Nonlinear Unmixing of Hyperspectral Images: Models and Algorithms
Open accessThe DOI matches its Crossref record; 55 of the 57 references it cites were found in a registry or an index.
Abstract
When considering the problem of unmixing hyperspectral images, most of the literature in the geoscience and image processing areas relies on the widely used linear mixing model (LMM). However, the LMM may be not valid, and other nonlinear models need to be considered, for instance, when there are multiscattering effects or intimate interactions. Consequently, over the last few years, several significant contributions have been proposed to overcome the limitations inherent in the LMM. In this article, we present an overview of recent advances in nonlinear unmixing modeling.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
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?
The cited source says what the claim attributes to it.
In the citing paper
“However, when nonlinear interactions become significant, more intricate models are required (96).”
From Hyperspectral unmixing for Raman spectroscopy via physics-constrained autoencoders (2024) · cites this paper as [96]
The cited source says what the claim attributes to it.
In the citing paper
“However, accounting for nonlinear mixing interactions increases the complexity and computational cost of unmixing (96, 97), an issue of especial relevance in Raman spectroscopy where datasets (e.g., imaging/volumetric scans) are typically larger than in remote sensing.”
From Hyperspectral unmixing for Raman spectroscopy via physics-constrained autoencoders (2024) · cites this paper as [96]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Hyperspectral Unmixing Overview: Geometrical, Statistical, and Sparse Regression-Based Approaches
Bioucas-Dias, J. M., Plaza, A., Dobigeon, N., Parente, M., Du, Q., Gader, P., & Chanussot, J. (2012) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2012.2194696 · Cited by 2,836 · cited 4×
“In [1], it is explained that linear mixtures are reasonable when two assumptions are wholly fulfilled.”
BackgroundMethodInfluentialKeshava, N., & Mustard, J. F. (2002) · IEEE Signal Processing Magazine · doi:10.1109/79.974727 · Cited by 2,549 · cited 2×
“More than 10 years after Keshava and Mustard’s comprehensive review article on spectral unmixing [11], this article provides an updated review focusing on non-linear unmixing techniques introduced in the past decade.”
BackgroundReflectance spectroscopy: Quantitative analysis techniques for remote sensing applications
Clark, R. N., & Roush, T. L. (1984) · Journal of Geophysical Research: Solid Earth · doi:10.1029/jb089ib07p06329 · Cited by 2,055 · cited 1×
“Secondly, the photons that reach the sensor must interact with only one material, as is the case in checkerboard type scenes [13].”
BackgroundBidirectional reflectance spectroscopy: 1. Theory
Hapke, B. (1981) · Journal of Geophysical Research: Solid Earth · doi:10.1029/jb086ib04p03039 · Cited by 1,888 · cited 3×
“In [2], the author derives an analytical model to express the measured reflectances as a function of parameters intrinsic to the mixtures, e.”
BackgroundMethodInfluentialTheory of Reflectance and Emittance Spectroscopy
Hapke, B. (1993) · Cambridge University Press eBooks · doi:10.1017/cbo9780511524998 · Cited by 1,849 · cited 4×
“The abundances can be interpreted as the relative areas occupied by the materials in a given image pixel [3].”
BackgroundInfluentialHeinz, D. C., & Chein-I-Chang (2001) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/36.911111 · Cited by 1,847 · cited 2×
“The fully constrained least square (FCLS) algorithm [35] was used for linear mixtures.”
MethodThe discrete-dipole approximation and its application to interstellar graphite grains
Draine, B. T. (1988) · The Astrophysical Journal · doi:10.1086/166795 · Cited by 1,528 · cited 1×
“Other popular approximating models include the discrete-dipole approximation [16] and the Shkuratov’s model [17] (interested readers are invited”
MethodA Model of Spectral Albedo of Particulate Surfaces: Implications for Optical Properties of the Moon
Shkuratov, Y., Starukhina, L., Hoffmann, H., & Arnold, G. (1999) · Icarus · doi:10.1006/icar.1998.6035 · Cited by 471
A Signal Processing Perspective on Hyperspectral Unmixing: Insights from Remote Sensing
Ma, W.-K., Bioucas-Dias, J. M., Chan, T.-H., Gillis, N., Gader, P., Plaza, A. J., Ambikapathi, A., & Chi, C.-Y. (2014) · IEEE Signal Processing Magazine · doi:10.1109/msp.2013.2279731 · Cited by 456
Nonlinear Unmixing of Hyperspectral Images Using a Generalized Bilinear Model
Halimi, A., Altmann, Y., Dobigeon, N., & Tourneret, J.-Y. (2011) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2010.2098414 · Cited by 443 · cited 2×
“linear model (GBM) has been proposed in [22] by setting βi,j,p = γi,j,pai,paj,p”
