A deep learning-based event camera pulse wave detection method

By combining event cameras and deep learning networks, the problem of insufficient signal quality in pulse wave detection under complex environments has been solved, achieving high-precision pulse wave signal recovery and physiological index calculation, thus improving the reliability of non-contact health monitoring.

CN121867722BActive Publication Date: 2026-09-22TAIYUAN UNIVERSITY OF TECHNOLOGY
3 Cites 0 Cited by

Patent Information

Application Number
CN202610022029.2
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2026-01-08
Publication Date
2026-09-22
Estimated Expiration
2046-01-08

AI Technical Summary

Technical Problem

Existing non-contact pulse wave detection technologies struggle to reliably extract high-quality pulse pulsation optical information in complex environments. Traditional cameras suffer from insufficient temporal resolution and dynamic range, and there is a lack of effective solutions for recovering continuous physiological waveforms from sparse event streams.

Method used

Pulse wave data was acquired using an event camera and preprocessed and reconstructed using a deep learning network, including region of interest extraction, time binning, and standardization. Multi-scale features were extracted using a 3D convolutional neural network and sparse attention mechanism. Temporal modeling was performed using an improved time-series converter and gated recurrent units. Supervised training was conducted using photoplethysmography signals to ensure high fidelity of the pulse wave signal and accuracy of physiological indicators.

Benefits of technology

Under complex lighting and environmental fluctuations, high signal-to-noise ratio pulse wave signal recovery was achieved, ensuring accurate calculation of physiological indicators such as heart rate and heart rate variability, and enhancing the clinical reference value of non-contact health monitoring.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The present application belongs to the field of physiological signal processing and artificial intelligence technology, and specifically relates to an event camera pulse wave detection method based on deep learning, aiming to realize reliable and high-precision non-contact pulse wave detection in complex real scenes. The method comprises collecting event stream data of the radial artery region of the wrist of a subject by using an event camera; wherein the event stream data refers to a collection of event signals containing pixel coordinates, time stamps and polarity information of events; performing a preprocessing operation on the event stream data to obtain a preprocessed count signal; the preprocessing includes region of interest extraction, time binning, detrending and standardization; inputting the preprocessed count signal into a deep learning network to recover the pulse wave signal in an end-to-end manner; using a photoplethysmography signal to supervise the training of the deep learning network, and calculating physiological indicators based on the recovered pulse wave signal.
Need to check novelty before this filing date? Find Prior Art