Hyperspectral Unmixing Overview: Geometrical, Statistical, and Sparse Regression-Based Approaches
Open accessThe DOI matches its Crossref record; 221 of the 230 references it cites were found in a registry or an index.
Abstract
Imaging spectrometers measure electromagnetic energy scattered in their instantaneous field view in hundreds or thousands of spectral channels with higher spectral resolution than multispectral cameras. Imaging spectrometers are therefore often referred to as hyperspectral cameras (HSCs). Higher spectral resolution enables material identification via spectroscopic analysis, which facilitates countless applications that require identifying materials in scenarios unsuitable for classical spectroscopic analysis. Due to low spatial resolution of HSCs, microscopic material mixing, and multiple scattering, spectra measured by HSCs are mixtures of spectra of materials in a scene. Thus, accurate estimation requires unmixing. Pixels are assumed to be mixtures of a few materials, called endmembers. Unmixing involves estimating all or some of: the number of endmembers, their spectral signatures, and their abundances at each pixel. Unmixing is a challenging, ill-posed inverse problem because of model inaccuracies, observation noise, environmental conditions, endmember variability, and data set size. Researchers have devised and investigated many models searching for robust, stable, tractable, and accurate unmixing algorithms. This paper presents an overview of unmixing methods from the time of Keshava and Mustard's unmixing tutorial to the present. Mixing models are first discussed. Signal-subspace, geometrical, statistical, sparsity-based, and spatial-contextual unmixing algorithms are described. Mathematical problems and potential solutions are described. Algorithm characteristics are illustrated experimentally.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Instead, quantitative chemometric characterization of unknown samples is commonly done using full reference spectra as a vector basis for least-squares fitting, also called regression, compensation, or spectral unmixing, to represent mixed measurements as a set of coefficients, or coordinates of abundance values relative to reference concentrations.16–18”
From Assessment of unmixing approaches for the quantitation of SERS nanoparticles in highly multiplexed spectral images (2024) · cites this paper as [16]
In the citing paper
“Fig. 3 shows that all AE models are faster than N-FINDR+FCLS and VCA+FCLS, which are already among the most computationally lightweight conventional unmixing techniques (85).”
From Hyperspectral unmixing for Raman spectroscopy via physics-constrained autoencoders (2024) · cites this paper as [85]
In the citing paper
“Hence, despite its limitations, the LMM remains a cornerstone of hyperspectral unmixing in most practical settings (41, 85).”
From Hyperspectral unmixing for Raman spectroscopy via physics-constrained autoencoders (2024) · cites this paper as [85]
Citations
Cites
Items 201–221 of 221
Robust hyperspectral data unmixing with spatial and spectral regularized NMF
Huck, A., & Guillaume, M. (2010) · Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing · doi:10.1109/whispers.2010.5594915 · Cited by 27
Hyperspectral Image Unmixing Using a Multiresolution Sticky HDP
Mittelman, R., Nicolas Dobigeon, B., & Hero, A. O. (2011) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2011.2180718 · Cited by 25
Plaza, A., Plaza, J., & Paz, A. (2009) · Concurrency and Computation Practice and Experience · doi:10.1002/cpe.1555 · Cited by 24 · cited 1×
“Although the role of different types of HPC architectures depends heavily on the considered application, cluster-based parallel computing has been used for efficient information extraction from very large data archives using spectral unmixing technniques [219], while on-board and real-time hardware architectures such…”
Self-citationBlind Decomposition of Transmission Light Microscopic Hyperspectral Cube Using Sparse Representation
Begelman, G., Zibulevsky, M., Rivlin, E., & Kolatt, T. (2009) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2009.2015145 · Cited by 23 · cited 2×
“This data set is generated with a mixing matrix sampled from the USGS library and with endmembers, spectral vectors, and fractional abundances given by mixtures of two Dirichlet modes with parameters [6, 25, 9] and [7, 8, 23] and mode weights of 0.”
Zare, A., & Gader, P. (2011) · IEEE International Conference on Fuzzy Systems (FUZZ-IEEE) · doi:10.1109/fuzzy.2011.6007622 · Cited by 22 · cited 1×
“This approach has been taken in [149]–[153].”
Self-citationSpatial-spectral unmixing using fuzzy local information
Zare, A. (2011) · IEEE International Geoscience and Remote Sensing Symposium (IGARSS) · doi:10.1109/igarss.2011.6049398 · Cited by 21
Spatially-smooth piece-wise convex endmember detection
Zare, A., Bchir, O., Frigui, H., & Gader, P. (2010) · Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing · doi:10.1109/whispers.2010.5594897 · Cited by 20 · cited 1×
“Other optimization algorithms operate following the same strategy (see for examples [205]–[207]).”
