Low-Rank and Sparse Matrix Recovery for Hyperspectral Image Reconstruction Using Bayesian Learning

• Published in: Sensors (Basel, Switzerland) Vol. 22; no. 1; p. 343
• Main Authors: Zhang, Yanbin, Huang, Long-Ting, Li, Yangqing, Zhang, Kai, Yin, Changchuan
• Format: Journal Article
• Language: English
• Published: Switzerland MDPI AG 01-01-2022; MDPI
• Subjects: Agricultural production; Algorithms; Bayesian analysis; Bayesian learning; China; Compression ratio; compressive sensing; Data compression; Data transmission; Ground stations; hyperspectral images; Hyperspectral imaging; hyperspectral remoting sensing; low-rank and joint-sparse; Methods; Natural resources; Remote sensing; Satellites; Signal to noise ratio; Sparse matrices; Sparsity; Spectrum analysis; Wavelet transforms; China; hyperspectral remoting sensing; low-rank and joint-sparse; hyperspectral images; compressive sensing; Bayesian learning
• ISSN: 1424-8220; 1424-8220
• DOI: 10.3390/s22010343

In order to reduce the amount of hyperspectral imaging (HSI) data transmission required through hyperspectral remote sensing (HRS), we propose a structured low-rank and joint-sparse (L&S) data compression and reconstruction method. The proposed method exploits spatial and spectral correlations in HSI data using sparse Bayesian learning and compressive sensing (CS). By utilizing a simultaneously L&S data model, we employ the information of the principal components and Bayesian learning to reconstruct the hyperspectral images. The simulation results demonstrate that the proposed method is superior to LRMR and SS&LR methods in terms of reconstruction accuracy and computational burden under the same signal-to-noise tatio (SNR) and compression ratio.