Hyperspectral Image Restoration Using Low-Rank Tensor Recovery

Fan, Houbao; Chen, Yunjin; Guo, Yulan; Zhang, Hongyan; Kuang, Gangyao

doi:10.1109/jstars.2017.2714338

Cited by 162 publications

(84 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The same strategy can also be applied to the endmember tensor if one considers the endmember variabilities to be small or highly correlated in low-dimensional structures within the HI. The low-rank property of HI tensors has been an important tool in the design of hyperspectral image completion [33] and restoration algorithms [34], consisting in one of the main lowdimensional structures that are currently being considered in hyperspectral imaging applications. Thus, assuming that A has a low-rank K A , and that M has a low-rank K M the global cost functional for the unmixing problem can be written as…”

Section: Low-rank Unmixing Problemmentioning

confidence: 99%

Low-Rank Tensor Modeling for Hyperspectral Unmixing Accounting for Spectral Variability

Imbiriba

Borsoi

Bermudez

2020

IEEE Trans. Geosci. Remote Sensing

View full text Add to dashboard Cite

Traditional hyperspectral unmixing methods neglect the underlying variability of spectral signatures often observed in typical hyperspectral images (HI), propagating these missmodeling errors throughout the whole unmixing process. Attempts to model material spectra as members of sets or as random variables tend to lead to severely ill-posed unmixing problems. Although parametric models have been proposed to overcome this drawback by handling endmember variability through generalizations of the mixing model, the success of these techniques depend on employing appropriate regularization strategies. Moreover, the existing approaches fail to adequately explore the natural multidimensinal representation of HIs. Recently, tensor-based strategies considered low-rank decompositions of hyperspectral images as an alternative to impose low-dimensional structures on the solutions of standard and multitemporal unmixing problems . These strategies, however, present two main drawbacks: 1) they confine the solutions to low-rank tensors, which often cannot represent the complexity of real-world scenarios; and 2) they lack guarantees that endmembers and abundances will be correctly factorized in their respective tensors. In this work, we propose a more flexible approach, called ULTRA-V, that imposes low-rank structures through regularizations whose strictness is controlled by scalar parameters. Simulations attest the superior accuracy of the method when compared with state-of-the-art unmixing algorithms that account for spectral variability.

show abstract

Section: Low-rank Unmixing Problemmentioning

confidence: 99%

Low-Rank Tensor Modeling for Hyperspectral Unmixing Accounting for Spectral Variability

Imbiriba

Borsoi

Bermudez

2020

IEEE Trans. Geosci. Remote Sensing

View full text Add to dashboard Cite

show abstract

“…To illustrate the effectiveness of the proposed method, experiments are conducted on the synthetic and the real data. The compared methods consist of LRTA [8], BM4D [14], LRMR [4], WSNLRMA [5], and LRTR [10]. The parameters of the compared methods are optimally assigned or selected as suggested in the reference papers.…”

Section: Methodsmentioning

confidence: 99%

“…The tensor tubal rank, based on the tensor singular value decomposition (t-SVD), is magnetic for well characterizing the inherent low-rank structure of a tensor. Tensor nuclear norm (TNN) was considered formulating a low-rank tensor recovery model (LRTR) [10] for effective HSIs denoising. Although TNN as a popular surrogate of the tubal rank has obtained promising results, it is just a suboptimal surrogate of the tubal rank.…”

Section: Introductionmentioning

confidence: 99%

Constrained Low-Tubal-Rank Tensor Recovery for Hyperspectral Images Mixed Noise Removal by Bilateral Random Projections

Zhang

Zhao

Jiang

et al. 2019

IGARSS 2019 - 2019 IEEE International Geoscience and Remote Sensing Symposium

View full text Add to dashboard Cite

In this paper, we propose a novel low-tubal-rank tensor recovery model, which directly constrains the tubal rank prior for effectively removing the mixed Gaussian and sparse noise in hyperspectral images. The constraints of tubal-rank and sparsity can govern the solution of the denoised tensor in the recovery procedure. To solve the constrained low-tubal-rank model, we develop an iterative algorithm based on bilateral random projections to efficiently solve the proposed model. The advantage of random projections is that the approximation of the low-tubal-rank tensor can be obtained quite accurately in an inexpensive manner. Experimental examples for hyperspectral image denoising are presented to demonstrate the effectiveness and efficiency of the proposed method.Index Terms-Tensor, bilateral random projections, low-tubal-rank, mixed noise, hyperspectral images.

show abstract

“…The wealth of spectral information in HSIs has opened new perspectives in different applications, such as target detection, spectral unmixing, object classification, and matching [1][2][3][4][5][6][7][8][9][10][11][12][13]. The underlying assumption in object classification techniques is that each pixel comprises the response of only one material.…”

Section: Introductionmentioning

confidence: 99%

“…In addition, the noise levels of Bands 1 and 220 are evidently higher than those of the other three bands, and previous sparse unmixing methods treat all the bands similarly. However, for real HSIs, the noise levels of different bands vary, and bands with high noise levels will dominate the loss function Y − EA 2 F , where Y denotes the collected mixed pixel, E denotes the spectral library, A denotes the abundance matrix, and . F represents the matrix Frobenius norm.…”

Section: Introductionmentioning

confidence: 99%

Sparse Unmixing of Hyperspectral Data with Noise Level Estimation

Mei

et al. 2017

Remote Sensing

View full text Add to dashboard Cite

Abstract:Recently, sparse unmixing has received particular attention in the analysis of hyperspectral images (HSIs). However, traditional sparse unmixing ignores the different noise levels in different bands of HSIs, making such methods sensitive to different noise levels. To overcome this problem, the noise levels at different bands are assumed to be different in this paper, and a general sparse unmixing method based on noise level estimation (SU-NLE) under the sparse regression framework is proposed. First, the noise in each band is estimated on the basis of the multiple regression theory in hyperspectral applications, given that neighboring spectral bands are usually highly correlated. Second, the noise weighting matrix can be obtained from the estimated noise. Third, the noise weighting matrix is integrated into the sparse regression unmixing framework, which can alleviate the impact of different noise levels at different bands. Finally, the proposed SU-NLE is solved by the alternative direction method of multipliers. Experiments on synthetic datasets show that the signal-to-reconstruction error of the proposed SU-NLE is considerably higher than those of the corresponding traditional sparse regression unmixing methods without noise level estimation, which demonstrates the efficiency of integrating noise level estimation into the sparse regression unmixing framework. The proposed SU-NLE also shows promising results in real HSIs.Keywords: alternative direction method of multipliers (ADMM); hyperspectral image (HSI); sparse unmixing method based on noise level estimation (SU-NLE)

show abstract

Hyperspectral Image Restoration Using Low-Rank Tensor Recovery

Cited by 162 publications

References 50 publications

Low-Rank Tensor Modeling for Hyperspectral Unmixing Accounting for Spectral Variability

Low-Rank Tensor Modeling for Hyperspectral Unmixing Accounting for Spectral Variability

Constrained Low-Tubal-Rank Tensor Recovery for Hyperspectral Images Mixed Noise Removal by Bilateral Random Projections

Sparse Unmixing of Hyperspectral Data with Noise Level Estimation

Contact Info

Product

Resources

About