Hyperspectral Unmixing Research Articles

Hyperspectral unmixing with LiDAR-Based total variation regularized non-negative tensor factorization

Hyperspectral unmixing with LiDAR-Based total variation regularized non-negative tensor factorization

Toward Convergence: A Gradient-Based Multiobjective Method With Greedy Hash for Hyperspectral Unmixing

Multiobjective optimization aims at addressing the conflicting objectives, which has been introduced to improve the performance of sparse hyperspectral unmixing. Recently proposed multiobjective unmixing methods usually employ evolutionary algorithms to improve the unmixing accuracy. However, evolutionary algorithms may suffer the challenge of convergence, in which case the reasonability of the solutions is hard to guarantee. To solve the problem of convergence, in this paper, we present a new gradient-based multiobjective unmixing method, which explores the optimization direction in a theoretically reliable manner. Furthermore, considering the mathematical model of hyperspectral sparse unmixing where sparsity error objective of selected endmembers is discrete, we develop a greedy hash based coding approach which is able to well describe the discrete constraints imposed on endmembers. The major components of the proposed method are a search approach and an update approach. In the search approach, we construct the pareto descent direction via a gradient-based strategy, which contributes to converging to an optimal continuous solution by searching along this direction. In the update approach, we update discrete binary endmember via hash coding under the guidance of greedy principle, which allows our method to handle the problem of discrete objective. The major contribution of the proposed method is designing a new framework that can get the optimal discrete endmembers in a convergent way. Moreover, we provide the theoretical analysis and proof for the convergence. Synthetic and real-world experiments have indicated the advantages of our algorithm when compared with evolutionary multiobjective unmixing methods.

Dynamical Hyperspectral Unmixing with Variational Recurrent Neural Networks.

Multitemporal hyperspectral unmixing (MTHU) is a fundamental tool in the analysis of hyperspectral image sequences. It reveals the dynamical evolution of the materials (endmembers) and of their proportions (abundances) in a given scene. However, adequately accounting for the spatial and temporal variability of the endmembers in MTHU is challenging, and has not been fully addressed so far in unsupervised frameworks. In this work, we propose an unsupervised MTHU algorithm based on variational recurrent neural networks. First, a stochastic model is proposed to represent both the dynamical evolution of the endmembers and their abundances, as well as the mixing process. Moreover, a new model based on a low-dimensional parametrization is used to represent spatial and temporal endmember variability, significantly reducing the amount of variables to be estimated. We propose to formulate MTHU as a Bayesian inference problem. However, the solution to this problem does not have an analytical solution due to the nonlinearity and non-Gaussianity of the model. Thus, we propose a solution based on deep variational inference, in which the posterior distribution of the estimated abundances and endmembers is represented by using a combination of recurrent neural networks and a physically motivated model. The parameters of the model are learned using stochastic backpropagation. Experimental results show that the proposed method outperforms state of the art MTHU algorithms.

Endmember Bundle Extraction Based on Improved Multiobjective Particle Swarm Optimization

Endmember extraction (EE) is a key task for hyperspectral image unmixing. The majority of EE algorithms extract only one pure spectrum for each class of material, which may lead to a large unmixing error in cases of spectral variability. Endmember bundle extraction (EBE), which identifies a set of endmembers representing the spectral variability within each class, has been developed to solve the spectral variability problem. To date, only a small number of EBE methods have been developed; moreover, these approaches mainly employ traditional convex-geometry-based EE methods to extract endmember bundles from subset data, which may result in the loss of some endmembers and an incomplete endmember bundle set. This paper proposes an improved multi-objective particle swarm optimization method for the identification of multiple endmember bundles, named IMPSO-EBE. The proposed approach follows the framework of the spatial-spectral EBE (SSEBE) method, which extracts endmember candidates first and then applies post-processing to remove redundant endmembers. However, unlike the SSEBE method, which uses the traditional pixel purity index (PPI) method to obtain candidate endmembers from single feature space, IMPSO-EBE proposes to cooperate across multiple dataspaces to obtain candidate endmembers based on multi-objective particle swarm optimization, making it able to extract candidate endmembers that cannot be identified in single feature space. We compare the performance of the proposed method with that of the single dataspace-based endmember bundle extraction methods using two real hyperspectral datasets. Results show that the endmember bundles identified by the proposed method are more complete than those of the comparison method.

