CN113397505A - Physiological signal detection method and system - Google Patents

Physiological signal detection method and system Download PDF

Info

Publication number
CN113397505A
CN113397505A CN202110713934.XA CN202110713934A CN113397505A CN 113397505 A CN113397505 A CN 113397505A CN 202110713934 A CN202110713934 A CN 202110713934A CN 113397505 A CN113397505 A CN 113397505A
Authority
CN
China
Prior art keywords
user
heart rate
physiological
detected
signal
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202110713934.XA
Other languages
Chinese (zh)
Inventor
黄杰
宋京泽
张习伟
饶轩横
孙晓
汪萌
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Institute of Artificial Intelligence of Hefei Comprehensive National Science Center
Original Assignee
Institute of Artificial Intelligence of Hefei Comprehensive National Science Center
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Institute of Artificial Intelligence of Hefei Comprehensive National Science Center filed Critical Institute of Artificial Intelligence of Hefei Comprehensive National Science Center
Priority to CN202110713934.XA priority Critical patent/CN113397505A/en
Publication of CN113397505A publication Critical patent/CN113397505A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/02—Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
    • A61B5/0205—Simultaneously evaluating both cardiovascular conditions and different types of body conditions, e.g. heart and respiratory condition
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/02—Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
    • A61B5/021—Measuring pressure in heart or blood vessels
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/02—Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
    • A61B5/024—Detecting, measuring or recording pulse rate or heart rate
    • A61B5/02405—Determining heart rate variability
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/08—Detecting, measuring or recording devices for evaluating the respiratory organs
    • A61B5/0816—Measuring devices for examining respiratory frequency
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/145—Measuring characteristics of blood in vivo, e.g. gas concentration, pH value; Measuring characteristics of body fluids or tissues, e.g. interstitial fluid, cerebral tissue
    • A61B5/14542—Measuring characteristics of blood in vivo, e.g. gas concentration, pH value; Measuring characteristics of body fluids or tissues, e.g. interstitial fluid, cerebral tissue for measuring blood gases
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
    • A61B5/7203—Signal processing specially adapted for physiological signals or for diagnostic purposes for noise prevention, reduction or removal
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
    • A61B5/7235—Details of waveform analysis
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
    • A61B5/7235—Details of waveform analysis
    • A61B5/7253—Details of waveform analysis characterised by using transforms
    • A61B5/7257—Details of waveform analysis characterised by using transforms using Fourier transforms
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods

Abstract

The invention discloses a physiological signal detection method and a system, which belong to the technical field of health detection and comprise the following steps: acquiring a facial video of a user to be detected; and based on the face video, carrying out key point positioning and ROI region cutting, and calculating the physiological index of the user to be detected. The scheme of the invention is a convenient and simple daily detection method, and can detect the self health condition and psychological stress state of the user in real time.

