Kernel sparse representation for hyperspectral unmixing based on high mutual coherence spectral library

2019 ◽  
Vol 41 (4) ◽  
pp. 1286-1301 ◽  
Author(s):  
Xuhui Weng ◽  
Wuhu Lei ◽  
Xiaodong Ren
Keyword(s):  
Sparse Representation ◽  
Spectral Library ◽  
Mutual Coherence ◽  
Hyperspectral Unmixing

scholarly journals Hyperspectral Unmixing via Low-Rank Representation with Space Consistency Constraint and Spectral Library Pruning

2018 ◽  
Vol 10 (2) ◽  
pp. 339 ◽  
Author(s):  
Xiangrong Zhang ◽  
Chen Li ◽  
Jingyan Zhang ◽  
Qimeng Chen ◽  
Jie Feng ◽  
...  
Keyword(s):  
Low Rank ◽  
Spectral Library ◽  
Hyperspectral Unmixing ◽  
Low Rank Representation ◽  
Consistency Constraint

A novel joint dictionary framework for sparse hyperspectral unmixing incorporating spectral library

2019 ◽  
Vol 356 ◽  
pp. 97-106 ◽  
Author(s):  
Lin Qi ◽  
Jie Li ◽  
Xinbo Gao ◽  
Ying Wang ◽  
Chongyue Zhao ◽  
...  
Keyword(s):  
Spectral Library ◽  
Hyperspectral Unmixing

scholarly journals Semiblind Hyperspectral Unmixing in the Presence of Spectral Library Mismatches

2016 ◽  
Vol 54 (9) ◽  
pp. 5171-5184 ◽  
Author(s):  
Xiao Fu ◽  
Wing-Kin Ma ◽  
Jose M. Bioucas-Dias ◽  
Tsung-Han Chan
Keyword(s):  
Spectral Library ◽  
Hyperspectral Unmixing

scholarly journals RETRIEVAL OF MINERAL ABUNDANCES OF THE DELTA REGION IN EBERSWALDE, MARS

2017 ◽  
Vol XLII-3/W1 ◽  
pp. 171-176
Author(s):  
X. Wu ◽  
X. Zhang ◽  
H. Lin
Keyword(s):  
Large Scale ◽  
Single Scattering ◽  
Alluvial Fan ◽  
Spectral Library ◽  
Delta Region ◽  
Bidirectional Reflectance ◽  
Imaging Spectrometer ◽  
Hyperspectral Unmixing ◽  
Reflectance Function ◽  
Hydrological System

Eberswalde Crater, a hotspot of Mars exploration, possesses an unambiguous hydrological system. However, little research has been performed on the large-scale mineral abundances retrieval in this region. Hence, we employed hyperspectral unmixing technology to quantitatively retrieve mineral abundances of the delta region in Eberswalde. In this paper, the single-scattering albedos were calculated by the Hapke bidirectional reflectance function from Compact Reconnaissance Imaging Spectrometer for Mars (CRISM) data (FRT000060DD) and CRISM spectral library respectively, and a sparse unmixing algorithm was adopted to quantitatively retrieve mineral abundances. The abundance maps show that there are six kinds of minerals (pyroxene, olivine, plagioclase, siderite, diaspore, and tremolite). By comparing minerals spectra obtained from images with corresponding spectra in spectral library, we found the similar trend in both curves. Besides, the mineral abundance maps derived in this study agree well spatially with CRISM parameter maps. From the perspective of mineralogy, the instability of pyroxene and olivine indicates the area in which they distribute is close to provenance, and the original provenance is ultrabasic rock (e.g. peridotite) and basic rock (e.g. gabbro), respectively. And minerals, existing in the area of alluvial fan, also distribute in the outside of alluvial fan, which might be caused by fluid transportation.

