Monitoring of Heart and Breathing Rates Using Dual Cameras on a Smartphone

PLoS One. 2016 Mar 10;11(3):e0151013. doi: 10.1371/journal.pone.0151013. eCollection 2016.

Abstract

Some smartphones have the capability to process video streams from both the front- and rear-facing cameras simultaneously. This paper proposes a new monitoring method for simultaneous estimation of heart and breathing rates using dual cameras of a smartphone. The proposed approach estimates heart rates using a rear-facing camera, while at the same time breathing rates are estimated using a non-contact front-facing camera. For heart rate estimation, a simple application protocol is used to analyze the varying color signals of a fingertip placed in contact with the rear camera. The breathing rate is estimated from non-contact video recordings from both chest and abdominal motions. Reference breathing rates were measured by a respiration belt placed around the chest and abdomen of a subject; reference heart rates (HR) were determined using the standard electrocardiogram. An automated selection of either the chest or abdominal video signal was determined by choosing the signal with a greater autocorrelation value. The breathing rate was then determined by selecting the dominant peak in the power spectrum. To evaluate the performance of the proposed methods, data were collected from 11 healthy subjects. The breathing ranges spanned both low and high frequencies (6-60 breaths/min), and the results show that the average median errors from the reflectance imaging on the chest and the abdominal walls based on choosing the maximum spectral peak were 1.43% and 1.62%, respectively. Similarly, HR estimates were also found to be accurate.

Publication types

  • Clinical Trial
  • Research Support, Non-U.S. Gov't
  • Research Support, U.S. Gov't, Non-P.H.S.

MeSH terms

  • Adult
  • Female
  • Heart Rate*
  • Humans
  • Male
  • Monitoring, Physiologic / instrumentation*
  • Monitoring, Physiologic / methods*
  • Respiratory Mechanics*
  • Smartphone*

Grants and funding

This work was supported by the Soonchunhyang University Research Fund, and in part by the US Army Medical Research and Materiel Command (USAMRMC) under Grant No. W81XWH-12-1-0541. The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript.