Generation of Human Micro-Doppler Signature Based on Layer-Reduced Deep Convolutional Generative Adversarial Network

Human activity recognition (HAR) using radar micro-Doppler has attracted the attention of researchers in the last decade. Using radar for human activity recognition has been very practical because of its unique advantages. There are several classifiers for the recognition of these activities, all of which require a rich database to produce fine output. Due to the limitations of providing and building a large database, radar micro-Doppler databases are usually limited in number. In this paper, a new method for the generation of radar micro-Doppler of the human body based on the deep convolutional generating adversarial network (DCGAN) is proposed. To generate the database, the required input is also generated by converting the existing motion database to simulated model-based radar data. The simulation results show the success of this method, even on a small amount of data.