Next Article in Journal
Integrating MNF and HHT Transformations into Artificial Neural Networks for Hyperspectral Image Classification
Next Article in Special Issue
Estimation of the Number of Endmembers in Hyperspectral Images Using Agglomerative Clustering
Previous Article in Journal
Conversion of Agricultural Land for Urbanization Purposes: A Case Study of the Suburbs of the Capital of Warmia and Mazury, Poland
Previous Article in Special Issue
Spatial Attraction Models Coupled with Elman Neural Networks for Enhancing Sub-Pixel Urban Inundation Mapping
Article

Hierarchical Sparse Nonnegative Matrix Factorization for Hyperspectral Unmixing with Spectral Variability

1
IRIT/INP-ENSEEIHT, University of Toulouse, CEDEX 7, 31071 Toulouse, France
2
CESBIO, CNES/CNRS/IRD/UPS/INRAE, University of Toulouse, CEDEX 9, 31401 Toulouse, France
3
Institut Universitaire de France, Ministère de l’Éducation Nationale, de l’Enseignement Supérieur et de la Recherche, 1 rue Descartes, CEDEX 05, 75231 Paris, France
*
Author to whom correspondence should be addressed.
Current address: RIKEN Center for Advanced Intelligence Project, Geoinformatics Unit RIKEN, Tokyo 103-0027, Japan.
Remote Sens. 2020, 12(14), 2326; https://doi.org/10.3390/rs12142326
Received: 25 June 2020 / Revised: 9 July 2020 / Accepted: 16 July 2020 / Published: 20 July 2020
(This article belongs to the Special Issue New Advances on Sub-pixel Processing: Unmixing and Mapping Methods)
Accounting for endmember variability is a challenging issue when unmixing hyperspectral data. This paper models the variability that is associated with each endmember as a conical hull defined by extremal pixels from the data set. These extremal pixels are considered as so-called prototypal endmember spectra that have meaningful physical interpretation. Capitalizing on this data-driven modeling, the pixels of the hyperspectral image are then described as combinations of these prototypal endmember spectra weighted by bundling coefficients and spatial abundances. The proposed unmixing model not only extracts and clusters the prototypal endmember spectra, but also estimates the abundances of each endmember. The performance of the approach is illustrated thanks to experiments conducted on simulated and real hyperspectral data and it outperforms state-of-the-art methods. View Full-Text
Keywords: hyperspectral imaging; spectral unmixing; sparse unmixing; endmember variability hyperspectral imaging; spectral unmixing; sparse unmixing; endmember variability
Show Figures

Graphical abstract

MDPI and ACS Style

Uezato, T.; Fauvel, M.; Dobigeon, N. Hierarchical Sparse Nonnegative Matrix Factorization for Hyperspectral Unmixing with Spectral Variability. Remote Sens. 2020, 12, 2326. https://doi.org/10.3390/rs12142326

AMA Style

Uezato T, Fauvel M, Dobigeon N. Hierarchical Sparse Nonnegative Matrix Factorization for Hyperspectral Unmixing with Spectral Variability. Remote Sensing. 2020; 12(14):2326. https://doi.org/10.3390/rs12142326

Chicago/Turabian Style

Uezato, Tatsumi, Mathieu Fauvel, and Nicolas Dobigeon. 2020. "Hierarchical Sparse Nonnegative Matrix Factorization for Hyperspectral Unmixing with Spectral Variability" Remote Sensing 12, no. 14: 2326. https://doi.org/10.3390/rs12142326

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop