Semi-NMF Regularization-Based Autoencoder Training for Hyperspectral Unmixing
Hyperspectral Unmixing (HSU) refers to the procedure of decomposing measured pixel spectra into a set of constituent spectral signatures known as endmembers and a corresponding set of fractional mixing ratios. In this work, we propose a novel autoencoder training procedure with adaptive proximal regularization, designed for performing the semi-nonnegative matrix factorization (semi-NMF) that manifests in the hyperspectral unmixing application. The proposed regularization of the autoencoder parameters is based on the Karush-Kuhn-Tucker (KKT) optimality conditions associated with the semi-NMF optimization that underlies the HSU problem. We invoke convex analysis to develop a proximal regularization scheme that encourages the trained autoencoder to encapsulate the properties of the linear mixture generative model of the hyperspectral images. We evaluate the performance of the proposed regularized autoencoder and demonstrate its superior performance against a conventionally-trained autoencoder in performing semi-NMF factorization of synthetic data matrices and unmixing of semi-synthetic hyperspectral images.
Code (1)
Tasks
Hyperspectral UnmixingMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
SSCU-Net: Spatial-Spectral Collaborative Unmixing Network for Hyperspectral Images
Linear spectral unmixing is an essential technique in hyperspectral image processing and interpretation. In recent years, deep learning-based approaches have shown great promise in hyperspectral unmixing, in particular, …
Hyperspectral UnmixingNonlinear unmixing of hyperspectral images using a semiparametric model and spatial regularization
Incorporating spatial information into hyperspectral unmixing procedures has been shown to have positive effects, due to the inherent spatial-spectral duality in hyperspectral scenes. Current research works that consider…
Hyperspectral UnmixingAE-RED: A Hyperspectral Unmixing Framework Powered by Deep Autoencoder and Regularization by Denoising
Spectral unmixing has been extensively studied with a variety of methods and used in many applications. Recently, data-driven techniques with deep learning methods have obtained great attention to spectral unmixing for i…
DenoisingHyperspectral UnmixingImproving Autoencoder Training Performance for Hyperspectral Unmixing with Network Reinitialisation
Neural networks, in particular autoencoders, are one of the most promising solutions for unmixing hyperspectral data, i.e. reconstructing the spectra of observed substances (endmembers) and their relative mixing fraction…
Hyperspectral UnmixingA Dual Symmetric Gauss-Seidel Alternating Direction Method of Multipliers for Hyperspectral Sparse Unmixing
Since sparse unmixing has emerged as a promising approach to hyperspectral unmixing, some spatial-contextual information in the hyperspectral images has been exploited to improve the performance of the unmixing recently.…
Hyperspectral Unmixing