Improved Pulse Pressure Estimation Based on Imaging Photoplethysmographic Signals

Abstract

Imaging photoplethysmography $(iPPG)$ enables the extraction of physiological signals from standard $RGB$ video recordings. For the assessment of the human health condition, pulse pressure is of utmost importance and is usually determined from conventional blood pressure signals. Within this work we present the fully automated estimation of pulse pressure using $iPPG$ We computed the pulse strength from the $iPPG$ signals and performed a linear correlation analysis with the corresponding pulse pressure. We compared different algorithmic $iPPG$ approaches amongst one is an artificial neural network. We measured a maximum pearson correlation of 0.65 for the artificial neural network and 0.63 for the best conventional approach. Our results show 0.1 increase in correlation coefficient compared to previous work based on manual processing, demonstrating the feasibility of automated contactless pulse pressure estimation from $RGB$ videos.