Filters








49 Hits in 7.6 sec

Using Low-rank Representation of Abundance Maps and Nonnegative Tensor Factorization for Hyperspectral Nonlinear Unmixing [article]

Lianru Gao, Zhicheng Wang, Lina Zhuang, Haoyang Yu, Bing Zhang, Jocelyn Chanussot
2021 arXiv   pre-print
Synthetic and real-data experiments show that the low rank of abundance maps and nonlinear interaction abundance maps exploited in our method can improve the performance of the nonlinear unmixing.  ...  Furthermore, the low-rank structures of abundance maps and nonlinear interaction abundance maps are exploited by minimizing their nuclear norm, thus taking full advantage of the high spatial correlation  ...  Professor Yuntao Qian provided the endmember data used in some of the experiments with synthetic data.  ... 
arXiv:2103.16204v1 fatcat:y5g2brgxjfanbcotpl333u6xcm

Nonnegative Tensor CP Decomposition of Hyperspectral Data

Miguel A. Veganzones, Jeremy E. Cohen, Rodrigo Cabral Farias, Jocelyn Chanussot, Pierre Comon
2016 IEEE Transactions on Geoscience and Remote Sensing  
Marie Dumont from Meteo-France and Dr. Mauro Dalla Mura from GIPSA-lab, Grenoble INP, for providing the experimental dataset.  ...  maps for each endmember while the CP decomposition outputs R < 8 × 44 abundance maps and time factors.  ...  Using the FCLSU, we obtained a set of 8 abundance maps for each of the 44 time acquisitions.  ... 
doi:10.1109/tgrs.2015.2503737 fatcat:oaojnm72d5bhbdaxccb4uapwfu

Matrix-Vector Nonnegative Tensor Factorization for Blind Unmixing of Hyperspectral Imagery

Yuntao Qian, Fengchao Xiong, Shan Zeng, Jun Zhou, Yuan Yan Tang
2017 IEEE Transactions on Geoscience and Remote Sensing  
Extended from NMF based methods, a matrix-vector nonnegative tensor factorization (NTF) model is proposed in this paper for spectral unmixing.  ...  The matrix-vector NTF decomposes a third-order tensor into the sum of several component tensors, with each component tensor being the outer product of a vector (endmember) and a matrix (corresponding abundances  ...  All these approaches use a low-rank tensor representation to approximate the original HSI data.  ... 
doi:10.1109/tgrs.2016.2633279 fatcat:v7ylggln7namdkiiqaa6bv3a7e

Sparsity-Constrained Coupled Nonnegative Matrix-Tensor Factorization for Hyperspectral Unmixing

Heng-Chao Li, Shuang Liu, Xin-Ru Feng, Shaoquan Zhang
2020 IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing  
In this paper, we propose a sparsityconstrained coupled nonnegative matrix-tensor factorization (SC-NMTF) model for unmixing, wherein MV-NTF and NMF are subtly coupled by sharing endmembers and abundances  ...  Index Terms-Hyperspectral unmixing, nonnegative matrix factorization (NMF), nonnegative tensor factorization (NTF), coupled decomposition, sparsity constraint.  ...  [36] proposed a matrixvector nonnegative tensor factorization (MV-NTF) unmixing method, which was the first to construct a straightforward link between LMM and tensor factorization.  ... 
doi:10.1109/jstars.2020.3019706 fatcat:6ntfniu5nbev7fts3zle3f4toy

Low-Rank Tensor Modeling for Hyperspectral Unmixing Accounting for Spectral Variability [article]

Tales Imbiriba, Ricardo Augusto Borsoi, José Carlos Moreira Bermudez
2019 arXiv   pre-print
that endmembers and abundances will be correctly factorized in their respective tensors.  ...  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  ...  Though a low-rank tensor representation may naturally describe the regularity of HIs and abundance maps, the forceful introduction of stringent rank constraints may prevent an adequate representation of  ... 
arXiv:1811.02413v3 fatcat:sx2wace7vfbt5knihbsrmep2we

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

Zhicheng Wang, Lina Zhuang, Lianru Gao, Andrea Marinoni, Bing Zhang, Michael K. Ng
2020 Remote Sensing  
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  ...  Yuntao Qian provided the abundance and endmember data used in some of the experiments with synthetic data. Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/rs12244117 fatcat:2v6dc7qmozhs7dwrr2fk7zml6a

Weighted Nonlocal Low-Rank Tensor Decomposition Method for Sparse Unmixing of Hyperspectral Images

Le Sun, Feiyang Wu, Tianming Zhan, Wei Liu, Jin Wang, Byeungwoo Jeon
2020 IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing  
Finally, weighted low-rank tensor regularization is enforced to constrain the patch group to obtain an estimated low-rank abundance image.  ...  This method exploits spectral correlation by using collaborative sparsity regularization and spatial information by employing total variation and weighted nonlocal low-rank tensor regularization.  ...  For WNLTDSU, λ W T represents the parameter of the weighted nonlocal low-rank tensor decomposition regularization. The parameter μ is the Lagrangian penalty factor for the six methods.  ... 
doi:10.1109/jstars.2020.2980576 fatcat:tj42cojeqzhefpqykapgm3qyrq

Table of contents

2019 IEEE Transactions on Geoscience and Remote Sensing  
Chakravortty 4309 Spectral Image Fusion From Compressive Measurements Using Spectral Unmixing and a Sparse Representation of Abundance Maps .............................................................  ...  Benediktsson 5085 Simultaneous Reconstruction and Anomaly Detection of Subsampled Hyperspectral Images Using l (1/2) Regularized Joint Sparse and Low-Rank Recovery .....................................  ... 
doi:10.1109/tgrs.2019.2923179 fatcat:nfaahnqzcvft5ezz36a6nyy2ri

