A Multitemporal Linear Spectral Unmixing: An Iterative Approach Accounting For Abundance Variations

Bhatt, Jignesh S.; Joshi, Manjunath V.; Vijayashekhar, S S

doi:10.1109/whispers.2018.8747263

Cited by 8 publications

(6 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With the advent of the United States Geological Survey (USGS) spectral library [18], sparse regression-based methods have attracted more and more attention in the industry. The sparse regression method needs to collect a large number of pure material spectra in advance, and then use them as the endmember dictionary to replace the process of extracting endmembers from images.…”

Section: A Model-based Methodsmentioning

confidence: 99%

IVIU-Net: Implicit Variable Iterative Unrolling Network for Hyperspectral Sparse Unmixing

Shao

Liu

Xiao

2023

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

At present, an emerging technique called the algorithm unrolling approach has attracted wide attention, because it is capable of developing efficient and interpretable layers to eliminate the black-box nature of deep learning (DL). In this paper, inspired by the sparse unmixing model, we propose a model-driven DL approach, namely, an implicit variable iterative unrolling network (IVIU-Net). First of all, the unmixing performance and adaptive ability of the model are enhanced by introducing learnable parameters into the sparse unmixing algorithm. Then, a specific spatial convolution module is integrated into the network to promote the smoothness of the latent abundance map. Finally, a comprehensive loss function with three terms such as average spectral angle distance, HSIs reconstruction error, and spectral information divergence, is presented to train the IVIU-Net in an unsupervised way. Compared to the unmixing results of most existing data-driven DL algorithms, our network has significant advantages in two folds: 1) it is able to achieve better stability instead of relying heavily on the endmember initialization results; 2) it has better interpretability and robustness in the unmixing procedure. Experimental results on synthetic and real data show that the proposed network outperforms the state-of-the-art in terms of better convergence, faster unmixing speed as well as better accuracy.

show abstract

Section: A Model-based Methodsmentioning

confidence: 99%

IVIU-Net: Implicit Variable Iterative Unrolling Network for Hyperspectral Sparse Unmixing

Shao

Liu

Xiao

2023

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

show abstract

“…LMM consider that the spectral signature of a mixed pixel is a weighted sum of the endmember spectra and that the weights associated with the endmembers are given by their corresponding relative area abundance in the pixel. LMMbased methods have been widely developed in last decades including linear, geometrical, nonnegative matrix factorization, bayesian and fuzzy models among others [27], [3], [28], [29], [30], [31]. LMM typically assumes that the spectrum of each LULC class is characterized by a single fixed endmember.…”

Section: B Spectral Unmixingmentioning

confidence: 99%

Bidirectional Recurrent Imputation and Abundance Estimation of LULC Classes With MODIS Multispectral Time-Series and Geo-Topographic and Climatic Data

Rodríguez-Ortega,

Khaldi,

Alcaraz-Segura

et al. 2024

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

Remotely sensed data are dominated by mixed Land Use and Land Cover (LULC) types. Spectral unmixing (SU) is a key technique that disentangles mixed pixels into constituent LULC types and their abundance fractions. While existing studies on Deep Learning (DL) for SU typically focus on single time-step hyperspectral (HS) or multispectral (MS) data, our work pioneers SU using MODIS MS time series, addressing missing data with end-to-end DL models. Our approach enhances a Long-Short Term Memory (LSTM)-based model by incorporating geographic, topographic (geo-topographic), and climatic ancillary information. Notably, our method eliminates the need for explicit endmember extraction, instead learning the input-output relationship between mixed spectra and LULC abundances through supervised learning. Experimental results demonstrate that integrating spectral-temporal input data with geo-topographic and climatic information significantly improves the estimation of LULC abundances in mixed pixels. To facilitate this study, we curated a novel labeled dataset for Andalusia (Spain) with monthly MODIS multispectral time series at 460m resolution for 2013. Named Andalusia MultiSpectral MultiTemporal Unmixing (Andalusia-MSMTU), this dataset provides pixellevel annotations of LULC abundances along with ancillary information. The dataset 1 and code 2 are available to the public.

show abstract

“…The flatness indicates the lack of prior knowledge over the abundances other than its physical constraints. The Dirichlet distribution properties made it a popular choice of prior for Bayesian HU strategies [82]- [84], and has also been used in conjunction with a Markov transition model to represent the abundances multitemporal HU [85]. Endmember model: Several models have been proposed to account for EM variability by representing the spectral signatures of the materials in each pixel using deterministic or statistical models.…”

Section: A the Mixing Modelmentioning

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

A Multitemporal Linear Spectral Unmixing: An Iterative Approach Accounting For Abundance Variations

Cited by 8 publications

References 13 publications

IVIU-Net: Implicit Variable Iterative Unrolling Network for Hyperspectral Sparse Unmixing

IVIU-Net: Implicit Variable Iterative Unrolling Network for Hyperspectral Sparse Unmixing

Bidirectional Recurrent Imputation and Abundance Estimation of LULC Classes With MODIS Multispectral Time-Series and Geo-Topographic and Climatic Data

Learning Interpretable Deep Disentangled Neural Networks for Hyperspectral Unmixing

Contact Info

Product

Resources

About