2018 IEEE International Conference on Internet of Things (iThings) and IEEE Green Computing and Communications (GreenCom) and IEEE Cyber, Physical and Social Computing (CPSCom) and IEEE Smart Data (SmartData)
Download PDF

Abstract

Aiming at the defects of traditional heart rate measurement, a blood volume pulse (BVP) signal and estimate heart rate estimate is proposed based on tree component analysis (TCA) and complete total empirical mode decomposition (CEEMD). The region of interest is selected from facial video, which is taken by non-contact camera, and then is separated by TCA to obtain noisy BVP. BVP signal is decomposed into different scale signal which is computed by spectrum analysis to get heart rate. The experiment indicates that the method is consistent with the pulse oximeter, and the 95% confidence interval of this measurement system is [-1.5, 1.5]. Benefiting from property of simplicity and non-contact, this method can be applied to live detection. Moreover, the method can avoid the selection of relevant parameters and reduce the workload of the operators.
Like what you’re reading?
Already a member?
Get this article FREE with a new membership!

Related Articles