FMCW Radar Deterministic Augmentation Applied to Deep Learning Networks.......- Part 2

This talk proposes a novel data augmentation method based on a deterministic model to generate a simulated dataset of radar micro-Doppler signatures suitable for unmanned aerial vehicle (UAV) target classification, without requiring measurement data. It is shown that the Deep neural networks trained using the properly generated model-based data offers improved classification accuracy performance. Results are presented for a two-class classification of the number of UAV motors using a 77-GHz frequency-modulated continuous wave (FMCW) automotive radar system.