Sparse Linear Spectral Unmixing of Hyperspectral Images Using Expectation-Propagation

This paper presents a novel Bayesian approach for hyperspectral image unmixing. The observed pixels are modeled by a linear combination of material signatures weighted by their corresponding abundances. A spike-and-slab abundance prior is adopted to promote sparse mixtures and an Ising prior model is used to capture spatial correlation of the mixture support across pixels. We approximate the posterior distribution of the abundances using the expectation-propagation (EP) method. We show that it can significantly reduce the computational complexity of the unmixing stage and meanwhile provide uncertainty measures, compared to expensive Monte Carlo strategies traditionally considered for uncertainty quantification. Moreover, many variational parameters within each EP factor can be updated in a parallel manner, which enables mapping of efficient algorithmic architectures based on graphics processing units (GPU). Under the same approximate Bayesian framework, we then extend the proposed algorithm to semi-supervised unmixing, whereby the abundances are viewed as latent variables and the expectation-maximization (EM) algorithm is used to refine the endmember matrix. Experimental results on synthetic data and real hyperspectral data illustrate the benefits of the proposed framework over state-of-art linear unmixing methods.

[1]  Daniel Hernández-Lobato,et al.  Expectation Propagation for microarray data classification , 2010, Pattern Recognit. Lett..

[2]  Mervyn Parakrama B. Ekanayake,et al.  Graph-Based Blind Hyperspectral Unmixing via Nonnegative Matrix Factorization , 2020, IEEE Transactions on Geoscience and Remote Sensing.

[3]  Johannes R. Sveinsson,et al.  Hyperspectral Unmixing With $l_{q}$ Regularization , 2014, IEEE Transactions on Geoscience and Remote Sensing.

[4]  José M. Bioucas-Dias,et al.  Vertex component analysis: a fast algorithm to unmix hyperspectral data , 2005, IEEE Transactions on Geoscience and Remote Sensing.

[5]  Chein-I Chang,et al.  Fully constrained least squares linear spectral mixture analysis method for material quantification in hyperspectral imagery , 2001, IEEE Trans. Geosci. Remote. Sens..

[6]  Masahiro Okuda,et al.  Joint Local Abundance Sparse Unmixing for Hyperspectral Images , 2017, Remote. Sens..

[7]  Tom Minka,et al.  Expectation Propagation for approximate Bayesian inference , 2001, UAI.

[8]  Liangpei Zhang,et al.  Spatial Group Sparsity Regularized Nonnegative Matrix Factorization for Hyperspectral Unmixing , 2017, IEEE Transactions on Geoscience and Remote Sensing.

[9]  Ying Wang,et al.  Spectral–Spatial-Weighted Multiview Collaborative Sparse Unmixing for Hyperspectral Images , 2020, IEEE Transactions on Geoscience and Remote Sensing.

[10]  Alfonso Fernández-Manso,et al.  Spectral unmixing , 2012 .

[11]  Konstantinos Koutroumbas,et al.  A Novel Hierarchical Bayesian Approach for Sparse Semisupervised Hyperspectral Unmixing , 2012, IEEE Transactions on Signal Processing.

[12]  Antonio J. Plaza,et al.  Collaborative Sparse Regression for Hyperspectral Unmixing , 2014, IEEE Transactions on Geoscience and Remote Sensing.

[13]  Mike E. Davies,et al.  Expectation-propagation Algorithms for Linear Regression with Poisson Noise: Application to Photon-limited Spectral Unmixing , 2019, ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[14]  José M. Bioucas-Dias,et al.  Collaborative sparse regression using spatially correlated supports - Application to hyperspectral unmixing , 2014, IEEE Transactions on Image Processing.

[15]  José M. Bioucas-Dias,et al.  Hyperspectral Unmixing Based on Mixtures of Dirichlet Components , 2012, IEEE Transactions on Geoscience and Remote Sensing.

[16]  Jean-Yves Tourneret,et al.  Toward a Sparse Bayesian Markov Random Field Approach to Hyperspectral Unmixing and Classification , 2017, IEEE Transactions on Image Processing.

[17]  Pol Coppin,et al.  Endmember variability in Spectral Mixture Analysis: A review , 2011 .

[18]  José M. Bioucas-Dias,et al.  Hyperspectral Subspace Identification , 2008, IEEE Transactions on Geoscience and Remote Sensing.

[19]  Philip Schniter,et al.  Hyperspectral Unmixing Via Turbo Bilinear Approximate Message Passing , 2015, IEEE Transactions on Computational Imaging.

[20]  Antonio J. Plaza,et al.  Hyperspectral Unmixing Overview: Geometrical, Statistical, and Sparse Regression-Based Approaches , 2012, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[21]  Antonio J. Plaza,et al.  A New Minimum-Volume Enclosing Algorithm for Endmember Identification and Abundance Estimation in Hyperspectral Data , 2012, IEEE Transactions on Geoscience and Remote Sensing.

