GRGB rPPG: An Efficient Low-Complexity Remote Photoplethysmography-Based Algorithm for Heart Rate Estimation.

Area of Science:

• Biomedical Engineering
• Signal Processing
• Computer Vision

Background:

• Remote photoplethysmography (rPPG) contactless technology extracts physiological data from facial videos.
• Existing rPPG methods often rely on complex algorithms or machine learning to process RGB signals.
• Variations in skin surface luminance are key to extracting health parameters like heart rate.

Purpose of the Study:

• To investigate simple, effective methods for converting RGB video signals to rPPG signals without complex mathematical models.
• To introduce and evaluate a novel GRGB rPPG method.
• To assess the robustness and accuracy of the proposed method against existing techniques.

Main Methods:

• Exploration of direct RGB signal transformations for rPPG extraction.
• Development and implementation of the GRGB rPPG method.
• Comparative analysis against established rPPG methods and machine learning-based approaches.

Main Results:

• The proposed GRGB rPPG method demonstrated superior performance compared to most machine-learning-based rPPG methods.
• The GRGB method exhibited robustness against variations in indoor lighting and participant motion.
• Accurate heart rate estimation was achieved, surpassing well-established rPPG techniques.

Conclusions:

• Simple RGB signal processing can yield effective rPPG-based heart rate monitoring.
• The GRGB rPPG method offers a promising, robust, and accurate alternative to complex existing approaches.
• Further research is recommended to explore the full potential and applications of this simplified rPPG technique.