Abstract
Due to the complex background and low spatial resolution of the hyperspectral sensor, observed ground reflectance is often mixed at the pixel level. Hyperspectral unmixing (HU) is a hot-issue in the remote sensing area because it can decompose the observed mixed pixel reflectance. Traditional sparse hyperspectral unmixing often leads to an ill-posed inverse problem, which can be circumvented by spatial regularization approaches. However, their adoption has come at the expense of a massive increase in computational cost. In this paper, a novel multiscale hierarchical model for a method of sparse hyperspectral unmixing is proposed. The paper decomposes HU into two domain problems, one is in an approximation scale representation based on resampling the method’s domain, and the other is in the original domain. The use of multiscale spatial resampling methods for HU leads to an effective strategy that deals with spectral variability and computational cost. Furthermore, the hierarchical strategy with abundant sparsity representation in each layer aims to obtain the global optimal solution. Both simulations and real hyperspectral data experiments show that the proposed method outperforms previous methods in endmember extraction and abundance fraction estimation, and promotes piecewise homogeneity in the estimated abundance without compromising sharp discontinuities among neighboring pixels. Additionally, compared with total variation regularization, the proposed method reduces the computational time effectively.
Highlights
Hyperspectral images possess abundant spectral information, which makes target detection and classification become feasible [1,2]
This paper proposes an unsupervised multiscale hierarchical sparsity unmixing method to improve the accuracy of hyperspectral unmixing
Considering the spatial contextual information with an abundance matrix regularization in a coarse domain, the proposed method leads to a simple and efficient strategy to deal with spectral variability, especially caused by shadow between neighboring pixels
Summary
Hyperspectral images possess abundant spectral information, which makes target detection and classification become feasible [1,2]. Non-negative matrix factorization (NMF) has been shown to be a useful unsupervised decomposition for hyperspectral unmixing [6]. To improve the performance of the NMF based hyperspectral unmixing method, further constraints were imposed on NMF [10,11,12,13,14]. Sparsity constraints have gained much attention since most of the pixels are mixtures of only a few endmembers in the scene, which implies that the abundance matrix is a large degree of sparsity. Regularization methods are usually utilized to define the sparsity constraint on the abundance matrix. Along these lines, L1/2 regularization is introduced into NMF so as to enforce the sparsity of the endmember abundance matrix [8]. A hierarchical strategy or multilayer NMF (MLNMF) is proposed to improve the performance of existing NMF, which is fully confirmed by extensive simulations with diverse types of data to blind source separation [16,17]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
