Wall Compensation in Synthetic Aperture Through-the-wall Radar Imaging Based on Generative Adversarial Nets

Abstract

In synthetic aperture through-the-wall radar imaging, wall penetration effect causes target images defocused and displaced from their true positions. To solve this problem, a wall compensation method based on generative adversarial nets (GAN) is proposed in this paper. Specifically, GAN constructs a spatial structure mapping from the original input images to the output images without wall penetration effect. Electromagnetic simulation show that the proposed method has acceptable computational load and great imaging results in both refocusing and correcting the displacement.