Deep Generative Models for Library Augmentation in Multiple Endmember Spectral Mixture Analysis

@article{Borsoi2021DeepGM,
  title={Deep Generative Models for Library Augmentation in Multiple Endmember Spectral Mixture Analysis},
  author={Ricardo Augusto Borsoi and Tales Imbiriba and Jos{\'e} Carlos Moreira Bermudez and C{\'e}dric Richard},
  journal={IEEE Geoscience and Remote Sensing Letters},
  year={2021},
  volume={18},
  pages={1831-1835}
}
Multiple endmember spectral mixture analysis (MESMA) is one of the leading approaches to perform spectral unmixing (SU) considering the variability of the endmembers (EMs). It represents each EM in the image using libraries of spectral signatures acquired a priori. However, existing spectral libraries are often small and unable to properly capture the variability of each EM in practical scenes, which compromises the performance of MESMA. In this letter, we propose a library augmentation… Expand
Model-Based Deep Autoencoder Networks for Nonlinear Hyperspectral Unmixing
TLDR
A model-based AEC for nonlinear HU is proposed by considering the mixing model a nonlinear fluctuation over a linear mixture and it is shown that this restriction naturally imposes a particular structure to both the encoder and to the decoder networks. Expand
A Fast Multiscale Spatial Regularization for Sparse Hyperspectral Unmixing
TLDR
Simulation results indicate that the proposed method outperforms the state-of-the-art total variation-based algorithms with a computation time comparable to that of their unregularized counterparts. Expand
A Novel Spectral Matching Approach for Pigment: Spectral Subsection Identification Considering Ion Absorption Characteristics
TLDR
The proposed spectral matching method can correctly identify the main pigments or components contained in the mixed area, which is better than the traditional method and more convenient than the unmixing method, except for some limitations in detecting white and black pigments. Expand
Fast Unmixing and Change Detection in Multitemporal Hyperspectral Data
TLDR
This work proposes an efficient multitemporal SU method that exploits the high temporal correlation between the abundances to provide more accurate results at a lower computational complexity and proposes a strategy to detect and address abrupt abundance variations in time. Expand
Spectral Variability Augmented Sparse Unmixing of Hyperspectral Images
  • Ge Zhang, Shaohui Mei, Mingyang Ma, Yan Feng, Qian Du
  • Engineering, Computer Science
  • 2021
TLDR
Experimental results over both synthetic and real-world data sets demonstrate that the augmented decomposition by spectral variability significantly improves the unmixing performance than the decomposition only by spectral library, as well as compared to state-of-the-art algorithms. Expand
A Blind Multiscale Spatial Regularization Framework for Kernel-Based Spectral Unmixing
TLDR
A theory-based statistical framework is employed to devise a consistent strategy to estimate all required parameters, including both the regularization parameters of the algorithm and the number of superpixels that result from a multiscale transformation, resulting in a truly blind unmixing method. Expand
Kalman Filtering and Expectation Maximization for Multitemporal Spectral Unmixing
TLDR
This work proposes a novel spectral unmixing (SU) strategy using physically motivated parametric endmember representations to account for temporal spectral variability by representing the multitemporal mixing process using a state-space formulation. Expand
Spectral Variability in�Hyperspectral Data�Unmixing: A Comprehensive Review
TLDR
A comprehensive literature review contextualizing both classic and recent approaches to solve the problem of spectral variability in spectral unmixing, and proposes a new taxonomy that organizes existing work according to a practitioner's point of view based on the necessary amount of supervision and on the computational cost they require. Expand

References

SHOWING 1-10 OF 27 REFERENCES
Deep Generative Endmember Modeling: An Application to Unsupervised Spectral Unmixing
TLDR
Simulations using both synthetic and real data indicate that the proposed EM model can outperform the competing state-of-the-art algorithms. Expand
Low-Rank Tensor Modeling for Hyperspectral Unmixing Accounting for Spectral Variability
TLDR
A more flexible approach, called unmixing with low-rank tensor regularization algorithm accounting for EM variability (ULTRA-V), that imposes low- rank structures through regularizations whose strictness is controlled by scalar parameters is proposed. Expand
Hyperspectral Unmixing With Endmember Variability via Alternating Angle Minimization
TLDR
This paper presents a new algorithm for dealing with endmember variability in spectral unmixing, analogous to the popular multiple endmember spectral mixture analysis technique but has a much more favorable computational complexity while producing similar results. Expand
Total Variation Spatial Regularization for Sparse Hyperspectral Unmixing
TLDR
The total variation (TV) regularization to the classical sparse regression formulation is included, thus exploiting the spatial-contextual information present in the hyperspectral images and developing a new algorithm called sparse unmixing via variable splitting augmented Lagrangian and TV. Expand
A Review of Nonlinear Hyperspectral Unmixing Methods
TLDR
This paper aims to give an historical overview of the majority of nonlinear mixing models and nonlinear unmixing methods, and to explain some of the more popular techniques in detail. Expand
Generalized Linear Mixing Model Accounting for Endmember Variability
TLDR
Simulations with real and synthetic data show that the unmixing process can benefit from the extra flexibility introduced by the GLMM. Expand
A Fast Multiscale Spatial Regularization for Sparse Hyperspectral Unmixing
TLDR
Simulation results indicate that the proposed method outperforms the state-of-the-art total variation-based algorithms with a computation time comparable to that of their unregularized counterparts. Expand
Band Selection for Nonlinear Unmixing of Hyperspectral Images as a Maximal Clique Problem
TLDR
The proposed BS approach is equivalent to solving a maximum clique problem, i.e., searching for the biggest complete subgraph in a graph, and a strategy for selecting the coherence threshold and the Gaussian kernel bandwidth using coherence bounds for linearly independent bases is devised. Expand
Endmember variability in Spectral Mixture Analysis: A review
TLDR
This review paper summarizes the available methods and results of endmember variability reduction in Spectral Mixture Analysis (SMA), drawing attention to the high complementarities between the different techniques and suggesting that an integrated approach is necessary to effectively address endmember heterogeneity issues in SMA. Expand
Data Augmentation Generative Adversarial Networks
TLDR
It is shown that a Data Augmentation Generative Adversarial Network (DAGAN) augments standard vanilla classifiers well and can enhance few-shot learning systems such as Matching Networks. Expand
...
1
2
3
...