Description

Physiological signal detection method and system
Technical Field
The invention relates to the technical field of health detection, in particular to a physiological signal detection method and system.
Background
At present, a human body physiological index measuring method generally comprises independent component analysis, principal component analysis and other ica blind source separation detection heart rate and Euler amplification extraction heart rate signal based on color and the like. The heart rate detection through the ica blind source separation generally means that pulse wave signals are obtained through the rgb channel blind source separation processing of an ROI area, and then filtering is carried out to calculate the heart rate; extracting heart rate signals through Euler amplification generally refers to recording videos, Euler amplification, extracting an ROI (region of interest) IPPG (internet protocol packet) signal, removing noise, and calculating the heart rate according to waveform peak value intervals or frequency corresponding to spectrum peak values.
The prior art described above has the following drawbacks: the blind source separation method is established under the condition that a pulse signal is unknown a priori, an optimal result needs to be selected from the blind source separation results to serve as a signal extraction result, and a heart rate signal cannot be effectively extracted under the condition that the illumination condition is not ideal. The euler amplification method amplifies the micro-motion, and the noise generated by the micro-motion of the head in the video is amplified.
Disclosure of Invention
The invention aims to overcome the defects in the background technology and realize accurate measurement of physiological indexes.
To achieve the above object, in one aspect, a physiological signal detection method includes:
acquiring a facial video of a user to be detected;
and based on the face video, carrying out key point positioning and ROI region cutting, and calculating the physiological index of the user to be detected.
Further, the physiological indexes of the user to be tested comprise heart rate, heart rate variability, respiratory rate, blood oxygen saturation and blood pressure change.
Further, the heart rate calculating step includes:
to the cutting to obtainSignal R of each RGB channel of the ROI arean、Gn、BnCorrecting to obtain corrected signal R of each RGB channels、Gs、Bs；
Eliminating the specular reflection component, and the formula is as follows:
Xn＝Rs-Gs
Yn＝0.5Rs+0.5Gs-Bs
eliminating motion effects, the formula is as follows:
Figure BDA0003134047810000021
for signal XsAnd YsFiltering to obtain signal XfAnd XfSignal XsAnd YsObtaining the corrected signal of each RGB channel through a space transformation formula;
based on signal XfAnd XfAnd correcting the synchronous change of the heart rate signals to obtain the heart rate signals, wherein the formula is as follows:
S＝Xf-αYf
wherein the content of the first and second substances,
Figure BDA0003134047810000022
and performing fast Fourier transform on the heart rate signal, and taking the frequency at the maximum peak value multiplied by 60 as the heart rate of the user to be detected.
Further, the heart rate variability calculating step comprises:
calculating a distance between each peak of the heart rate signal;
multiplying the distance between each peak value by the sampling time interval to obtain the actual peak value distance;
and calculating the standard deviation of the actual peak distance as the heart rate variability of the user to be detected.
Further, the respiratory rate calculating step includes:
carrying out non-uniform sampling spectrum analysis on the heart rate signal, and obtaining a power spectral density map by adopting a LOMB normalization periodogram;
based on the power spectral density map, finding the frequency corresponding to the maximum peak value in the respiratory frequency range, and multiplying the frequency by 60 to obtain the respiratory frequency of the user to be detected.
Further, the step of calculating the blood pressure change comprises:
obtaining pulse wave conduction time of two parts of ROI areas based on the two parts of ROI areas of the face of the user to be detected;
and substituting the pulse wave conduction time of the user to be detected into a linear relation between the pulse wave conduction time and the diastolic pressure and the systolic pressure obtained by fitting in advance to obtain the diastolic pressure and the systolic pressure of the user to be detected.
Further, the calculation formula of the blood oxygen saturation is as follows:
Figure BDA0003134047810000031
wherein the content of the first and second substances,
Figure BDA0003134047810000032
is the amplitude of the alternating current component of red light,
Figure BDA0003134047810000033
is the amplitude of the alternating current component of the blue light,
Figure BDA0003134047810000034
is the amplitude of the dc component of the red light,
Figure BDA0003134047810000035
for the amplitude of the dc component of blue light, a and B are the oximetry fitting parameters.
Further, still include:
and inputting the calculated physiological indexes of the user to be detected into a pre-trained deep learning pressure model, and predicting the pressure grade of the user to be detected.
In another aspect, a physiological signal detection system is employed, comprising: the device comprises an acquisition module and a physiological index calculation module, wherein:
the acquisition module is used for acquiring a facial video of a user to be detected;
and the physiological index calculation module is used for positioning key points and cutting ROI areas based on the face video and calculating the physiological index of the user to be detected.
Further, the physiological indexes of the user to be detected comprise heart rate, heart rate variability, respiratory rate, blood oxygen saturation and blood pressure change;
the physiological index calculation module is used for reading video frames, positioning key points of human faces, cutting RI regions and calculating physiological indexes in a multithread parallel mode.
