CN110367961A - Blood pressure data processing method, device, equipment and readable storage medium storing program for executing - Google Patents
Blood pressure data processing method, device, equipment and readable storage medium storing program for executing Download PDFInfo
- Publication number
- CN110367961A CN110367961A CN201810332101.7A CN201810332101A CN110367961A CN 110367961 A CN110367961 A CN 110367961A CN 201810332101 A CN201810332101 A CN 201810332101A CN 110367961 A CN110367961 A CN 110367961A
- Authority
- CN
- China
- Prior art keywords
- pulse wave
- blood pressure
- characteristic parameter
- time
- data processing
- 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
Links
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
- A61B5/021—Measuring pressure in heart or blood vessels
- A61B5/022—Measuring pressure in heart or blood vessels by applying pressure to close blood vessels, e.g. against the skin; Ophthalmodynamometers
- A61B5/02225—Measuring pressure in heart or blood vessels by applying pressure to close blood vessels, e.g. against the skin; Ophthalmodynamometers using the oscillometric method
-
- 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
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Public Health (AREA)
- Molecular Biology (AREA)
- Cardiology (AREA)
- Vascular Medicine (AREA)
- Physics & Mathematics (AREA)
- Veterinary Medicine (AREA)
- Biophysics (AREA)
- Pathology (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Medical Informatics (AREA)
- Physiology (AREA)
- Surgery (AREA)
- Animal Behavior & Ethology (AREA)
- General Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Ophthalmology & Optometry (AREA)
- Signal Processing (AREA)
- Psychiatry (AREA)
- Measuring Pulse, Heart Rate, Blood Pressure Or Blood Flow (AREA)
Abstract
The invention discloses a kind of blood pressure data processing method, device, equipment and readable storage medium storing program for executing, belong to technical field of data processing, this method comprises: obtaining the video image of target area；Pulse wave information is obtained from video image, using the ratio of the maximum value of the pulse wave information and mean value as pulse wave detection information；Extract the characteristic parameter in the pulse wave detection information；The mathematical model of the characteristic parameter Yu real-time blood pressure is established by regression analysis, by the video image for obtaining the sensitizing ranges such as face, palm, therefrom accurately extract pulse wave, and then continuous blood pressure of the personage during recorded video in video is obtained by algorithm, the continuous measurement for realizing blood pressure, has been completed at the same time the measurement of systolic pressure and diastolic pressure, cost is relatively low, it is easily achieved, versatility is higher.
Description
Technical field
The present invention relates to technical field of data processing more particularly to a kind of blood pressure data processing method, device, equipment and can
Read storage medium.
Background technique
Blood pressure detecting is divided into direct method and indirect method, and conduit is placed in the intravascular of tested position by puncturing by direct method,
Through pressure sensor measuring blood pressure, this method can realize continuous precise measurement, but have wound, easy infection.The blood pressure indirect method of measurement
It include: Korotkoff's Sound method, oscillographic method, vascular unloading technique, ultrasonic method, pulse wave characteristic parameters measuring method etc., Korotkoff's Sound method will auscultate
Hear first of device and cuff pressure when the last one Korotkoff's Sound are as systolic pressure SBP and diastolic pressure DBP.Oscillographic method is based on
Pressure fluctuation obtains oscilloscopic waveform in subject's upper arm cuff, acquires blood pressure (as shown in Figure 1) using various oscillography algorithms.It is constant
Volumetric method makes arteries be in constant volume state by impressed pressure, obtains continuous arterial blood by measuring impressed pressure
Pressure value.Ultrasonic method application doppler principle is found out the motion conditions of vascular wall and blood flow by the ultrasonic wave that body surface emits.Pulse wave
Characteristic parameter measuring method estimates pressure value using the various characteristic values of pulse wave and the correlation of blood pressure；These are detected indirectly
Method needs to be unsuitable for measuring for a long time by means of cuff or electrode.
