Related Experiment Video
Updated: May 24, 2025
10:14
Author Spotlight: Ex Vivo OCT-Based Multimodal Imaging of Human Donor Eyes for Research into Age-Related Macular Degeneration
Published on: May 26, 2023
3.0K
Illumination-robust Camera-PPG via Skin-Guided Auto-Exposure
Summary
This study introduces Skin-Guided Auto-Exposure (Skin-AE) to improve remote photoplethysmography (rPPG) signal quality. Skin-AE enhances heart rate measurement accuracy under challenging lighting conditions.
Area of Science:
- Biomedical Engineering
- Signal Processing
- Computer Vision
Background:
- Remote photoplethysmography (rPPG) methods struggle with varying lighting, particularly frontal and backlighting.
- Accurate rPPG signal extraction is crucial for non-contact physiological monitoring.
Purpose of the Study:
- To propose and evaluate a novel Skin-Guided Auto-Exposure (Skin-AE) strategy for enhancing rPPG signal quality.
- To improve the robustness of rPPG measurements under adverse lighting conditions.
Main Methods:
- Developed Skin-AE to control camera exposure settings in real-time using facial skin intensity.
- Employed a Proportional-Integral-Derivative (PID) algorithm for dynamic exposure time adjustment based on facial brightness.
- Tested Skin-AE's performance against existing Global-AE algorithms.
Main Results:
- Skin-AE significantly improved rPPG signal extraction quality under frontal and backlighting.
- Achieved a heart rate measurement accuracy of 94.25% with Skin-AE.
- Outperformed the Global-AE algorithm, which yielded 57.96% accuracy.
Conclusions:
- Skin-AE effectively enhances rPPG signal measurement accuracy in challenging lighting.
- The proposed method offers a robust solution for real-time, non-contact heart rate monitoring.
