Hyperspectral Mixed Noise Removal By $\ell _1$-Norm-Based Subspace Representation

Zhuang, Lina; Ng, Michael K.

doi:10.1109/jstars.2020.2979801

Cited by 72 publications

(24 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We perform the simulated and real experiments to illustrate the efficiency and performance of our NLBTD method to restore HSI in this section. There are six methods are used to compare the performance of remove noise, consist of the lowrank matrix factorization with TV [22] (denoted as LRTV), a method combining with HyRes and sparse noise removal technique [54] (denoted as HyMiNoR), three-directional tensor nuclear norm method [23] (denoted as 3DTNN), a subspacebased method [52] (denoted as L1HyMixDe), low-rank tucker decomposition with spatial-spectral TV [55] (denoted as LRT-DTV), and block terms decomposition with spatial-spectral TV [41] (denoted as LRTFL0). According to the author's suggestions, we tune the parameters of these state-of-the-art methods to achieve optimal performance.…”

Section: Methodsmentioning

confidence: 99%

“…To tackle the proposed model, we designed an efficient algorithm based on the proximal alternating minimization and theoretically prove its global convergence. Extensive experimental results demonstrated that our NLBTD has superior performance in mixed noise removal compared with the state-of-the-art competing methods, including LRTV [22], HyMiNoR [54], 3DTNN [23], L1HyMixDe [52], LRT-DTV [55], and LRTFL0 [41]. In the future, we will improve our model to further enhance efficiency by using advanced techniques, e.g., parallel computing.…”

Section: ) Efficiency Analysismentioning

confidence: 97%

“…However, in practice, observed HSI is polluted by not only Gaussian noise but also other noises, which results in the fact that the similar blocks of the clean HSI cannot be approximated by the similar blocks of observed HSI. In this paper, we employ L1HyMixDe [52] to initialize the observed HSI to match similar blocks. Note that we only use the restored result of L1HyMixDe to initialize the observed HSI to match similar image blocks.…”

Section: Casementioning

confidence: 99%

See 2 more Smart Citations

Nonlocal Block-Term Decomposition for Hyperspectral Image Mixed Noise Removal

Zeng

Huang

Chen

et al. 2021

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

View full text Add to dashboard Cite

Since the facility restrictions and weather conditions, hyperspectral image (HSI) is generally seriously polluted by a variety of noises. Recently, the method based on block term decomposition with rank-(L, L, 1) (BTD) has attracted wide attention in HSI mixed noise removal. BTD factorizes thirdorder HSI data into the sum of a series of component tensors, where each of the component tensors is represented by the outer product of a rank-L matrix ArB T r and a column vector cr. BTD has clear physical interpretation because its latent factors ArB T r and cr can be interpreted abundance map and spectral signature respectively. The essential uniqueness of BTD is under the lowrank assumption of ArB T r . However, the low-rank assumption is not always held in real scenarios. The BTD-based method usually sets L to full rank to achieve satisfactory results. In this paper, we suggest a novel model based on nonlocal block term decomposition (NLBTD) for HSI mixed noise removal. More specifically, for each grouped similar image block, BTD is introduced to capture nonlocal self-similarity and global spectral lowrankness, the unidirectional total variation (TV) is introduced to preserve local spectral smoothness. By faithfully exploring nonlocal self-similarity, global spectral low-rankness, and local spectral smoothness, the proposed method is expected to produce promising results with guarantee the essential uniqueness of BTD. To tackle the resulting model, we design an efficient algorithm based on the proximal alternating minimization with the theoretical guarantees. Extensive numerical experiments in HSI mixed noise removal demonstrate that the proposed NLBTD method achieves satisfactory performance compared with stateof-the-art methods.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: ) Efficiency Analysismentioning

confidence: 97%

Section: Casementioning

confidence: 99%

See 1 more Smart Citation

Nonlocal Block-Term Decomposition for Hyperspectral Image Mixed Noise Removal

Zeng

Huang

Chen

et al. 2021

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

View full text Add to dashboard Cite

show abstract

“…Recently, the subspace low-rank (SLR) representation method has shown great potential to address the above challenges [48][49][50][51][52]. The theory of manifold learning suggests that the data in high-dimensional space is immoderately redundant, and principal information lives in the low-dimensional subspace [53].…”

