HBP-net for robust remote heart rate estimation using heartbeat probability

TL;DR

This paper introduces HBP-Net, a new method for accurately estimating heart rate from facial videos, even during motion and lighting changes, by predicting heartbeat probability directly.

Contribution

The novel contribution is reframing heart rate estimation as a heartbeat probability detection problem, bypassing traditional signal reconstruction.

Findings

HBP-Net achieves competitive accuracy under static and motion conditions across multiple datasets.

The method demonstrates state-of-the-art performance on motion-intensive benchmark datasets.

An open-source code and unified evaluation framework are released for community use.

Abstract

Remote photoplethysmography (rPPG) enables contactless heart rate monitoring but remains vulnerable to motion and lighting changes. We address this by reframing heart rate estimation as a heartbeat detection problem, bypassing the need to reconstruct full blood volume pulse signals. Our approach, HBP-Net, predicts heartbeat probability directly from facial video using a spatiotemporal attention architecture, improving robustness while reducing computational complexity. Evaluated across multiple datasets—including a new motion-challenged benchmark—HBP-Net achieves competitive accuracy under static conditions and maintains performance as motion increases. This shift from signal reconstruction to probabilistic event detection offers a conceptually simpler and more resilient framework for rPPG. The method advances the feasibility of reliable, camera-based vital sign monitoring in real-world settings such as telehealth, fitness tracking, and continuous patient assessment.

•Introduces a probabilistic approach for robust remote heart rate estimation•Achieves reliable performance under real-world motion and lighting changes•Demonstrates state-of-the-art performance on motion-intensive benchmark datasets•Releases open-source code and a unified evaluation framework for the community

Introduces a probabilistic approach for robust remote heart rate estimation

Achieves reliable performance under real-world motion and lighting changes

Demonstrates state-of-the-art performance on motion-intensive benchmark datasets

Releases open-source code and a unified evaluation framework for the community

Health sciences

Figures