Coupled Nonnegative Matrix Factorization Unmixing for Hyperspectral and Multispectral Data Fusion

By Naoto Yokoya, Takehisa Yairi, Akira Iwasaki. IEEE Transactions on Geoscience and Remote Sensing, 2012

1,069 citations recorded by the source corpus.

Subfields: Atmospheric Science, Media Technology

View Paper: https://www.semanticscholar.org/paper/a2cb99c666dbcbca53c84c69d9321676d0026e4e

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Atmospheric Science

In Media Technology

Citations in the corpus

Fusing Hyperspectral and Multispectral Images via Coupled Sparse Tensor Factorization (2018, background): “Instead of estimating spectral basis in advance and keeping them fixed, works [21]–[23] alternately update the spectral basis and the”
A Signal Processing Perspective on Hyperspectral Unmixing: Insights from Remote Sensing (2014, background): “Specifically, we carry out the following heuristic: for , , ,k N1 f= determine an estimate IEEE SIGNAL PROCESSING MAGAZINE [74] JANUARY 2014 { [ ], , [ ]},arg maxb P f b x x L1s.t. conv b Fk k k2 2”
Hyperspectral Image Super-Resolution via Non-local Sparse Tensor Factorization (2017, methodology): “Instead of estimating spectral basis in advance and keeping it fixed, non-negative coupled matrix factorization methods [38, 15] are utilized to unmix both the LR-HSI and HR-MSI simultaneously.”
Hyperspectral and Multispectral Image Fusion Based on a Sparse Representation (2014, methodology): “Yokoya for sharing the codes of [18], Prof.”
Hyperspectral and Multispectral Data Fusion: A comparative review of the recent literature (2017, methodology): “proposed coupled nonnegative matrix factorization (CNMF) that estimates the endmember and abundance matrices via alternating spectral unmixing based on NMF under the constraints of an observation model which incorporates both the relative SRF and PSF [44], [48].”
A Convex Formulation for Hyperspectral Image Superresolution via Subspace-Based Regularization (2014, background): “1 On the other hand, MSIs generally offer a higher spatial resolution, but each band covers a larger range of the spectrum, resulting in a much smaller number of bands.”
Hyperspectral Image Super-Resolution via Non-Negative Structured Sparse Representation (2016, methodology): “(f) Error of X. (g) Error of Z. (h) CNMF [22].”
Hyperspectral Pansharpening: A Review (2015, methodology): “CNMF starts with NMF unmixing of the low spatial resolution HS data.”
Deep Hyperspectral Image Sharpening (2018, positive): “Furthermore, methods proposed in [36]–[38] use the priors of spectral unmixing to regularize the fusion problem.”
Bayesian sparse representation for hyperspectral image super resolution (2015, methodology): “We compare our results with the recently proposed approaches, namely, the Matrix Factorization based method (MF) [18], the Spatial Spectral Fusion Model (SSFM) [17], the ADMM based approach [29], the Coupled Matrix Factorization method (CMF) [31] and the spatio-spectral sparse representation approac”
Hyperspectral Remote Sensing Data Analysis and Future Challenges (2013, background): “Alternatively, similar subpixel mapping strategies as in the spatial-spectral fusion can be applied, in which the high-resolution image can deliver the required materials spectral information [34], [35].”
Hyperspectral Super-Resolution by Coupled Spectral Unmixing (2015, methodology): “These results suggest that our method and [29] are particularly good at reconstructing the spectral distribution of the intensities, and perform evenly over all spectral bands.”
Multisource and Multitemporal Data Fusion in Remote Sensing: A Comprehensive Review of the State of the Art (2019, methodology): “This category of techniques includes various methods based on Bayesian probability [68], matrix factorization [66], and spectral unmixing [75].”
Multimodal Data Fusion: An Overview of Methods, Challenges, and Prospects (2015, methodology): “This type of optimization is used in group NMF [186], coupled NMF [182], certain SCA-based methods [98], [176]–[178], and numerous coupled tensor decompositions, see e.g., [16], [99], [124] and references therein.”
Learning a Low Tensor-Train Rank Representation for Hyperspectral Image Super-Resolution (2019, methodology): “Recently, various priors have been used for the super-resolution problem, including sparse priors [26], [32], [35], priors of spectral unmixing [27]–[29], low-rank priors [42], nonlocal spatial similarities [33], and spatial smoothness [31].”