BackgroundMethodSelf-citation
Research works printed but not linked: 6
- [30] J. Plaza, P. Martinez, R. Perez, and A. Plaza, 'Nonlinear neural network mixture models for fractional abundance estimation in AVIRIS hyperspectral images,' in Proc. XIII NASA/Jet Propulsion Laboratory Airborne Earth Science Workshop , Pasadena, CA, USA, 2004. -
- [59] N. Dobigeon and C. F´ evotte, 'Robust nonnegative matrix factorization for nonlinear unmixing of hyperspectral images,' in Proc. IEEE GRSS Workshop Hyperspectral Image SIgnal Process.: Evolution in Remote Sens. (WHISPERS) , Gainesville, FL, June 2013. -
- [54] M. Winter, 'Fast autonomous spectral end-member determination in hyperspectral data,' in Proc. 13th Int. Conf. on Applied Geologic Remote Sensing , vol. 2, Vancouver, April 1999, pp. 337-344. -
- [53] RSI (Research Systems Inc.), ENVI User's guide Version 4.0 , Boulder, CO 80301 USA, Sept. 2003. -
- [12] R. B. Singer and T. B. McCord, 'Mars: Large scale mixing of bright and dark surface materials and implications for analysis of spectral reflectance,' in Proc. 10th Lunar and Planetary Sci. Conf. , March 1979, pp. 1835-1848. -
- [49] --, 'Nonlinear abundance estimation of hyperspectral images with L1-norm spatial regularization,' IEEE Trans. Geosci. and Remote Sensing , 2013, submitted. -
Cited by
Items 101–200 of 472
Siebels, K., Goïta, K., & Germain, M. (2020) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2020.2969577 · Cited by 39
“Comprehensive overviews of nonlinear models can be found in [34] and [35].”
BackgroundCentralized Collaborative Sparse Unmixing for Hyperspectral Images
Wang, R., Li, H.-C., Liao, W., Huang, X., & Philips, W. R. (2017) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2017.2651063 · Cited by 37
“In the context of spectral unmixing, both linear and nonlinear mixture models are utilized to describe the mixing process of mixed pixels [2], [3], among which the former has attracted significant interest of researchers in terms of its simplicity and definite physical meaning.”
BackgroundNonparametric Detection of Nonlinearly Mixed Pixels and Endmember Estimation in Hyperspectral Images
Imbiriba, T., Bermudez, J. C. M., Richard, C., & Tourneret, J. (2015) · IEEE Transactions on Image Processing · doi:10.1109/tip.2015.2509258 · Cited by 36
“Mixing phenomena depend on a variety of factors such as the resolution of observation devices, the properties of materials, and how these materials interact with incident light in the scene [6].”
InfluentialSelf-citationKizel, F., Shoshany, M., Netanyahu, N. S., Even-Tzur, G., & Benediktsson, J. A. (2017) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2017.2692999 · Cited by 36
“In addition to the wide use of the LMM in the majority of existing methods, nonlinear models have been recently introduced in various works (see [38], [39] for detailed surveys).”
MethodPure endmember extraction using robust kernel archetypoid analysis for hyperspectral imagery
Sun, W., Yang, G., Wu, K., Li, W., & Zhang, D. (2017) · ISPRS Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2017.08.001 · Cited by 37
Hybrid Spectral Unmixing: Using Artificial Neural Networks for Linear/Non-Linear Switching
Ahmed, A. M., Duran, O., Zweiri, Y., & Smith, M. J. (2017) · Remote Sensing · doi:10.3390/rs9080775 · Cited by 36
“A model proposed by Hapke [6] describes the interactions suffered by light when it comes into contact with a surface composed of particles; they involve meaningful and interpretable quantities that have physical significance, however, these models require a nonlinear formulation which is complex and complicates the de…”
BackgroundMethodInfluentialCram$\acute{\text{e}}$r–Rao Bound for Constrained Parameter Estimation Using Lehmann-Unbiasedness
Nitzan, E., Routtenberg, T., & Tabrikian, J. (2018) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2018.2883915 · Cited by 34
Roscher, R., Bohn, B., Duarte, M. F., & Garcke, J. (2020) · ISPRS annals of the photogrammetry, remote sensing and spatial information sciences · doi:10.5194/isprs-annals-v-3-2020-817-2020 · Cited by 42
“However, the physical process involving the spectrum acquisition from the mixture does not follow the linear model assumed by the regression methods, and nonlinear unmixing approaches have been proposed to remediate this discrepancy (Dobigeon et al., 2014).”
BackgroundWang, Z., Chen, B., Zhang, H., & Liu, H. (2020) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2020.3028772 · Cited by 36
Nonlocal Tensor-Based Sparse Hyperspectral Unmixing
Huang, J. W., Huang, T., Zhao, X.-L., & Deng, L.-J. (2020) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2020.3030233 · Cited by 38
“3030233 The mixing process in numerous state-of-the-art unmixing algorithms is either characterized as linear [2] or nonlinear [15].”
