16 May 2017 Motion correction for improved estimation of heart rate using a visual spectrum camera
Author Affiliations +
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
© (2017) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Elizabeth A. Tarbox, Elizabeth A. Tarbox, Christian Rios, Christian Rios, Balvinder Kaur, Balvinder Kaur, Shaun Meyer, Shaun Meyer, Lauren Hirt, Lauren Hirt, Vy Tran, Vy Tran, Kaitlyn Scott, Kaitlyn Scott, Vasiliki Ikonomidou, 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); doi: 10.1117/12.2262932; https://doi.org/10.1117/12.2262932

Back to Top