Non-Contact Health Monitoring During Daily Personal Care Routines

TL;DR

This paper introduces LADH, a new long-term dataset for non-contact health monitoring during personal care routines, demonstrating improved accuracy by combining RGB and IR video inputs and multi-task learning.

Contribution

The paper presents LADH, the first long-term rPPG dataset with synchronized RGB and IR videos for personal care scenarios, and shows that combining these inputs improves physiological monitoring accuracy.

Findings

Combining RGB and IR videos enhances heart rate estimation accuracy.

Multi-task learning improves performance across multiple physiological signals.

Achieved a mean absolute error of 4.99 BPM in heart rate estimation.

Abstract

Remote photoplethysmography (rPPG) enables non-contact, continuous monitoring of physiological signals and offers a practical alternative to traditional health sensing methods. Although rPPG is promising for daily health monitoring, its application in long-term personal care scenarios, such as mirror-facing routines in high-altitude environments, remains challenging due to ambient lighting variations, frequent occlusions from hand movements, and dynamic facial postures. To address these challenges, we present LADH (Long-term Altitude Daily Health), the first long-term rPPG dataset containing 240 synchronized RGB and infrared (IR) facial videos from 21 participants across five common personal care scenarios, along with ground-truth PPG, respiration, and blood oxygen signals. Our experiments demonstrate that combining RGB and IR video inputs improves the accuracy and robustness of non-contact physiological monitoring, achieving a mean absolute error (MAE) of 4.99 BPM in heart rate estimation. Furthermore, we find that multi-task learning enhances performance across multiple physiological indicators simultaneously. Dataset and code are open at https://github.com/McJackTang/FusionVitals.