Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Remote photoplethysmography (RPPG)-based self-calibration method of sentiment detection device

A detection device and self-calibration technology, applied in the field of biomedical engineering, can solve the problems of high cost of heart rate monitors, discomfort of subjects, difficulty in entering people's daily life, etc., and achieve high accuracy

Pending Publication Date: 2021-02-02
TIANJIN POLYTECHNIC UNIV
View PDF10 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

With the development of science and technology, people have invented heart rate monitors to measure people's heart rate, but the cost of heart rate monitors is very high, usually only used for clinical monitoring in hospitals, and it is difficult to enter people's daily life
Subsequently, the appearance of the finger-clip heart rate oximeter greatly reduced the cost of equipment on the basis of high measurement accuracy, and it was more convenient to use. As long as the finger-clip heart rate oximeter is clipped on your finger, you can accurately obtain your own However, the use of the finger clip heart rate oximeter must have direct contact with the human body. Long-term contact will cause discomfort to the subjects, so it is not suitable for long-term heart rate measurement

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
  • Remote photoplethysmography (RPPG)-based self-calibration method of sentiment detection device
  • Remote photoplethysmography (RPPG)-based self-calibration method of sentiment detection device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment approach 1

[0018] Step 1: Select a suitable lighting environment, determine the position where the face area can be clearly and relatively completely imaged, and fix the camera;

[0019] Step 2: Start the camera to collect video of the scene in the face area. During the collection process, the face is allowed to move and deflect slightly within the imaging range, and save the collected data as a video file in MP4 format;

[0020] The third step: select the face area of ​​the collected video file, determine the ROI area, and then separate the RGB channels and take the mean value;

[0021] Step 4: Save the obtained RGB values, and continue to process the next frame of data until the total number of video frames is processed, and use matlab software to draw the mean curve of the RGB three channels;

[0022] Step 5: According to the drawn curve, it can be seen that the G channel contains pulse information;

[0023] Step 6: Set the size of the adopted window and the sliding window, and then ...

Embodiment approach 2

[0028] According to the steps of Embodiment 1, 10 adults were tested;

[0029] Step 1: Take a video of 10 adults answering questions normally;

[0030] Step 2: Take a video of 10 adults in a state of lying;

[0031] Step 3: Analyze the video information of answering the question in the normal state, and calculate the emotional impact index H value;

[0032] Step 4: Analyze the video information of answering questions in the state of lying, and calculate the emotional impact index H value;

[0033] Step 5: By comparing the H value, it is found that in the state of lying, the H value of the emotional impact index is a little higher.

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 face video-based self-calibration method of a non-contact heart rate and sentiment detection device. The method comprises the following steps: (1) turning on a camera, and carrying out collection of face videos; (2) performing frame transformation on the collected videos, and determining an a region of interest (ROI); (3) carrying out separation of R, G and B channels onthe ROI; (4) performing normalization processing, independent component analysis and Fourier transformation on separated data, extracting a maximum power spectrum value and a corresponding frequency,extracting a numerical value of a pulse, and storing the numerical value in a pulse array; (4) working out a heart rate number HR=pulse(round((i-450) / 15)+1)*60 according to a formula; (5) working outa heart rate amplitude HRA and heart rate variability HRV according to an extracted heart rate waveform; and (6) establishing a model among the HR, the HRA and the HRV, and working out a sentiment index H=a.HR+b.HRA+c.H.

Description

technical field [0001] The invention relates to a heart rate measurement method based on human face video, which is used to judge human mental health and emotion through the measured heart rate information, and belongs to the related field of biomedical engineering. Background technique [0002] Heart rate is the most basic information of pulse wave and one of the four vital signs of human body. Its stability directly reflects the quality of heart function and is an important physiological index of human health. Heart rate is an important parameter for monitoring cardiovascular disease. At the same time, heart rate is also an important index to guide physical exercise. Kinematic studies have shown that heart rate is one of the more sensitive parameters of physiological changes, and it is also important in criminal investigation methods such as polygraph detection. [0003] The most traditional heart rate detection is obtained by doctors using pulse pulse or auscultation. T...

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): A61B5/024A61B5/16A61B5/00G16H50/20
CPCA61B5/02416A61B5/165A61B5/0033A61B5/0077G16H50/20
Inventor 王慧泉何森田磊赵喆韩嘉文
Owner TIANJIN POLYTECHNIC UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products