[22]  Mario Winter,et al.  N-FINDR: an algorithm for fast autonomous spectral end-member determination in hyperspectral data , 1999, Optics & Photonics.

[23]  D. Rubin,et al.  Maximum likelihood from incomplete data via the EM - algorithm plus discussions on the paper , 1977 .

[24]  Susanto Rahardja,et al.  Superpixel construction for hyperspectral unmixing , 2018, 2018 26th European Signal Processing Conference (EUSIPCO).

[25]  J. Boardman Automating spectral unmixing of AVIRIS data using convex geometry concepts , 1993 .

[26]  Ole Winther,et al.  Bayesian Inference for Spatio-temporal Spike-and-Slab Priors , 2015, J. Mach. Learn. Res..

[27]  Alfred O. Hero,et al.  Hyperspectral Image Unmixing Using a Multiresolution Sticky HDP , 2012, IEEE Transactions on Signal Processing.

[28]  Liangpei Zhang,et al.  Total Variation Regularized Reweighted Sparse Nonnegative Matrix Factorization for Hyperspectral Unmixing , 2017, IEEE Transactions on Geoscience and Remote Sensing.

[29]  Sen Jia,et al.  Spectral and Spatial Complexity-Based Hyperspectral Unmixing , 2007, IEEE Transactions on Geoscience and Remote Sensing.

[30]  Jun Li,et al.  Spectral–Spatial Weighted Sparse Regression for Hyperspectral Image Unmixing , 2018, IEEE Transactions on Geoscience and Remote Sensing.

[31]  C. L. Philip Chen,et al.  Reweighted Sparse Regression for Hyperspectral Unmixing , 2016, IEEE Transactions on Geoscience and Remote Sensing.

[32]  Jon Atli Benediktsson,et al.  Adaptive Markov Random Fields for Joint Unmixing and Segmentation of Hyperspectral Images , 2013, IEEE Transactions on Image Processing.

[33]  Daniel Hernández-Lobato,et al.  Expectation propagation in linear regression models with spike-and-slab priors , 2015, Machine Learning.

[34]  Mohammad Hossein Kahaei,et al.  New Bayesian approach for semi-supervised hyperspectral unmixing in linear mixing models , 2017, 2017 Iranian Conference on Electrical Engineering (ICEE).

[35]  Mireille Guillaume,et al.  Minimum Dispersion Constrained Nonnegative Matrix Factorization to Unmix Hyperspectral Data , 2010, IEEE Transactions on Geoscience and Remote Sensing.

[36]  Radford M. Neal Pattern Recognition and Machine Learning , 2007, Technometrics.

[37]  Min Zhou,et al.  Collaborative Sparse Hyperspectral Unmixing Using $l_{0}$ Norm , 2018, IEEE Transactions on Geoscience and Remote Sensing.

[38]  Alfredo Braunstein,et al.  Compressed sensing reconstruction using expectation propagation , 2019, Journal of Physics A: Mathematical and Theoretical.

[39]  Antonio J. Plaza,et al.  Sparse Unmixing of Hyperspectral Data , 2011, IEEE Transactions on Geoscience and Remote Sensing.

[40]  Jie Chen,et al.  A Plug-and-Play Priors Framework for Hyperspectral Unmixing , 2020, IEEE Transactions on Geoscience and Remote Sensing.

[41]  Rui Wang,et al.  Hyperspectral Unmixing Based on Sparsity-Constrained Nonnegative Matrix Factorization with Adaptive Total Variation , 2019, IGARSS 2019 - 2019 IEEE International Geoscience and Remote Sensing Symposium.

[42]  Mário A. T. Figueiredo,et al.  Regularization Parameter Selection in Minimum Volume Hyperspectral Unmixing , 2019, IEEE Transactions on Geoscience and Remote Sensing.

[43]  Jie Chen,et al.  Hyperspectral Unmixing Via Plug-And-Play Priors , 2020, 2020 IEEE International Conference on Image Processing (ICIP).

[44]  Aleksandra Pizurica,et al.  Hyperspectral Unmixing Using Double Reweighted Sparse Regression and Total Variation , 2017, IEEE Geoscience and Remote Sensing Letters.

[45]  Hairong Qi,et al.  Endmember Extraction From Highly Mixed Data Using Minimum Volume Constrained Nonnegative Matrix Factorization , 2007, IEEE Transactions on Geoscience and Remote Sensing.

[46]  Antonio J. Plaza,et al.  Total Variation Spatial Regularization for Sparse Hyperspectral Unmixing , 2012, IEEE Transactions on Geoscience and Remote Sensing.

[47]  Feiyun Zhu,et al.  Hyperspectral Unmixing: Ground Truth Labeling, Datasets, Benchmark Performances and Survey , 2017, 1708.05125.

[48]  José M. Bioucas-Dias,et al.  Alternating direction algorithms for constrained sparse regression: Application to hyperspectral unmixing , 2010, 2010 2nd Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing.