EPMD: A Multimodal Event-RGB Dataset for Non-contact Pulse Wave Reconstruction (Part 1 of 9)

The Event-Pulse Multimodal Dataset (EPMD) is a comprehensive dataset designed for non-contact high-fidelity pulse wave reconstruction and heart rate estimation. This dataset aims to exploit the synergy between frame-based integral imaging and neuromorphic event-based differential sensing for physiological measurement. The dataset comprises 195 multimodal recordings (68 seconds each) collected from 83 subjects. For each recording, the data acquisition system simultaneously captures: Wrist Event Streams: Captured using a high-speed event camera (Prophesee EVK4) focusing on the radial artery region, with a spatial resolution of 1280 × 720 and a timestamp precision of 1 µs. A low-power continuous-wave laser pointer (660 nm) is used as an active illumination source to enhance the event camera's sensitivity to pulse-induced micro-motions on the skin. Facial RGB Videos: Recorded using an industrial-grade RGB camera (FLIR BFS-U3-31S4C-C) at an original resolution of 2048 × 1536 and 30 Hz (downsampled and compressed to 640 × 480 for the released dataset). These are designed for traditional remote photoplethysmography (rPPG) extraction methods (e.g., CHROM, ICA, POS). Ground-Truth PPG: High-fidelity contact-based photoplethysmography (PPG) waveforms and heart rate (HR) recorded synchronously at 60Hz using a clinically validated contact-type finger-clip pulse oximeter (CONTEC CMS50E). All devices are coordinated by a laptop for synchronous start/stop control and data recording. The dataset captures diverse physiological states, including resting and post-exercise conditions, providing a standardized benchmark for developing and evaluating event-camera-driven biomedical signal processing and multimodal (Event-RGB) fusion networks. Note: Due to file size limits, this dataset is divided into 9 independent parts. Each part contains a distinct set of subjects with complete synchronized multimodal data. This is Part 1.