Section: Restoration By Subspace Projectionmentioning

confidence: 99%

SLRL4D: Joint Restoration of Subspace Low-Rank Learning and Non-Local 4-D Transform Filtering for Hyperspectral Image

Sun

Zheng

et al. 2020

Remote Sensing

View full text Add to dashboard Cite

During the process of signal sampling and digital imaging, hyperspectral images (HSI) inevitably suffer from the contamination of mixed noises. The fidelity and efficiency of subsequent applications are considerably reduced along with this degradation. Recently, as a formidable implement for image processing, low-rank regularization has been widely extended to the restoration of HSI. Meanwhile, further exploration of the non-local self-similarity of low-rank images are proven useful in exploiting the spatial redundancy of HSI. Better preservation of spatial-spectral features is achieved under both low-rank and non-local regularizations. However, existing methods generally regularize the original space of HSI, the exploration of the intrinsic properties in subspace, which leads to better denoising performance, is relatively rare. To address these challenges, a joint method of subspace low-rank learning and non-local 4-d transform filtering, named SLRL4D, is put forward for HSI restoration. Technically, the original HSI is projected into a low-dimensional subspace. Then, both spectral and spatial correlations are explored simultaneously by imposing low-rank learning and non-local 4-d transform filtering on the subspace. The alternating direction method of multipliers-based algorithm is designed to solve the formulated convex signal-noise isolation problem. Finally, experiments on multiple datasets are conducted to illustrate the accuracy and efficiency of SLRL4D.

show abstract

“…Plug and play technique is a flexible framework that allows imaging models to be combined with state-of-the-art priors or denoising models [37]. This is the main idea of plug-and-play technique, which has been successfully used to solve inverse problems of images, such as image inpainting [38,39], compressive sensing [40], and super-resolution [41,42]. Instead of investing effort in designing more powerful regularizations on abundances, we use directly a prior from a state-of-the-art denoiser as the regularization, which is conceived to exploit the spatial correlation of abundance maps.…”

Section: Introductionmentioning

confidence: 99%

Hyperspectral Nonlinear Unmixing by Using Plug-and-Play Prior for Abundance Maps

et al. 2020

Self Cite

View full text Add to dashboard Cite

Spectral unmixing (SU) aims at decomposing the mixed pixel into basic components, called endmembers with corresponding abundance fractions. Linear mixing model (LMM) and nonlinear mixing models (NLMMs) are two main classes to solve the SU. This paper proposes a new nonlinear unmixing method base on general bilinear model, which is one of the NLMMs. Since retrieving the endmembers’ abundances represents an ill-posed inverse problem, prior knowledge of abundances has been investigated by conceiving regularizations techniques (e.g., sparsity, total variation, group sparsity, and low rankness), so to enhance the ability to restrict the solution space and thus to achieve reliable estimates. All the regularizations mentioned above can be interpreted as denoising of abundance maps. In this paper, instead of investing effort in designing more powerful regularizations of abundances, we use plug-and-play prior technique, that is to use directly a state-of-the-art denoiser, which is conceived to exploit the spatial correlation of abundance maps and nonlinear interaction maps. The numerical results in simulated data and real hyperspectral dataset show that the proposed method can improve the estimation of abundances dramatically compared with state-of-the-art nonlinear unmixing methods.

show abstract

Hyperspectral Mixed Noise Removal By $\ell _1$-Norm-Based Subspace Representation

Cited by 72 publications

References 50 publications

Nonlocal Block-Term Decomposition for Hyperspectral Image Mixed Noise Removal

Nonlocal Block-Term Decomposition for Hyperspectral Image Mixed Noise Removal

SLRL4D: Joint Restoration of Subspace Low-Rank Learning and Non-Local 4-D Transform Filtering for Hyperspectral Image

Hyperspectral Nonlinear Unmixing by Using Plug-and-Play Prior for Abundance Maps

Contact Info

Product

Resources

About