A Real-Time Non-Contact Heart Rate Measurement based on Imaging Photoplethysmography (iPPG)-Power Spectral Density (PSD)

Abstract

The demands of accessible physiological information have opened an interest among researchers to integrate contact to non-contact techniques to assess health status. This paper presents a real-time and non-contact heart rate (HR) assessment based on imaging photoplethysmography (iPPG) – Power Spectral Density (PSD) to quantify dynamic changes of blood volume at the forehead due to cardiac activity. The HR assessment was implemented on ten healthy subjects using a built-in camera laptop with an executable algorithm (Python-OpenCV) in PyCharm environment. A commercial pulse amped sensor was attached to the subject’s right index finger to extract contact photoplethysmography (cPPG) signal simultaneously. The cPPG signal was processed using the post-processing techniques in the MATLAB environment. The statistical analysis was demonstrated on HRcPPG and HRiPPG to determine the correlation between the measurement. The results show correlation between the measurement with correlation coefficient, r = 0.67, and the linear regression, r2 = 0.49, p-value = 0.024. The 95% of the Limit of Agreement (LOA) from the Bland-Altman plot was 12.77 to -22.37 (BPM). The outcomes from the analysis are significant to improve measurement and post-processing techniques.