Compared with the prior art, the invention has the following technical effects: according to the method, the heart rate variability, the respiratory rate, the blood oxygen saturation and the blood pressure change of the user for a period of time are obtained by analyzing the facial video of the user to be detected; the scheme is a convenient and simple daily detection method, and can detect the self health condition and the psychological stress state of the user in real time, thereby predicting the heart disease condition in time and preventing diseases such as cardiovascular and cerebrovascular diseases and the like.
Drawings
The following detailed description of embodiments of the invention refers to the accompanying drawings in which:
FIG. 1 is a flow chart of a method of physiological signal detection;
FIG. 2 is an overall flow diagram of a physiological signal detection method;
fig. 3 is a block diagram of a physiological signal detection system.
Detailed Description
To further illustrate the features of the present invention, refer to the following detailed description of the invention and the accompanying drawings. The drawings are for reference and illustration purposes only and are not intended to limit the scope of the present disclosure.
As shown in fig. 1, the present embodiment discloses a physiological signal detection method, which includes the following steps S1 to S2:
s1, acquiring a facial video of the user to be detected;
it should be noted that the face video is a video of about 30 seconds meeting the quality requirement, the video meeting the composite quality requirement is a video with a stable frame rate of 30fps, uniform face illumination, no serious exposure and serious over-darkness, and a resolution at least up to 720 p.
And S2, positioning key points and cutting ROI areas based on the face video, and calculating the physiological indexes of the user to be detected.
It should be noted that in this embodiment, four processes are started to respectively perform video frame reading, face key point positioning, region of interest (ROI) and physiological index calculation, and the multi-process processing realizes the function of accelerating physiological value calculation.
As a further preferable technical solution, the physiological index of the user to be measured includes heart rate, heart rate variability, respiratory rate, blood oxygen saturation, blood pressure change, and pressure level.
As a further preferred technical solution, the heart rate calculating step includes:
(1) signal R of each RGB channel of the ROI obtained by cuttingn、Gn、BnCorrecting to obtain corrected signal R of each RGB channels、Gs、Bs；
It should be noted that the correction of each rgb channel of each ROI region is performed by multiplying the signal of each channel by the corresponding normalization coefficient, which is [0.7682,0.5121,0.3842 ]]，Rs＝0.7682Rn Gs＝0.5131Gn Bs＝0.3841Bn。
(2) Eliminating the specular reflection component, and the formula is as follows:
Xn＝Rs-Gs
Yn＝0.5Rs+0.5Gs-Bs
in addition, X isnIs a red and green channelDifference, YnIs a weighted value of three channels, representing a spatial transformation from rgb to xy two dimensions, XnAnd YnOrthogonality, and the motion interference can be eliminated through the ratio of two orthogonal signals;
eliminating motion effects, the formula is as follows:
Figure BDA0003134047810000051
(3) for signal XsAnd YsFiltering to obtain signal XfAnd XfSignal XsAnd YsThe method comprises the steps of multiplying three channels rgb by a standardized coefficient respectively to obtain standard chrominance signals, and then obtaining the standard chrominance signals through a spatial transformation formula;
note that, by performing filtering processing on the signal to suppress out-of-band noise, a stable signal is obtained.
(4) Based on signal XfAnd XfCorrecting the synchronous change of the heart rate signals by a ratio factor of the two signal variances to obtain the heart rate signals, wherein the formula is as follows:
S＝Xf-αYf
wherein the content of the first and second substances,
Figure BDA0003134047810000061
Xfand XfThe processing in the reverse direction is beneficial to improving heart rate signals and inhibiting motion noise;
(5) and performing fast Fourier transform on the heart rate signal, and taking the frequency at the maximum peak value multiplied by 60 as the heart rate of the user to be detected.
The method based on skin chromaticity is introduced into the heart rate analysis algorithm, so that the effect of eliminating skin color deviation, motion artifact and specular reflection is achieved.
As a further preferred technical solution, the step of calculating the heart rate variability includes:
(1) calculating a distance between each peak of the heart rate signal;
(2) multiplying the distance between each peak value by the sampling time interval to obtain the actual peak value distance rri;
(3) and calculating the standard deviation of the actual peak distance rri as the heart rate variability sdnn of the user to be detected.
As a further preferable aspect, the breathing frequency calculating step includes:
(1) carrying out non-uniform sampling spectrum analysis on the heart rate signal, and obtaining a power spectral density map by adopting a LOMB normalization periodogram;
(2) based on the power spectral density map, finding the frequency corresponding to the maximum peak value in the respiratory frequency range, and multiplying the frequency by 60 to obtain the respiratory frequency of the user to be detected.
As a more preferable aspect, the step of calculating the blood pressure change includes:
(1) obtaining pulse wave conduction time of two parts of ROI areas based on the two parts of ROI areas of the face of the user to be detected;
(2) and substituting the pulse wave conduction time of the user to be detected into a linear relation between the pulse wave conduction time and the diastolic pressure and the systolic pressure obtained by fitting in advance to obtain the diastolic pressure and the systolic pressure of the user to be detected.
