Non-contact visual heart rate detection method for eliminating motion noise of video ballistocardiogram signal

A cardiac shock signal, non-contact technology, applied in the field of biomedical signal processing, can solve problems such as interference without considering motion noise

Active Publication Date: 2020-11-27
HEFEI UNIV OF TECH
View PDF3 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Their method does not take into account the interference of motion noise, such as: rigid motion (voluntary head movement) or non-rigid motion (facial expression) interference
Since the slight mechanical motion of the head caused b

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 visual heart rate detection method for eliminating motion noise of video ballistocardiogram signal
  • Non-contact visual heart rate detection method for eliminating motion noise of video ballistocardiogram signal
  • Non-contact visual heart rate detection method for eliminating motion noise of video ballistocardiogram signal

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0033] In this embodiment, a non-contact heart rate detection method for eliminating the motion noise of the video cardiac shock signal is to first obtain the first frame of the video image and determine the region of interest and the feature points of the face, and then use the tracking algorithm to track the feature points , for different facial regions of interest, delete the abnormal feature point trajectories, and then use the two datasets of feature point lateral motion trajectory signal and longitudinal motion trajectory signal as the input of canonical correlation analysis, and then set the canonical correlation variable to 0 according to the specified rules And get the longitudinal motion trajectory signal to remove the rigid motion noise, then perform detrending and band-pass filtering processing, and then use the principal component analysis method to reduce the dimensionality, and select the first five principal components as a data set, the two faces of interest Th...

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 visual heart rate detection method for eliminating motion noise of a video ballistocardiogram signal. The method comprises the following steps that firstly, a face region of interest and feature points in the region are acquired; transverse and longitudinal coordinate motion track signals of the feature points are obtained by adopting a tracking algorithm; twosets are respectively constituted, rigid and non-rigid motion noise is removed through two-step canonical correlation analysis; pulse signals are screened out from typical correlation variables obtained through typical correlation analysis in the second step, the heart rate is extracted from the pulse signals through a power spectrum analysis method, and finally abnormal heart rate values are found out according to heart rate continuity and replaced with correct heart rate values. According to the invention, the interference of rigid and rigid motion noise can be removed, so that the accuracyof non-contact video heart rate detection is improved.

Description

technical field [0001] The invention belongs to the technical field of biomedical signal processing, and in particular relates to a non-contact heart rate detection method for eliminating motion noise of a video cardiac shock signal. Background technique [0002] Heart rate is one of the important physiological parameters of the human body, and its long-term detection is of great significance to the early prevention of cardiovascular diseases, clinical diagnosis, and monitoring of human health. Traditional clinical heart rate detection methods require related equipment such as electrocardiograph electrodes or other sensors to be in contact with the human body, which can easily cause physical discomfort and is not suitable for some special constitutions such as sensitive skin, nor for infants or burn patients. The heart rate detection method can overcome these deficiencies of the traditional contact method. The video-based heart rate detection method is a non-contact heart r...

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): G06T5/00G06T7/246G06K9/00G06K9/32G06K9/62A61B5/024
CPCG06T5/002G06T7/246A61B5/024G06T2207/10016G06T2207/30201G06V40/168G06V10/25G06F18/2135
Inventor 宋仁成李吉吉成娟李畅刘羽陈勋
Owner HEFEI UNIV OF 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