Contactless Cardiac Pulse Monitoring Using Event Cameras

2025-05-14

AI Summary

This study addresses the limitations of conventional frame-based cameras—namely, restricted dynamic range and temporal resolution—in non-contact facial heart rate (HR) estimation. To overcome these constraints, we propose an event-camera-based approach that asynchronously maps sparse event streams into multi-rate 2D frames (30/60/120 FPS) and employs a supervised convolutional neural network (CNN) for end-to-end photoplethysmographic (PPG) signal regression. This work constitutes the first empirical validation that high-fidelity physiological information is intrinsically encoded in event data. Experimental results demonstrate that the 60 FPS and 120 FPS event-frame models achieve root-mean-square errors (RMSE) of 2.54 and 2.13 bpm, respectively—significantly outperforming the 30 FPS frame-camera baseline (2.92 bpm). The method further offers low latency and low power consumption, enabling robust, remote, and high-accuracy non-contact physiological monitoring.

Technology Category

• Computer Vision: Biometrics, Face, Gesture & Pose
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Security and Privacy: Large-scale security measurements
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Systems and Infrastructure for Web, Mobile and WoT: Data management and stream processing for Web, mobile and wireless applications

Abstract

Time event cameras are a novel technology for recording scene information at extremely low latency and with low power consumption. Event cameras output a stream of events that encapsulate pixel-level light intensity changes within the scene, capturing information with a higher dynamic range and temporal resolution than traditional cameras. This study investigates the contact-free reconstruction of an individual's cardiac pulse signal from time event recording of their face using a supervised convolutional neural network (CNN) model. An end-to-end model is trained to extract the cardiac signal from a two-dimensional representation of the event stream, with model performance evaluated based on the accuracy of the calculated heart rate. The experimental results confirm that physiological cardiac information in the facial region is effectively preserved within the event stream, showcasing the potential of this novel sensor for remote heart rate monitoring. The model trained on event frames achieves a root mean square error (RMSE) of 3.32 beats per minute (bpm) compared to the RMSE of 2.92 bpm achieved by the baseline model trained on standard camera frames. Furthermore, models trained on event frames generated at 60 and 120 FPS outperformed the 30 FPS standard camera results, achieving an RMSE of 2.54 and 2.13 bpm, respectively.

Problem

• Contactless cardiac pulse monitoring using event cameras
• Reconstructing cardiac signals from facial event recordings
• Evaluating CNN model accuracy for remote heart rate measurement

Innovation

• Event cameras capture high dynamic range data
• CNN model extracts cardiac pulse from events
• Event frames outperform standard camera heart rate