Non-contact heart rate measurement method and system based on face video image

A video image, non-contact technology, applied in the measurement of pulse rate/heart rate, character and pattern recognition, instruments, etc., can solve the problems of measurement stability, different regions, and the accuracy of measurement, so as to achieve convenient measurement, Avoid the effect of affecting

Pending Publication Date: 2020-01-03
SHANGHAI BERRY ELECTRONICS TECH
View PDF7 Cites 14 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, when the object under test is in a natural state, the face inevitably moves. Using the face detection algorithm to select the face area will bring about the problem of different areas selected by different frames, which will affect the accuracy of the measurement.
In addition, different ambient light will affect the signal-to-noise ratio of the measurement signal, which will affect the measurement stability

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Non-contact heart rate measurement method and system based on face video image
  • Non-contact heart rate measurement method and system based on face video image
  • Non-contact heart rate measurement method and system based on face video image

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0038] Such as figure 1 As shown, a non-contact heart rate measurement method based on face video images includes the following steps:

[0039] S101: Acquire multiple frames of RGB images;

[0040] In practical applications, the acquisition of multiple frames of RGB images specifically includes: turning on the camera, and extracting the RGB images from the acquired video.

[0041] In practical applications, the frame rate of the camera is usually set at 10 to 60 frames per second, and the embodiment of the present invention takes 30 frames per second as an example.

[0042]S102: Search the face area of ​​the RGB image in a single frame and determine the cheek center area as the face area of ​​interest ROI1, and perform spatial pixel averaging on the green channel of ROI1 to obtain the average value s1 i ;

[0043] In practical applications, the face area of ​​the RGB image is searched in combination with the Adaboost algorithm and the pyramid map, and the face area of ​​the...

Embodiment 2

[0072] Such as image 3 As shown, a non-contact heart rate measurement system based on face video images has the following modules:

[0073] Image acquisition module 1, used to collect video, and be divided into multi-frame RGB images;

[0074] The face feature extraction module 2 is used to extract image face feature points, determine the face area of ​​interest, and perform spatial pixel averaging on the green channel to obtain an average value;

[0075] The background area extraction module 3 is used to extract the background area of ​​interest in the image, and perform spatial pixel averaging on the green channel to obtain an average value;

[0076] The integration module 4 is used to integrate the pixel average value of each frame of RGB image to obtain an effective signal flow and a reference noise signal flow;

[0077] The signal flow processing module 5 is used to normalize the effective signal flow and the reference noise signal flow;

[0078] The denoising module ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses a non-contact heart rate measurement method based on a face video image. The method comprises the following steps: acquiring multiple frames of RGB images; searching a face area of the single-frame RGB image and determining a cheek center area as an interested face area ROI1, and performing space pixel averaging on a green channel of the ROI1 to obtain an average value s1i;extracting a part of fixed background area of the single-frame RGB image as an interested background area ROI2, and performing space pixel averaging on a green channel of the ROI2 to obtain an average value s2i; integrating the plurality of s1i to obtain an effective signal flow s1, and integrating the plurality of s2i to obtain a reference noise signal flow s2; performing normalization processing on the effective signal flow s1 and the reference noise signal flow s2, and then performing noise reduction to obtain a reconstructed signal flow sign; and calculating a heart rate value according to the reconstructed signal flow sign. According to the invention, the problems of low face motion and signal-to-noise ratio and the like in heart rate monitoring based on the face video image can be effectively solved.

Description

technical field [0001] The invention relates to the fields of digital image processing technology and digital signal processing technology, in particular to a non-contact heart rate measurement method and system based on human face video images. Background technique [0002] Heart rate refers to the number of times the heart beats per minute, and it is one of the important physiological parameters of the human body. Resting heart rate refers to the heart rate when a person is awake, inactive, and in a quiet state. Resting heart rate reflects a person's state of health and can vary with age, gender, and other physiological conditions. Studies have shown that people with high resting heart rates are more likely to die from heart disease. Real-time monitoring of heart rate can help people understand changes in their physical condition, reduce the occurrence of accidents, and is of great significance to the prevention and control of cardiovascular diseases. [0003] Usually p...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/00G06K9/32A61B5/024
CPCA61B5/024G06V40/168G06V40/171G06V10/25
Inventor 吴华健周梅尹学志王东力
Owner SHANGHAI BERRY ELECTRONICS TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap