Motion Classification using Kinematically Sifted ACGAN-Synthesized Radar Micro-Doppler Signatures
This addresses data scarcity for radar applications in security and healthcare, but is incremental as it builds on existing adversarial methods with a kinematic refinement.
The paper tackled the problem of limited training data for radar-based human activity classification by generating synthetic radar micro-Doppler signatures using an adversarial learning approach with kinematic sifting, achieving 93% accuracy and a 9% improvement from sifting.
Deep neural networks (DNNs) have recently received vast 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 paper, 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 is evaluated using visual interpretation, analysis of kinematic consistency, data diversity, dimensions of the latent space, and saliency maps. A principle-component analysis (PCA) 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 (DCNN) to classify micro-Doppler signatures acquired from an environment different from that of the dataset supplied to the adversarial network. An overall accuracy 93% is achieved on a dataset that contains multiple aspect angles (0 deg., 30 deg., and 45 deg. as well as 60 deg.), with 9% improvement as a result of kinematic sifting.