Abstract
Compared with natural image super-resolution, hyperspectral image super-resolution (HSR) is more complex because the redundancy in spectral bands and spatial information. To overcome the difficulties exist in HSR, in this paper, we propose a tensor spatial-spectral joint correlation based HSR method. Start with the tensor representation, we construct a series of fourth-order tensors to preserve the intrinsic structure of hyperspectral images, and then explore the spatial-spectral joint correlation based on meaningful interpretations of tensor canonical matrices. To further constrain the spectral characteristics, we analyze the sparsity of the spectral gradients and model it with Laplacian prior. Then, the two regularizations are combined with the reconstruction model to develop a new HSR method. Finally, an iterative optimization algorithm based on alternating direction method of multiplier (ADMM) and augmented Lagrangian multiplier method is proposed to reconstruct the high-resolution hyperspectral images. Experimental results on several data sets illustrate the effectiveness of our proposed method both in visual and numerical comparisons.
Highlights
The hyperspectral imaging system usually produces the multi-band images at a high spectral resolution of 10nm in the visible and infrared wavelength region
Because of the similarities in essence, many works generalized the techniques in pan-sharpening to Hyperspectral image super-resolution (HSR) [6]–[8], there are some differences between pan-sharpening and HSR, for instance, unlike the pan-sharpening, in HSR, the spectral information contained in both multispectral images (MSIs) and hyperspectral images (HSIs), which results in the inefficiency of generalization of pan-sharpening methods
Zhang et al [22] designed a low-rank decomposition based HSR method that constructed two graphs in spatial and spectral domains to keep the spatial consistency and spectral smoothness. Even though these methods were based on the tensor decomposition and explored other characteristics such as low-rank, sparse and non-local properties, they have not considered the joint correlations exist in the HSIs
Summary
The hyperspectral imaging system usually produces the multi-band images at a high spectral resolution of 10nm in the visible and infrared wavelength region. Zhang et al [22] designed a low-rank decomposition based HSR method that constructed two graphs in spatial and spectral domains to keep the spatial consistency and spectral smoothness Even though these methods were based on the tensor decomposition and explored other characteristics such as low-rank, sparse and non-local properties, they have not considered the joint correlations exist in the HSIs. Very recently, Zhang et al proposed a dimension-discriminative low-rank tensor recovery (DLTR) model for computational hyperspectral imaging [28]. Zhang et al proposed a dimension-discriminative low-rank tensor recovery (DLTR) model for computational hyperspectral imaging [28] They constructed several third-order tensors and claimed that the three modes of the tensor represent the spatial self-similarity, spectral correlation and the joint correlation respectively.
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 call
