Advancing Non-Contact Vital Sign Measurement using Synthetic Avatars

Abstract

Non-contact physiological measurement has the potential to provide low-cost, non-invasive health monitoring. However, machine vision approaches are often limited by the availability and diversity of annotated video datasets resulting in poor generalization to complex real-life conditions. To address these challenges, this work proposes the use of synthetic avatars that display facial blood flow changes and allow for systematic generation of samples under a wide variety of conditions. Our results show that training on both simulated and real video data can lead to performance gains under challenging conditions. We show state-of-the-art performance on three large benchmark datasets and improved robustness to skin type and motion.

References in corpus (5)

• Multi-Task Temporal Shift Attention Networks for On-Device Contactless Vitals Measurement
• Identifying Bias in AI using Simulation
• Model-driven Simulations for Deep Convolutional Neural Networks
• Simulations for Validation of Vision Systems
• Model Validation for Vision Systems via Graphics Simulation

Cited by in corpus (5)

• MobilePhys: Personalized Mobile Camera-Based Contactless Physiological Sensing
• EfficientPhys: Enabling Simple, Fast and Accurate Camera-Based Vitals Measurement
• MetaPhys: Few-Shot Adaptation for Non-Contact Physiological Measurement
• Overcoming Difficulty in Obtaining Dark-skinned Subjects for Remote-PPG by Synthetic Augmentation
• Learning Higher-Order Dynamics in Video-Based Cardiac Measurement