A Novel Micro-Doppler Coherence Loss for Deep Learning Radar Applications

TL;DR

This paper introduces a micro-Doppler coherence loss function for deep learning models, improving their robustness to noise in radar applications by emphasizing relevant micro-Doppler features.

Contribution

The paper proposes a novel loss function tailored for micro-Doppler radar data, enhancing deep learning model performance and noise resilience.

Findings

Models with the coherence loss are more noise-resistant.

The loss encourages models to focus on micro-Doppler features.

Experimental results show improved robustness on real data.

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.