BackgroundMoser, G., Giorgi, A. D., & Serpico, S. B. (2016) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2016.2547027 · Cited by 34
Hybrid Unmixing Based on Adaptive Region Segmentation for Hyperspectral Imagery
Zhang, X., Zhang, J., Li, C., Cheng, C., Jiao, L., & Zhou, H. (2018) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2018.2815044 · Cited by 33
“The whole idea of this paper is to use the model of the GBM which considers the second-order photon interactions between different materials.”
BackgroundMethodInfluentialConstrained Least Squares Algorithms for Nonlinear Unmixing of Hyperspectral Imagery
Pu, H., Chen, Z., Wang, B., & Xia, W. (2014) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2014.2336858 · Cited by 34
Band Selection for Nonlinear Unmixing of Hyperspectral Images as a Maximal Clique Problem
Imbiriba, T., Bermudez, J. C. M., & Richard, C. (2017) · IEEE Transactions on Image Processing · doi:10.1109/tip.2017.2676344 · Cited by 32
“Though BS has been actively employed in classification of spectral patterns [16]–[20], subspace projection techniques [21]–[23] tend to be preferred over BS [24], [25] for reducing the complexity of linear unmixing processes.”
Self-citationIllumination Invariant Hyperspectral Image Unmixing Based on a Digital Surface Model
Uezato, T., Yokoya, N., & He, W. (2020) · IEEE Transactions on Image Processing · doi:10.1109/tip.2020.2963961 · Cited by 33
“The variable topography also causes multiple scatterings of light, leading to nonlinear interactions of endmembers [18], [19].”
BackgroundMethodShadow Detection and Restoration for Hyperspectral Images Based on Nonlinear Spectral Unmixing
Zhang, G., Cerra, D., & Müller, R. (2020) · Remote Sensing · doi:10.3390/rs12233985 · Cited by 35
“Modeling nonlinear effects for spectral unmixing has been explored for decades (see reviews in [38,49]).”
BackgroundToward a Sparse Bayesian Markov Random Field Approach to Hyperspectral Unmixing and Classification
Chen, P., Nelson, J. D. B., & Tourneret, J. (2016) · IEEE Transactions on Image Processing · doi:10.1109/tip.2016.2622401 · Cited by 31
“Although some recent research considers nonlinear unmixing, such as [1] and those reviewed in [14], linear models continue to receive much attention.”
BackgroundSelf-citationA Blind Multiscale Spatial Regularization Framework for Kernel-Based Spectral Unmixing
Borsoi, R. A., Imbiriba, T., Bermudez, J. C. M., & Richard, C. (2020) · IEEE Transactions on Image Processing · doi:10.1109/tip.2020.2978342 · Cited by 34
Self-citationGBM-Based Unmixing of Hyperspectral Data Using Bound Projected Optimal Gradient Method
Li, C., Ma, Y., Huang, J., Mei, X., Liu, C., & Ma, J. (2016) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2016.2555341 · Cited by 30
“The mixture model associated with SU imagery can be linear or nonlinear, which depends on the hyperspectral image under research [7].”
BackgroundHyperspectral Unmixing With Endmember Variability via Alternating Angle Minimization
Heylen, R., Zare, A., Gader, P., & Scheunders, P. (2016) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2016.2554160 · Cited by 32
“review papers [1]–[3] for more details.”
Thouvenin, P.-A., Nicolas Dobigeon, B., & Tourneret, J. (2017) · IEEE Transactions on Computational Imaging · doi:10.1109/tci.2017.2777484 · Cited by 32
Self-citationℓ0-Norm Sparse Hyperspectral Unmixing Using Arctan Smoothing
Salehani, Y. E., Gazor, S., Kim, I., & Yousefi, S. (2016) · Remote Sensing · doi:10.3390/rs8030187 · Cited by 28
“However, the linear SU methods are being scrutinized by researchers and scientists extensively because of their capabilities in many applications [4,5,11–13], Remote Sens.”
Tang, M., Gao, L., Marinoni, A., Gamba, P. E., & Zhang, B. (2017) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2017.2771482 · Cited by 30
“Therefore, in recent years, research efforts have been devoted to study and design nonlinear spectral mixing models (NLMMs) [5].”
BackgroundA Nonconvex Framework for Sparse Unmixing Incorporating the Group Structure of the Spectral Library
Ren, L., Ma, Z., Bovolo, F., & Bruzzone, L. (2021) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2021.3081101 · Cited by 34
“We refer readers to [6] and [7] for a detailed review of the nonlinear unmixing models.”
MethodNonlinear Unmixing for Hyperspectral Images via Kernel-Transformed Bilinear Mixing Models
Gu, J., Yang, B., & Wang, B. (2021) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2021.3135571 · Cited by 30
“To avoid the dependence of large numbers of physical parameters, many NMMs are developed by incorporating nonlinear mixing terms into the LMM [10].”