The fitting process of the linear relation between the pulse wave transit time and the diastolic and systolic pressures is as follows:
firstly, according to pulse waves obtained by ROI blocks of two parts of the face, further filtering and purifying the heart rate numerical value obtained by calculation, then calculating the mean value of the time difference of the pulse waves of the two parts of the face corresponding to the wave crests to be used as the pulse wave conduction time (PTT) of the two parts of the face, then carrying out linear fitting through a large amount of recorded face videos and the blood pressure data recorded during recording, and establishing the linear relation among the PTT, diastolic pressure (DBP) and systolic pressure (SBP), as follows:
SBP＝A1×PTT+B1
DBP＝C1×PTT+D1
wherein A is1、B1、C1、D1Respectively representing fitting parametersAnd (4) counting.
As a further preferred technical solution, since pulse wave signal characteristics and blood vessel wall models of people of different ages and sexes are slightly different, this embodiment collects videos of different ages and sexes, performs deep learning model training, and performs secondary adjustment for people of different ages and sexes to ensure an optimal effect. The deep learning model is used for carrying out nonlinear fitting on multi-feature data and is a nonlinear regression model, the input of the model is heart rate, PTT, gender, age, height, weight, whether hypertension exists, whether diabetes exists, whether medicines are taken, the feature of each area such as energy, peak interval and the like, and the output of the model is a blood pressure value.
In the blood pressure detection, a large number of blood pressure samples are adopted to fit blood pressure model parameters, so that the method has guiding significance for the blood pressure detection, and the psychological state of a subject is predicted by further analyzing and modeling physiological indexes.
As a further preferred embodiment, the blood oxygen saturation can be calculated by the relative pulse amplitude of the light with two wavelengths, and the calculation formula is as follows:
Figure BDA0003134047810000081
wherein the content of the first and second substances,
Figure BDA0003134047810000082
is the amplitude of the alternating current component of red light,
Figure BDA0003134047810000083
is the amplitude of the alternating current component of the blue light,
Figure BDA0003134047810000084
is the amplitude of the dc component of the red light,
Figure BDA0003134047810000085
for the amplitude of the DC component of blue light, A and B are recorded by collecting a large amount of video data and using a contact deviceAnd fitting the recorded blood oxygen saturation to obtain corresponding parameters.
As a more preferable embodiment, as shown in fig. 2, the method further includes:
and inputting the calculated physiological indexes of the user to be detected into a pre-trained deep learning pressure model, and predicting the pressure grade of the user to be detected.
Specifically, the heart rate and the heart rate variability are input into a pre-trained deep learning pressure model, and the pressure level of the user is obtained through statistical synthesis after time domain and frequency domain indexes of the heart rate variability (hrv) are calculated through heart rate and subcutaneous pulse data.
This example uses private data collected in the laboratory, 112 subjects of the data, video recording and statistical synthesis of new data after time and frequency domain indices of heart rate variability (hrv) calculation by recording the subjects' heart rate and electrodermal pulse data by the device upon contact, and the pressure level fed back by the subjects after completion of the stress test. And training a deep learning model through the data, and establishing a model structure reflecting the pressure level through the pulse signal for calculating the conversion of the physiological signal into the pressure level.
As shown in fig. 3, the present embodiment discloses a physiological signal detection system, including: an acquisition module 10 and a physiological index calculation module 20, wherein:
the acquisition module 10 is used for acquiring a facial video of a user to be detected;
the physiological index calculation module 20 is configured to perform key point positioning and ROI region clipping based on the facial video, and calculate a physiological index of the user to be detected.
As a further preferred technical solution, the physiological indexes of the user to be measured include heart rate, heart rate variability, respiratory rate, blood oxygen saturation and blood pressure variation;
the physiological index calculation module is used for reading video frames, positioning key points of human faces, cutting RI regions and calculating physiological indexes in a multithread parallel mode.
The system provided by the embodiment of the present invention is used for executing the above method embodiments, and for details of the process and the details, reference is made to the above embodiments, which are not described herein again.
This scheme has following beneficial effect:
(1) compared with other non-contact physiological index measuring systems, the method has the advantages that the image processing mode based on the chromaticity space is adopted, the influence caused by specular reflection and motion is eliminated, the deviation caused by the skin color problem is corrected, the robustness of the algorithm is high, and a good operation result can be obtained under the condition of poor ambient light.
(2) The comprehensive analysis of the physiological indexes is provided, the comprehensive measurement of the heart rate, the respiratory rate, the heart rate variability, the blood oxygen saturation and the blood pressure indexes is included, the predicted value can reach higher accuracy, the psychological pressure condition of a measurer can be further quantized by combining the physiological indexes, and the psychological state of the measurer is reflected.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.

