491 Hits in 9.6 sec

Sparse pixel-wise spectral unmixing — Which algorithm to use and how to improve the results

Jakub Bieniarz, Rupert Muller, Xiao Xiang Zhu, Peter Reinartz
2015 2015 IEEE International Geoscience and Remote Sensing Symposium (IGARSS)  
Recently, many sparse approximation methods have been applied to solve spectral unmixing problems.  ...  These methods in contrast to traditional methods for spectral unmixing are designed to work with large a-prori given spectral dictionaries containing hundreds of labelled material spectra enabling to skip  ...  To obey this step, recently sparse spectral unmixing (SSU) has been proposed [2, 3, 4] , a method which uses large spectral dictionaries containing hundreds of labelled endmembers for abundance estimation  ... 
doi:10.1109/igarss.2015.7326411 dblp:conf/igarss/BieniarzMZR15 fatcat:kn5iuwrx6jaetldllbrqeiqtf4

Sparse Unmixing for Hyperspectral Imagery via Comprehensive-Learning-based Particle Swarm Optimization

Yapeng Miao, Bin Yang
2021 IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing  
His main research interests include hyperspectral remote sensing image analysis, machine learning, pattern recognition, and computational intelligence.  ...  A series of sparse unmixing algorithms are proposed, which can produce unmixing results closer to the ground truth. Iordache et al.  ...  The global spatial similarity between the pixels of HSIs and the local spectral similarity between superpixels have also been exploited to improve the sparse NMF [41] .  ... 
doi:10.1109/jstars.2021.3115177 fatcat:kvpbzduq2reofpablsalvkguqm

Restoration of Simulated EnMAP Data through Sparse Spectral Unmixing

Daniele Cerra, Jakub Bieniarz, Rupert Müller, Tobias Storch, Peter Reinartz
2015 Remote Sensing  
This paper proposes the use of spectral unmixing and sparse reconstruction methods to restore a simulated dataset for the Environmental Mapping and Analysis Program (EnMAP), the forthcoming German spaceborne  ...  The first assessment of the results is encouraging, as the original bands taken into account are reconstructed with a high signal-to-noise ratio and low overall distortions.  ...  Acknowledgments The simulated EnMAP dataset was produced by VISTA, Munich, and processed by Karl Segel, German Research Centre for Geosciences (GFZ), Potsdam.  ... 
doi:10.3390/rs71013190 fatcat:w5kuxois5jcbra25u7p2b5rk5q


J.M. Andiria Joslin, R. .
2019 International Journal of Recent Trends in Engineering and Research  
Section IV describes experimental results and section V concludes the paper with some future directions II.PROBLEM DEESCRIPTION AND FORMULATION This section describes how linear unmixing problem can  ...  The results shows that by imposing total variation, the unmixing results improve significantly with latent clean image, especially highly contaminated with noise.  ... 
doi:10.23883/ijrter.conf.20190304.005.rclxe fatcat:ns7ipbcz7jg2nbglxyz677r3qi

Improved Collaborative Nonnegative Matrix Factorization and Total Variation for Hyperspectral Unmixing

Yuan Yuan, Zihan Zhang, Qi Wang
2020 IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing  
Over the last years, the linear spectral unmixing problem has been approached as the sparse regression by different algorithms.  ...  Experiment results on simulation dataset and real dataset demonstrate the proposed algorithm outperforms most of the similar sparse regression algorithms.  ...  ACKNOWLEDGMENT The authors would like to thank G. Liu for his feedback on the text.  ... 
doi:10.1109/jstars.2020.2977399 fatcat:nljeifudgfdvhafzgq5nadw7wm

Double Regression-Based Sparse Unmixing for Hyperspectral Images

Shuaiyang Zhang, Wenshen Hua, Gang Li, Jie Liu, Fuyu Huang, Qianghui Wang, Penghai Wu
2021 Journal of Sensors  
The unmixing result of the first sparse regression is added as a constraint to the second. DRSUM is an open model, and we can add different constraints to improve the unmixing accuracy.  ...  The improved K -means clustering algorithm is first used for preprocessing, and then we impose single sparsity and joint sparsity (using l 2 , 0 norm to control the sparsity) constraints on the first and  ...  Acknowledgments This research was supported by the Department of Electronic and Optical Engineering, Shijiazhuang Campus, AEU.  ... 
doi:10.1155/2021/5575155 fatcat:fjby6vo7nbezbmy64w5iulahwa

Hyperspectral Unmixing in the Presence of Mixed Noise Using Joint-Sparsity and Total Variation

Hemant Kumar Aggarwal, Angshul Majumdar
2016 IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing  
The unmixing model explicitly takes into account both Gaussian noise and sparse noise. The unmixing problem has been formulated to exploit joint-sparsity of abundance maps.  ...  The split-Bregman technique has been utilized to derive an algorithm for solving resulting optimization problem.  ...  Our work improves over the state of the art sparse regression based unmixing techniques sparse regression (SR) [18] and its variants total variation spatial regularization (SRTV) [19] and collaborative  ... 
doi:10.1109/jstars.2016.2521898 fatcat:dsygey4jp5d5ro5fpru55kzaqu

A Dynamic Unmixing Framework for Plant Production System Monitoring

Marian-Daniel Iordache, Laurent Tits, Jose M. Bioucas-Dias, Antonio Plaza, Ben Somers
2014 IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing  
., MESMA) and sparse regression algorithms (e.g., SUnSAL) are widely used to tackle the unmixing problem in this case.  ...  Our goal is two-fold: 1) to obtain high-accuracy unmixing output using sparse unmixing, with low-execution time; and 2) to improve MESMA performances in terms of accuracy.  ...  Similar to MESMA, sparse unmixing algorithms make use of large spectral libraries.  ... 
doi:10.1109/jstars.2014.2314960 fatcat:y6jz53gqk5aaljwkzceogyjqea