BackgroundMethodInfluentialA Low-Rank Tensor Regularization Strategy for Hyperspectral Unmixing
Imbiriba, T., Borsoi, R. A., & Bermudez, J. C. M. (2018) · IEEE Statistical Signal Processing Workshop (SSP) · doi:10.1109/ssp.2018.8450853 · Cited by 28
“Different mixing models have been used to explain the interaction between light and the endmembers [4–6] or spectral variability along the image [7, 8].”
MethodSelf-citationNonlinear Hyperspectral Unmixing With Graphical Models
Heylen, R., Andrejchenko, V., Zahiri, Z., Parente, M. C., & Scheunders, P. (2019) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2019.2893489 · Cited by 30
“divided into several classes [6], [7] depending on the complexity.”
BackgroundDeep Generative Models for Library Augmentation in Multiple Endmember Spectral Mixture Analysis
Borsoi, R. A., Imbiriba, T., Bermudez, J. C. M., & Richard, C. (2020) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2020.3007161 · Cited by 28
“e the EMs are known a priori, or unsupervised, where the EMs are estimated from the observed HI [2]. Different models have been proposed to describe the interaction between light and the targets [1], [3]. The most popular among these is the Linear Mixing Model (LMM), which represents the reflectance at each pixel as a…”
BackgroundSelf-citationNonlinear Unmixing by Using Different Metrics in a Linear Unmixing Chain
Heylen, R., Scheunders, P., Rangarajan, A., & Gader, P. (2014) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2014.2375342 · Cited by 26
Luo, W., Gao, L., Plaza, A., Marinoni, A., Yang, B., Zhong, L., Gamba, P. E., & Zhang, B. (2016) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2016.2602882 · Cited by 26
“For additional details of the formulation of the bilinear term, we refer to [33]–[35].”
BackgroundMetric similarity regularizer to enhance pixel similarity performance for hyperspectral unmixing
Ahmad, M. I., Bashir, A. K., & Khan, A. (2017) · Optik · doi:10.1016/j.ijleo.2017.03.051 · Cited by 28
Kalman Filtering and Expectation Maximization for Multitemporal Spectral Unmixing
Borsoi, R. A., Imbiriba, T., Closas, P., Bermudez, J. C. M., & Richard, C. (2020) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2020.3025781 · Cited by 25
Self-citationBlind Source Separation in Nonlinear Mixtures: Separability and a Basic Algorithm
Ehsandoust, B., Babaie‐Zadeh, M., Rivet, B., & Jutten, C. (2017) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2017.2708025 · Cited by 24
“Hyperspectral imaging [13], [14], remote sensing data [15], determining the concentra-”
Residual Dense Autoencoder Network for Nonlinear Hyperspectral Unmixing
Yang, X., Chen, J., Wang, C., & Chen, Z. (2022) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2022.3188565 · Cited by 25
Multiharmonic Postnonlinear Mixing Model for Hyperspectral Nonlinear Unmixing
Tang, M., Zhang, B., Marinoni, A., Gao, L., & Gamba, P. E. (2018) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2018.2856406 · Cited by 25
“However, they cannot provide good HSU performance in more complex situations [3].”
BackgroundMethodInfluentialProcessing Hyperspectral Images
Ceamanos, X., & Valero, S. (2016) · Elsevier eBooks · doi:10.1016/b978-1-78548-102-4.50004-1 · Cited by 27
Improving deep hyperspectral image classification performance with spectral unmixing
Guo, A. J. X., & Zhu, F. (2021) · Signal Processing · doi:10.1016/j.sigpro.2020.107949 · Cited by 25
A Graph Regularized Multilinear Mixing Model for Nonlinear Hyperspectral Unmixing
Li, M., Zhu, F., Guo, A. J. X., & Chen, J. (2019) · Remote Sensing · doi:10.3390/rs11192188 · Cited by 24
“The aim of SU is to extract the endmembers and to determine their respective proportions, referred to as abundances [2].”
BackgroundSpectral Unmixing Using a Sparse Multiple-Endmember Spectral Mixture Model
Fen, C., Wang, K., & Tang, T. F. (2016) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2016.2574331 · Cited by 24
“be referred to in these review papers [1]–[3], [12], [13], [23].”
BackgroundMethodKumar, U., Ganguly, S., Nemani, R., Raja, K. S., MILESI, C., Sinha, R., Michaelis, A., Votava, P., Hashimoto, H., Li, S., et al. (2017) · Remote Sensing · doi:10.3390/rs9111105 · Cited by 25
“Theoretically, radiative transfer is the physical phenomenon of energy transfer and describes the propagation of radiation on the Earth’s surface affected by interaction processes between radiation, atmospheric constituents and the Earth’s physical surface [4].”
BackgroundTian, K., Zhong, Y., Song, M., Wang, X., & Zhang, L. (2024) · ISPRS Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2024.09.020 · Cited by 25
Fast and Structured Block-Term Tensor Decomposition for Hyperspectral Unmixing
Ding, M., Fu, X., & Zhao, X.-L. (2023) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2023.3238653 · Cited by 24
“It is worth noting that many nonlinear mixture models are also proposed for HU; see [16] and recent developments using neural networks, e.”