Claims (10)

1. A method of physiological signal detection, comprising:
acquiring a facial video of a user to be detected;
and based on the face video, carrying out key point positioning and ROI region cutting, and calculating the physiological index of the user to be detected.
2. The method according to claim 1, wherein the physiological indicators of the user to be tested include heart rate, heart rate variability, respiratory rate, blood oxygen saturation and blood pressure variation.
3. The physiological signal detection method of claim 2, wherein the heart rate calculation step comprises:
signal R of each RGB channel of the ROI obtained by cuttingn、Gn、BnCorrecting to obtain corrected signal R of each RGB channels、Gs、Bs；
Eliminating the specular reflection component, and the formula is as follows:
Xn＝Rs-Gs
Yn＝0.5Rs+0.5Gs-Bs
eliminating motion effects, the formula is as follows:
Figure FDA0003134047800000011
for signal XsAnd YsFiltering to obtain signal XfAnd XfSignal XsAnd YsObtaining the corrected signal of each RGB channel through a space transformation formula;
based on signal XfAnd XfAnd correcting the synchronous change of the heart rate signals to obtain the heart rate signals, wherein the formula is as follows:
S＝Xf-αYf
wherein the content of the first and second substances,
Figure FDA0003134047800000021
and performing fast Fourier transform on the heart rate signal, and taking the frequency at the maximum peak value multiplied by 60 as the heart rate of the user to be detected.
4. A method of detecting physiological signals according to claim 3, wherein the step of calculating heart rate variability comprises:
calculating a distance between each peak of the heart rate signal;
multiplying the distance between each peak value by the sampling time interval to obtain the actual peak value distance;
and calculating the standard deviation of the actual peak distance as the heart rate variability of the user to be detected.
5. The physiological signal detection method of claim 3 wherein said respiratory rate calculation step comprises:
carrying out non-uniform sampling spectrum analysis on the heart rate signal, and obtaining a power spectral density map by adopting a LOMB normalization periodogram;
based on the power spectral density map, finding the frequency corresponding to the maximum peak value in the respiratory frequency range, and multiplying the frequency by 60 to obtain the respiratory frequency of the user to be detected.
6. The physiological signal detection method according to claim 2, wherein the step of calculating the blood pressure change comprises:
obtaining pulse wave conduction time of two parts of ROI areas based on the two parts of ROI areas of the face of the user to be detected;
and substituting the pulse wave conduction time of the user to be detected into a linear relation between the pulse wave conduction time and the diastolic pressure and the systolic pressure obtained by fitting in advance to obtain the diastolic pressure and the systolic pressure of the user to be detected.
7. The physiological signal detecting method according to claim 3, wherein the calculation formula of the blood oxygen saturation is as follows:
Figure FDA0003134047800000031
wherein the content of the first and second substances,
Figure FDA0003134047800000032
is the amplitude of the alternating current component of red light,
Figure FDA0003134047800000033
is the amplitude of the alternating current component of the blue light,
Figure FDA0003134047800000034
is the amplitude of the dc component of the red light,
Figure FDA0003134047800000035
for the amplitude of the dc component of blue light, a and B are the oximetry fitting parameters.
8. The physiological signal detection method according to any one of claims 1 to 7, further comprising:
and inputting the calculated physiological indexes of the user to be detected into a pre-trained deep learning pressure model, and predicting the pressure grade of the user to be detected.
9. A physiological signal detection system, comprising: the device comprises an acquisition module and a physiological index calculation module, wherein:
the acquisition module is used for acquiring a facial video of a user to be detected;
and the physiological index calculation module is used for positioning key points and cutting ROI areas based on the face video and calculating the physiological index of the user to be detected.
10. The physiological signal detection system of claim 9 wherein the physiological indicators of the user under test include heart rate, heart rate variability, respiratory rate, blood oxygen saturation, and blood pressure changes;
the physiological index calculation module is used for reading video frames, positioning key points of human faces, cutting RI regions and calculating physiological indexes in a multithread parallel mode.
CN202110713934.XA 2021-06-25 2021-06-25 Physiological signal detection method and system Pending CN113397505A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110713934.XA CN113397505A (en) 2021-06-25 2021-06-25 Physiological signal detection method and system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110713934.XA CN113397505A (en) 2021-06-25 2021-06-25 Physiological signal detection method and system

Publications (1)

Publication Number Publication Date
CN113397505A true CN113397505A (en) 2021-09-17

Family

ID=77679712

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110713934.XA Pending CN113397505A (en) 2021-06-25 2021-06-25 Physiological signal detection method and system

Country Status (1)

Country Link
CN (1) CN113397505A (en)