Hyperspectral Unmixing Using Spectral Library Sparse Scaling and Guided Filter

2020 ◽  
pp. 1-5
Author(s):  
Zuoyu Zhang ◽  
Shouyi Liao ◽  
Hao Fang ◽  
Hexin Zhang ◽  
Shicheng Wang
Keyword(s):  
Guided Filter ◽  
Spectral Library ◽  
Hyperspectral Unmixing

Region-Based Multiview Sparse Hyperspectral Unmixing Incorporating Spectral Library

2019 ◽  
Vol 16 (7) ◽  
pp. 1140-1144 ◽  
Author(s):  
Lin Qi ◽  
Jie Li ◽  
Ying Wang ◽  
Xinbo Gao
Keyword(s):  
Spectral Library ◽  
Hyperspectral Unmixing

Sparse Hyperspectral Unmixing Using Spectral Library Adaptive Adjustment

2019 ◽  
Vol 12 (12) ◽  
pp. 4873-4887
Author(s):  
Zuoyu Zhang ◽  
Shouyi Liao ◽  
Hao Fang ◽  
Hexin Zhang ◽  
Shicheng Wang
Keyword(s):  
Spectral Library ◽  
Hyperspectral Unmixing ◽  
Adaptive Adjustment

scholarly journals ARCHETYPAL ANALYSIS FOR SPARSE REPRESENTATION-BASED HYPERSPECTRAL SUB-PIXEL QUANTIFICATION

2017 ◽  
Vol IV-1/W1 ◽  
pp. 133-139
Author(s):  
L. Drees ◽  
R. Roscher
Keyword(s):  
Land Cover ◽  
Sparse Representation ◽  
Surface Characteristics ◽  
Absolute Error ◽  
Reconstruction Error ◽  
Spectral Library ◽  
Archetypal Analysis ◽  
Heuristic Technique ◽  
Efficient Alternative ◽  
Cover Class

This paper focuses on the quantification of land cover fractions in an urban area of Berlin, Germany, using simulated hyperspectral EnMAP data with a spatial resolution of 30m×30m. For this, sparse representation is applied, where each pixel with unknown surface characteristics is expressed by a weighted linear combination of elementary spectra with known land cover class. The elementary spectra are determined from image reference data using simplex volume maximization, which is a fast heuristic technique for archetypal analysis. In the experiments, the estimation of class fractions based on the archetypal spectral library is compared to the estimation obtained by a manually designed spectral library by means of reconstruction error, mean absolute error of the fraction estimates, sum of fractions and the number of used elementary spectra. We will show, that a collection of archetypes can be an adequate and efficient alternative to the spectral library with respect to mentioned criteria.

scholarly journals Incoherent Dictionary Learning Method Based on Unit Norm Tight Frame and Manifold Optimization for Sparse Representation

2016 ◽  
Vol 2016 ◽  
pp. 1-10 ◽  
Author(s):  
HongZhong Tang ◽  
Xiaogang Zhang ◽  
Hua Chen ◽  
Ling Zhu ◽  
Xiang Wang ◽  
...  
Keyword(s):  
Sparse Representation ◽  
Optimization Problem ◽  
Tight Frame ◽  
Gram Matrix ◽  
Mutual Coherence ◽  
Learned Dictionary ◽  
Manifold Optimization ◽  
Audio Data ◽  
Update Process ◽  
Unit Norm

Optimizing the mutual coherence of a learned dictionary plays an important role in sparse representation and compressed sensing. In this paper, a efficient framework is developed to learn an incoherent dictionary for sparse representation. In particular, the coherence of a previous dictionary (or Gram matrix) is reduced sequentially by finding a new dictionary (or Gram matrix), which is closest to the reference unit norm tight frame of the previous dictionary (or Gram matrix). The optimization problem can be solved by restricting the tightness and coherence alternately at each iteration of the algorithm. The significant and different aspect of our proposed framework is that the learned dictionary can approximate an equiangular tight frame. Furthermore, manifold optimization is used to avoid the degeneracy of sparse representation while only reducing the coherence of the learned dictionary. This can be performed after the dictionary update process rather than during the dictionary update process. Experiments on synthetic and real audio data show that our proposed methods give notable improvements in lower coherence, have faster running times, and are extremely robust compared to several existing methods.

Sign in / Sign up

Export Citation Format

Share Document