Hyperspectral Unmixing Based on Nonnegative Matrix Factorization: A Comprehensive Review [article]

Xin-Ru Feng, Heng-Chao Li, Rui Wang, Qian Du, Xiuping Jia, Antonio Plaza
2022 arXiv   pre-print
Taking the NMF model as a baseline, we show how to improve NMF by utilizing the main properties of HSIs (e.g., spectral, spatial, and structural information).  ...  Furthermore, several experiments are conducted to illustrate the effectiveness of associated algorithms.  ...  By using multiview collaborative sparse and spectral-spatial-weights, the new sparse unmixing model [30] took the advantage of spectral information as well as spatial information.  ... 
arXiv:2205.09933v1 fatcat:77udhvg55fdftidm554qwarqzy

Total Variation Spatial Regularization for Sparse Hyperspectral Unmixing

Marian-Daniel Iordache, José M. Bioucas-Dias, Antonio Plaza
2012 IEEE Transactions on Geoscience and Remote Sensing  
developing a new algorithm called sparse unmixing via variable splitting augmented Lagrangian and TV.  ...  Our experimental results, conducted with both simulated and real hyperspectral data sets, indicate the potential of including spatial information (through the TV term) on sparse unmixing formulations for  ...  Last but not least, the authors gratefully thank the Associate Editor and the three anonymous reviewers for their outstanding comments and suggestions, which greatly improved the quality and presentation  ... 
doi:10.1109/tgrs.2012.2191590 fatcat:2ujkyygjgrc2lbye4twsv2uoy4

Hypergraph-Regularized Sparse NMF for Hyperspectral Unmixing

Wenhong Wang, Yuntao Qian, Yuan Yan Tang
2016 IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing  
Using the hypergraph, the pixels with similar abundances can be accurately found, which enables the unmixing algorithm to obtain promising results.  ...  In order to improve the performance of NMF-based unmixing approaches, spectral and spatial constrains have been added into the unmixing model, but spectral-spatial joint structure is required to be more  ...  Therefore, to improve the unmixing performance of the sparse NMF, spatial and spectral joint information available in the data needs to be fully exploited in the unmixing process.  ... 
doi:10.1109/jstars.2015.2508448 fatcat:25zk4jy6jfgxdbdpvgvg5aaooq

Hyperspectral image non-linear unmixing using joint extrinsic and intrinsic priors with L1/2-norms to non-negative matrix factorisation

K. Priya, K. Rajkumar
2022 Journal of Spectral Imaging  
to improve the quality of unmixing.  ...  Therefore, the proposed method enhances spatial as well as spectral data and considers the non-linearity of the pixels in the image by adding a residual term to the model.  ...  Nowadays, many algorithms have been introduced to improve the spectral and spatial quality of HSI.  ... 
doi:10.1255/jsi.2022.a4 fatcat:37r2umyapnegnogia4vjcxipbu

MUSIC-CSR: Hyperspectral Unmixing via Multiple Signal Classification and Collaborative Sparse Regression

Marian-Daniel Iordache, Jose M. Bioucas-Dias, Antonio Plaza, Ben Somers
2014 IEEE Transactions on Geoscience and Remote Sensing  
Sparse unmixing has attracted much attention as it sidesteps two common limitations of classic spectral unmixing approaches, namely, the lack of pure pixels in hyperspectral scenes and the need to estimate  ...  In recent years, sparse unmixing has been widely used as a reliable spectral unmixing methodology.  ...  An example is the group sparse unmixing via variable splitting and augmented Lagrangian [12] algorithm, which is designed to refine the solution at group level (in each pixel, instead of enforcing sparsity  ... 
doi:10.1109/tgrs.2013.2281589 fatcat:7llbkr5vijh23btguqz2qhxoym

Double Reweighted Sparse Regression and Graph Regularization for Hyperspectral Unmixing

Si Wang, Ting-Zhu Huang, Xi-Le Zhao, Gang Liu, Yougan Cheng
2018 Remote Sensing  
Specifically, a graph regularizer is employed to capture the correlation information between abundance vectors, which makes use of the property that similar pixels in a spectral neighborhood have higher  ...  a hyperspectral image typically contains fewer endmembers compared to the overcomplete spectral library and the other weight is exploited to improve the sparsity of the abundance matrix.  ...  Acknowledgments: The authors would like to thank the supports by NSFC (61772003) and the Fundamental Research Funds for the Central Universities (ZYGX2016J132).  ... 
doi:10.3390/rs10071046 fatcat:fia3mdudrjdptpxesl6t4bkrbe

Hyperspectral Unmixing via $L_{1/2}$ Sparsity-Constrained Nonnegative Matrix Factorization

Yuntao Qian, Sen Jia, Jun Zhou, Antonio Robles-Kelly
2011 IEEE Transactions on Geoscience and Remote Sensing  
We propose an iterative estimation algorithm for L 1/2 -NMF, which provides sparser and more accurate results than those delivered using the L1 norm.  ...  We illustrate the utility of our method on synthetic and real hyperspectral data and compare our results to those yielded by other state-of-the-art methods.  ...  Our contribution is, hence, to introduce a novel NMF method which recovers a sparse solution to the unmixing problem using an optimization algorithm that guarantees stable convergence to a local minimum  ... 
doi:10.1109/tgrs.2011.2144605 fatcat:gih5tznrenfjliivcndhhzzrje
« Previous Showing results 1 — 15 out of 491 results