Summary of the invention
The invention reside in a kind of blood pressure data processing method, device, equipment and readable storage medium storing program for executing is provided, pass through the face of acquisition
The video image of the sensitizing ranges such as portion, palm therefrom accurately extracts pulse wave, and then obtains personage in video by algorithm and recording
Continuous blood pressure during video processed realizes the continuous measurement of blood pressure, has been completed at the same time the measurement of systolic pressure and diastolic pressure, cost
It is lower, it is easy to accomplish, versatility is higher.
It is as follows that the present invention solves technical solution used by above-mentioned technical problem:
According to an aspect of the present invention, a kind of blood pressure data processing method provided, comprising:
Obtain the video image of target area；
Pulse wave information is obtained from video image, using the ratio of the maximum value of the pulse wave information and mean value as arteries and veins
It fights wave detection information；
Extract the characteristic parameter in the pulse wave detection information；
The mathematical model of the characteristic parameter Yu real-time blood pressure is established by regression analysis.
Optionally, described that pulse wave information is obtained from video image, by the maximum value and mean value of the pulse wave information
Ratio include: as pulse wave detection information
The grey scale signal of the video image is pre-processed；
Pulse wave component is isolated from the video image by independent component analysis method；
Fourier transformation is carried out to the pulse wave component, using the ratio of maximum value in Fourier transformation and mean value as arteries and veins
It fights wave detection information.
Optionally, the characteristic parameter includes: pulse wave transmission time, shrinks rise time, diastolic time and between the time
Every.
Optionally, the mathematical model for establishing the characteristic parameter and real-time blood pressure by regression analysis includes:
Founding mathematical models；
The real-time blood pressure of multiple groups is measured, and obtains the corresponding characteristic parameter of the real-time blood pressure of the multiple groups；
According to the real-time blood pressure of the multiple groups and its corresponding characteristic parameter, by unitary non-linear regression method to the number
The undetermined coefficient for learning model is demarcated.
As another aspect of the present invention, a kind of blood pressure data processing unit for providing, comprising:
Video acquiring module, for obtaining the video image of target area；
Pulse wave obtains module, for obtaining pulse wave information from video image, by the maximum of the pulse wave information
The ratio of value and mean value is as pulse wave detection information；
Characteristic parameter extraction module, for extracting the characteristic parameter in the pulse wave detection information；
Modeling module, for establishing the mathematical model of the characteristic parameter Yu real-time blood pressure by regression analysis.
Optionally, the pulse wave acquisition module includes:
Pretreatment unit is pre-processed for the grey scale signal to the video image；
Separative unit, for isolating pulse wave component from the video image by independent component analysis method；
Selecting unit, for carrying out Fourier transformation to the pulse wave component, by maximum value in Fourier transformation and
The ratio of value is as pulse wave detection information.
Optionally, the characteristic parameter includes: pulse wave transmission time, shrinks rise time, diastolic time and between the time
Every.
Optionally, the modeling module includes:
Modeling unit is used for founding mathematical models；
Measuring unit for measuring the real-time blood pressure of multiple groups, and obtains the corresponding characteristic parameter of the real-time blood pressure of the multiple groups；
Unit is returned, for passing through unitary non-linear time according to the real-time blood pressure of the multiple groups and its corresponding characteristic parameter
Method is returned to demarcate the undetermined coefficient of the mathematical model.
According to a further aspect of the invention, a kind of electronic equipment provided, including memory, processor and at least one
It is stored in the memory and is configured as the application program executed by the processor, the application program is configured as
For executing above-described blood pressure data processing method.
According to a further aspect of the invention, a kind of readable storage medium storing program for executing provided, is stored thereon with computer program, should
Above-described blood pressure data processing method is realized when program is executed by processor.
