Spatiotemporal Deep Learning Network for Photon-Level Block Compressed Sensing Imaging

In this paper, we propose a spatiotemporal deep learning network for photon-level Block Compressed Sensing Imaging, aimed to address challenges such as signal loss, artifacts, and noise interference in large-pixel dynamic imaging and tracking at the photon level. This approach combines information in the time and frequency domains with a U-Net-LSTM deep learning model, significantly improving the restoration quality of dynamic target images at high frame rates. The experimental results demonstrate that dynamic target imaging with an average photon number of less than 10 per pixel can be achieved using 16-channel parallel detection, where the pixel size is 256*256 and the frame rate is 200 fps.. Compared to conventional Block Compressed Sensing Imaging, this method increases the peak signal-to-noise ratio to 38.66 dB and improves the structural similarity index to 0.96. In the presence of a dynamic scattering medium and a static complex background, we successfully achieved imaging and tracking of two targets undergoing complex motion. Even in scenarios where the targets overlap or obstruct each other, we can still reconstruct clear images of each individual target separately.. This method provides an effective solution for large-pixel dynamic target recognition, tracking, and real-time imaging in complex environments, offering promising applications in remote sensing, military reconnaissance, and beyond.