LifWavNet: Lifting Wavelet-based Network for Non-contact ECG Reconstruction from Radar

TL;DR

The paper tackles non-contact ECG reconstruction from radar, a challenging cross-domain mapping affected by respiration and noise. It introduces LifWavNet, a lifting wavelet network built on a multi-resolution analysis and synthesis (MRAS) framework with learnable lifting and inverse lifting units to adaptively map radar echoes to physiological ECG waveforms. A multi-resolution STFT loss enforces both temporal and spectral fidelity, and extensive experiments on two public datasets demonstrate state-of-the-art ECG reconstruction and reliable vitals estimation, with interpretable multi-scale feature visualizations supporting the method's transparency. The approach highlights the potential of learnable lifting wavelets for cross-domain signal transformation and offers a practical, efficient solution for radar-based non-contact cardiac monitoring.

Abstract

Non-contact electrocardiogram (ECG) reconstruction from radar signals offers a promising approach for unobtrusive cardiac monitoring. We present LifWavNet, a lifting wavelet network based on a multi-resolution analysis and synthesis (MRAS) model for radar-to-ECG reconstruction. Unlike prior models that use fixed wavelet approaches, LifWavNet employs learnable lifting wavelets with lifting and inverse lifting units to adaptively capture radar signal features and synthesize physiologically meaningful ECG waveforms. To improve reconstruction fidelity, we introduce a multi-resolution short-time Fourier transform (STFT) loss, that enforces consistency with the ground-truth ECG in both temporal and spectral domains. Evaluations on two public datasets demonstrate that LifWavNet outperforms state-of-the-art methods in ECG reconstruction and downstream vital sign estimation (heart rate and heart rate variability). Furthermore, intermediate feature visualization highlights the interpretability of multi-resolution decomposition and synthesis in radar-to-ECG reconstruction. These results establish LifWavNet as a robust framework for radar-based non-contact ECG measurement.

Figures (8)

• Figure 1: Overview of radar signal-based non-contact ECG reconstruction. The radar measures the chest movement signal in a non-contact manner, from which a neural network reconstructs the ECG signal.
• Figure 2: Illustration of wavelet and inverse wavelet transforms using (a) Filter banks, (b) Lifting scheme.
• Figure 3: Structure of lifting and inverse lifting units.
• Figure 4: Overall architecture of LifWavNet.
• Figure 5: Our loss function constrains the similarity between reconstructed ($S_E$) and ground-truth ECG signal ($S_{GT}$) in both time and STFT domains. The multi-resolution STFT (MR-STFT) performs STFT with different window lengths.