BackgroundBrezini, S. E., & Deville, Y. (2023) · Sensors · doi:10.3390/s23042341 · Cited by 22
Liu, W., Ma, Y., Wang, X., Huang, J., Chen, Q., Li, H., & Mei, X. (2024) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2024.3375934 · Cited by 28
“LMM assumes the mixed pixel is the linear combination of endmembers while NLMM additionally considers the nonlinear interactions between pure spectrum [16].”
BackgroundMarinoni, A., & Gamba, P. E. (2015) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2015.2504048 · Cited by 22
“Several papers have addressed the topic of nonlinear unmixing of hyperspectral images [23].”
BackgroundHyperspectral Unmixing with Bandwise Generalized Bilinear Model
Li, C., Liu, Y., Cheng, J., Song, R., Peng, H., Chen, Q., & Chen, X. (2018) · Remote Sensing · doi:10.3390/rs10101600 · Cited by 21
“The reason is that the interactions of orders larger than two, not only have minor contribution for improving the unmixing accuracy than that of second-order scattering, but also bring in tremendous computational costs [21].”
BackgroundVariability of the endmembers in spectral unmixing
Drumetz, L., Chanussot, J., & Jutten, C. (2019) · Data handling in science and technology · doi:10.1016/b978-0-444-63977-6.00009-2 · Cited by 24
Zhao, M., Chen, J., & Dobigeon, N. (2024) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2024.3377472 · Cited by 31
“…this limitation, hyperspectral unmixing (HU) aims at decomposing the i th observed pixel spectrum y i ∈ R B into a set of R spectral signatures of so-called endmembers collected in the matrix S = [ s 1 , . . . , s R ] ∈ R B × R and their associated fractions or abundances a i ∈ R R [5], [6], [7].”
BackgroundReinforcement Learning for Neural Architecture Search in Hyperspectral Unmixing
Han, Z., Hong, D., Gao, L., Roy, S. K., Zhang, B., & Chanussot, J. (2022) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2022.3199583 · Cited by 23
“In contrast, the nonlinear mixing model (NLMM) considers scattering interactions of photons between multiple materials at an intimate or multilayered level and introduces second-order or high-order interactions to model nonlinearities in the scene [4], [5].”
BackgroundCheng, Y., Zhao, L., Chen, S., & Li, X. (2023) · Remote Sensing · doi:10.3390/rs15153890 · Cited by 19
“Several typical nonlinear mixing models have been proposed, for example, the Fan model [7], the Nasci-mento model [8], the Hapke model [9], the generalized bilinear model (GBM) [10], and the post-nonlinear mixed model [11].”
A Two-Stream Stacked Autoencoder With Inter-Class Separability for Bilinear Hyperspectral Unmixing
Cao, C., Song, W., Xiang, H., Hong-bo, Y., Xiao, F., & Gao, X. (2024) · IEEE Transactions on Computational Imaging · doi:10.1109/tci.2024.3369410 · Cited by 20
Hyperspectral Unmixing Based on Constrained Bilinear or Linear-Quadratic Matrix Factorization
Benhalouche, F. Z., Deville, Y., Karoui, M. S., & Ouamri, A. (2021) · Remote Sensing · doi:10.3390/rs13112132 · Cited by 22
“These models are suitable when facing flat landscape and irradiance homogeneity in the observed scene [36].”
BackgroundBilateral Joint-Sparse Regression for Hyperspectral Unmixing
Huang, J. W., Di, W.-C., Wang, J.-J., Lin, J., & Huang, T. (2021) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2021.3115172 · Cited by 20
“The mixing process can be characterized as either linear [1] or nonlinear [4], [5].”
BackgroundYang, B. (2022) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2022.3177648 · Cited by 22
“…of the mixing process’s expression, the LMM simplifies light’s interactions among different ground covers to be only single scatterings (i.e., pixels are assumed to be linearly constituted by endmembers), while the NMMs’ central assumption lies on the nonnegligible multiple scatterings [3], [4].”
BackgroundHyperspectral Nonlinear Unmixing by Using Plug-and-Play Prior for Abundance Maps
Wang, Z., Zhuang, L., Gao, L., Marinoni, A., Zhang, B., & Ng, M. K. (2020) · Remote Sensing · doi:10.3390/rs12244117 · Cited by 21
“To satisfy the physical assumptions and overcome the limitations of the FM [1], the GBM redefines the parameter bi,j as bi,j = γi,jaiaj.”
BackgroundNon-linear spectral unmixing of hyperspectral data using Modified PPNMM
Dixit, A., & Agarwal, S. (2021) · Applied Computing and Geosciences · doi:10.1016/j.acags.2021.100053 · Cited by 18
Hyperspectral Nonlinear Unmixing via Generative Adversarial Network
Tang, M., Qu, Y., & Qi, H. (2020) · IEEE International Geoscience and Remote Sensing Symposium (IGARSS) · doi:10.1109/igarss39084.2020.9324087 · Cited by 21
“In order to solve this problem, several nonlinear mixture models have been developed [2].”
