Fast Terahertz Coded-Aperture Imaging Based on Convolutional Neural Network

Fengjiao Gan,Long Peng,Xingyue Liu,Hongqiang Wang,Chenggao Luo

doi:10.3390/app10082661

Fengjiao Gan, Long Peng + Show 3 more

Open Access

https://doi.org/10.3390/app10082661

Copy DOI

Journal: Applied sciences	Publication Date: Apr 12, 2020
Citations: 6	License type: CC BY 4.0

Affiliation: National University of Defense Technology

Abstract

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

Highlights

Since the terahertz wave (0.1–10 THz) lies between the visible and microwave frequencies, it has stronger penetration capability than light and higher resolution than microwave, allowing for visualization of hidden objects at the millimeter level
We propose a neural network for fast Terahertz coded-aperture imaging (TCAI) which includes the nonlinear part of the encoded information and the linear part of the decoded information
The feasibility of the Deep learning (DL) based approach is verified by numerical experiments

Summary

Introduction

Since the terahertz wave (0.1–10 THz) lies between the visible and microwave frequencies, it has stronger penetration capability than light and higher resolution than microwave, allowing for visualization of hidden objects at the millimeter level. It does little harm to the human body compared to X-rays. THz technology has attracted increasing attention, and the generation and detection of THz have been extensively researched utilizing various approaches. Generation by nonlinear optical effects such as optical parametric oscillation [1] and detection by GaSe electro-optic sensors [2] are one of the typical approaches. In order to overcome the limitations of THz band, some practical methods have been proposed [5,6] Solid-state electronic devices [3] and a lowtemperature-grown GaAs photoconductive antenna gated [4] are used as emitters and detectors.

Methods

Results

Discussion

Conclusion