Non-contact physiological parameter detection method based on improved three-dimensional convolution network
10.3969/j.issn.1005-202X.2025.04.009
- VernacularTitle:基于改进三维卷积网络的非接触式生理参数检测方法
- Author:
Zhanyu XU
1
;
Zhaoxue CHEN
1
Author Information
1. 上海理工大学健康科学与工程学院,上海 200093
- Publication Type:Journal Article
- Keywords:
non-contact type;
heart rate detection;
hybrid attention mechanism;
signal processing
- From:
Chinese Journal of Medical Physics
2025;42(4):479-488
- CountryChina
- Language:Chinese
-
Abstract:
Remote photoplethysmography is a method of measuring physiological parameters such as heart rate from facial video.For overcoming the difficulties in achieving both high accuracy and lightweight by the existing heart rate measurement methods,an improved three-dimensional convolution network model is proposed to realize non-contact physiological parameter detection in facial video.In the pre-processing,YuNet model takes place of the traditional face detector,so that the face region can be recognized quickly and accurately.In addition,attention mechanisms and residual modules are embed into three-dimensional convolution network to extract key channel and spatial features,with long short-term memory networks used as period memory modules to capture long-term dependencies in the data.The experimental results show that the proposed Res-CHATM model achieves excellent results of MAE=2.19 BPM,RMSE=7.02 BPM,C=0.95,and MAE=1.65 BPM,RMSE=3.44 BPM,C=0.98 in the cross experiments on public datasets UBFC-rPPG and PURE for heart rate estimation.The consistency between the predicted value and the real value and the effectiveness of the fusion module are further verified,demonstrating the potential of efficient lightweight model in remote photoplethysmography.