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

Xiangrong Zhang, Chen Li, Jingyan Zhang, Qimeng Chen, Jie Feng, Licheng Jiao, Huiyu Zhou
2018 Remote Sensing  
In this paper, a new unmixing algorithm via low-rank representation (LRR) based on space consistency constraint and spectral library pruning is proposed.  ...  Spectral unmixing is a popular technique for hyperspectral data interpretation.  ...  Our future work will focus on the study of tensor based low-rank representation model for hyperspectral unmixing.  ... 
doi:10.3390/rs10020339 fatcat:t5n6xsoapneyvepkvvqxblvkfa

Bilateral Joint-Sparse Regression for Hyperspectral Unmixing

Jie Huang, Wu-Chao Di, Jinju Wang, Jie Lin, Ting-Zhu Huang
2021 IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing  
Moreover, we propose to simultaneously impose the bilateral joint-sparse structure and low rankness on the abundance and develop a new algorithm named bilateral joint-sparse and low-rank unmixing.  ...  To make further use of the spatial information of HSIs, in this article, we propose a bilateral joint-sparse structure for hyperspectral unmixing in an attempt to exploit the local joint sparsity of the  ...  ACKNOWLEDGMENT The authors would like to thank the authors of SUnSAL, CLSUnSAL, SUnSAL-TV, and ADSpLRU for sharing their codes.  ... 
doi:10.1109/jstars.2021.3115172 fatcat:yuzfpmobgzggzb2goevwnhnlza

Editorial for Special Issue "Hyperspectral Imaging and Applications"

Chein-I Chang, Meiping Song, Junping Zhang, Chao-Cheng Wu
2019 Remote Sensing  
The aim of this Special Issue "Hyperspectral Imaging and Applications" is to publish new ideas and technologies to facilitate the utility of hyperspectral imaging in data exploitation and to further explore  ...  This Special Issue has accepted and published 25 papers in various areas, which can be organized into 7 categories, Data Unmixing, Spectral variability, Target Detection, Hyperspectral Image Classification  ...  paper proposes propose an algorithm that exploits the low-rank local abundance by applying the nuclear norm to the abundance matrix for local regions of spatial and abundance domains where the local abundance  ... 
doi:10.3390/rs11172012 fatcat:c23u3rahgjhctowk5xwllt2qea

Joint-Sparse-Blocks Regression for Total Variation Regularized Hyperspectral Unmixing

Jie Huang, Ting-Zhu Huang, Xi-Le Zhao, Liang-Jian Deng
2019 IEEE Access  
Sparse unmixing has attracted much attention in recent years. It aims at estimating the fractional abundances of pure spectral signatures in mixed pixels in hyperspectral images.  ...  Simulated and real-data experiments show the advantages of the proposed algorithm. INDEX TERMS Hyperspectral images, spectral unmixing, total variation regularization, joint-sparse-blocks regression.  ...  In addition, the TV based unmixing algorithms: SUnSAL-TV, DRSU-TV, and JSBUnSAL-TV give more smooth background than the low-rank representation based ADSpLRU and JSpBLRU.  ... 
doi:10.1109/access.2019.2943110 fatcat:dewrwniyzzbopey2mqnepdlgbi

Interpretable Hyperspectral AI: When Non-Convex Modeling meets Hyperspectral Remote Sensing [article]

Danfeng Hong and Wei He and Naoto Yokoya and Jing Yao and Lianru Gao and Liangpei Zhang and Jocelyn Chanussot and Xiao Xiang Zhu
2021 arXiv   pre-print
In the past decade, enormous efforts have been made to process and analyze these hyperspectral (HS) products mainly by means of seasoned experts.  ...  For this reason, it is, therefore, urgent to develop more intelligent and automatic approaches for various HS RS applications.  ...  [122] jointly imposed sparsity and low-rank properties on the abundances for better estimating abundance maps. Hong et al.  ... 
arXiv:2103.01449v1 fatcat:jvo4pr5atvfb5kohpslvkhhmky

2020 Index IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Vol. 13

2020 IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing  
., +, JSTARS 2020 2974-2985 Weighted Nonlocal Low-Rank Tensor Decomposition Method for Sparse Unmixing of Hyperspectral Images.  ...  ., +, JSTARS 2020 5609-5622 Sparsity-Constrained Coupled Nonnegative Matrix-Tensor Factorization for Hyperspectral Unmixing.  ...  A New Deep-Learning-Based Approach for Earthquake-Triggered Landslide Detection From Single-Temporal RapidEye Satellite Imagery. Yi, Y., +, JSTARS 2020  ... 
doi:10.1109/jstars.2021.3050695 fatcat:ycd5qt66xrgqfewcr6ygsqcl2y

A Modified Huber Nonnegative Matrix Factorization Algorithm for Hyperspectral Unmixing

Ziyang Guo, Anyou Min, Bing Yang, Junhong Chen, Hong Li
2021 IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing  
Recently, nonnegative matrix factorization (NMF) has shown its superiority in hyperspectral unmixing due to its flexible modeling and little prior requirement.  ...  Hypersepctral unmixing has been one of the most challenging tasks in hyperspectral image research.  ...  Nonnegative tensor factorization (NTF) [16] has been developed by considering spatial information of hyperspectral image.  ... 
doi:10.1109/jstars.2021.3081984 fatcat:566xw6kbsjeolfvgc2vtme27x4
« Previous Showing results 1 — 15 out of 49 results