SynRhythm: Learning a Deep Heart Rate Estimator from General to Specific
Authors:
- 1 August 2018
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 3580-3585
Abstract
Remote photoplethysmography (rPPG) based noncontact heart rate (HR) measurement from a face video has drawn increasing attention recently because of its potential applications in many scenarios such as training aid, health monitoring, and nursing care. Although a number of methods have been proposed, most of them are designed under certain assumptions and could fail when such assumptions do not hold. At the same time, while deep learning based methods have been reported to achieve promising results in many computer vision tasks, their use in rPPG-based heart rate estimation has been limited due to the very limited data available in public domain. To overcome this limitation and leverage the strong modeling ability of deep neural networks, in this paper, we propose a novel spatial-temporal representation for the HR signal and design a general-to-specific transfer learning strategy to train a deep heart rate estimator from a large volume of synthetic rhythm signals and a limited number of available face video data. Experiment results on the public-domain databases show the effectiveness of the proposed approach.Keywords
This publication has 19 references indexed in Scilit:
- AgeNet: Deeply Learned Regressor and Classifier for Robust Apparent Age Estimation2015
- ImageNet Large Scale Visual Recognition ChallengeInternational Journal of Computer Vision, 2015
- DistancePPG: Robust non-contact vital signs monitoring using a cameraBiomedical Optics Express, 2015
- Exploiting Spatial Redundancy of Image Sensor for Motion Robust rPPGIEEE Transactions on Biomedical Engineering, 2014
- Remote Heart Rate Measurement from Face Videos under Realistic Situations2014
- Robust Pulse Rate From Chrominance-Based rPPGIEEE Transactions on Biomedical Engineering, 2013
- Detecting Pulse from Head Motions in Video2013
- Eulerian video magnification for revealing subtle changes in the worldACM Transactions on Graphics, 2012
- Non-contact, automated cardiac pulse measurements using video imaging and blind source separationOptics Express, 2010
- STATISTICAL METHODS FOR ASSESSING AGREEMENT BETWEEN TWO METHODS OF CLINICAL MEASUREMENTThe Lancet, 1986