BackgroundSadashivaiah, V., Tippani, M., Page, S. C., Kwon, S., Bach, S. V., Bharadwaj, R. A., Hyde, T. M., Kleinman, J. E., Jaffe, A. E., & Maynard, K. R. (2023) · BMC Neuroscience · doi:10.1186/s12868-022-00765-1 · Cited by 19
“Non-linear unmixing has also been explored in the field of remote sensing (28,29), but both groups of methods fail to account for spectral variability.”
BackgroundLi, M., Yang, B., & Wang, B. (2023) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2023.3308211 · Cited by 23
Marine plastic detection using PRISMA hyperspectral satellite imagery in a controlled environment
Corbari, L., Capodici, F., Ciraolo, G., & Topouzelis, K. (2023) · International Journal of Remote Sensing · doi:10.1080/01431161.2023.2275324 · Cited by 18
“The nonlinear spectral unmixing (Dobigeon et al. 2014) was combined with the spectral angle mapper (SAM) (Kruse et al. 1993) to infer iteratively the spectral signatures of the plastic target, R p , which was considered as the endmember of the unmixing procedure applied to retrieve the abundance of…”
MethodHyperspectral Unmixing Via Turbo Bilinear Approximate Message Passing
Vila, J. P., Schniter, P., & Meola, J. (2015) · IEEE Transactions on Computational Imaging · doi:10.1109/tci.2015.2465161 · Cited by 24
Joint Anomaly Detection and Spectral Unmixing for Planetary Hyperspectral Images
Nakhostin, S., Clénet, H., Corpetti, T., & Courty, N. (2016) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2016.2586188 · Cited by 18
Relationships Between Nonlinear and Space-Variant Linear Models in Hyperspectral Image Unmixing
Drumetz, L., Ehsandoust, B., Chanussot, J., Rivet, B., Babaie‐Zadeh, M., & Jutten, C. (2017) · IEEE Signal Processing Letters · doi:10.1109/lsp.2017.2747478 · Cited by 20
“, in tree canopies) [4], [5].”
A novel nonlinear hyperspectral unmixing approach for images of oil spills at sea
Li, Y., Lu, H., Zhang, Z., & Liu, P. (2020) · International Journal of Remote Sensing · doi:10.1080/01431161.2020.1723179 · Cited by 19
“Methods to unmix spectral information are at the core of hyperspectral applications (Dobigeon et al. 2014; Imbiriba, Bermudez, and Richard 2017; Seyyedsalehi et al. 2007).”
BackgroundHyperspectral Shadow Removal via Nonlinear Unmixing
Zhao, M., Chen, J., & Rahardja, S. (2020) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2020.2987353 · Cited by 20
“However, linear methods usually provide sufficiently accurate extraction results when the degree of nonlinearity in the data is not extremely high because most of these methods are able to extract the vertices of the distorted simplex of data clouds [9].”
BackgroundLearning Interpretable Deep Disentangled Neural Networks for Hyperspectral Unmixing
Borsoi, R. A., Erdogmus, D., & Imbiriba, T. (2023) · IEEE Transactions on Computational Imaging · doi:10.1109/tci.2023.3321985 · Cited by 19
“Another point is that the residual formulation of the mixing model, i.e., a linear mixing model augmented with a flexible nonlinear component, see (6), copes with different types of mixtures, such as, e.g., the multiple mixture pixel model [90] or BLMMs [4].”
BackgroundMethodInfluentialWang, L., Zhang, X., Zhang, J., Dong, H., Meng, H., & Jiao, L. (2024) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2024.3368286 · Cited by 18
A Global Spatial-Spectral Feature Fused Autoencoder for Nonlinear Hyperspectral Unmixing
Zhang, M., Yang, M., Xie, H., Yue, P., Zhang, W., Jiao, Q., Xu, L., & Tan, X. (2024) · Remote Sensing · doi:10.3390/rs16173149 · Cited by 17
MSSF-Net: A Multimodal Spectral–Spatial Feature Fusion Network for Hyperspectral Unmixing
Gao, W., Zhang, Y., Akoudad, Y., & Chen, J. (2025) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2025.3563647 · Cited by 20
“However, in many real-world scenarios, photons undergo multiple scattering events and complex reflections, resulting in significant nonlinear mixing effects [8].”
Yang, B., Wang, B., & Wu, Z. (2018) · Remote Sensing · doi:10.3390/rs10050801 · Cited by 19
Chen, X., Zhang, X., Ren, M., Zhou, B., Feng, Z., & Cheng, J. (2023) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2023.3323748 · Cited by 18
Sparse Hyperspectral Unmixing via Heuristic $\ell _p$ -Norm Approach
Salehani, Y. E., Gazor, S., & Cheriet, M. (2017) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2017.2775567 · Cited by 17
“S PECTRAL unmixing (SU) is a procedure to characterize the mixed pixels of hyperspectral images as a mixture of a number of materials [1]–[4].”
