A Fast Snapshot Hyperspectral Image Reconstruction Method Based on Three-Dimensional Low Rank Constraint. Issue 4 (4th July 2021)

• Record Type: Journal Article
• Authors: Wei, Chunsheng; Li, Qifeng; Zhang, Xiaodong; Ma, Xiangyun; Du, Jianbin
• Is Part Of: Canadian journal of remote sensing. Volume 47:Issue 4(2021)
• Page Start: 588
• Page End: 595
• Publication Date: 2021-07-04
• Subjects: Remote sensing -- Periodicals; 621.367805
• DOI: 10.1080/07038992.2021.1943340
• Languages: English
• ISSNs: 0703-8992

Abstract

Abstract: The snapshot hyperspectral imaging is an emerging technique with numerous applications. However, the hyperspectral imaging reconstruction is often time-consuming, which is placing a limit on the development of snapshot hyperspectral imaging. We present an efficient reconstruction algorithm based on the tensor analysis and the low-rank constraint. The hyperspectral data cube is regarded as a low rank three-order tensor, which can jointly treat both spatial and spectral modes. The 3D-LRC method can greatly decrease the computation time without unfolding the hyperspectral data cube into 2D patches. Compared with the-state-of-the-art method, the proposed method has a great improvement in the reconstruction speed and quality. The method has been implemented on two typical snapshot hyperspectral imaging systems.