Fast HSI super resolution using linear regression. Issue 10 (4th July 2019)

• Record Type: Journal Article
• Authors: Song, Lingfei; Fu, Ying; Huang, Hua; Chen, Yufeng
• Is Part Of: IET image processing. Volume 13:Issue 10(2019)
• Page Start: 1671
• Page End: 1679
• Publication Date: 2019-07-04
• Subjects: approximation theory -- image reconstruction -- hyperspectral imaging -- regression analysis -- geophysical image processing -- remote sensing -- image resolution -- image fusion; high spatial resolution multispectral image -- high spatial resolution HSI -- fast HSI super‐resolution method -- hyperspectral super resolution -- linear regression problem -- imaging process -- low‐dimensional space -- LR‐HSI -- fast HSI super resolution -- inherent low spatial resolution -- hyperspectral image super resolution -- low spatial resolution HSI -- C language implementation -- HR‐MSI; Image processing -- Periodicals; 621.36705
• DOI: 10.1049/iet-ipr.2018.5475
• Languages: English
• ISSNs: 1751-9659

Abstract

Abstract : Hyperspectral imaging has great achievements in agriculture, astronomy, surveillance, and so on. However, the inherent low spatial resolution of hyperspectral imaging, unfortunately, limits its more widespread applications. Recently, hyperspectral image (HSI) super resolution addresses this problem by fusing a low spatial resolution HSI (LR‐HSI) with a high spatial resolution multispectral image (HR‐MSI), but most of these methods did not consider real‐time restoration of high spatial resolution HSI. In this study, the authors propose a fast HSI super‐resolution method which fills this blank. Specifically, they model the hyperspectral super resolution as a linear regression problem according to the fact that the imaging process is a linear transform and the inverse of this transform can be approximately estimated, as the spectra of a typical scene lie in a very low‐dimensional space. To further exploit the low‐dimensional nature of the spectra, they divide the HR‐MSI and LR‐HSI into several patches and learn the inverse transform patch‐by‐patch. Experiments on several public datasets show that their method approximates state‐of‐the‐art methods in accuracy, but is several orders of magnitude faster than all of them. Furthermore, they provide an efficient C language implementation of their methods, which can meet the real‐time request.