Journal
IEEE TRANSACTIONS ON AEROSPACE AND ELECTRONIC SYSTEMS
Volume 56, Issue 4, Pages 3197-3213Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TAES.2020.2969579
Keywords
Kinematics; Time-frequency analysis; Doppler radar; Spectrogram; Training; Radar antennas
Ask authors/readers for more resources
Deep neural networks have recently received a great deal of attention in applications requiring classification of radar returns, including radar-based human activity recognition for security, smart homes, assisted living, and biomedicine. However, acquiring a sufficiently large training dataset remains a daunting task due to the high human costs and resources required for radar data collection. In this article, an extended approach to adversarial learning is proposed for generation of synthetic radar micro-Doppler signatures that are well adapted to different environments. The synthetic data are evaluated using visual interpretation, analysis of kinematic consistency, data diversity, dimensions of the latent space, and saliency maps. A principle-component analysis-based kinematic-sifting algorithm is introduced to ensure that synthetic signatures are consistent with physically possible human motions. The synthetic dataset is used to train a 19-layer deep convolutional neural network to classify micro-Doppler signatures acquired from an environment different from that of the dataset supplied to the adversarial network. An overall accuracy of 93% is achieved on a dataset that contains multiple aspect angles (0 degrees, 30 degrees, and 45 degrees as well as 60 degrees), with 9% improvement as a result of kinematic sifting.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available