A kind of blood pressure data processing method, device, equipment and the readable storage medium storing program for executing of the embodiment of the present invention, this method packet
It includes: obtaining the video image of target area；Pulse wave information is obtained from video image, by the maximum value of the pulse wave information
Ratio with mean value is as pulse wave detection information；Extract the characteristic parameter in the pulse wave detection information；Divided by returning
Analysis method establishes the mathematical model of the characteristic parameter Yu real-time blood pressure, by the video figure for obtaining the sensitizing ranges such as face, palm
Picture therefrom accurately extracts pulse wave, and then obtains continuous blood pressure of the personage during recorded video in video by algorithm, realizes
The continuous measurement of blood pressure, has been completed at the same time the measurement of systolic pressure and diastolic pressure, cost is relatively low, it is easy to accomplish, versatility is higher.
Detailed description of the invention
Fig. 1 is a kind of blood pressure data processing method flow chart that the embodiment of the present invention one provides；
Fig. 2 is the method flow diagram of step S20 in Fig. 1；
Fig. 3 is the schematic diagram for the characteristic parameter that the embodiment of the present invention one provides；
Fig. 4 is the grey scale signal change curve schematic diagram that the embodiment of the present invention one provides；
Fig. 5 is the partial waveform figure for the ICA decomposition result that the embodiment of the present invention one provides；
Fig. 6 is the pulse wave signal schematic diagram that the embodiment of the present invention one provides；
Fig. 7 is the method flow diagram of step S30 in Fig. 1；
Fig. 8 is a kind of blood pressure data processing unit exemplary block diagram provided by Embodiment 2 of the present invention；
Fig. 9 is the exemplary block diagram that pulse wave obtains module in Fig. 8；
Figure 10 is the exemplary block diagram of modeling module in Fig. 8.
The embodiments will be further described with reference to the accompanying drawings for the realization, the function and the advantages of the object of the present invention.
Specific embodiment
In order to be clearer and more clear technical problems, technical solutions and advantages to be solved, tie below
Drawings and examples are closed, the present invention will be described in further detail.It should be appreciated that specific embodiment described herein is only
To explain the present invention, it is not intended to limit the present invention.
Embodiment one
As shown in Figure 1, in the present embodiment, a kind of blood pressure data processing method, comprising:
S10, the video image for obtaining target area；
S20, pulse wave information is obtained from video image, the ratio of the maximum value of the pulse wave information and mean value is made
For pulse wave detection information；
Characteristic parameter in S30, the extraction pulse wave detection information；
S40, the mathematical model that the characteristic parameter Yu real-time blood pressure are established by regression analysis.
In the present embodiment, by obtaining the video image of the sensitizing ranges such as face, palm, pulse is therefrom accurately extracted
Wave, and then continuous blood pressure of the personage during recorded video in video is obtained by algorithm, the continuous measurement of blood pressure is realized, together
When complete the measurement of systolic pressure and diastolic pressure, cost is relatively low, it is easy to accomplish, versatility is higher.
In the present embodiment, using the picture pick-up devices such as intelligent mobile phone terminal acquisition subject in static or light exercise situation
The 20s of lower recording includes the video in the sensitive targets regions such as face, palm, is then calculated using the detection of the target areas such as Face datection
Method progress extracts the target areas such as face from video, and the target areas such as face that will test are as area-of-interest.
In the present embodiment, the resolution ratio of video image is in 640*480 or more, and frame per second is in 30fps or more.
In the present embodiment, the blood pressure detecting based on video can carry out offline, if while because of memory space problem, can will
Video is uploaded to cloud, detects in the lower continuous blood pressure frame by frame that carries out of 3G, 4G or wireless.In the occasions such as tele-medicine, then also need
To utilize 3G, 4G or wireless network.
As shown in Fig. 2, in the present embodiment, the step S20 includes:
S21, the grey scale signal of the video image is pre-processed；
S22, pulse wave component is isolated from the video image by independent component analysis method；
S23, Fourier transformation is carried out to the pulse wave component, the ratio of maximum value in Fourier transformation and mean value is made
For pulse wave detection information.
In the present embodiment, the characteristic parameter include: pulse wave transmission time, shrink the rise time, diastolic time and
Time interval.
