Spatial Group Sparsity Regularized Nonnegative Matrix Factorization for Hyperspectral Unmixing

Wang, Xinyu; Zhang, Liangpei; Xu, Yinghui

doi:10.1109/tgrs.2017.2724944

Cited by 193 publications

(98 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The spatial information could be incorporated with the L 2 sparse constraint in order to achieve a more accuracy result. Similar to [30] and [31], a pixel-wise or region-smart L 2 sparse constraint might be developed.…”

Section: Discussionmentioning

confidence: 99%

“…We considered the ASC constraint in the same way as [13]. When updating S during the iteration, X and A were replaced by X C and A C , which were defined as Equation (31). Where δ controlled the strength of the constraint, in this paper, we set δ to 20.…”

Section: Implementation Issuesmentioning

confidence: 99%

“…Zhu et al has proposed a data-guided sparse method, in which the value of q for each pixel is determined by a learned data-guided map in order to adaptively impose the sparseness constraint [30]. A similar idea was adopted by Wang et al, as they incorporated a spatial group sparseness constraint into NMF for HU, which supposes that the pixels within a local spatial group share the same sparse structure [31].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Bilateral Filter Regularized L2 Sparse Nonnegative Matrix Factorization for Hyperspectral Unmixing

et al. 2018

View full text Add to dashboard Cite

Hyperspectral unmixing (HU) is one of the most active hyperspectral image (HSI) processing research fields, which aims to identify the materials and their corresponding proportions in each HSI pixel. The extensions of the nonnegative matrix factorization (NMF) have been proved effective for HU, which usually uses the sparsity of abundances and the correlation between the pixels to alleviate the non-convex problem. However, the commonly used L 1/2 sparse constraint will introduce an additional local minima because of the non-convexity, and the correlation between the pixels is not fully utilized because of the separation of the spatial and structural information. To overcome these limitations, a novel bilateral filter regularized L 2 sparse NMF is proposed for HU. Firstly, the L 2 -norm is utilized in order to improve the sparsity of the abundance matrix. Secondly, a bilateral filter regularizer is adopted so as to explore both the spatial information and the manifold structure of the abundance maps. In addition, NeNMF is used to solve the object function in order to improve the convergence rate. The results of the simulated and real data experiments have demonstrated the advantage of the proposed method.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Implementation Issuesmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Bilateral Filter Regularized L2 Sparse Nonnegative Matrix Factorization for Hyperspectral Unmixing

et al. 2018

View full text Add to dashboard Cite

show abstract

“…By feature extraction, a projection matrix is used to map the original spectral data to a feature space while holding the dominant spectral information [13]. Typical feature extraction algorithms include principal component analysis (PCA) [14], linear discriminant analysis (LDA) [15], manifold learning [16], nonnegative matrix factorization (NMF) [17] and spatial-spectral feature extraction [18].…”

Section: Introductionmentioning

confidence: 99%

Comparison of CNN Algorithms on Hyperspectral Image Classification in Agricultural Lands

Hsieh

Kiang

2020

Sensors

View full text Add to dashboard Cite

Several versions of convolutional neural network (CNN) were developed to classify hyperspectral images (HSIs) of agricultural lands, including 1D-CNN with pixelwise spectral data, 1D-CNN with selected bands, 1D-CNN with spectral-spatial features and 2D-CNN with principal components. The HSI data of a crop agriculture in Salinas Valley and a mixed vegetation agriculture in Indian Pines were used to compare the performance of these CNN algorithms. The highest overall accuracy on these two cases are 99.8% and 98.1%, respectively, achieved by applying 1D-CNN with augmented input vectors, which contain both spectral and spatial features embedded in the HSI data.

show abstract

“…Several works, such as SUnSAL-TV [5] or S2WSU [6], proposed to use TV-norm regularization to achieve this goal. Identification of clusters of spectrally similar pixels, scattered in small groups, was also used to impose spatial smoothing of the abundances, e.g., in [7]- [9]. In a different way, other works used the local neighborhood to identify the subset of endmembers present in the neighborhood.…”

Section: Introductionmentioning

confidence: 99%

Matrix Cofactorization for Joint Spatial–Spectral Unmixing of Hyperspectral Images

Lagrange

Fauvel

May

et al. 2020

IEEE Trans. Geosci. Remote Sensing

View full text Add to dashboard Cite

Hyperspectral unmixing aims at identifying a set of elementary spectra and the corresponding mixture coefficients for each pixel of an image. As the elementary spectra correspond to the reflectance spectra of real materials, they are often very correlated yielding an ill-conditioned problem. To enrich the model and to reduce ambiguity due to the high correlation, it is common to introduce spatial information to complement the spectral information. The most common way to introduce spatial information is to rely on a spatial regularization of the abundance maps. In this paper, instead of considering a simple but limited regularization process, spatial information is directly incorporated through the newly proposed context of spatial unmixing. Contextual features are extracted for each pixel and this additional set of observations is decomposed according to a linear model. Finally the spatial and spectral observations are unmixed jointly through a cofactorization model. In particular, this model introduces a coupling term used to identify clusters of shared spatial and spectral signatures. An evaluation of the proposed method is conducted on synthetic and real data and shows that results are accurate and also very meaningful since they describe both spatially and spectrally the various areas of the scene.

show abstract

Spatial Group Sparsity Regularized Nonnegative Matrix Factorization for Hyperspectral Unmixing

Cited by 193 publications

References 44 publications

Bilateral Filter Regularized L2 Sparse Nonnegative Matrix Factorization for Hyperspectral Unmixing

Bilateral Filter Regularized L2 Sparse Nonnegative Matrix Factorization for Hyperspectral Unmixing

Comparison of CNN Algorithms on Hyperspectral Image Classification in Agricultural Lands

Matrix Cofactorization for Joint Spatial–Spectral Unmixing of Hyperspectral Images

Contact Info

Product

Resources

About