Self-citationManifold learning techniques for the analysis of hyperspectral ocean data
Gillis, D., Bowles, J. H., Lamela, G. M., Rhea, W. J., Bachmann, C. M., Montes, M. J., & Ainsworth, T. (2005) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.603660 · Cited by 20
Nicolas Dobigeon, B., Tourneret, J., & Hero, A. O. (2008) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2008.4518389 · Cited by 19 · cited 1×
“Note that the case of a coloredGaussian noise with unknown covariance matrix has been handled in [168].”
Total variation regulatization in sparse hyperspectral unmixing
Iordache, M.-D., Bioucas‐Dias, J. M., & Plaza, A. (2011) · Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing · doi:10.1109/whispers.2011.6080882 · Cited by 17
Self-citationBachmann, C. M., & Donato, T. F. (2000) · International Journal of Remote Sensing · doi:10.1080/01431160050121339 · Cited by 14 · cited 1×
“Independent component analysis [108], [109], projection pursuit [110], [111], and wavelet decomposition [112], [113] have also been considered.”
Kernel Methods for Unmixing Hyperspectral Imagery
Broadwater, J. B., Banerjee, A., & Burlina, P. (2009) · Wiley eBooks · doi:10.1002/9780470748992.ch11 · Cited by 12 · cited 1×
“In [53] and following works [54]–[57], Broadwater et al.”
Kernel Based Subspace Projection of Near Infrared Hyperspectral Images of Maize Kernels
Larsen, R., Arngren, M., Hansen, P. W., & Nielsen, A. A. (2009) · Lecture notes in computer science · doi:10.1007/978-3-642-02230-2_57 · Cited by 12 · cited 1×
“They have also been used in food safety [14]–[17], pharmaceutical process monitoring and quality control [18]–[22], and biomedical, industrial, and biometric, and forensic applications [23]–[27].”
Moeller, M., Esser, E., Osher, S., Sapiro, G., & Xin, J. X. (2010) · Defense Technical Information Center (DTIC) · doi:10.21236/ada540658 · Cited by 11 · cited 1×
“ The collaborative convex framework [128] factorizes the data matrix into a nonnegative mixing matrix and a sparse and also nonnegative abundance matrix .”
Modal mineralogy of planetary surfaces from visible and near-infrared spectral data
Poulet, F., Ehlmann, B. L., Mustard, J. F., Vincendon, M., & Langevin, Y. (2010) · Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing · doi:10.1109/whispers.2010.5594898 · Cited by 11 · cited 1×
“ical solution to the RTT. The former has been widely used to study diffuse reflection spectra in chemistry [51] whereas the later two have been used, for example, in mineral unmixing applications [1], [52]. One wide class of strategies is aimed at avoiding the complex physical models using simpler but physics inspired…”
MethodMultiple model endmember detection based on spectral and spatial information
Bchir, O., Frigui, H., Zare, A., & Gader, P. (2010) · Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing · doi:10.1109/whispers.2010.5594866 · Cited by 8
Self-citationAn Investigation of Likelihoods and Priors for Bayesian Endmember Estimation
Zare, A., Gader, P., Ali Mohammad-djafari, A., Bercher, J., & Bessìère, P. (2011) · AIP conference proceedings · doi:10.1063/1.3573631 · Cited by 8
Self-citationA comparison of deterministic and probabilistic approaches to endmember representation
Zare, A., Bchir, O., Frigui, H., & Gader, P. (2010) · Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing · doi:10.1109/whispers.2010.5594884 · Cited by 8 · cited 1×
“A robust version also exists that uses a combination of fuzzy and possibilistic clustering [151].”
Self-citationConvex Constraint Decomposition of Circular Dichroism Curves of Proteins
Perczel, A., Hollósi, M., Tusnády, G., & Fasman, G. D. (1989) · University of Zagreb University Computing Centre (SRCE) · Cited by 7
Endmember and proportion estimation using physics-based macroscopic and microscopic mixture models
Close, R. (2011) · Cited by 4
Robust Endmember detection using L1 norm factorization
Zare, A., & Gader, P. (2010) · IEEE International Geoscience and Remote Sensing Symposium (IGARSS) · doi:10.1109/igarss.2010.5653679 · Cited by 3 · cited 1×
“versions also exist [143].”
