Motion correction for improved estimation of heart rate using a visual spectrum camera

Elizabeth A. Tarbox; Christian Rios; Balvinder Kaur; Shaun Meyer; Lauren Hirt; Vy Tran; Kaitlyn Scott; Vasiliki Ikonomidou

doi:10.1117/12.2262932

16 May 2017 Motion correction for improved estimation of heart rate using a visual spectrum camera

Elizabeth A. Tarbox, Christian Rios, Balvinder Kaur, Shaun Meyer, Lauren Hirt, Vy Tran, Kaitlyn Scott, Vasiliki Ikonomidou

Author Affiliations +

Proceedings Volume 10216, Smart Biomedical and Physiological Sensor Technology XIV; 1021607 (2017) https://doi.org/10.1117/12.2262932
Event: SPIE Commercial + Scientific Sensing and Imaging, 2017, Anaheim, CA, United States

Abstract

Heart rate measurement using a visual spectrum recording of the face has drawn interest over the last few years as a technology that can have various health and security applications. In our previous work, we have shown that it is possible to estimate the heart beat timing accurately enough to perform heart rate variability analysis for contactless stress detection. However, a major confounding factor in this approach is the presence of movement, which can interfere with the measurements. To mitigate the effects of movement, in this work we propose the use of face detection and tracking based on the Karhunen-Loewe algorithm in order to counteract measurement errors introduced by normal subject motion, as expected during a common seated conversation setting. We analyze the requirements on image acquisition for the algorithm to work, and its performance under different ranges of motion, changes of distance to the camera, as well and the effect of illumination changes due to different positioning with respect to light sources on the acquired signal. Our results suggest that the effect of face tracking on visual-spectrum based cardiac signal estimation depends on the amplitude of the motion. While for larger-scale conversation-induced motion it can significantly improve estimation accuracy, with smaller-scale movements, such as the ones caused by breathing or talking without major movement errors in facial tracking may interfere with signal estimation. Overall, employing facial tracking is a crucial step in adapting this technology to real-life situations with satisfactory results.

Conference Presentation

Citation Download Citation

Elizabeth A. Tarbox, Christian Rios, Balvinder Kaur, Shaun Meyer, Lauren Hirt, Vy Tran, Kaitlyn Scott, and Vasiliki Ikonomidou "Motion correction for improved estimation of heart rate using a visual spectrum camera", Proc. SPIE 10216, Smart Biomedical and Physiological Sensor Technology XIV, 1021607 (16 May 2017); https://doi.org/10.1117/12.2262932

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available