Fast Linear Unmixing of Hyperspectral Image by Slow Feature Analysis and Simplex Volume Ratio Approach

Das, Samiran; Chakraborty, Sohom; Routray, Aurobinda; Deb, Alok Kanti

doi:10.1109/igarss.2019.8898127

Cited by 12 publications

(6 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the subsequent stage, we carried out library-pruning using the covariance similarity approach [83] due to its inherent capacity to identify the exact, optimal endmember set and reduced computational requirement. In the final step, we computed the abundance of the end members using according to Das et al [84]. The sparse inversion method enlisted in this work incorporated characteristic attributes, such as the structural dissimilarity of the abundance images, the sparsity, and the low-rank attribute of the abundance, and obtained ameliorated performance.…”

Section: E Result: Effect Of Band Selection On Unmixing Performancementioning

confidence: 99%

Sparsity Regularized Deep Subspace Clustering for Multicriterion-Based Hyperspectral Band Selection

Das¹,

Pratiher

Kyal

et al. 2022

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

Self Cite

View full text Add to dashboard Cite

Hyperspectral images provide rich spectral information corresponding to visible and Near-infrared imaging (NIR) regions, facilitating accurate classification, object identification, and target detection. However, the high volume of data creates a computational challenge in processing. The band selection process identifies specific informative and discriminative spectral bands from the data to speed up the processing without impeding the performance. This paper presents an application-independent band selection framework that utilizes improved sparse deep subspace clustering and introduces an efficient multicriteria-based representative band selection (BS). The proposed sparse deep subspace clustering approach efficiently identifies the underlying non-linear subspace structure of the data and organizes the data accordingly. The work introduces a novel, robust sparsity measure to obtain a powerful self-representation and ameliorated performance compared to the prevalent subspace clustering methods. The work subsequently selects the representative bands from each cluster by combining structural information of the band images with the statistical similarity measure. We evaluate the BS performance on standard real images using informationtheoretic criterion, classification, and unmixing performance. The comparative performance assessment demonstrates that our proposed method identifies the informative bands and outperforms the other approaches in terms of the subsequent tasks.

show abstract

Section: E Result: Effect Of Band Selection On Unmixing Performancementioning

confidence: 99%

Sparsity Regularized Deep Subspace Clustering for Multicriterion-Based Hyperspectral Band Selection

Das¹,

Pratiher

Kyal

et al. 2022

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

Self Cite

View full text Add to dashboard Cite

show abstract

“…Besides, the individual abundance maps are spatially dissimilar to each other. However, some work 7 demonstrated that pq-norm instead of the standard l0.5 norm or l1 norm, results in improved abundance maps 64 . This work utilized pq-norm sparsity, as well as the low-rankness and the structural dissimilarity as regularization terms according to the following formulation: arg minA ‖X−AD‖2+λ1‖A‖pq−Norm+λ2‖A‖*+λ3∑i=1P∑j=i+1P1FSIM(ai,aj)+ϵ,where the feature similarity index 65 FSIM() quantifies the structural similarity between two abundance images, and D denotes the spectral library comprising of …”

Section: Proposed Workmentioning

confidence: 99%

“…In this treatise, we have proposed a novel hyperspectral compression paradigm based on library-based unmixing. 7 The unmixing framework includes determining the number of endmembers by a novel eigenvalue-based index called mixed norm, library pruning by covariance similarity approach, 8 and abundance computation by a new norm relaxation-based regularized sparse inversion formulation. The unmixing process attains a highly sparse and low-rank abundance tensor, which follows the sum-to-one constraint.…”

Section: Introductionmentioning

confidence: 99%

Unmixing aware compression of hyperspectral image by rank aware orthogonal parallel factorization decomposition

Das,

Ghosal

2023

J. Appl. Rem. Sens.

Self Cite

View full text Add to dashboard Cite

.Efficient compression is pertinent for the convenient storage, transmission, and processing of modern high-resolution hyperspectral images (HSI). We propose a high-performance HSI compression method using library-based spectral unmixing and tensor decomposition. Unlike the existing approaches, our proposed work incorporates unmixing in the compression framework and achieves significantly higher compression performance with negligible loss. The proposed library-based unmixing method includes an index for accurate endmember number estimation, followed by exact library pruning and a sparsity regularized formulation with norm-smoothing to compute the abundance maps. As the spectral library is available at the reconstruction (decoder) side also; compressing the abundance maps is as good as compressing the original HSI data. Since the abundance constraints used for the unmixing indicate the correlation of the abundance maps, compressing all abundance maps seems to cause redundant computation. A metric using the image smoothness and information measures is used here to identify the abundance map hardest to compress and the remaining part is left uncompressed. Subsequently, the work compresses the abundance map tensor using orthogonal PARAFAC decomposition with optimal rank determination. The orthogonalization process ensures that the factors span independent subspaces and reduces redundancy, whereas the rank selection prevents noisy or insignificant components. Extensive experiments are carried out to demonstrate that the unmixing workflow leads to negligible loss due to accurate endmember number estimation, exact library pruning, and accurate physically meaningful sparse inversion. Comparative assessments of compression efficacy suggest that the proposed work corresponds to better compression performance and higher classification accuracy.

show abstract

“…We employ sparsity of the abundance matrix, the low-rank attribute of the abundance matrix as regularization terms in the abundance computation (27). We also utilized the structural dissimilarity between the abundance images for the inversion Algorithm 2 Proposed GAP Index based Dictionary Pruning (DP-GAPVD)…”

Section: Abundance Computation By Low-rank and Structured Sparse Imentioning

confidence: 99%

Semi-blind Unmixing of Hyperspectral Image by Eigenvalue based Virtual Dimensionality Estimation

Das¹

2020

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

Fast Linear Unmixing of Hyperspectral Image by Slow Feature Analysis and Simplex Volume Ratio Approach

Cited by 12 publications

References 23 publications

Sparsity Regularized Deep Subspace Clustering for Multicriterion-Based Hyperspectral Band Selection

Sparsity Regularized Deep Subspace Clustering for Multicriterion-Based Hyperspectral Band Selection

Unmixing aware compression of hyperspectral image by rank aware orthogonal parallel factorization decomposition

Semi-blind Unmixing of Hyperspectral Image by Eigenvalue based Virtual Dimensionality Estimation

Contact Info

Product

Resources

About