Filters








285 Hits in 8.1 sec

Nonnegative-Matrix-Factorization-Based Hyperspectral Unmixing With Partially Known Endmembers

Lei Tong, Jun Zhou, Yuntao Qian, Xiao Bai, Yongsheng Gao
2016 IEEE Transactions on Geoscience and Remote Sensing  
In this paper, we address the hyperspectral unmixing problem with partially known endmembers.  ...  This is, however, not true for some unmixing tasks for which part of the endmember signatures may be known in advance.  ...  These form the basis for the proposed method on hyperspectral unmixing with partially known prior knowledge.  ... 
doi:10.1109/tgrs.2016.2586110 fatcat:k7bn4smjmvf4fndpoeb22f5l24

A Projected Gradient-Based Algorithm To Unmix Hyperspectral Data

Massoud Babaie-Zadeh, Ch. Jutten, Azar Zandifar
2012 Zenodo  
Under the constraints of non-negativity of A and S, (1) may be regarded as a general NMF problem which tries to factorize the non-negative matrix X into two nonnegative matrices A and S, while N represents  ...  Different methods based on constrained nonnegative matrix factorization have been recently proposed to unmix hyperspectral data [10, 11, 12] .  ... 
doi:10.5281/zenodo.43026 fatcat:odtvhisy2ferrgnjwfomfpw42q

Using a Panchromatic Image to Improve Hyperspectral Unmixing

Simon Rebeyrol, Yannick Deville, Véronique Achard, Xavier Briottet, Stephane May
2020 Remote Sensing  
Then, in order to complete this first endmember set, a local approach using a constrained non-negative matrix factorization strategy, is proposed.  ...  Our method, called Heterogeneity-Based Endmember Extraction coupled with Local Constrained Non-negative Matrix Factorization (HBEE-LCNMF), has several steps: a first set of endmembers is estimated based  ...  Schaepman for providing us with the Basel database and answering our questions. We thank Philippe Deliot from ONERA for providing us with the Mauzac HS acquisition.  ... 
doi:10.3390/rs12172834 fatcat:keexmj4ejndxhiqdjwben3n2b4

A comparative analysis of GPU implementations of spectral unmixing algorithms

Sergio Sanchez, Antonio Plaza, Bormin Huang, Antonio J. Plaza
2011 High-Performance Computing in Remote Sensing  
Spectral unmixing is a very important task for remotely sensed hyperspectral data exploitation.  ...  These two steps comprise a hyperspectral unmixing chain, which can be very time-consuming (particularly for high-dimensional hyperspectral images).  ...  This decomposition is known as Gaussian elimination or the LU factorization (with partial row pivoting).  ... 
doi:10.1117/12.897329 fatcat:upuwl4uvyfabrkudo5nwez4gvy

Supervised Nonlinear Unmixing of Hyperspectral Images Using a Pre-image Methods [chapter]

N.H. Nguyen, J. Chen, C. Richard, P. Honeine, C. Theys
2020 New Concepts in Imaging: Optical and Statistical Models  
Spectral unmixing is an important issue to analyze remotely sensed hyperspectral data.  ...  This involves the decomposition of each mixed pixel into its pure endmember spectra, and the estimation of the abundance value for each endmember.  ...  In the spirit of these derivations, we suggest to consider kernels of the form κ(r i , r j ) = (1 − γ) r i Σ r j + γ κ (r i , r j ) (4.2) with κ (r i , r j ) a reproducing kernel, Σ a non-negative matrix  ... 
doi:10.1051/978-2-7598-2487-8-021 fatcat:bk5vck5u35gfbiqjtmrh24stbm

