Adaptive Parameter Optimization for Robust Remote Photoplethysmography

2025-11-26

AI Summary

Existing remote photoplethysmography (rPPG) methods rely on fixed parameters, limiting adaptability to varying illumination conditions and imaging devices. This paper proposes PRISM—a training-free algorithm that jointly and adaptively optimizes signal detrending and chrominance channel mixing based on real-time signal quality assessment—marking the first such approach. Executed entirely on CPU in real time, PRISM achieves both robustness and computational efficiency. On the PURE and UBFC-rPPG benchmarks, it attains mean absolute errors of 0.77 bpm and 0.66 bpm for heart rate estimation, respectively, with accuracy rates of 97.3% and 97.5% within a 5-bpm error threshold. Its core contribution lies in eliminating supervised training: instead, it employs projection-based robust signal mixing to enable end-to-end, online parameter adaptation—substantially enhancing generalizability and deployment flexibility of contactless heart rate monitoring in real-world scenarios.

Technology Category

• Computer Vision: Computational Photography, Image & Video Synthesis
• Machine Learning: Calibration & Uncertainty Quantification
• Intelligent Robots: State Estimation

Application Category

• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

Remote photoplethysmography (rPPG) enables contactless vital sign monitoring using standard RGB cameras. However, existing methods rely on fixed parameters optimized for particular lighting conditions and camera setups, limiting adaptability to diverse deployment environments. This paper introduces the Projection-based Robust Signal Mixing (PRISM) algorithm, a training-free method that jointly optimizes photometric detrending and color mixing through online parameter adaptation based on signal quality assessment. PRISM achieves state-of-the-art performance among unsupervised methods, with MAE of 0.77 bpm on PURE and 0.66 bpm on UBFC-rPPG, and accuracy of 97.3% and 97.5% respectively at a 5 bpm threshold. Statistical analysis confirms PRISM performs equivalently to leading supervised methods ($p > 0.2$), while maintaining real-time CPU performance without training. This validates that adaptive time series optimization significantly improves rPPG across diverse conditions.

Problem

• Optimizes photometric detrending and color mixing adaptively
• Enhances remote photoplethysmography robustness across varied environments
• Achieves unsupervised state-of-the-art performance without training requirements

Innovation

• Training-free online parameter adaptation for rPPG
• Projection-based Robust Signal Mixing (PRISM) algorithm
• Joint optimization of photometric detrending and color mixing