Regularization Parameter Selection in Minimum Volume Hyperspectral Unmixing

Zhuang, Lina; Lin, Chia-Hsiang; Figueiredo, Mário A. T.; Bioucas-Dias, José M.

doi:10.1109/tgrs.2019.2929776

Cited by 98 publications

(53 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this section, we conduct extensive experiments on synthetic and real data to demonstrate the performance of the proposed approach, referred to as "gtvMBO", in comparison with the state-of-the-art methods in blind and nonblind hyperspectral unmixing. Methods that we compare include FCLSU [11], SUnSAL-TV [15] (denoted by STV), GLNMF [31], fractional norm q regularized unmixing method with q = 0.1 (denoted by FRAC) [13], NMF-QMV [21] (denoted by QMV), and our earlier unmixing work based on the graph Laplacian [50] (denoted by GraphL).…”

Section: Numerical Experimentsmentioning

confidence: 99%

“…Other TV-based variants include TV with 1 [16], TV with sparse NMF [17], TV with nonnegative tensor factorization [18], and an improved collaborative NMF with TV (ICoNMF-TV) [19] that combines robust collaborative NMF (R-CoNMF) [20] and TV. Recently, TV is considered as a quadratic regularization promoting minimum volume in the NMF framework, referred to as NMF-QMV [21]. An extension of TV to nonlocal spatial operators [22], [23] has led to nonlocal TV being considered for the blind hyperspectral unmixing problem [24], [25].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Blind Hyperspectral Unmixing Based on Graph Total Variation Regularization

Qin

Lee

Jocelyn

et al. 2021

IEEE Trans. Geosci. Remote Sensing

View full text Add to dashboard Cite

Remote sensing data from hyperspectral cameras suffer from limited spatial resolution, in which a single pixel of a hyperspectral image may contain information from several materials in the field of view. Blind hyperspectral image unmixing is the process of identifying the pure spectra of individual materials (i.e., endmembers) and their proportions (i.e., abundances) at each pixel. In this paper, we propose a novel blind hyperspectral unmixing model based on the graph total variation (gTV) regularization, which can be solved efficiently by the alternating direction method of multipliers (ADMM). To further alleviate the computational cost, we apply the Nyström method to approximate a fully-connected graph by a small subset of sampled points. Furthermore, we adopt the Merriman-Bence-Osher (MBO) scheme to solve the gTV-involved subproblem in ADMM by decomposing a grayscale image into a bit-wise form. A variety of numerical experiments on synthetic and real hyperspectral images are conducted, showcasing the potential of the proposed method in terms of identification accuracy and computational efficiency.

show abstract

Section: Numerical Experimentsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Blind Hyperspectral Unmixing Based on Graph Total Variation Regularization

Qin

Lee

Jocelyn

et al. 2021

IEEE Trans. Geosci. Remote Sensing

View full text Add to dashboard Cite

show abstract

“…We simulate a clean semireal HSI based on the public available TERRAIN image (see Fig. 7) following the generation steps in [48]. 6 The original TERRAIN image has size 500 (rows) × 307 (columns) × 166 (bands), and is mainly composed of soil, tree, grass, and shadows.…”

Section: F Application In Hyperspectral Unmixingmentioning

confidence: 99%

“…6 The original TERRAIN image has size 500 (rows) × 307 (columns) × 166 (bands), and is mainly composed of soil, tree, grass, and shadows. The number of endmembers is empirically set to 5 like [48]- [50]. Briefly, a clean TERRAIN image is synthesized based on the linear mixing model, i.e., X = AS, where A and S are the matrices of endmember and abundance, respectively, estimated from the original TERRAIN image.…”

Section: F Application In Hyperspectral Unmixingmentioning

confidence: 99%

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

Zhuang

2020

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

Self Cite

View full text Add to dashboard Cite

This article introduces a new hyperspectral image (HSI) denoising method that is able to cope with additive mixed noise, i.e., mixture of Gaussian noise, impulse noise, and stripes, which usually corrupt hyperspectral images in the acquisition process. The proposed method fully exploits a compact and sparse HSI representation based on its low-rank and self-similarity characteristics. In order to deal with mixed noise having a complex statistical distribution, we propose to use the robust 1 data fidelity instead of using the 2 data fidelity, which is commonly employed for Gaussian noise removal. In a series of experiments with simulated and real datasets, the proposed method competes with state-of-the-art methods, yielding better results for mixed noise removal.

show abstract

“…Interestingly, content-based image retrieval (CBIR) [4][5][6] is widely involved in many real-world tasks, such as natural image retrieval and network searches. Nevertheless, large variations are usually contained in the RS images due to their large data volume, small object size and rich background [7,8], and thus how to extract valuable information and further adapt existing CBIR methods to remote sensing image retrieval (RSIR) is considered a key issue [9,10].…”

Section: Introductionmentioning

confidence: 99%

Low-Rank Hypergraph Hashing for Large-Scale Remote Sensing Image Retrieval

et al. 2020

View full text Add to dashboard Cite

As remote sensing (RS) images increase dramatically, the demand for remote sensing image retrieval (RSIR) is growing, and has received more and more attention. The characteristics of RS images, e.g., large volume, diversity and high complexity, make RSIR more challenging in terms of speed and accuracy. To reduce the retrieval complexity of RSIR, a hashing technique has been widely used for RSIR, mapping high-dimensional data into a low-dimensional Hamming space while preserving the similarity structure of data. In order to improve hashing performance, we propose a new hash learning method, named low-rank hypergraph hashing (LHH), to accomplish for the large-scale RSIR task. First, LHH employs a l2-1 norm to constrain the projection matrix to reduce the noise and redundancy among features. In addition, low-rankness is also imposed on the projection matrix to exploit its global structure. Second, LHH uses hypergraphs to capture the high-order relationship among data, and is very suitable to explore the complex structure of RS images. Finally, an iterative algorithm is developed to generate high-quality hash codes and efficiently solve the proposed optimization problem with a theoretical convergence guarantee. Extensive experiments are conducted on three RS image datasets and one natural image dataset that are publicly available. The experimental results demonstrate that the proposed LHH outperforms the existing hashing learning in RSIR tasks.

show abstract

Regularization Parameter Selection in Minimum Volume Hyperspectral Unmixing

Cited by 98 publications

References 48 publications

Blind Hyperspectral Unmixing Based on Graph Total Variation Regularization

Blind Hyperspectral Unmixing Based on Graph Total Variation Regularization

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

Low-Rank Hypergraph Hashing for Large-Scale Remote Sensing Image Retrieval

Contact Info

Product

Resources

About