Towards Accurate Heart Rate Measurement from Ultra-Short Video Clips via Periodicity-Guided rPPG Estimation and Signal Reconstruction

2025-06-27

AI Summary

Accurate heart rate (HR) estimation from ultra-short (2-second) video clips remains challenging due to insufficient cardiac cycles and spectral leakage, leading to low precision in remote photoplethysmography (rPPG). Method: This paper proposes a periodicity-guided rPPG signal estimation and reconstruction framework. It incorporates a periodicity-constrained module into the rPPG estimation network to enforce physiological rhythm consistency in short-duration signals. Furthermore, it introduces a generative-model-based signal extrapolation mechanism that imposes periodic priors in the frequency domain to reconstruct long, coherent rPPG waveforms, thereby enhancing HR estimation robustness. Contribution/Results: Evaluated on four public benchmark datasets, the method achieves state-of-the-art performance, significantly outperforming existing approaches. It is the first to enable high-accuracy and high-stability HR measurement from 2-second videos, establishing a new paradigm for real-time, contactless physiological monitoring.

Technology Category

• Computer Vision: Video Understanding & Activity Analysis
• Planning, Routing, and Scheduling: Activity and Plan Recognition
• Intelligent Robots: State Estimation

Application Category

• Security and Privacy: Large-scale security measurements
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs

Abstract

Many remote Heart Rate (HR) measurement methods focus on estimating remote photoplethysmography (rPPG) signals from video clips lasting around 10 seconds but often overlook the need for HR estimation from ultra-short video clips. In this paper, we aim to accurately measure HR from ultra-short 2-second video clips by specifically addressing two key challenges. First, to overcome the limited number of heartbeat cycles in ultra-short video clips, we propose an effective periodicity-guided rPPG estimation method that enforces consistent periodicity between rPPG signals estimated from ultra-short clips and their much longer ground truth signals. Next, to mitigate estimation inaccuracies due to spectral leakage, we propose including a generator to reconstruct longer rPPG signals from ultra-short ones while preserving their periodic consistency to enable more accurate HR measurement. Extensive experiments on four rPPG estimation benchmark datasets demonstrate that our proposed method not only accurately measures HR from ultra-short video clips but also outperform previous rPPG estimation techniques to achieve state-of-the-art performance.

Problem

• Accurate HR measurement from ultra-short 2-second video clips
• Overcome limited heartbeat cycles in ultra-short clips
• Mitigate spectral leakage for precise rPPG signal reconstruction

Innovation

• Periodicity-guided rPPG estimation for ultra-short videos
• Generator reconstructs longer rPPG signals accurately
• State-of-the-art HR measurement from 2-second clips