Automatic and Adaptive Signal- and Background-ROIs With Analytic-Representation-Based Processing for Robust Webcam-Based Heart-Rate Estimation

James John,Syam Krishna,Ramesh R Galigekere

doi:10.1109/access.2020.2973815

Abstract

Determining a suitable, adaptive region of interest (ROI) automatically for extracting information related to cardiac activity (signal-ROI/S-ROI), and another containing information on ambient light-fluctuation (background-ROI/B-ROI, as close as possible to the signal-ROI ), and robust signal processing are important in webcam based heart-rate (HR) estimation – in real life situations. We describe a novel method of automatically determining both the ROIs. The forehead is the candidate for the S-ROI, due to its uniformity and minimum vulnerability for deformation. We first identify the skin-pixels within the face-region detected by the Viola-Jones (VJ) algorithm. The forehead-region, and a uniform sub-rectangle within it not containing hair – determined by using variance as a measure – yields the S-ROI. The B-ROI – consisting of 3 rectangles – each of the same size as that of S-ROI, at the two sides and the top of the VJ-rectangle – is used to generate a reference signal for an adaptive noise-cancellation scheme. The situation arising from (possibly simultaneous) facial expressions deforming the S-ROI , is addressed – by extracting the phase sequence associated with the analytic representation of the signal. Experiments conducted with 21 healthy subjects, using this novel array of techniques, have produced good correspondence with the ground truth obtained from a standard finger-pulse transducer – as reflected by the Bland-Altman plot.

Highlights

Cardiovascular diseases have been the cause of morbidity and mortality throughout the world [1], leading to efforts towards understanding the human cardiovascular system, in terms of the heart rate (HR), and its variability [2]
We investigated the efficacy of B-region of interest (ROI) with one and two sub-regions each, respectively
While the problem arising from a deformation of the SIGNAL ROI (S-ROI) due to involuntary facial expressions has been indicated in the literature, a solution to that – has not been suggested – to the best of our knowledge

Summary

Introduction

Cardiovascular diseases have been the cause of morbidity and mortality throughout the world [1], leading to efforts towards understanding the human cardiovascular system, in terms of the heart rate (HR), and its variability [2]. Estimating HR by a webcam is a topic of current interest, due to low cost and non-contact nature In this context, Verkrussye et al [3] proposed the use of forehead as a region of interest and the green-channel to record the photoplethysmogram, containing information on HR. Poh et al [4], [5] proposed the use of a webcam in ambient light conditions, and independent component analysis (ICA) on the color channels to get information pertaining to HR. They used the central 60% width and the. As discussed in the sequel and ( addressed in this paper), the presence of hair and involuntary facial expressions can affect the cardiac-component – even while

Methods

Results

Discussion

Conclusion