Terahertz coded-aperture imaging (TCAI) has many advantages such as forward-looking\nimaging, staring imaging and low cost and so forth. However, it is difficult to resolve the target under\nlow signal-to-noise ratio (SNR) and the imaging process is time-consuming. Here, we provide an\nefficient solution to tackle this problem. A convolution neural network (CNN) is leveraged to develop\nan off-line end to end imaging network whose structure is highly parallel and free of iterations.\nAnd it can just act as a general and powerful mapping function. Once the network is well trained and\nadopted for TCAI signal processing, the target of interest can be recovered immediately from echo\nsignal. Also, the method to generate training data is shown, and we find that the imaging network\ntrained with simulation data is of good robustness against noise and model errors. The feasibility\nof the proposed approach is verified by simulation experiments and the results show that it has a\ncompetitive performance with the state-of-the-art algorithms.
Loading....