Hyperspectral Sparse Unmixing via Nonconvex Shrinkage Penalties

Hyperspectral sparse unmixing aims at finding the optimal subset of spectral signatures in the given spectral library and estimating their proportions in each pixel. Recently, simultaneously sparse and low-rank representations (SSLRRs) have been widely used in the hyperspectral sparse unmixing task. This article developed a new unified framework to approximate the SSLRR-based unmixing model. The heart of the proposed framework is to design the new nonconvex penalties for efficient minimization by the means of two families of thresholding mappings, including the firm thresholding mapping and generalized shrinkage mapping. Both mappings can be regarded as generalizations of both soft thresholding and hard thresholding. Unlike previous approaches with explicit penalties, the proposed framework does not require explicit forms of penalties but only relevant thresholding mappings. Furthermore, an alternating direction method of multipliers (ADMM) was designed to solve the resulting optimization problem. Experiments conducted on the synthetic data and real data demonstrate the superiority of the proposed framework in improving the unmixing performance with respect to state-of-the-art methods.

First-Order Graph Trend Filtering for Sparse Hyperspectral Unmixing

First-Order Graph Trend Filtering for Sparse Hyperspectral Unmixing

Extended-Aggregated Strategy for Hyperspectral Unmixing Based on Dilated Convolution

Extended-Aggregated Strategy for Hyperspectral Unmixing Based on Dilated Convolution

Graph l₁-Laplacians Regularized GMM for Hyperspectral Unmixing

Graph <i>l</i>₁-Laplacians Regularized GMM for Hyperspectral Unmixing

A Coarse-to-Fine Scheme for Unsupervised Nonlinear Hyperspectral Unmixing Based on an Extended Multilinear Mixing Model

A Coarse-to-Fine Scheme for Unsupervised Nonlinear Hyperspectral Unmixing Based on an Extended Multilinear Mixing Model

Hyperspectral unmixing based on adversarial autoencoder network

Hyperspectral unmixing based on adversarial autoencoder network

Unrolling Nonnegative Matrix Factorization With Group Sparsity for Blind Hyperspectral Unmixing

Unrolling Nonnegative Matrix Factorization With Group Sparsity for Blind Hyperspectral Unmixing

Weighted Sparse Cauchy Nonnegative Matrix Factorization Hyperspectral Unmixing Based on Spatial-Spectral Constraints

Weighted Sparse Cauchy Nonnegative Matrix Factorization Hyperspectral Unmixing Based on Spatial-Spectral Constraints

MultiHU-TD: Multifeature Hyperspectral Unmixing Based on Tensor Decomposition

MultiHU-TD: Multifeature Hyperspectral Unmixing Based on Tensor Decomposition

An Improved Hyperspectral Unmixing Approach Based on a Spatial–Spectral Adaptive Nonlinear Unmixing Network

An Improved Hyperspectral Unmixing Approach Based on a Spatial–Spectral Adaptive Nonlinear Unmixing Network

Graph-Based Active Learning for Nearly Blind Hyperspectral Unmixing

Graph-Based Active Learning for Nearly Blind Hyperspectral Unmixing

Spatial-Spectral Attention Bilateral Network for Hyperspectral Unmixing

Spatial-Spectral Attention Bilateral Network for Hyperspectral Unmixing

Global centralised and structured discriminative non‐negative matrix factorisation for hyperspectral unmixing

AbstractAdvances have been achieved in hyperspectral unmixing using the existing manifold Non‐negative Matrix Factorisation methods, although most of these methods only exploit the preliminary structural information, that is, the nearest neighbour graph. Consequently, the performance of these methods would be degraded when considering only the geometrical structure due to the diverse distribution of the hyperspectral data, that is, the close pixels could belong to different categories or the distant points could be sampled from the same classes. In this context, the present study worked from the perspective of both global and local data relationships to develop and propose a novel approach—the Global centralised and Structured discriminative Non‐negative Matrix Factorisation (GSNMF)—to achieve a further effective representation of hyperspectral unmixing. GSNMF involved maintaining the global centralised clustering and the local structured discriminative regularisation, based on which it could perfectly mine the structure information and drive a discriminative representation of the data. Experiments comparing the application of GSNMF and the state‐of‐the‐art methods to synthetic data demonstrated the superiority of GSNMF. In addition, the consistency of the fractional abundances obtained using GSNMF with the real distributions of spectral data was evaluated on two real‐world datasets.

