Phase-shifted remote photoplethysmography for estimating heart rate and blood pressure from facial video

2024-01-09

arXiv.org

AI Summary

This study addresses the low accuracy and poor robustness of contactless physiological parameter estimation. We propose a two-stage remote photoplethysmography (rPPG) framework that simultaneously estimates heart rate (HR) and systolic/diastolic blood pressure (SBP/DBP) by extracting phase-shifted rPPG signals from facial and distal (e.g., hand) video regions. Our key innovations include: (1) a phase-shift modeling mechanism; (2) a synergistic dual-network architecture—DRP-Net for HR and BBP-Net for BP estimation; and (3) frame interpolation-based data augmentation combined with bounded sigmoid constraints to enhance BP regression stability. On the MMSE-HR dataset, our method achieves mean absolute errors (MAEs) of 1.78 BPM (HR), 10.19 mmHg (SBP), and 7.09 mmHg (DBP), reducing HR error by 34.31% over the state-of-the-art. On the V4V dataset, the corresponding MAEs are 3.83 BPM, 13.64 mmHg, and 9.40 mmHg, demonstrating both effectiveness and strong generalizability.

Technology Category

• Computer Vision: Biometrics, Face, Gesture & Pose
• Intelligent Robots: State Estimation
• Planning, Routing, and Scheduling: Activity and Plan Recognition

Application Category

• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Security and Privacy: Large-scale security measurements
• Responsible Web: Data and user privacy-enhancing technologies for the Web

Abstract

Human health can be critically affected by cardiovascular diseases, such as hypertension, arrhythmias, and stroke. Heart rate and blood pressure are important biometric information for the monitoring of cardiovascular system and early diagnosis of cardiovascular diseases. Existing methods for estimating the heart rate are based on electrocardiography and photoplethyomography, which require contacting the sensor to the skin surface. Moreover, catheter and cuff-based methods for measuring blood pressure cause inconvenience and have limited applicability. Therefore, in this thesis, we propose a vision-based method for estimating the heart rate and blood pressure. This thesis proposes a 2-stage deep learning framework consisting of a dual remote photoplethysmography network (DRP-Net) and bounded blood pressure network (BBP-Net). In the first stage, DRP-Net infers remote photoplethysmography (rPPG) signals for the acral and facial regions, and these phase-shifted rPPG signals are utilized to estimate the heart rate. In the second stage, BBP-Net integrates temporal features and analyzes phase discrepancy between the acral and facial rPPG signals to estimate SBP and DBP values. To improve the accuracy of estimating the heart rate, we employed a data augmentation method based on a frame interpolation model. Moreover, we designed BBP-Net to infer blood pressure within a predefined range by incorporating a scaled sigmoid function. Our method resulted in estimating the heart rate with the mean absolute error (MAE) of 1.78 BPM, reducing the MAE by 34.31 % compared to the recent method, on the MMSE-HR dataset. The MAE for estimating the systolic blood pressure (SBP) and diastolic blood pressure (DBP) were 10.19 mmHg and 7.09 mmHg. On the V4V dataset, the MAE for the heart rate, SBP, and DBP were 3.83 BPM, 13.64 mmHg, and 9.4 mmHg, respectively.

Problem

• Estimating heart rate and blood pressure non-invasively from facial video
• Overcoming limitations of contact-based sensors for cardiovascular monitoring
• Improving accuracy of remote photoplethysmography using deep learning

Innovation

• Phase-shifted rPPG signals for heart rate estimation
• Dual-stage deep learning framework DRP-Net and BBP-Net
• Frame interpolation data augmentation for accuracy