A snapshot near-infrared hyperspectral demosaicing method with convolutional neural networks in low illumination environment

Abstract

Snapshot near-infrared hyperspectral imaging technology based on multispectral color filter array has been widely utilized in quantitative and visualized analysis. Hyperspectral demosaicing method is a key part to increase spatial resolution for the snapshot hyperspectral imaging. However, the existing demosaicing methods will be disturbed by noise in case of the low illumination. In this paper, a snapshot hyperspectral demosaicing method is proposed to reconstruct raw mosaic images into full-resolution hyperspectral images. The demosaicing process is integrated with Convolutional Neural Network (CNN) to extract features automatically, guaranteeing a good performance and strong robustness without parameter adjustment. We experimentally validate the merits of the method by 5 × 5 raw mosaic images. The Peak Signal-to-Noise Ratio (PSNR) and Spectral Angle Mapper (SAM) values of reconstructed hyperspectral images can be improved by the proposed method, which has been successfully used in commercial hyperspectral cameras.