Linear Spatial Misregistration Detection and Correction Based on Spectral Unmixing for FAHI Hyperspectral Imagery.

In push-broom hyperspectral imaging systems, the sensor rotation to the optical plane leads to linear spatial misregistration (LSM) in hyperspectral images (HSIs). To compensate for hardware defects through software, this paper develops four methods to detect LSM in HSIs. Different from traditional methods for grayscale images, the method of fitting the sum of abundance (FSAM) and the method of searching for equal abundance (SEAM) are achieved by hyperspectral unmixing for a selected rectangular transition areas containing an edge, which makes good use of spatial and spectral information. The method based on line detection for band-interleaved-by-line (BIL) images (LDBM) and the method based on the Fourier transform of BIL images (FTBM) aim to characterize the slope of line structure in BIL images and get rid of the dependence on scene and wavelength. A full strategy is detailed from aspects of data selection, LSM detection, and image correction. The full spectrum airborne hyperspectral imager (FAHI) is China's new generation push-broom scanner. The HSIs obtained by FAHI are tested and analyzed. Experiments on simulation data compare the four proposed methods with traditional methods and prove that FSAM outperforms other methods in terms of accuracy and stability. In experiments on real data, the application of the full strategy on FAHI verifies its effectiveness. This work not only provides reference for other push-broom imagers with similar problems, but also helps to reduce the requirement for hardware calibration.

An Efficient Attention-Based Convolutional Neural Network That Reduces the Effects of Spectral Variability for Hyperspectral Unmixing

The purpose of hyperspectral unmixing (HU) is to obtain the spectral features of materials (endmembers) and their proportion (abundance) in a hyperspectral image (HSI). Due to the existence of spectral variabilities (SVs), it is difficult to obtain accurate spectral features. At the same time, the performance of unmixing is not only affected by SVs but also depends on the effective spectral and spatial information. To solve these problems, this study proposed an efficient attention-based convolutional neural network (EACNN) and an efficient convolution block attention module (ECBAM). The EACNN is a two-stream network, which is learned from nearly pure endmembers through an additional network, and the aggregated spectral and spatial information can be obtained effectively with the help of the ECBAM, which can reduce the influence of SVs and improve the performance. The unmixing network helps the whole network to pay attention to meaningful feature information by using efficient channel attention (ECA) and guides the unmixing process by sharing parameters. Experimental results on three HSI datasets showed that the method proposed in this study outperformed other unmixing methods.

Estimation of sub-endmembers using spatial-spectral approach for hyperspectral images

In Blind Hyperspectral Unmixing, the accuracy of the estimated number of endmembers affects the succeeding steps of extraction of endmember signatures and acquiring their fractional abundances. The characteristics of endmember signature depend on the nature of the material on the ground and share similar characteristics for variants of the same material. In this paper, we introduce a new concept of sub-endmembers to identify similar materials that are variants of a global endmember. Identifying the sub-endmembers will provide a meaningful interpretation of the endmember variability along with increased unmixing accuracy. This paper proposes a new algorithm exploiting both the spatial and spectral information present in hyperspectral data. The hyperspectral data are segmented into homogenous regions (superpixels) based on the Simple Linear Iterative Clustering (SLIC) algorithm, and the mean spectral of each region is accounted for in finding the global endmembers. The difference of eigenvalues-based thresholding method is used to find the number of global and sub-endmembers. The method has been tested on synthetic and real hyperspectral data and has successfully estimated the number of global endmembers as well as sub-endmembers. The method is also compared with other state-of-the-art methods, and better performances are obtained at a reasonably lower computational complexity.