A novel micro-doppler coherence loss for deep learning radar applications

Czerkawski, Mikolaj and Ilioudis, Christos and Clemente, Carmine and Michie, Craig and Andonovic, Ivan and Tachtatzis, Christos; (2022) A novel micro-doppler coherence loss for deep learning radar applications. In: 2021 18th European Radar Conference (EuRAD). IEEE, GBR. ISBN 978-2-87487-065-1 (https://doi.org/10.23919/EuRAD50154.2022.9784491)

[thumbnail of Czerkawski-etal-ERC-2021-A novel-micro-doppler-coherence-loss-for-deep-learning-radar-applications]
Preview
 Text. Filename: Czerkawski_etal_ERC_2021_A_novel_micro_doppler_coherence_loss_for_deep_learning_radar_applications.pdf
Accepted Author Manuscript
Download (4MB)| Preview

Abstract

Deep learning techniques are subject to increasing adoption for a wide range of micro-Doppler applications, where predictions need to be made based on time-frequency signal representations. Most, if not all, of the reported applications focus on translating an existing deep learning framework to this new domain with no adjustment made to the objective function. This practice results in a missed opportunity to encourage the model to prioritize features that are particularly relevant for micro-Doppler applications. Thus the paper introduces a micro-Doppler coherence loss, minimized when the normalized power of micro-Doppler oscillatory components between input and output is matched. The experiments conducted on real data show that the application of the introduced loss results in models more resilient to noise.

CORE (COnnecting REpositories)