Generative Adversarial Network for Radar Signal Synthesis

Abstract

A major obstacle in ultra-wideband radar based approaches for object detection concealed on human body is the difficulty in collecting high quality radar signal data. Generative adversarial networks (GAN) have shown promise in synthesizing data for image and audio processing. This paper proposes the design of a GAN for application in radar signal generation. Data collected using the Finite-Difference Time-Domain (FDTD) method on three concealed object classes (no object, large object, and small object) are used as training data. A GAN is trained to generate radar signal samples for each class. The proposed GAN is capable of synthesizing the radar signal data which is indistinguishable from the training data by qualitative analysis performed by human observers.