Effects of Lighting and Window Length on Heart Rate Assessment through Video Magnification

Abstract

Screening people for signs of illness through contactless measurement of vital signs could be beneficial in public transportation settings or long-term care facilities. To achieve this goal, one solution could utilize Red/Green/Blue (RGB) video cameras to measure heart rate. In this work, we present results for the assessment of heart rate through Video Magnification (VM) techniques applied to RGB face video recordings from 19 subjects. The work specifically explores (1) the effect of two lighting illumination levels and (2) the effect of window length on the accuracy of heart rate extraction via Video Magnification. The results show that higher illumination, as a result of combining halogen light with LED, yielded lower average errors in heart rate measured through Video Magnification. Additionally, the results show that increasing the window length from 10 seconds up to 30 seconds improves VM heart rate accuracy when there are small frequent head movements in the video but decreases heart rate accuracy in the absence of head motion.