Abstract
Hyperspectral image compressive sensing reconstruction (HSI-CSR) is an important issue in remote sensing, and has recently been investigated increasingly by the sparsity prior based approaches. However, most of the available HSI-CSR methods consider the sparsity prior in spatial and spectral vector domains via vectorizing hyperspectral cubes along a certain dimension. Besides, in most previous works, little attention has been paid to exploiting the underlying nonlocal structure in spatial domain of the HSI. In this paper, we propose a nonlocal tensor sparse and low-rank regularization (NTSRLR) approach, which can encode essential structured sparsity of an HSI and explore its advantages for HSI-CSR task. Specifically, we study how to utilize reasonably the l 1 -based sparsity of core tensor and tensor nuclear norm function as tensor sparse and low-rank regularization, respectively, to describe the nonlocal spatial-spectral correlation hidden in an HSI. To study the minimization problem of the proposed algorithm, we design a fast implementation strategy based on the alternative direction multiplier method (ADMM) technique. Experimental results on various HSI datasets verify that the proposed HSI-CSR algorithm can significantly outperform existing state-of-the-art CSR techniques for HSI recovery.
Highlights
Hyperspectral image (HSI) is a three-dimension data cube by simultaneously capturing the information over two spatial and one spectral dimensions
We present a unified framework for Hyperspectral image compressive sensing reconstruction (HSI-CSR) using the structured sparsity via nonlocal tensor sparse representation and low-rank approximation
Various experiments on real HSI datasets are executed to assess the performance of the proposed nonlocal tensor sparse and low-rank regularization (NTSRLR) method
Summary
Hyperspectral image (HSI) is a three-dimension data cube by simultaneously capturing the information over two spatial and one spectral dimensions. Du [41] proposed a patch-based low-rank tensor decomposition for HSI-CSR algorithm that combined the nonlocal similarity across the spatial domain and the low-rank property over spectral domain in a united framework. In [42,43], this reasonable usage of the global correlation across spectrum (GCS) and nonlocal self-similarity over space (NSS) prior knowledge have led to quite powerful HSI denoising algorithms, and the effectiveness of GCS and NSS for HSI-CSR has not been reported in the public literature
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: 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.