Non-contact video-based vital sign monitoring using ambient light and auto-regressive models

TLDR

Remote sensing of reflectance photoplethysmograms with a video camera positioned about 1 m from a patient’s face offers a promising non‑contact method for vital‑sign monitoring, though most studies have been limited to volunteers in controlled settings. The study aims to develop a technique that cancels aliased frequency components caused by artificial light flicker using auto‑regressive modelling and pole cancellation. The technique achieves this by applying auto‑regressive modelling to the video signal and performing pole cancellation to remove the aliased frequencies. The method yielded accurate heart‑rate and respiratory‑rate estimates from haemodialysis patients, with mean absolute errors comparable to pulse‑oximeter measurements, enabled spatial mapping of these signals via AR coefficients, matched chest‑belt respiratory‑rate accuracy, and allowed oxygen‑saturation tracking during obstructive sleep apnoea using calibrated colour‑channel ratios.

Abstract

Remote sensing of the reflectance photoplethysmogram using a video camera typically positioned 1 m away from the patient's face is a promising method for monitoring the vital signs of patients without attaching any electrodes or sensors to them. Most of the papers in the literature on non-contact vital sign monitoring report results on human volunteers in controlled environments. We have been able to obtain estimates of heart rate and respiratory rate and preliminary results on changes in oxygen saturation from double-monitored patients undergoing haemodialysis in the Oxford Kidney Unit. To achieve this, we have devised a novel method of cancelling out aliased frequency components caused by artificial light flicker, using auto-regressive (AR) modelling and pole cancellation. Secondly, we have been able to construct accurate maps of the spatial distribution of heart rate and respiratory rate information from the coefficients of the AR model. In stable sections with minimal patient motion, the mean absolute error between the camera-derived estimate of heart rate and the reference value from a pulse oximeter is similar to the mean absolute error between two pulse oximeter measurements at different sites (finger and earlobe). The activities of daily living affect the respiratory rate, but the camera-derived estimates of this parameter are at least as accurate as those derived from a thoracic expansion sensor (chest belt). During a period of obstructive sleep apnoea, we tracked changes in oxygen saturation using the ratio of normalized reflectance changes in two colour channels (red and blue), but this required calibration against the reference data from a pulse oximeter.