Non-linear hyperspectral unmixing with 3D convolutional encoders

Date

2022-01-01

Author

Özdemir, Okan Bilge
Koz, Alper
Yardımcı Çetin, Yasemin

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

112
views

0
downloads

Deep learning-based methods are accepted as a viable alternative to conventional statistical and geometrical methods for hyperspectral unmixing in recent years. These methods are however mainly based on linear mixture assumption on the hyperspectral data. The vast majority of presented algorithms process individual hyperspectral pixels while neglecting the spatial relationships between pixels. In order to address these two missing aspects, we propose a convolutional autoencoder-based hyperspectral unmixing method in this paper. The proposed structure incorporates the spatial neighbourhood relation with its convolutional layers in the first stage and possible non-linearities in the observed data with the included non-linear layer in the final stage. The experiments have first revealed that Adam optimizer have the best performance among different optimization methods for the proposed network. Second, the proposed method has indicated about 20–40% accuracy improvement in terms of mean squared error (MSE) metric compared to traditional hyperspectral abundance estimation methods. Third, the contribution of the non-linear layer is verified by comparing the proposed network with the conventional LMM-based autoencoder structure without the non-linear layer. Finally, the accuracy improvement for the proposed network with non-linear layer compared to the state-of-the-art deep learning-based methods using linear mixture assumption is evaluated in terms of MSE and reported as about 10% and 20% for synthetic and real data, respectively.

Subject Keywords

Autoencoders, convolutional neural networks, hyperspectral unmixing, non-linear unmixing, VARIABILITY, ALGORITHM, IMAGES, MODEL, Autoencoders, convolutional neural networks, hyperspectral unmixing, non-linear unmixing

URI

https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85133225276&origin=inward
https://hdl.handle.net/11511/101603

Journal

International Journal of Remote Sensing

DOI

https://doi.org/10.1080/01431161.2022.2088258

Collections

Graduate School of Informatics, Article

Suggestions

OpenMETU
Core

Image generation using only a discriminator network with gradient norm penalty Yeşilçimen, Cansu Cemre; Akbaş, Emre; Department of Computer Engineering (2022-9) This thesis explores the idea of generating images using only a discriminator network by extending a previously proposed method (Tapli, 2021) in several ways. The base method works by iteratively updating the input image, which is pure noise at the beginning while increasing the discriminator's score. We extend the training procedure of the base network by adding the following new losses: (i) total variation, (ii) N-way classification (if labels are available), and (iii) gradient norm penalty on real exam...
Configuration of Neural Networks for the Analysis of Seasonal Time Series Taşkaya Temizel, Tuğba (2005-08-25) Time series often exhibit periodical patterns that can be analysed by conventional statistical techniques. These techniques rely upon an appropriate choice of model parameters that are often difficult to determine. Whilst neural networks also require an appropriate parameter configuration, they offer a way in which non-linear patterns may be modelled. However, evidence from a limited number of experiments has been used to argue that periodical patterns cannot be modelled using such networks. In this paper, ...
Metamodeling complex systems using linear and nonlinear regression methods Kartal, Elçin; Batmaz, İnci; Department of Statistics (2007) Metamodeling is a very popular approach for the approximation of complex systems. Metamodeling techniques can be categorized according to the type of regression method employed as linear and nonlinear models. The Response Surface Methodology (RSM) is an example of linear regression. In classical RSM metamodels, parameters are estimated using the Least Squares (LS) Method. Robust regression techniques, such as Least Absolute Deviation (LAD) and M-regression, are also considered in this study due to the outli...
Deep Spectral Convolution Network for Hyperspectral Unmixing Akar, Gözde (2018-10-10) In this paper, we propose a novel hyperspectral unmixing technique based on deep spectral convolution networks (DSCN). Particularly, three important contributions are presented throughout this paper. First, fully-connected linear operation is replaced with spectral convolutions to extract local spectral characteristics from hyperspectral signatures with a deeper network architecture. Second, instead of batch normalization, we propose a spectral normalization layer which improves the selectivity of filters b...
Dynamics of Coupled Structures, Volume 4 Kalaycıoğlu, Taner; Özgüven, Hasan Nevzat (null, Springer, 2016-01-01) Substructuring methods are well known and are widely used in predicting dynamics of coupled structures. In theory, there is no reason why the same techniques could not be used in a reverse problem of predicting the dynamic behavior of a particular substructure from the knowledge of the dynamics of the coupled structure and of all the other substructures. However, the reverse problem, known as decoupling, usually requires matrix inversions, and therefore even small measurement errors may easily affect the ac...

Citation Formats

O. B. Özdemir, A. Koz, and Y. Yardımcı Çetin, “Non-linear hyperspectral unmixing with 3D convolutional encoders,” International Journal of Remote Sensing, vol. 43, no. 9, pp. 3236–3257, 2022, Accessed: 00, 2023. [Online]. Available: https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85133225276&origin=inward.