Supervised Nonlinear Unmixing of Hyperspectral Images Using a Pre-image Methods

N. H. Nguyen, J. Chen, C. Richard, P. Honeine, C. Theys, D. Mary, C. Theys, C. Aime
2013 EAS Publications Series  
Spectral unmixing is an important issue to analyze remotely sensed hyperspectral data.  ...  This involves the decomposition of each mixed pixel into its pure endmember spectra, and the estimation of the abundance value for each endmember.  ...  In the spirit of these derivations, we suggest to consider kernels of the form κ(r i , r j ) = (1 − γ) r i Σ r j + γ κ (r i , r j ) (4.2) with κ (r i , r j ) a reproducing kernel, Σ a non-negative matrix  ... 
doi:10.1051/eas/1359019 fatcat:5kqo4dr45fdn5iof4y7bgs65ja

Fast Constrained Least Squares Spectral Unmixing Using Primal-Dual Interior-Point Optimization

Emilie Chouzenoux, Maxime Legendre, Said Moussaoui, Jerome Idier
2014 IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing  
For large hyperspectral image data sets, the estimation of the abundance maps requires the resolution of a large-scale optimization problem subject to linear constraints such as non-negativity and sum  ...  Abstract Hyperspectral data unmixing aims at identifying the components (endmembers) of an observed surface and at determining their fractional abundances inside each pixel area.  ...  Actually, there is an increasing interest to joint estimation methods based either on non-negative source separation [5, 6] or constrained non-negative matrix factorization [7, 8] .  ... 
doi:10.1109/jstars.2013.2266732 fatcat:ipj63r3a6vb5hbaisjqo6uca3y

Hyperspectral Unmixing Based on Constrained Bilinear or Linear-Quadratic Matrix Factorization

Fatima Zohra Benhalouche, Yannick Deville, Moussa Sofiane Karoui, Abdelaziz Ouamri
2021 Remote Sensing  
These methods are based on bilinear or linear-quadratic matrix factorization with non-negativity constraints. Two types of algorithms are considered.  ...  In this work, unsupervised hyperspectral unmixing methods, designed for the bilinear and linear-quadratic mixing models, are proposed.  ...  Acknowledgments: The authors would like to thank the developers of the used literature algorithms for sharing their MATLAB implementations.  ... 
doi:10.3390/rs13112132 fatcat:valjref6sfcbjbtlrzytx2fxx4

Cluster-Wise Weighted NMF for Hyperspectral Images Unmixing with Imbalanced Data

Xiaochen Lv, Wenhong Wang, Hongfu Liu
2021 Remote Sensing  
In recent years, non-negative matrix factorization (NMF) has received extensive attention due to its good adaptability for mixed data with different degrees.  ...  Hyperspectral unmixing is an important technique for analyzing remote sensing images which aims to obtain a collection of endmembers and their corresponding abundances.  ...  NMF aims to decompose a given non-negative matrix into two non-negative factor matrices with low ranks, so that the minimum error between the product of these factor matrices and the original matrix is  ... 
doi:10.3390/rs13020268 fatcat:fdteqnmxnjdzfbw7x7vangyehi

Parallel unmixing of remotely sensed hyperspectral images on commodity graphics processing units

Sergio Sánchez, Abel Paz, Gabriel Martín, Antonio Plaza
2011 Concurrency and Computation  
Spectral unmixing involves the separation of a pixel spectrum into its pure component endmember spectra, and the estimation of the abundance value for each endmember [4] .  ...  For instance, the pixel vector labeled as 'vegetation' in Figure 1 may actually be a mixed pixel comprising a mixture of vegetation and soil, or different types of soil and vegetation canopies.  ...  CUDA kernel ISRA that computes endmember abundances in each pixel of the hyperspectral image imposing the abundance non-negativity constraint. • Figure A2 shows the code for the Unmixing kernel used  ... 
doi:10.1002/cpe.1720 fatcat:y5nwiqbacvbz7oowntksw2cyom

A Hierarchical Sparsity Unmixing Method to Address Endmember Variability in Hyperspectral Image

