An Open Framework for Remote-PPG Methods and Their Assessment

Giuseppe Boccignone,Alessandro D'Amelio,Giuliano Grossi,Raffaella Lanzarotti,Donatello Conte,Vittorio Cuculo

doi:10.1109/access.2020.3040936

Abstract

This paper presents a comprehensive framework for studying methods of pulse rate estimation relying on remote photoplethysmography (rPPG). There has been a remarkable development of rPPG techniques in recent years, and the publication of several surveys too, yet a sound assessment of their performance has been overlooked at best, whether not undeveloped. The methodological rationale behind the framework we propose is that in order to study, develop and compare new rPPG methods in a principled and reproducible way, the following conditions should be met: 1) a structured pipeline to monitor rPPG algorithms’ input, output, and main control parameters; 2) the availability and the use of multiple datasets; and 3) a sound statistical assessment of methods’ performance. The proposed framework is instantiated in the form of a Python package named pyVHR (short for Python tool for Virtual Heart Rate), which is made freely available on GitHub ( github.com/phuselab/pyVHR ). Here, to substantiate our approach, we evaluate eight well-known rPPG methods, through extensive experiments across five public video datasets, and subsequent nonparametric statistical analysis. Surprisingly, performances achieved by the four best methods, namely POS, CHROM, PCA and SSR, are not significantly different from a statistical standpoint higighting the importance of evaluate the different approaches with a statistical assessment.

Highlights

Heart beats cause capillary dilation and constriction that, in turn, modulate the transmission or reflection of visible light emitted to and detected from the skin
To overcome these problems and promote the development of new methods and their experimental analysis, we propose a framework supporting the main steps of the remote PPG (rPPG)-based pulse rate recovery, together with a sound statistical assessment of methods’ performance
To improve the SNR of the signal, the input video sequence is divided into smaller temporal intervals and pulse rate is estimated from the short video intervals; the final signal is derived by overlap-adding the partial segments

Summary

Introduction

Heart beats cause capillary dilation and constriction that, in turn, modulate the transmission or reflection of visible (or infra-red) light emitted to and detected from the skin. An advancement towards contactless technology is given by the possibility of measuring backscattered light remotely using a RGB-video camera Such remote PPG (rPPG) measurement, formerly proposed in [3]– [5], is required in particular applications where contact has to be prevented for some reasons (e.g. surveillance, fitness, health, emotion analysis) [6]–[9]. All these works postulate that the RGB temporal traces can produce a time signal which is very close to the waveforms generated by classical PPG sensors. Standardizing such procedures would allow to set up a fair comparison for all the rPPG methods involved in the analysis

Objectives

Methods

Findings

Conclusion