Near-infrared single-pixel imaging method and system based on deep expansion network

The invention provides a near-infrared single-pixel imaging method and system based on a deep expansion network, and the method comprises the steps: constructing a supervised near-infrared single-pixel imaging training data set based on a single-pixel imaging principle; constructing a deep expansion imaging network based on a Transform model and a generalized alternating projection algorithm framework, and training the deep expansion imaging network through the training data set; the method comprises the following steps: establishing an imaging light path according to a near-infrared single-pixel imaging principle, and collecting a one-dimensional under-sampling near-infrared single-pixel measurement value corresponding to a current to-be-imaged target scene through a near-infrared single-pixel detector in the imaging light path; and inputting the one-dimensional under-sampling near-infrared single-pixel measurement value into the trained deep expansion imaging network, and obtaining a target scene image reco