Hyperspectral Unmixing Using Sparsity-Constrained Deep Nonnegative Matrix Factorization With Total Variation

Feng, Xin-Ru; Li, Heng-Chao; Li, Jun; Du, Qian; Plaza, Antonio; Emery, William J.

doi:10.1109/tgrs.2018.2834567

Cited by 117 publications

(69 citation statements)

References 53 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To verify the effectiveness of our proposed method, we conducted experiments on both simulated and real-world dataset. The compared hyperspectral unmixing methods include baseline methods VCA-FCLS [16] and NMF [23], sparsity-based methods L 1/2 -NMF [28] and graph-regularized L 1/2 -NMF (GLNMF) [37], spatial information based methods SGSNMF [41], TV-RSNMF [34], Multilayer NMF method MLNMF [52] and sparsity-constrained deep NMF with total variation (SDNMF-TV) [35]. The results were evaluated with two commonly used measures to assess the quantitative unmixing performance: spectral angle distance (SAD) and rootmean-square error (RMSE).…”

Section: Resultsmentioning

confidence: 99%

“…This is due to the fact that endmembers are distributed to form coherent geometric structures, and two correlated pixels usually have similar fractional abundances for the same endmembers. Therefore, the total variation (TV) regularizer [33]- [35] was incorporated to promote piece-wise smooth transitions in the abundance matrix for neighboring pixels of the same endmember category. In [36], abundance separation and smoothness constrained NMF (ASSNMF) was proposed for hyperspectral unmixing.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Subspace Structure Regularized Nonnegative Matrix Factorization for Hyperspectral Unmixing

Zhou

Zhang

Wang

et al. 2020

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

Hyperspectral unmixing is a crucial task for hyperspectral images (HSI) processing, which estimates the proportions of constituent materials of a mixed pixel. Usually, the mixed pixels can be approximated using a linear mixing model. Since each material only occurs in a few pixels in real HSI, sparse nonnegative matrix factorization (NMF) and its extensions are widely used as solutions. Some recent works assume that materials are distributed in certain structures, which can be added as constraints to sparse NMF model. However, they only consider the spatial distribution within a local neighborhood and define the distribution structure manually, while ignoring the real distribution of materials that is diverse in different images. In this paper, we propose a new unmixing method that learns a subspace structure from the original image and incorporate it into the sparse NMF framework to promote unmixing performance. Based on the self-representation property of data points lying in the same subspace, the learned subspace structure can indicate the global similar graph of pixels that represents the real distribution of materials. Then the similar graph is used as a robust global spatial prior which is expected to be maintained in the decomposed abundance matrix. The experiments conducted on both simulated and real-world HSI datasets demonstrate the superior performance of our proposed method.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Subspace Structure Regularized Nonnegative Matrix Factorization for Hyperspectral Unmixing

Zhou

Zhang

Wang

et al. 2020

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

show abstract

“…Finally, as deep learning for NMF has recently been preliminarily investigated (e.g. [43],), deep NMF models for binary image representation and decomposition would be worth investigating in future work.…”

Section: Discussionmentioning

confidence: 99%

A novel non-negative matrix factorization technique for decomposition of Chinese characters with application to secret sharing

Lin

Huang

et al. 2019

EURASIP J. Adv. Signal Process.

View full text Add to dashboard Cite

The decomposition of Chinese characters is difficult and has been rarely investigated in the literature. In this paper, we propose a novel non-negative matrix factorization (NMF) technique to decompose a Chinese character into several graphical components without considering the strokes of the character or any semantic or phonetic properties of the components. Chinese characters can usually be represented as binary images. However, traditional NMF is only suitable for representing general gray-level or color images. To decompose a binary image using NMF, we force all of the elements of the two matrices (obtained by factorizing the binary image/matrix to be decomposed) as close to 0 or 1 as possible. As a result, a Chinese character can be efficiently decomposed into several components, where each component is semantically unreadable. Moreover, our NMF-based Chinese character decomposition method is suitable for applications in visual secret sharing by distributing the shares (different character components) among multiple parties, so that only when the parties are taken together with their respective shares can the secret (the original Chinese character(s)) be reconstructed. Experimental results have verified the decomposition performance and the feasibility of the proposed method.

show abstract

“…The most popular algorithms for NMF belong to the class of multiplicative Lee-Seung algorithms, which have relatively low complexity but are characterized by slow convergence and risk becoming stuck in local minima [9]. To improve the performance of the NMF based hyperspectral unmixing method, further constraints were imposed on NMF [10][11][12][13][14]. Miao and Qi proposed a minimum volume constrained non-negative matrix factorization [15].…”

Section: Introductionmentioning

confidence: 99%

A Multiscale Hierarchical Model for Sparse Hyperspectral Unmixing

Zou

Lan

2019

Remote Sensing

View full text Add to dashboard Cite

Due to the complex background and low spatial resolution of the hyperspectral sensor, observed ground reflectance is often mixed at the pixel level. Hyperspectral unmixing (HU) is a hot-issue in the remote sensing area because it can decompose the observed mixed pixel reflectance. Traditional sparse hyperspectral unmixing often leads to an ill-posed inverse problem, which can be circumvented by spatial regularization approaches. However, their adoption has come at the expense of a massive increase in computational cost. In this paper, a novel multiscale hierarchical model for a method of sparse hyperspectral unmixing is proposed. The paper decomposes HU into two domain problems, one is in an approximation scale representation based on resampling the method’s domain, and the other is in the original domain. The use of multiscale spatial resampling methods for HU leads to an effective strategy that deals with spectral variability and computational cost. Furthermore, the hierarchical strategy with abundant sparsity representation in each layer aims to obtain the global optimal solution. Both simulations and real hyperspectral data experiments show that the proposed method outperforms previous methods in endmember extraction and abundance fraction estimation, and promotes piecewise homogeneity in the estimated abundance without compromising sharp discontinuities among neighboring pixels. Additionally, compared with total variation regularization, the proposed method reduces the computational time effectively.

show abstract

Hyperspectral Unmixing Using Sparsity-Constrained Deep Nonnegative Matrix Factorization With Total Variation

Cited by 117 publications

References 53 publications

Subspace Structure Regularized Nonnegative Matrix Factorization for Hyperspectral Unmixing

Subspace Structure Regularized Nonnegative Matrix Factorization for Hyperspectral Unmixing

A novel non-negative matrix factorization technique for decomposition of Chinese characters with application to secret sharing

A Multiscale Hierarchical Model for Sparse Hyperspectral Unmixing

Contact Info

Product

Resources

About