Algorithmic Principles of Remote PPG

TLDR

The model’s insights can inform the design of robust or application‑specific rPPG solutions. The paper introduces a mathematical model of skin reflection properties to explain existing rPPG pulse‑extraction choices and guide the design of new methods. The authors construct the model and use it to design an alternative rPPG method that projects onto a plane orthogonal to skin tone for pulse extraction. Benchmarking many rPPG methods demonstrates that their relative merits are captured by the proposed model.

Abstract

This paper introduces a mathematical model that incorporates the pertinent optical and physiological properties of skin reflections with the objective to increase our understanding of the algorithmic principles behind remote photoplethysmography (rPPG). The model is used to explain the different choices that were made in existing rPPG methods for pulse extraction. The understanding that comes from the model can be used to design robust or application-specific rPPG solutions. We illustrate this by designing an alternative rPPG method, where a projection plane orthogonal to the skin tone is used for pulse extraction. A large benchmark on the various discussed rPPG methods shows that their relative merits can indeed be understood from the proposed model.