Jinlin Zou, Jinhui Lan, Yang Shao
2018 Remote Sensing  
With that in mind, this paper proposes a hierarchical weighted sparsity unmixing (HWSU) method to improve the separation of similar interclass endmembers.  ...  With a low spectral resolution hyperspectral sensor, the signal recorded from a given pixel against the complex background is a mixture of spectral contents.  ...  We would like to thank the editor and reviewers for their reviews that improved the content of this paper.  ... 
doi:10.3390/rs10050738 fatcat:f6fhdc7a2vhhfhwxds7zxrsks4

Real-time implementation of a full hyperspectral unmixing chain on graphics processing units

Sergio Sanchez, Antonio Plaza
2011 Satellite Data Compression, Communications, and Processing VII  
Hyperspectral unmixing is a very important task for remotely sensed hyperspectral data exploitation.  ...  In this paper, we develop a real-time implementation of a full unmixing chain for hyperspectral data on graphics processing units (GPUs).  ...  This decomposition is known as Gaussian elimination or the LU factorization (with partial row pivoting).  ... 
doi:10.1117/12.892284 fatcat:giiksnxhbve7vazppxnaceyngq

Superpixel-Based Hyperspectral Unmixing with Regional Segmentation

Mohammed Q. Alkhatib, Miguel Velez-Reyes
2018 IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium  
DEDICATION This work is dedicated to my great wife for her support and help during this period of my life. To my great parents for their prayers and support. Finally, to my beautiful daughter Zaina.  ...  Given a non-negative matrix Y, NMF tries to find non-negative matrices S (Basis matrix) and A (encoding Matrix), such that Y ≈ SA.  ...  This method only uses one of the smoothed images from the multiscale representation for spectral endmember extraction [38] . • The Spatially Adaptive Constrained Non Negative Matrix Factorization for  ... 
doi:10.1109/igarss.2018.8518222 dblp:conf/igarss/AlkhatibV18 fatcat:ebpfobydubdoljs7toqa2bfwoe

Constrained Nonnegative Matrix Factorization for Blind Hyperspectral Unmixing incorporating Endmember Independence [article]

E.M.M.B. Ekanayake, H.M.H.K. Weerasooriya, D.Y.L. Ranasinghe, S. Herath, B. Rathnayake, G.M.R.I. Godaliyadda, M.P.B. Ekanayake, H.M.V.R. Herath
2021 arXiv   pre-print
Hyperspectral unmixing (HU) has become an important technique in exploiting hyperspectral data since it decomposes a mixed pixel into a collection of endmembers weighted by fractional abundances.  ...  As a promising step toward finding an optimum constraint to extract endmembers, this paper presents a novel blind HU algorithm, referred to as Kurtosis-based Smooth Nonnegative Matrix Factorization (KbSNMF  ...  In the paper, Matrix-Vector NTF for Blind Unmixing of Hyperspectral Imagery (MVNTF) [48] , the authors have formalized a novel way of unmixing while preserving the spatial information by factorizing hyper  ... 
arXiv:2003.01041v5 fatcat:jys4xvzs4vepddyflgttqbcbby

Unsupervised unmixing of hyperspectral imagery using the constrained positive matrix factorization

Yahya M. Masalmah, Miguel Vélez-Reyes, Harold H. Szu
2006 Independent Component Analyses, Wavelets, Unsupervised Smart Sensors, and Neural Networks IV  
This research dealt with the unsupervised determination of the constituents and their fractional abundance in each pixel in a hyperspectral image using a constrained positive matrix factorization (cPMF  ...  In hyperspectral imaging, hundreds of images are taken at narrow and contiguous spectral bands providing us with high spectral resolution spectral signatures that can be used to discriminate between objects  ...  NNLS Non-Negative Least Squares. PMF Positive Matrix Factorization. NNMF Non-Negative Matrix Factorization. ALS Alternating Least Squares.  ... 
doi:10.1117/12.667976 fatcat:yj3xl6cyqjg2ze4jtnuxdkymzi
« Previous Showing results 1 — 15 out of 285 results