An efficient heart rate measurement system that resists natural head movements

A heart rate and natural technology, applied in the field of effective heart rate measurement system, can solve problems such as not being able to require human faces, not moving, and affecting measurement accuracy

Active Publication Date: 2021-08-20
YANGO UNIV
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] In recent years, the use of computer vision technology to measure physiological signals such as heart rate has attracted widespread attention because it is cheap and suitable for long-term monitoring. This method uses an ordinary cheap camera to obtain vital signs from the face to measure heart rate. Generally speaking, this The method is to obtain a region of interest (Region of Interest; ROI) from the face, and then use the Fast Fourier Transform (Fast Fourier Transform) to obtain the frequency spectrum to calculate the heart rate. However, this method usually needs to be manually defined on the face A fixed ROI, and the subject's face is required to be still; if the face moves, the measurement accuracy will be seriously affected. This method is not suitable for real application situations, because even if the person is still, There will still be natural movement of the head, especially if you want to monitor and measure heart rate for a long time, you can't ask the person's face to face the camera without moving

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
  • An efficient heart rate measurement system that resists natural head movements
  • An efficient heart rate measurement system that resists natural head movements
  • An efficient heart rate measurement system that resists natural head movements

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0030] see image 3 , an efficient heart rate measurement system that resists natural head movements, comprising the following steps:

[0031] Step 1: Detect and track the feature points of the face. The face detection uses the features and the classifier HOG (Histogram of Oriented Gradient) SVM (Support Vector Machine) to get it, and then uses the shape detection method to detect the side face 68 feature points, face tracking Utilizes the golden ratio of the standard human face, design the search box and narrow the search range to improve the tracking speed, 68 feature points are distributed on the eyes, mouth, nose and face contour of the face , from the human face golden ratio map, we know that the width of the human face is about 5 eye widths WEYE, the height is about 3 nose bridge lengths WN, the right eye width WRE=d(36,39), and the left eye width WLE=d (42, 45), WEYE=0.5(WRE+WLE); the height of the bridge of the nose WN=d(33, E), E=0.5(x19+x24), use the golden ratio of...

Embodiment 2

[0049] The experiment was carried out on 15 test subjects respectively, and each test subject carried out 20 measurements, a total of 300 measurement results. The test subjects were all yellow people with different skin tones. The video uses a normal webcam with a resolution of 640 x 480. There are many variations and difficulties in these videos, including changes in camera angles and shooting distances, and the environment of the testees is disturbed by different degrees of light.

[0050] The heart rate measured by this system Heart rate measured with a reference device , find the mean and standard deviation of all test records, and calculate and The correlation coefficient (correlation) and absolute error are as follows

[0051] Correlation coefficient:

Absolute error:

[0052] The optimal position is automatically selected from three ROI positions: the forehead and the left and right cheeks. In order to test this adaptive ROI te...

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 an effective heart rate measurement system that can resist the natural movement of the head, including two processing units: the first unit is for obtaining stable ROI, opening the camera lens, importing real-time images, the system will automatically detect and Track the face and facial feature points. After the face is detected, use the golden ratio of the face to reduce the search frame to increase the tracking speed; design the ROI positions of the region of interest on the forehead, right cheek and left cheek respectively, and use The facial feature points judge the pose of the head movement, and automatically select the most suitable ROI based on this, and use motion filtering to obtain a stable ROI signal. The second unit is the heart rate signal processing. The ROI signal is preprocessed first, and the green channel is taken out from the ROI area for pixel averaging. The average value of each time point is concatenated to form a time series signal, and then standardized processing is used to eliminate light fluctuations. The impact on signal quality highlights the main signal, and after fast Fourier transform and band-pass filtering, the heartbeat data can be calculated.

Description

technical field [0001] The present invention relates to a heart rate measurement system, in particular to an effective heart rate measurement system which can resist the natural movement of the head. Background technique [0002] In recent years, the use of computer vision technology to measure physiological signals such as heart rate has attracted widespread attention because it is cheap and suitable for long-term monitoring. This method uses an ordinary cheap camera to obtain vital signs from the face to measure heart rate. Generally speaking, this The method is to obtain a region of interest (Region of Interest; ROI) from the face, and then use the Fast Fourier Transform (Fast Fourier Transform) to obtain the frequency spectrum to calculate the heart rate. However, this method usually needs to be manually defined on the face A fixed ROI, and the subject's face is required to be still; if the face moves, the measurement accuracy will be seriously affected. This method is n...

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 Patents(China)
IPC IPC(8): A61B5/024
Inventor 张容娟谢朝和王琨刘大茂
Owner YANGO UNIV
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