A New Framework for Robust Heart Rate Measurement Based on the Head Motion State Estimation

Area of Science:

• Biomedical Engineering
• Physiological Monitoring
• Signal Processing

Background:

• Accurate physiological parameter monitoring is crucial for health management and disease prevention, particularly for cardiovascular conditions.
• Imaging photoplethysmography (iPPG) offers a non-invasive method for physiological monitoring but is susceptible to artifacts from ambient illumination and subject motion.
• Existing iPPG methods require robust solutions to mitigate these common interference sources for reliable heart rate (HR) measurements.

Purpose of the Study:

• To develop and validate a novel framework for robust heart rate (HR) measurement using imaging photoplethysmography (iPPG).
• The proposed framework aims to effectively address and minimize artifacts caused by variations in ambient illumination and subject motion.
• To enhance the accuracy and reliability of non-invasive HR monitoring in real-world scenarios.

Main Methods:

• A novel framework combining the projection-plane-switching (2PS) iPPG method with singular spectrum analysis (SSA) was developed.
• The method involves determining an optimal projection plane based on head motion estimation, projecting normalized RGB signals, and applying alpha-tuning to obtain a pulse signal.
• Singular spectrum analysis (SSA) was subsequently applied to the pulse signal and facial region of interest (ROI) B-channel signals to remove residual artifacts.

Main Results:

• The proposed 2PS-SSA method demonstrated superior agreement in HR measurement compared to five other methods on both self-collected and public PURE databases.
• Bland-Altman analysis indicated low mean biases of 0.59 bpm and 0.034 bpm for the two datasets, respectively.
• The 95% limits of agreement were narrow, ranging from -2.59 bpm to 3.78 bpm and -1.97 bpm to 2.04 bpm, highlighting the method's precision.

Conclusions:

• The developed 2PS-SSA framework provides a robust and accurate solution for heart rate (HR) measurement using iPPG, effectively mitigating illumination and motion artifacts.
• The method shows significant improvements in agreement and precision over existing techniques, making it suitable for reliable physiological monitoring.
• This advancement holds promise for improved non-invasive health monitoring and disease management, particularly for cardiovascular health.