MethodNonlinear Extended Blind End-Member and Abundance Extraction for Hyperspectral Images
Campos-Delgado, D. U., Cruz-Guerrero, I. A., Mendoza-Chavarría, J. N., Mejia-Rodriguez, A. R., Ortega, S., Fabelo, H. A., & Callicó, G. M. (2022) · Signal Processing · doi:10.1016/j.sigpro.2022.108718 · Cited by 16
Nonlinear Multiview Analysis: Identifiability and Neural Network-Assisted Implementation
Lyu, Q., & Fu, X. (2020) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2020.2986351 · Cited by 16
“, in brain signal processing [44], [45] and hyperspectral imaging [46].”
BackgroundSeparation of Nonlinearly Mixed Sources Using End-to-End Deep Neural Networks
Zamani, H., Razavikia, S., Shahreza, H. O., & Amini, A. (2019) · IEEE Signal Processing Letters · doi:10.1109/lsp.2019.2957675 · Cited by 15
“Examples include hyperspectral imaging [9], [10], remote sensing [11] and removing show-through in scanned documents [12].”
BackgroundA Spectral-Spatial Attention Network for Hyperspectral Unmixing
Tao, X., Koirala, B., Rasti, B., Plaza, A., & Scheunders, P. (2025) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2025.3576479 · Cited by 18
“Traditional [54], [55], [56] and DL methods [57], [58], [59], [60] have been proposed.”
Perfect Recovery Conditions for Non-negative Sparse Modeling
Itoh, Y., Duarte, M. F., & Parente, M. C. (2016) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2016.2613067 · Cited by 18
“In the case of spectral unmixing, nonlinear mixing may come from nonlinear mixing of atoms [26], [27] or spectral mismatches between the spectra of the minerals in the library and those involved in the observation [28].”
BackgroundBand selection in RKHS for fast nonlinear unmixing of hyperspectral images
Imbiriba, T., Bermudez, J. C. M., Richard, C., & Tourneret, J. (2015) · European Signal Processing Conference (EUSIPCO) · doi:10.1109/eusipco.2015.7362664 · Cited by 15
“Several mixing models have been presented in the literature, depending on the linearity or nonlinearity of , type of mixture, scale, and other properties [3].”
Self-citationFusing Multiple Multiband Images
Arablouei, R. (2018) · Journal of Imaging · doi:10.3390/jimaging4100118 · Cited by 15
Advances in hyperspectral image unmixing: From algorithmic frameworks to practical applications
Ren, L., Han, Z., Gao, L., Zhang, T., Wu, R., & Zhang, H. (2025) · Information Geography · doi:10.1016/j.infgeo.2025.100035 · Cited by 22
Spectral mixture analysis of intimate mixtures for lithological mapping
Ahmad, A., & Nair, A. M. (2024) · ISPRS Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2023.12.014 · Cited by 15
Adaptive Multiorder Graph Regularized NMF With Dual Sparsity for Hyperspectral Unmixing
Chen, H., Liu, L., Xiu, X., & Liu, W. (2025) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2025.3602505 · Cited by 15
“Nowadays, LMM has been widely regarded as a reasonable first-order approximation of the physical measurement process due to its strong physical interpretability [21].”
Learning Nonlinear Mixtures: Identifiability and Algorithm
Yang, B., Fu, X., Sidiropoulos, N. D., & Huang, K. (2020) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2020.2989551 · Cited by 15
Unmixing of hyperspectral data for mineral detection using a hybrid method, Sar Chah-e Shur, Iran
Moghadam, H. J., Oskouei, M. M., & Nouri, T. (2020) · Arabian Journal of Geosciences · doi:10.1007/s12517-020-06070-7 · Cited by 14
Image patch analysis of sunspots and active regions: I. Intrinsic dimension and correlation analysis
Moon, K. R., Delouille, V., Li, J. J., Visscher, R. D., Watson, F., & Hero, A. O. (2016) · Journal of Space Weather and Space Climate · doi:10.1051/swsc/2015043 · Cited by 19
Self-citationDeep Hyperspectral and Multispectral Image Fusion With Inter-Image Variability
Wang, X., Borsoi, R. A., Richard, C., & Chen, J. (2023) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2023.3273118 · Cited by 19
“with the widely used linear mixing model (LMM) [9], [10], which represents each pixel of an HI as a linear combination of a small number of spectral signatures.”
MethodSelf-citationDetection of nonlinear mixtures using Gaussian processes: Application to hyperspectral imaging
Imbiriba, T., Bermudez, J. C. M., Tourneret, J., & Richard, C. (2014) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2014.6855148 · Cited by 13
“L’archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau recherche, publiés ou non, émanant des établissements d’enseignement et de recherche français ou étrangers, des laboratoires publics ou privés.”
