A Practical Approach for Hyperspectral Unmixing Using Deep Learning

Vijayashekhar, S S; Deshpande, Vijay S.; Bhatt, Jignesh S.

doi:10.1109/lgrs.2021.3127075

Cited by 23 publications

(12 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A 5 × 5 low-pass filter is used. Then Gaussian noise with zero mean at six different SNR values, i.e., SNR = [15,20,25,30,35,40] is added to the generated data. For the different values of the parameter β ¼ ½0.1; 0.5; 1 the proposed algorithm is implemented.…”

Section: Synthetic Datamentioning

confidence: 99%

“…A general deep learning framework for self-supervised hyperspectral unmixing called endmember-guided unmixing network (EGU-Net) is introduced by Hong et al 24 EGU-Net uses a two-stream Siamese network to learn a network from pure or nearly-pure endmembers for the purpose of correcting the weights of another network by adding SU constraints like abundance sum to one and positivity. Another deep learning method for hyperspectral unmixing is proposed by Deshpande et al 25 based on two-stage fully connected self-supervised network. In this method, the main goal is reconstructing the hyperspectral data using a jointly optimized network based on two-stage loss function.…”

Section: Introductionmentioning

confidence: 99%

“…EGU-Net uses a two-stream Siamese network to learn a network from pure or nearly-pure endmembers for the purpose of correcting the weights of another network by adding SU constraints like abundance sum to one and positivity. Another deep learning method for hyperspectral unmixing is proposed by Deshpande et al 25 . based on two-stage fully connected self-supervised network.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Spectral unmixing of hyperspectral images based on block sparse structure

Azarang

Rajabi

Zayyani

et al. 2023

J. Appl. Rem. Sens.

View full text Add to dashboard Cite

Spectral unmixing (SU) of hyperspectral images (HSIs) is one of the important areas in remote sensing (RS) that needs to be carefully addressed in different RS applications. Despite the high spectral resolution of the hyperspectral data, the relatively low spatial resolution of the sensors may lead to mixture of different pure materials within the image pixels. In this case, the spectrum of a given pixel recorded by the sensor can be a combination of multiple spectra each belonging to a unique material in that pixel. SU is then used as a technique to extract the spectral characteristics of the different materials within the mixed pixels and to recover the spectrum of each pure spectral signature, called endmember. Block-sparsity exists in hyperspectral images as a result of spectral similarity between neighboring pixels. In block-sparse signals, the nonzero samples occur in clusters and the pattern of the clusters is often supposed to be unavailable as prior information. This paper presents an innovative SU approach for HSIs based on block-sparse structure. Hyperspectral unmixing problem is solved using pattern coupled sparse Bayesian learning strategy. To evaluate the performance of the proposed SU algorithm, it is tested on both synthetic and real hyperspectral data and the quantitative results are compared to those of other state-of-the-art methods in terms of abundance angle distance and mean squared error. The achieved results show the superiority of the proposed algorithm over the other competing methods by a significant margin.

show abstract

Section: Synthetic Datamentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Spectral unmixing of hyperspectral images based on block sparse structure

Azarang

Rajabi

Zayyani

et al. 2023

J. Appl. Rem. Sens.

View full text Add to dashboard Cite

show abstract

“…A cycle-consistency loss was used in [78] to guide the reconstruction of two cascaded AECs in HU. Self-supervised learning has also been integrated into the design of AEC strategies for HU [79]. Moreover, non-AEC approaches were also proposed for HU, such as parametrizations of the abundances using untrained deep prior models [80] or designing NNs for unmixing by unfolding optimization algorithms such as the ADMM [81] or sparse regression methods [12].…”

Section: Related Workmentioning

confidence: 99%

Learning Interpretable Deep Disentangled Neural Networks for Hyperspectral Unmixing

Borsoi,

Erdoğmuş,

Imbiriba

2023

IEEE Trans. Comput. Imaging

View full text Add to dashboard Cite

Although considerable effort has been dedicated to improving the solution to the hyperspectral unmixing problem, non-idealities such as complex radiation scattering and endmember variability negatively impact the performance of most existing algorithms and can be very challenging to address. Recently, deep learning-based frameworks have been explored for hyperspectral umixing due to their flexibility and powerful representation capabilities. However, such techniques either do not address the non-idealities of the unmixing problem, or rely on black-box models which are not interpretable. In this paper, we propose a new interpretable deep learning method for hyperspectral unmixing that accounts for nonlinearity and endmember variability. The proposed method leverages a probabilistic variational deeplearning framework, where disentanglement learning is employed to properly separate the abundances and endmembers. The model is learned end-to-end using stochastic backpropagation, and trained using a self-supervised strategy which leverages benefits from semi-supervised learning techniques. Furthermore, the model is carefully designed to provide a high degree of interpretability. This includes modeling the abundances as a Dirichlet distribution, the endmembers using low-dimensional deep latent variable representations, and using two-stream neural networks composed of additive piecewise-linear/nonlinear components. Experimental results on synthetic and real datasets illustrate the performance of the proposed method compared to state-of-the-art algorithms.

show abstract

“…Deep learning algorithms have shown promising results in enhancing the classification of oxygenated and deoxygenated hemoglobin in measurements with unstable sources and low signal-to-noise ratio [27] , [28] . Furthermore, several implementations have proven the efficiency of deep learning for the classification of spectral signals, which can significantly improve these processes even with minimal training samples, as long as these can accurately represent the main features of the spectra [29] , [30] , [31] .…”

Section: Introductionmentioning

confidence: 99%