1007/s00041-008-9045-xhttp://dx.doi.org/10.1007/s00041-008-9045-x]
Chan T H, Chi C Y, Huang Y M and Ma W K. 2009. A convex analysis-based minimum-volume enclosing simplex algorithm for hyperspectral unmixing. IEEE Transactions on Signal Processing, 57(11): 4418-4432 [DOI: 10.1109/tsp.2009.2025802http://dx.doi.org/10.1109/tsp.2009.2025802]
相关作者
相关机构