Reliability-Aware Weighted Multi-Scale Spatio-Temporal Maps for Heart Rate Monitoring

TL;DR

This paper introduces a reliability-aware multi-scale spatio-temporal map for improving contactless heart rate estimation from facial videos, enhancing robustness against environmental noise and motion artifacts.

Contribution

It proposes a novel WMST map modeling pixel reliability, combined with a contrastive learning approach using Swin-Unet and a new wavelet map for better HR estimation.

Findings

Improved heart rate estimation accuracy on public benchmarks.

Enhanced robustness to motion and illumination variations.

Higher Pearson correlation compared to existing SSL-based methods.

Abstract

Remote photoplethysmography (rPPG) allows for the contactless estimation of physiological signals from facial videos by analyzing subtle skin color changes. However, rPPG signals are extremely susceptible to illumination changes, motion, shadows, and specular reflections, resulting in low-quality signals in unconstrained environments. To overcome these issues, we present a Reliability-Aware Weighted Multi-Scale Spatio-Temporal (WMST) map that models pixel reliability through the suppression of environmental noises. These noises are modeled using different weighting strategies to focus on more physiologically valid areas. Leveraging the WMST map, we develop an SSL contrastive learning approach based on Swin-Unet, where positive pairs are generated from conventional rPPG signals and temporally expanded WMST maps. Moreover, we introduce a new High-High-High (HHH) wavelet map as a negative example that maintains motion and structural details while filtering out physiological information. Here, our aim is to estimate heart rate (HR), and the experiments on public rPPG benchmarks show that our approach enhances motion and illumination robustness with lower HR estimation error and higher Pearson correlation than existing Self-Supervised Learning (SSL) based rPPG methods.