BackgroundSelf-citationKernel-Based Nonlinear Anomaly Detection via Union Dictionary for Hyperspectral Images
Gao, Y., Gu, J., Cheng, T., & Wang, B. (2021) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2021.3093591 · Cited by 16
End-to-End Convolutional Autoencoder for Nonlinear Hyperspectral Unmixing
Dhaini, M., Bérar, M., Honeiné, P., & Exem, A. V. (2022) · Remote Sensing · doi:10.3390/rs14143341 · Cited by 13
Weighted Residual NMF With Spatial Regularization for Hyperspectral Unmixing
İnce, T., & Nicolas Dobigeon, B. (2022) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2022.3182042 · Cited by 13
Shadow-Aware Nonlinear Spectral Unmixing for Hyperspectral Imagery
Zhang, G., Scheunders, P., Cerra, D., & Müller, R. (2022) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2022.3188896 · Cited by 15
Li, M., Yang, B., & Wang, B. (2022) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2022.3223434 · Cited by 14
“Therefore, the nonlinear mixing models (NMMs) and corresponding methods are essential to tackle the unmixing problems properly in real scenarios [5].”
MethodLiang, Y., Zheng, H., Yang, G., Du, Q., & Su, H. (2023) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2023.3298491 · Cited by 13
“Compared to NLSMM, LSMM has computational tractability and flexibility [14].”
BackgroundBorsoi, R. A., Imbiriba, T., & Bermudez, J. C. M. (2019) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2019.8683155 · Cited by 13
“Many parametric models have been proposed to describe the interaction between light and the target surface [1,2].”
BackgroundSelf-citationProgrammable Spectrometry: Per-pixel Material Classification using Learned Spectral Filters
Saragadam, V., & Sankaranarayanan, A. C. (2020) · IEEE International Conference on Computational Photography (ICCP) · doi:10.1109/iccp48838.2020.9105281 · Cited by 13
“Generative techniques rely on decomposing the HSI as a linear combination of basic materials that are called end-members [9].”
MethodCui, Y., Sun, H., Wang, G., Li, C., & Xu, X. (2019) · Remote Sensing · doi:10.3390/rs11243038 · Cited by 13
“[39] conducted a review of spectral unmixing models and algorithms based on hyperspectral imagery.”
BackgroundLiu, J., Luo, B., Douté, S., & Chanussot, J. (2018) · Remote Sensing · doi:10.3390/rs10050737 · Cited by 15
“Non-linear effects due to more complex mixtures may exist in a hyperspectral image because of intimate assemblages of compounds at the surface and multiple scattering between reflecting topographical facets, or between the latter and the atmosphere [26,27].”
BackgroundLi, C., Cai, R., & Yu, J. (2023) · Remote Sensing · doi:10.3390/rs15020451 · Cited by 13
Hyperspectral Local Intrinsic Dimensionality
Drumetz, L., Veganzones, M. A., Marrero, R., Tochon, G., Mura, M. D., Licciardi, G., Jutten, C., & Chanussot, J. (2016) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2016.2536480 · Cited by 12
“Many approaches exist in the literature to perform spectral unmixing [10], [19], [32], and almost”
Rational Optimization for Nonlinear Reconstruction With Approximate $\ell _0$ Penalization
Castella, M., Pesquet, J.-C., & Marmin, A. (2019) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2018.2890065 · Cited by 12
Metadata
- Authors
- Dobigeon, N., Tourneret, J.-Y., Richard, C., Bermudez, J. C. M., McLaughlin, S., & Hero, A. O.
- Affiliations
- Institut National Polytechnique de Toulouse (FR)
- Université de Toulouse (FR)
- Universidade Federal de Santa Catarina (BR)
- Heriot-Watt University (GB)
- University of Michigan (US)
- Venue
- IEEE Signal Processing Magazine
- Published
- 2014-01
- Volume
- 31
- Issue
- 1
- Pages
- 82-94
- ISSN
- 1053-5888 (ISSN-L)
- OpenAlex
- W2005818237
- Cited by
- 420
- References
- 57
- Citations by year
- 2026: 11 · 2025: 23 · 2024: 32 · 2023: 38 · 2022: 36 · 2021: 34 · 2020: 45 · 2019: 31 · 2018: 36 · 2017: 39 · 2016: 45 · 2015: 29 · 2014: 20
- FWCI
- 61.72
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- IEEE Signal Processing Magazine (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- HAL (submittedVersion, other-oa)
- arXiv (Cornell University)
- Funders
- Agence Nationale de la Recherche (ANR-12-BS03-0003)
- Engineering and Physical Sciences Research Council (EP/J015180/1)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Remote-Sensing Image Classification
- Physical Sciences › Chemistry › Analytical Chemistry › Spectroscopy and Chemometric Analyses
- Physical Sciences › Earth and Planetary Sciences › Geochemistry and Petrology › Geochemistry and Geologic Mapping
- Keywords
- nonlinear unmixing, hyperspectral unmixing, linear mixing model, multiple scattering, end-member mixing model, endmember extraction
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.