A Compressive Hyperspectral Video Imaging System Using A Single-pixel Detector

This article discusses the development of a hyperspectral video imaging system called the “Single-Doxel Imager” (SDI) that uses a single-pixel detector to achieve high-throughput hyperspectral video recording at a low bandwidth. The system utilizes a CS-based sensing scheme and an optimization-based reconstruction algorithm to achieve a compression ratio of 900:1 and a data throughput of 900x compared to conventional imaging. The article also introduces a deep learning reconstruction approach for faster recovery and promising reconstruction quality.