VideoPulse: Neonatal heart rate and peripheral capillary oxygen saturation (SpO2) estimation from contact free video

2026-02-27

AI Summary

This study addresses the challenge of monitoring heart rate and blood oxygen saturation (SpO₂) in neonates, whose delicate skin limits the use of conventional contact-based sensors. The authors propose the first end-to-end, non-contact video analysis method capable of accurately estimating both vital signs jointly from unaligned, short-duration (2-second) neonatal facial videos. The approach integrates face alignment, a 3D CNN backbone, label distribution smoothing, weighted regression, and a novel artifact-aware supervision mechanism based on denoised photoplethysmographic signals. To support this research, the authors introduce VideoPulse, a new dataset comprising 157 multi-pose neonatal videos. On the NBHR dataset, the method achieves a mean absolute error (MAE) of 2.97 bpm for heart rate and 1.69% for SpO₂; in cross-dataset evaluation, the SpO₂ MAE further improves to 1.68%.

Technology Category

• Computer Vision: Video Understanding & Activity Analysis
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Search and Optimization: Non-convex Optimization

Application Category

• Security and Privacy: Large-scale security measurements
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets

Abstract

Remote photoplethysmography (rPPG) enables contact free monitoring of vital signs and is especially valuable for neonates, since conventional methods often require sustained skin contact with adhesive probes that can irritate fragile skin and increase infection control burden. We present VideoPulse, a neonatal dataset and an end to end pipeline that estimates neonatal heart rate and peripheral capillary oxygen saturation (SpO2) from facial video. VideoPulse contains 157 recordings totaling 2.6 hours from 52 neonates with diverse face orientations. Our pipeline performs face alignment and artifact aware supervision using denoised pulse oximeter signals, then applies 3D CNN backbones for heart rate and SpO2 regression with label distribution smoothing and weighted regression for SpO2. Predictions are produced in 2 second windows. On the NBHR neonatal dataset, we obtain heart rate MAE 2.97 bpm using 2 second windows (2.80 bpm at 6 second windows) and SpO2 MAE 1.69 percent. Under cross dataset evaluation, the NBHR trained heart rate model attains 5.34 bpm MAE on VideoPulse, and fine tuning an NBHR pretrained SpO2 model on VideoPulse yields MAE 1.68 percent. These results indicate that short unaligned neonatal video segments can support accurate heart rate and SpO2 estimation, enabling low cost non invasive monitoring in neonatal intensive care.

Problem

• neonatal monitoring
• contact-free video
• heart rate estimation
• SpO2 estimation
• remote photoplethysmography

Innovation

• remote photoplethysmography
• neonatal monitoring
• contact-free vital signs
• 3D CNN
• SpO2 estimation