Preliminary Results of Multipath Ghost Suppression Based on Generative Adversarial Nets in TWRI

Abstract

In this paper, we propose an approach that uses generative adversarial nets (GAN) to eliminate multipath ghosts with respect to through-the-wall radar imaging (TWRI). The applied GAN is composed of two adversarial networks, namely generator G and discriminator D. The generator G learns the spatial characteristics of an input radar image to construct a mapping from input to an output image with suppressed ghosts. The discriminator D evaluates the difference (namely the residual multipath ghosts) between the output image and the ground truth image without multipath ghosts. On the one hand, by training G, the image difference is diminished gradually. In other words, the multipath ghosts are suppressed increasingly in the output image of G. On the other hand, D is trained to improve the ability of evaluating the diminishing difference accompanied with multipath ghosts as much as possible. These two networks G and D fight with each other until G eliminate multipath ghosts. Preliminary simulation results demonstrate GAN can effectively eliminate multipath ghosts in TWRI.