Heart Rate Variability Extraction From Videos Signals: ICA vs. EVM Comparison

Medical researchers have always been interested in heart rate (HR) and heart rate variability (HRV) analysis. However, nowadays, investigators from a variety of other fields are also probing the subject. Recent advancements in non-contact HR and HRV measurement techniques will likely further boost interest in emotional estimation through HRV. Such measurement methods involve the extraction of the photoplethysmography (PPG) signal from the human's face through a camera. The latest approaches apply independent component analysis (ICA) on the color channels of video recordings to extract a PPG signal. Other investigated methods rely on Eulerian video magnification (EVM) to detect subtle changes in skin color associated with the PPG. To the best of our knowledge, EVM has not been successfully employed to extract HRV features from a video of a human face. In this paper, we present a comparison between our two approaches, one which is based on the ICA and the other is based on EVM. Final results show that the proposed ICA-based method yields better results when it comes to the high frequency (HF) and low frequency over high-frequency (LF/HF) HRV parameters mean absolute error (MAE) of 0.57 and 0.419 when compared with the EVM-based method (MAE 0.76 and 1.69); however, the second method showed better MAE results for low frequency (LF) and higher correlation with the ground truth. Also our proposed ICA method showed better results in general by improving HF estimates, but the EVM-based method might be more appropriate when motion is involved or when the HF component is not important.