In the present embodiment, pulse wave transmission time refers to pressure pulse between heart and peripheral arterial position or two
The time advanced between artery site can use the biography between the pulse wave of two different parts (face and palm) in the present case
Defeated delay acquires；And rise time ST, diastolic time DT and time interval T1 are shunk, it is detected using the second peak detection algorithm
Naked-eye observation less than pulse wave second peak value, while pulse wave wave crest and trough are detected using extremum extracting algorithm,
Finally obtain ST, DT, T1；Its schematic diagram is as shown in Figure 3.
In the present embodiment, in step S21 to the pretreatment of the grey scale signal of the video image include template matching and
Statistical learning.
In the present embodiment, what imaging sensor acquired is not the light intensity of accurate three primary colours light, but cmos image
The schematic diagram of quantum efficiency of the sensor under Baeyer array three primary colours filter layer.Red luminous intensity is perceived on imaging sensor
Location of pixels can also sense that part is green, information of blue light, and the location of pixels for similarly perceiving green and blue luminous intensity also can
Sense the information of part red light.After being pre-processed from three grey scale change sequences of video extraction, through independent element point
Analysis ICA isolates pulse wave signal；ICA decomposition result has randomness, by independent element periodically strongest in decomposition result
As pulse wave component.It, should using the ratio of greatest measure and mean value in sequence obtained by the Fourier transformation of signal as index
The maximum independent element of index is the independent element for including pulse wave.
In the present embodiment, the grey scale signal change curve of three kinds of colors (RGB) of video image is as shown in figure 4, right
Average intensity change waveform in Fig. 4, is decomposed with FastICA algorithm, and the partial waveform of decomposition result is as shown in Figure 5；For
Noise in removal independent component selects stopband to decline faster Chebyshev type iir filter and carries out bandpass filtering, band logical
Filter passband is 0.8Hz~3Hz, and cutoff frequency is 0.5Hz and 4Hz, and passband maximum attenuation is 1dB, and minimum attenuation in stop band is
15dB.ICA decomposition result has randomness, the greatest measure and mean value in sequence obtained by our Fourier transformations signal
For ratio as index, the maximum independent element of the index is the independent element for including pulse wave.The pulse finally extracted
For wave as shown in fig. 6, solid line is the pulse wave signal that video finally extracts in Fig. 6, dotted line is the finger tip arteries and veins acquired with audio video synchronization
It fights wave signal.
As shown in fig. 7, in the present embodiment, the step S40 includes:
S41, founding mathematical models；
S42, the measurement real-time blood pressure of multiple groups, and obtain the corresponding characteristic parameter of the real-time blood pressure of the multiple groups；
S43, according to the real-time blood pressure of the multiple groups and its corresponding characteristic parameter, by unitary non-linear regression method to institute
The undetermined coefficient for stating mathematical model is demarcated.
In the present embodiment, the selection of regression equation should meet three conditions: 1, equation form should be with related substance
The basic theories of science is consistent, 2, equation have a higher degree of fitting, 3, the mathematical form of equation should be as simple as possible.Based on existing
There are technology and the above principle, there are three mathematical models relevant to this case:
It one, is the non-linear relation model of PTT and mean pressure, equation are as follows:
It, can be real according to the measured value of formula and PTT using the value of available suitable undetermined coefficient b, c of finite measurement
The monitoring of existing blood pressure P.
It two, is the linear relationship mould of pulse wave contraction rise time, diastolic time, time interval and systolic pressure, diastolic pressure
Type, wherein the linear relationship between systolic pressure and diastolic time DT are as follows:
SBP=a1·DT+b1
The linear relationship of diastolic pressure and time interval are as follows:
DBP=a2·T1+b2
It is practical to calculate this four parameters using two groups of systolic pressures and diastolic blood pressure values, but only acquiring with two groups of data
Pressure value error is larger, thus finally using the method for one-variable linear regression acquire four parameters a1, a2 in the regression model and
B1, b2, final realize determine systolic pressure and diastolic pressure using gained regression equation.