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101489478A (en) * 2006-06-01 2009-07-22 必安康医疗有限公司 Apparatus, system, and method for monitoring physiological signs
CN102355852A (en) * 2009-02-06 2012-02-15 必安康医疗有限公司 Apparatus, system and method for chronic disease monitoring
CN109009052A (en) * 2018-07-02 2018-12-18 南京工程学院 The embedded heart rate measurement system and its measurement method of view-based access control model
CN109106384A (en) * 2018-07-24 2019-01-01 安庆师范大学 A kind of psychological pressure condition predicting method and system
CN110367961A (en) * 2018-04-13 2019-10-25 中兴通讯股份有限公司 Blood pressure data processing method, device, equipment and readable storage medium storing program for executing
CN111248928A (en) * 2020-01-20 2020-06-09 北京津发科技股份有限公司 Pressure identification method and device
CN111714105A (en) * 2020-07-24 2020-09-29 长春理工大学 Human vital sign perception system based on IPPG
CN112890792A (en) * 2020-11-25 2021-06-04 合肥工业大学 Cloud computing cardiovascular health monitoring system and method based on network camera

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101489478A (en) * 2006-06-01 2009-07-22 必安康医疗有限公司 Apparatus, system, and method for monitoring physiological signs
CN102355852A (en) * 2009-02-06 2012-02-15 必安康医疗有限公司 Apparatus, system and method for chronic disease monitoring
CN110367961A (en) * 2018-04-13 2019-10-25 中兴通讯股份有限公司 Blood pressure data processing method, device, equipment and readable storage medium storing program for executing
CN109009052A (en) * 2018-07-02 2018-12-18 南京工程学院 The embedded heart rate measurement system and its measurement method of view-based access control model
CN109106384A (en) * 2018-07-24 2019-01-01 安庆师范大学 A kind of psychological pressure condition predicting method and system
CN111248928A (en) * 2020-01-20 2020-06-09 北京津发科技股份有限公司 Pressure identification method and device
CN111714105A (en) * 2020-07-24 2020-09-29 长春理工大学 Human vital sign perception system based on IPPG
CN112890792A (en) * 2020-11-25 2021-06-04 合肥工业大学 Cloud computing cardiovascular health monitoring system and method based on network camera

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
DE HAAN, G ，等: "Robust Pulse Rate From Chrominance-Based rPPG", 《IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING》, vol. 60, no. 10, pages 2878 - 2886, XP011526965, DOI: 10.1109/TBME.2013.2266196 *
孙晟珂，等: "基于IPPG 非接触式血压测量方法", 《信息技术》, vol. 44, no. 10, pages 31 - 38 *

Similar Documents

Publication Publication Date Title
Tasli et al. Remote PPG based vital sign measurement using adaptive facial regions
CN110269600B (en) Non-contact video heart rate detection method based on multivariate empirical mode decomposition and combined blind source separation
US10987036B2 (en) Systems, devices, and methods for performing trans-abdominal fetal oximetry and/or trans-abdominal fetal pulse oximetry using diffuse optical tomography
CN111387959A (en) Non-contact physiological parameter detection method based on IPPG
CN104173051A (en) Automatic noncontact respiration assessing system and assessing method
CN112294282A (en) Self-calibration method of emotion detection device based on RPPG
Huang et al. Image based contactless blood pressure assessment using Pulse Transit Time
CN103263271A (en) Non-contact automatic blood oxygen saturation degree measurement system and measurement method
CN111714105A (en) Human vital sign perception system based on IPPG
CN203290905U (en) Non-contact automatic respiration measuring system
CN112232256B (en) Contactless sports and body measurement data acquisition system
Li et al. An improvement for video-based heart rate variability measurement
CN112890792A (en) Cloud computing cardiovascular health monitoring system and method based on network camera
CN113591769B (en) Non-contact heart rate detection method based on photoplethysmography
CN106691410B (en) Pulse and red blood cell concentration monitor and method
CN111839488A (en) Non-invasive continuous blood pressure measuring device and method based on pulse wave
CN112869737B (en) Non-contact human body blood oxygen saturation detection method
CN113397505A (en) Physiological signal detection method and system
CN104688199A (en) Non-contact type pulse measurement method based on skin pigment concentration difference
CN110353700A (en) Contactless method for detecting blood oxygen saturation
CN112690771B (en) Human face video heart rate detection method using linear regression model
Suleman et al. Respiratory Events Estimation From PPG Signals Using a Simple Peak Detection Algorithm
CN113040734A (en) Non-contact blood pressure estimation method based on signal screening
Farjana et al. Cuffless Blood Pressure Determination Using Photoplethysmogram (PPG) Signal Based on Multiple Linear Regression Analysis
CN113425282A (en) Respiration rate monitoring method and device based on multispectral PPG blind source separation method

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination