Contactless Cardiac Pulse Monitoring Using Event Cameras

TL;DR

This paper demonstrates that event cameras can be used for contactless, real-time cardiac pulse monitoring by reconstructing heart rate signals from facial recordings with high accuracy using a CNN model.

Contribution

It introduces a novel approach using event cameras and deep learning for contactless heart rate estimation, outperforming traditional camera-based methods.

Findings

Event cameras effectively capture facial cardiac signals.

The CNN model achieves an RMSE of 2.13 bpm at 120 FPS.

Higher frame rates improve heart rate estimation accuracy.

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.