A Reproducible Study on Remote Heart Rate Measurement

TL;DR

This study evaluates the reproducibility of remote heart rate measurement methods using a new public database and open-source algorithms, revealing current techniques lack sufficient accuracy for real-world application.

Contribution

The paper introduces a new publicly available database and open-source implementations of state-of-the-art algorithms for reproducible evaluation in rPPG research.

Findings

None of the evaluated algorithms achieved sufficient accuracy for real-world use.

The new database enables standardized benchmarking of rPPG methods.

Open-source implementations facilitate reproducibility and further research.

Abstract

This paper studies the problem of reproducible research in remote photoplethysmography (rPPG). Most of the work published in this domain is assessed on privately-owned databases, making it difficult to evaluate proposed algorithms in a standard and principled manner. As a consequence, we present a new, publicly available database containing a relatively large number of subjects recorded under two different lighting conditions. Also, three state-of-the-art rPPG algorithms from the literature were selected, implemented and released as open source free software. After a thorough, unbiased experimental evaluation in various settings, it is shown that none of the selected algorithms is precise enough to be used in a real-world scenario.