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

Non-contact type heart rate measuring method based on convolutional neural network

A convolutional neural network, non-contact technology, applied in the field of non-contact physiological signal detection and analysis, can solve problems such as the difficulty of non-contact heart rate measurement

Active Publication Date: 2019-06-07
HEFEI UNIV OF TECH
View PDF5 Cites 19 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Non-contact heart rate measurement directly from video containing scenes such as dramatic ambient light changes, facial expressions, or head movements is difficult because the mapping from video images to heart rate values ​​is non-linear

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 type heart rate measuring method based on convolutional neural network
  • Non-contact type heart rate measuring method based on convolutional neural network
  • Non-contact type heart rate measuring method based on convolutional neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0062] In this embodiment, a non-contact heart rate measurement method based on convolutional neural network, such as figure 1 shown, including the following steps:

[0063] Step 1. Construct a pre-training image reflecting the change of human heart rate according to the peak-to-peak distance information of the ECG signal or BVP signal. The complete pre-training image generation process is as follows: figure 2 shown;

[0064] Step 1.1, take 10 seconds of ECG signal or BVP signal for peak detection, and obtain the sequence of peak positions;

[0065] Then calculate the difference between adjacent peaks to obtain the peak-to-peak interval sequence, which is recorded as A=[A 1 ,A 2 ,...,A N-1 ];A N-1 Indicates the difference between the Nth peak position and the N-1th peak position in the peak position sequence;

[0066] Step 1.2, using the peak-to-peak interval sequence A to construct the first key point sequence C 1 and the second keypoint sequence C 2 , respectively d...

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 type heart rate measuring method based on convolutional neural network. The non-contact heart rate measuring method comprises the steps of 1, according to the peak-to-peak value spacing information of an ECG signal or a BVP signal, constructing a pre-training image for reflecting the heart rate changes of a human body; 2, adjusting the structure of a model, and initializing the convolutional neural network through parameters which are pre-trained on an ImageNet data set; 3, inputting the pre-trained image as a training set into the convolutional neural network for training, and regulating the parameters of the network; 4, generating a time and space characteristic image for reflecting the heart rate changes of the human body through real human face videos; and 5, inputting the time and space characteristic image into the convolutional neural network for training, adjusting the parameters of the network, and finally obtaining the optimal heart rateforecasting model. The non-contact type heart rate measuring method disclosed by the invention can improve the accuracy and the robustness of heart rate measurement under complex scene.

Description

technical field [0001] The invention relates to the technical field of non-contact physiological signal detection and analysis, in particular to a non-contact heart rate measurement method based on a convolutional neural network. Background technique [0002] Heart rate is an important physiological parameter that reflects the physiological and emotional activities of the human body. The measurement of heart rate can be used for training assistance, health monitoring and clinical care. Compared with the discomfort caused by clinical contact heart rate monitoring equipment, the non-contact heart rate measurement method can measure heart rate through ordinary cameras, which is very convenient and easy to implement. [0003] Traditional non-contact heart rate measurement methods mainly include methods based on color difference model and methods based on blind source separation technology, etc. These technologies are mainly based on the combination of hand-designed features and ...

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): A61B5/024A61B5/0402A61B5/00
Inventor 宋仁成张森乐陈勋成娟李畅刘爱萍刘羽
Owner HEFEI UNIV OF TECH
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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com