It three, is linear relation model between pulse wave transmission time and mean pressure, systolic pressure, diastolic pressure, equation are as follows:
P=a+bPTT
Wherein a, b are undetermined coefficient, related with the arterial vascular property of individual, and are occurred with the change of blood vessel elasticity
Variation.In short time, individual coefficient a, b are to maintain constant.
In the present embodiment, the undetermined coefficient of the mathematical model originally can use two groups of blood pressure and pulse wave conduction time values
Etc. features can be in the hope of, but for high-precision requirement, we are using spies such as measurement multiple groups blood pressure and pulse wave conduction times
The respective value of sign, and then pass through the calibration of unitary nonlinear regression progress coefficient.The real-time blood pressure of multiple groups be greater than etc.
In two groups.
Embodiment two
As shown in figure 8, in the present embodiment, a kind of blood pressure data processing unit, comprising:
Video acquiring module 10, for obtaining the video image of target area；
Pulse wave obtains module 20, for obtaining pulse wave information from video image, most by the pulse wave information
The ratio of big value and mean value is as pulse wave detection information；
Characteristic parameter extraction module 30, for extracting the characteristic parameter in the pulse wave detection information；
Modeling module 40, for establishing the mathematical model of the characteristic parameter Yu real-time blood pressure by regression analysis.
In the present embodiment, by obtaining the video image of the sensitizing ranges such as face, palm, pulse is therefrom accurately extracted
Wave, and then continuous blood pressure of the personage during recorded video in video is obtained by algorithm, the continuous measurement of blood pressure is realized, together
When complete the measurement of systolic pressure and diastolic pressure, cost is relatively low, it is easy to accomplish, versatility is higher.
In the present embodiment, using the picture pick-up devices such as intelligent mobile phone terminal acquisition subject in static or light exercise situation
The 20s of lower recording includes the video in the sensitive targets regions such as face, palm, is then calculated using the detection of the target areas such as Face datection
Method progress extracts the target areas such as face from video, and the target areas such as face that will test are as area-of-interest.
In the present embodiment, the resolution ratio of video image is in 640*480 or more, and frame per second is in 30fps or more.
In the present embodiment, the blood pressure detecting based on video can carry out offline, if while because of memory space problem, can will
Video is uploaded to cloud, detects in the lower continuous blood pressure frame by frame that carries out of 3G, 4G or wireless.In the occasions such as tele-medicine, then also need
To utilize 3G, 4G or wireless network.
As shown in figure 9, in the present embodiment, the pulse wave obtains module and includes:
Pretreatment unit 21 is pre-processed for the grey scale signal to the video image；
Separative unit 22, for isolating pulse wave component from the video image by independent component analysis method；
Selecting unit 23, for the pulse wave component carry out Fourier transformation, by maximum value in Fourier transformation with
The ratio of mean value is as pulse wave detection information.
In the present embodiment, the characteristic parameter include: pulse wave transmission time, shrink the rise time, diastolic time and
Time interval.
In the present embodiment, pulse wave transmission time refers to pressure pulse between heart and peripheral arterial position or two
The time advanced between artery site can use the biography between the pulse wave of two different parts (face and palm) in the present case
Defeated delay acquires；And rise time ST, diastolic time DT and time interval T1 are shunk, it is detected using the second peak detection algorithm
Naked-eye observation less than pulse wave second peak value, while pulse wave wave crest and trough are detected using extremum extracting algorithm,
Finally obtain ST, DT, T1；Its schematic diagram is as shown in Figure 3.
It in the present embodiment, include template matching and statistical learning to the pretreatment of the grey scale signal of the video image.