Self-citation
Research works printed but not linked: 15
- vikneswaran, 2011, Techniques of Parallelization in Markov Chain Monte Carlo Methods
- singer, 1979, Mars: Large scale mixing of bright and dark surface materials and implications for analysis of spectral reflectance, Proc 15th Lunar and Planetary Science Conf, 1835
- broadwater, 2011, Optical Remote Sensing Advances in Signal Processing and Exploitation, 247
- gillespie, 1990, Interpretation of residual images: Spectral mixture analysis of AVIRIS images, Owens Valley, California, Proc 2nd AVIRIS Workshop, 9054, 243
- swayze, 1992, Ground-truthing AVIRIS mineral mapping at Cuprite, Nevada, Proc JPL Airborne Earth Sci Workshop, 47
- kulbelka, 1931, Reflection characteristics of paints, Zeitschrift fur Technische Physik, 12, 593
- close, 2012, Hyperspectral endmember and proportion estimation using macroscopic and microscopic mixture models, IEEE Trans Geosci Remote Sens
- harsanyi, 1993, Determining the number and identity of spectral endmembers: An integrated approach using Neyman-Pearson eigenthresholding and iterative constrained RMS error minimization, Proc Thematic Conf Geologic Remote Sens, 1, 1
- 10.1109/whispers.2010.5594897 · DOI
- 10.1109/fuzzy.2011.6007622 · DOI
- iordache, 2012, Collaborative hierarchical sparse unmixing of hyperspectral data, Proc IEEE Int Conf Geosci Remote Sens (IGARSS)
- arngren, 2007, Modelling Cognitive Representations
- 10.1007/s11265-010-0533-2 · DOI
- 10.1109/tsp.2009.2025802 · DOI · Paper page
- kruse, 1998, Spectral identification of image endmembers determined from AVIRIS data, Proc JPL Airborne Earth Sci Workshop, 1, 1
Cited by
Hyperspectral remote sensing data analysis and future challenges
Bioucas-Dias, J. M., Plaza, A., Camps-Valls, G., Scheunders, P., Nasrabadi, N., & Chanussot, J. (2013) · IEEE Geoscience and Remote Sensing Magazine · doi:10.1109/mgrs.2013.2244672 · Cited by 2,223
“6, are the linear model, the bilinear model, and the Hapke model [3], [40].”
BackgroundMethodInfluentialSelf-citationGraph Convolutional Networks for Hyperspectral Image Classification
Hong, D., Gao, L., Yao, J., Zhang, B., Plaza, A., & Chanussot, J. (2021) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2020.3015157 · Cited by 1,691
“However, the high spectral mixing between materials [5] and spectral variability and complex noise effects [6] bring difficulties in extracting discriminative information from such data.”
BackgroundSelf-citationAdão, T., Hruška, J., Pádua, L., Bessa, J., Peres, E., Morais, R., & Sousa, J. (2017) · Remote Sensing · doi:10.3390/rs9111110 · Cited by 1,318
“According to Bioucas-Dias [54] spectral unmixing (see, for example, [74,75]) purpose is to restore the ability of ascertain materials, i.”
BackgroundPixel-level image fusion: A survey of the state of the art
Li, S., Kang, X., Fang, L., Hu, J., & Yin, H. (2017) · Information Fusion · doi:10.1016/j.inffus.2016.05.004 · Cited by 1,276
Deep learning classifiers for hyperspectral imaging: A review
Paoletti, M. E., Haut, J. M., Plaza, J., & Plaza, A. (2019) · ISPRS Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2019.09.006 · Cited by 1,073
“The most popular ones include: (i) spectral unmixing (Bioucas-Dias et al., 2012; Heylen et al., 2014; Shi and Wang, 2014; Sánchez et al., 2015; Zhong et al., 2016a), (ii) resolution enhancement (Eismann and Hardie, 2005; Mookambiga and Gomathi, 2016; Yi et al.”
BackgroundSelf-citation
Metadata
- Authors
- Bioucas-Dias, J. M., Plaza, A., Dobigeon, N., Parente, M., Du, Q., Gader, P., & Chanussot, J.
- Affiliations
- Universidad de Extremadura (ES)
- Université Toulouse III - Paul Sabatier (FR)
- University of Massachusetts Amherst (US)
- Mississippi State University (US)
- Institut polytechnique de Grenoble (FR)
- Venue
- IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Published
- 2012-04
- Volume
- 5
- Issue
- 2
- Pages
- 354-379
- ISSN
- 1939-1404 (ISSN-L)
- 2151-1535
- OpenAlex
- W2163886442
- Cited by
- 2,836
- References
- 230
- Citations by year
- 2026: 128 · 2025: 164 · 2024: 176 · 2023: 193 · 2022: 175 · 2021: 249 · 2020: 244 · 2019: 257 · 2018: 232 · 2017: 237 · 2016: 224 · 2015: 196 · 2014: 187 · 2013: 139 · 2012: 32
- FWCI
- 389.94
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- HAL (submittedVersion, other-oa)
- arXiv (Cornell University)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Remote-Sensing Image Classification
- Physical Sciences › Earth and Planetary Sciences › Geochemistry and Petrology › Geochemistry and Geologic Mapping
- Physical Sciences › Chemistry › Analytical Chemistry › Spectroscopy and Chemometric Analyses
- Keywords
- hyperspectral unmixing, endmember extraction, abundance estimation, mixing models, sparse regression, ill-posed inverse problems, imaging spectrometer, endmember variability
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.