Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

EMPD: An Event-based Multimodal Physiological Dataset for Remote Pulse Wave Detection

Qian Feng, Pengfei Li, Rongshan Gao, Jiale Xu, Rui Gong, Yidi Li

Abstract

Remote photoplethysmography (rPPG) based on traditional frame-based cameras often struggles with motion artifacts and limited temporal resolution. To address these limitations, we introduce EMPD (Event-based Multimodal Physiological Dataset), the first benchmark dataset specifically designed for non-contact physiological sensing via event cameras. The dataset leverages a laser-assisted acquisition system where a high-coherence laser modulates subtle skin vibrations from the radial artery into significant signals detectable by a neuromorphic sensor. The hardware platform integrates a high-resolution event camera to capture micro-motions and intensity transients, an industrial RGB camera to provide traditional rPPG benchmarks, and a clinical-grade pulse oximeter to record ground truth PPG waveforms. EMPD contains 193 valid records collected from 83 subjects, covering a wide heart rate range (40-110 BPM) under both resting and post-exercise conditions. By providing precisely synchronized multimodal data with microsecond-level temporal precision, EMPD serves as a crucial resource for developing robust algorithms in the field of neuromorphic physiological monitoring. The dataset is publicly available at: https://doi.org/10.5281/zenodo.18765701

EMPD: An Event-based Multimodal Physiological Dataset for Remote Pulse Wave Detection

Abstract

Remote photoplethysmography (rPPG) based on traditional frame-based cameras often struggles with motion artifacts and limited temporal resolution. To address these limitations, we introduce EMPD (Event-based Multimodal Physiological Dataset), the first benchmark dataset specifically designed for non-contact physiological sensing via event cameras. The dataset leverages a laser-assisted acquisition system where a high-coherence laser modulates subtle skin vibrations from the radial artery into significant signals detectable by a neuromorphic sensor. The hardware platform integrates a high-resolution event camera to capture micro-motions and intensity transients, an industrial RGB camera to provide traditional rPPG benchmarks, and a clinical-grade pulse oximeter to record ground truth PPG waveforms. EMPD contains 193 valid records collected from 83 subjects, covering a wide heart rate range (40-110 BPM) under both resting and post-exercise conditions. By providing precisely synchronized multimodal data with microsecond-level temporal precision, EMPD serves as a crucial resource for developing robust algorithms in the field of neuromorphic physiological monitoring. The dataset is publicly available at: https://doi.org/10.5281/zenodo.18765701

Paper Structure

This paper contains 13 sections, 4 figures, 2 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Traditional Frame-based rPPG Datasets
  4. The Need for Neuromorphic Benchmarks
  5. The EMPD Dataset
  6. Laser-Assisted Data Acquisition Platform
  7. Experimental Protocol
  8. Dataset Characteristics
  9. Experiments and Baseline Evaluation
  10. Event-Driven Baseline Framework
  11. Signal Validity and Physical Plausibility
  12. Quantitative Comparison and Agreement Analysis
  13. Conclusion and Future Work

Figures (4)

  • Figure 1: Schematic of the pulse signal acquisition system. The system simultaneously records three signal sources: (a) facial video for traditional remote photoplethysmography (rPPG) extraction, (b) contact-based PPG as the ground truth, and (c) wrist event stream for our proposed method.
  • Figure 2: Real-world picture of the experimental equipment. It includes: (1) Prophesee EVK4 event camera; (2) FLIR industrial-grade RGB camera; (3) CONTEC fingertip pulse oximeter; (4) Active laser light source used to enhance micro-motion signals.
  • Figure 3: Histogram of heart rate (BPM) distribution measured by the contact pulse oximeter across 7527 valid samples. Data are stratified by (a) gender (Male vs. Female) and (b) activity state (Rest vs. Exercise).
  • Figure 4: Visualization of event-pulse synchronization. (a) Continuous raw event stream. (b) Magnified cross-sectional view of event bursts. (c) Corresponding circular cross-sections reflecting rhythmic size variations. (d) Ground-truth PPG waveform. Red dashed arrows highlight the temporal alignment between the high-density event bursts and systolic peaks.