In the present embodiment, what imaging sensor acquired is not the light intensity of accurate three primary colours light, but cmos image
The schematic diagram of quantum efficiency of the sensor under Baeyer array three primary colours filter layer.Red luminous intensity is perceived on imaging sensor
Location of pixels can also sense that part is green, information of blue light, and the location of pixels for similarly perceiving green and blue luminous intensity also can
Sense the information of part red light.After being pre-processed from three grey scale change sequences of video extraction, through independent element point
Analysis ICA isolates pulse wave signal；ICA decomposition result has randomness, by independent element periodically strongest in decomposition result
As pulse wave component.It, should using the ratio of greatest measure and mean value in sequence obtained by the Fourier transformation of signal as index
The maximum independent element of index is the independent element for including pulse wave.
In the present embodiment, the grey scale signal change curve of three kinds of colors (RGB) of video image is as shown in figure 4, right
Average intensity change waveform in Fig. 4, is decomposed with FastICA algorithm, and the partial waveform of decomposition result is as shown in Figure 5；For
Noise in removal independent component selects stopband to decline faster Chebyshev type iir filter and carries out bandpass filtering, band logical
Filter passband is 0.8Hz~3Hz, and cutoff frequency is 0.5Hz and 4Hz, and passband maximum attenuation is 1dB, and minimum attenuation in stop band is
15dB.ICA decomposition result has randomness, the greatest measure and mean value in sequence obtained by our Fourier transformations signal
For ratio as index, the maximum independent element of the index is the independent element for including pulse wave.The pulse finally extracted
For wave as shown in fig. 6, solid line is the pulse wave signal that video finally extracts in Fig. 6, dotted line is the finger tip arteries and veins acquired with audio video synchronization
It fights wave signal.
As shown in Figure 10, in the present embodiment, the modeling module includes:
Modeling unit 41 is used for founding mathematical models；
Measuring unit 42 for measuring the real-time blood pressure of multiple groups, and obtains the corresponding characteristic parameter of the real-time blood pressure of the multiple groups；
Unit 43 is returned, is used for according to the real-time blood pressure of the multiple groups and its corresponding characteristic parameter, it is non-linear by unitary
Homing method demarcates the undetermined coefficient of the mathematical model.
In the present embodiment, the selection of regression equation should meet three conditions: 1, equation form should be with related substance
The basic theories of science is consistent, 2, equation have a higher degree of fitting, 3, the mathematical form of equation should be as simple as possible.Based on existing
There are technology and the above principle, there are three mathematical models relevant to this case:
It one, is the non-linear relation model of PTT and mean pressure, equation are as follows:
It, can be real according to the measured value of formula and PTT using the value of available suitable undetermined coefficient b, c of finite measurement
The monitoring of existing blood pressure P.
It two, is the linear relationship mould of pulse wave contraction rise time, diastolic time, time interval and systolic pressure, diastolic pressure
Type, wherein the linear relationship between systolic pressure and diastolic time DT are as follows:
SBP=a1·DT+b1
The linear relationship of diastolic pressure and time interval are as follows:
DBP=a2·T1+b2
It is practical to calculate this four parameters using two groups of systolic pressures and diastolic blood pressure values, but only acquiring with two groups of data
Pressure value error is larger, thus finally using the method for one-variable linear regression acquire four parameters a1, a2 in the regression model and
B1, b2, final realize determine systolic pressure and diastolic pressure using gained regression equation.
It three, is linear relation model between pulse wave transmission time and mean pressure, systolic pressure, diastolic pressure, equation are as follows:
P=a+bPTT
Wherein a, b are undetermined coefficient, related with the arterial vascular property of individual, and are occurred with the change of blood vessel elasticity
Variation.In short time, individual coefficient a, b are to maintain constant.
In the present embodiment, the undetermined coefficient of the mathematical model originally can use two groups of blood pressure and pulse wave conduction time values
Etc. features can be in the hope of, but for high-precision requirement, we are using spies such as measurement multiple groups blood pressure and pulse wave conduction times
The respective value of sign, and then pass through the calibration of unitary nonlinear regression progress coefficient.The real-time blood pressure of multiple groups be greater than etc.
In two groups.
