Non-Contact Heart Rate Monitoring by Combining Convolutional Neural Network Skin Detection and Remote Photoplethysmography via a Low-Cost Camera

Chuanxiang Tang, Jiwu Lu, Jie Liu; The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2018, pp. 1309-1315

Abstract


In this paper, we present a versatile methodology to flexibly accomplish the non-contact monitoring of heart rate signals in various environments, by combining the convolutional neural network (CNN) skin detection and the camera-based remote photoplethysmography (rPPG) method. Compared to the widely-used three-step skin detection method (i.e., face detection, face tracking, and skin classification), the CNN method used here could significantly enhances the monitoring robustness by achieving the skin detection in one single step. The proposed CNN-rPPG method has been demonstrated in an unconstrained environment (e.g., office conditions) to directly verify its applicability. Combined with the subsequent rPPG heart rate monitoring based on a low-cost camera, the method presented here is of practical interests for the large-scale deployment of the non-contact heart rate monitoring technologies.

Related Material


[pdf]
[bibtex]
@InProceedings{Tang_2018_CVPR_Workshops,
author = {Tang, Chuanxiang and Lu, Jiwu and Liu, Jie},
title = {Non-Contact Heart Rate Monitoring by Combining Convolutional Neural Network Skin Detection and Remote Photoplethysmography via a Low-Cost Camera},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops},
month = {June},
year = {2018}
}