Non-contact blood pressure measuring equipment based on face video

Abstract

The invention relates to non-contact blood pressure measuring equipment based on a face video. The non-contact blood pressure measuring equipment comprises a face video acquisition terminal, a data enhancement module, a spatial feature processing module and a neural network calculation module, wherein the face video acquisition terminal is used for acquiring the face video and performing ROI splicing and feature extraction on each frame of image in the face video to obtain a feature sequence; the data enhancement module is used for enhancing dimension features of blood volume pulse wave related information in a color space by adopting a YUVT color space according to the feature sequence obtained by the face video acquisition terminal to obtain a video sequence after the dimension features are enhanced; the spatial feature processing module is used for calculating feature vectors of the video sequence after the dimension features are enhanced, splicing the feature vectors of all frames into a spatial-temporal feature map and performing spatial slicing on the spatial-temporal feature map to form a multi-time-domain spatial feature map; the neural network calculation module is used for performing high-dimensional feature extraction on the multi-time-domain spatial feature map and enhancing time-domain feature association of the extracted high-dimensional features by using LSTM to obtain a blood pressure measuring model.

Description

technical field [0001] The invention relates to the technical field of face video feature processing, in particular to a non-contact blood pressure measurement device based on face video. Background technique [0002] Blood pressure is an important physiological parameter of the human body. For a long time, blood pressure measurement is mainly divided into direct measurement method and indirect measurement method. Receptor pulse wave, extract features according to the pulse wave changes, and then use the features to calculate the systolic and diastolic blood pressure of the pulse. [0003] However, the measurement accuracy of the traditional method is easily affected by many factors, such as the professional ability of the surveyor, and the height, weight, age, and measurement environment of the person being measured. In the field of blood pressure measurement, traditional measurement equipment is highly stable, but not easy to carry. Blood pressure measurement equipment ba...

AI Technical Summary

Problems solved by technology

[0003] However, the measurement accuracy of the traditional method is easily affected by many factors, such as the professional ability of the surveyor, and the height, weight, age, and measurement environment of the measured person, etc.

In the field of blood pressure measurement, traditional measurement equipment is stable, but not easy to carry. PPG signal-based blood pressure measurement equipment has many applicable scenarios, but its accuracy and stability need to be improved

Moreover, both traditional measurement equipment and feature extraction measurement equipment based on PPG technology are contact passive measurement, and long-term contact measurement will inevitably cause physical discomfort to the tested personnel.

Images