Heart rate and respiration rate detection method and system and computer storage medium

A detection method and respiration rate technology, applied in the field of image processing, can solve the problems of lower value, large measurement error, and difficulty in meeting the requirements of high robustness of physiological parameters, so as to ensure robustness, multi-dimensionality and accuracy, Reduces the effect of lighting non-uniformity

Active Publication Date: 2021-08-03
CENT SOUTH UNIV +1
View PDF6 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

At this time, changes in facial expressions, mouth opening and blinking often occur, and lighting conditions may change at any time, thus bringing strong interference factors, causing considerable measurement errors to the actual detection results, and it is difficult to meet the long-range measurement of physiological parameters.

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
  • Heart rate and respiration rate detection method and system and computer storage medium
  • Heart rate and respiration rate detection method and system and computer storage medium
  • Heart rate and respiration rate detection method and system and computer storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0029] This embodiment discloses a heart rate and respiration rate detection method, such as Figure 1 to Figure 5 shown, including the following steps:

[0030] (1), video and heart rate and respiration rate data acquisition. The face video is recorded by the camera, and a video data set composed of multiple frame images is obtained from the acquired video stream. Set the video recording frame rate to x frames per second, record t duration, and get m=x×t frames of images in total. While collecting the video, use the heart rate and respiration rate measurement device to obtain the heart rate and respiration rate values ​​synchronized with the video in real time.

[0031] (2) Subset division of video images. Video image acquisition takes a long time, and it is difficult to avoid changes in the position of the face and lighting conditions. Divide the m frames of images into n subsets in time sequence, denoted as D 1 ,D 2 ,D 3 ,D 4 ,...,D n , each set contains frame im...

Embodiment 2

[0050] Corresponding to the above method embodiments, this embodiment also discloses a heart rate and respiration rate detection system, including a memory, a processor, and a computer program stored in the memory and operable on the processor, and the processor executes the When describing a computer program, implement the steps of the following corresponding methods:

[0051] Gather m frames of human face video images, and measure the heart rate and respiration rate values ​​synchronously with the human face video images with a measuring device;

[0052] The collected video images are evenly divided into n sub-sets according to the time sequence; and for each frame image in each sub-set, four regions of interest (forehead, left cheek, right cheek and side face) are extracted with a square marquee, and compared with the same sub-set The coordinates, height and width of the upper left corner of the series of boxes corresponding to the same region of interest in the collection ...

Embodiment 3

[0059] This embodiment discloses a computer storage medium on which a computer program is stored, and when the program is executed by a processor, the corresponding steps of the above method and system are realized.

[0060] In summary, the heart rate and respiration rate detection method, system and computer storage medium disclosed in the embodiments of the present invention have the following beneficial effects:

[0061] The present invention extracts image data sets and performs model training based on four areas of forehead, left cheek, right cheek, and side face. The image noise in the collection is affected by facial expressions, actions, and postures; on the other hand, considering that the illumination of the video acquisition is uneven and changes globally at low frequency, the illumination of the local area can be considered as a constant, and the removal network The average value of grid data also removes the local constant value of illumination, so the signal data...

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 relates to the technical field of image processing, and discloses a heart rate and respiration rate detection method and a system and a computer storage medium so as to improve robustness. The method comprises the steps: image data set extraction and model training are carried out based on four areas of a forehead, a left cheek, a right cheek and a side face, on one hand, whether the four areas of interest move or not is analyzed, and image noise influenced by facial expressions, actions, postures and the like in the set is eliminated; second, in consideration of the fact that illumination of video collection is uneven and changes globally at low frequency, illumination of a local area can be regarded as a constant, the mean value of grid data is removed, and the local constant value of illumination is also removed, so that a signal data sequence obtained after mean value removal processing can weaken the influence of illumination non-uniformity; and third, the data sequences with high correlation screened out from the regions of interest are summarized into an effective data sequence set, so that the multidimensional and accuracy of the data are further ensured.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a heart rate and respiration rate detection method, system and computer storage medium. Background technique [0002] Heart rate and respiration rate are important physiological parameters of the human body, which are closely related to the health of the cardiovascular system of the human body. Sudden onset and high mortality are important features of cardiovascular diseases. Long-term and accurate monitoring of changes in the heart rate and respiration rate of the human body can provide an effective early warning of sudden cardiovascular diseases, thereby intervening in time and effectively reducing mortality. Non-contact or remote detection of heart rate and respiratory rate is a current research hotspot. This type of method is mainly realized by photoplethysmography based on video images. It has remote real-time detection, does not need to wear a detection device, an...

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
IPC IPC(8): A61B5/0205
CPCA61B5/0077A61B5/0205A61B5/7264
Inventor 喻罡肖嘉莹孙凯蒋召杰袁楚琪朱宜飞
Owner CENT SOUTH 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