Generative Adversarial Networks for Classification of Micro-Doppler Signatures of Human Activity

Abstract

We propose using generative adversarial networks (GANs) for the classification of micro-Doppler signatures measured by the radar. Despite Deep Convolutional Neural Networks (DCNNs) having been used extensively in radar image classification in recent years, their performance could not be fully implemented in the radar field because of the deficiency of the training data set. This is a key issue because of the extremely high labor and monetary costs involved in obtaining radar images. As such, attempts have been made to resolve this issue via the production of radar data by simulation or by the use of transfer learning. In this letter, we propose the use of GANs to produce a large number of micro-Doppler signatures with which to increase the training data set. Once the GANs are trained, a large amount of similar data, with the same distribution as the original data, can be easily generated. The generated fake micro-Doppler images can then be included in the DCNN training process. The proposed method is applied to classifying human activities measured by the Doppler radar. For each human activity, corresponding GANs that generate micro-Doppler signatures for a particular activity are constructed. Using the micro-Doppler signatures produced by the GANs along with the original data, the DCNN is trained. According to the results, the use of GANs improves the accuracy of classification. Moreover, the use of GANs was found to be more effective than the use of transfer learning.