Microwave Through Wall Imaging via An Induced Current Learning Method

Abstract

In this paper, an induced current learning method (ICLM) for microwave through wall imaging (TWI), named as TWI-ICLM, is proposed. In the inversion of induced current, the unknown object along with the enclosed walls are treated as a combination of scatterers. Firstly, a non-iterative method called distorted-Born backpropagation (DB-BP) is utilized to generate the initial result. In the training stage, several convolutional neural networks (CNNs) are cascaded to improve the estimated induced current. In addition, a hybrid loss function consisting of the induced current error and the permittivity error is used to optimize the network parameters. Finally, the relative permittivity images are conducted analytically using the predicted current based on ICLM. Both the numerical and experimental TWI tests prove that, the proposed method can achieve better imaging accuracy compared to traditional distorted-Born iterative method (DBIM).

Keywords

through wall imaging / inverse scattering problem / convolutional neural network (CNN)