Embodiment three
In the present embodiment, a kind of electronic equipment, including memory, processor and at least one be stored in the storage
In device and it is configured as the application program executed by the processor, the application program is configurable for executing embodiment one
The blood pressure data processing method.
Example IV
The embodiment of the present invention provides a kind of readable storage medium storing program for executing, is stored thereon with computer program, and the program is by processor
The embodiment of the method as described in any in above-mentioned blood pressure data processing method embodiment is realized when execution.
It should be noted that above-mentioned apparatus, equipment reality and readable storage medium storing program for executing embodiment and embodiment of the method belong to it is same
Design, specific implementation process is detailed in embodiment of the method, and the technical characteristic in embodiment of the method is right in Installation practice
It should be applicable in, which is not described herein again.
A kind of blood pressure data processing method, device, equipment and the readable storage medium storing program for executing of the embodiment of the present invention, this method packet
It includes: obtaining the video image of target area；Pulse wave information is obtained from video image, by the maximum value of the pulse wave information
Ratio with mean value is as pulse wave detection information；Extract the characteristic parameter in the pulse wave detection information；Divided by returning
Analysis method establishes the mathematical model of the characteristic parameter Yu real-time blood pressure, by the video figure for obtaining the sensitizing ranges such as face, palm
Picture therefrom accurately extracts pulse wave, and then obtains continuous blood pressure of the personage during recorded video in video by algorithm, realizes
The continuous measurement of blood pressure, has been completed at the same time the measurement of systolic pressure and diastolic pressure, cost is relatively low, it is easy to accomplish, versatility is higher.
Through the above description of the embodiments, those skilled in the art can be understood that above-described embodiment side
Method can be realized by means of software and necessary general hardware platform, naturally it is also possible to be realized by hardware, but very much
In the case of the former be more preferably embodiment.Based on this understanding, technical solution of the present invention is substantially in other words to existing
The part that technology contributes can be embodied in the form of software products, which is stored in a storage
In medium (such as ROM/RAM, magnetic disk, CD), including some instructions are used so that a terminal device (can be mobile phone, calculate
Machine, server, air conditioner or network equipment etc.) execute method described in each embodiment of the present invention.
Preferred embodiments of the present invention have been described above with reference to the accompanying drawings, not thereby limiting the scope of the invention.This
Field technical staff without departing from the scope and spirit of the invention in made by any modifications, equivalent replacements, and improvements, should all this
Within the interest field of invention.
Claims (10)
1. a kind of blood pressure data processing method characterized by comprising
Obtain the video image of target area；
Pulse wave information is obtained from video image, using the ratio of the maximum value of the pulse wave information and mean value as pulse wave
Detection information；
Extract the characteristic parameter in the pulse wave detection information；
The mathematical model of the characteristic parameter Yu real-time blood pressure is established by regression analysis.
2. a kind of blood pressure data processing method according to claim 1, which is characterized in that described to be obtained from video image
Pulse wave information, the ratio using the maximum value of the pulse wave information and mean value include: as pulse wave detection information
The grey scale signal of the video image is pre-processed；
Pulse wave component is isolated from the video image by independent component analysis method；
Fourier transformation is carried out to the pulse wave component, using the ratio of maximum value in Fourier transformation and mean value as pulse wave
Detection information.
3. a kind of blood pressure data processing method according to claim 2, which is characterized in that the characteristic parameter includes: arteries and veins
Fight wave transmission time, shrink rise time, diastolic time and time interval.
4. a kind of blood pressure data processing method according to claim 3, which is characterized in that described to be built by regression analysis
The mathematical model for founding the characteristic parameter and real-time blood pressure includes:
Founding mathematical models；
The real-time blood pressure of multiple groups is measured, and obtains the corresponding characteristic parameter of the real-time blood pressure of the multiple groups；
According to the real-time blood pressure of the multiple groups and its corresponding characteristic parameter, by unitary non-linear regression method to the mathematical modulo
The undetermined coefficient of type is demarcated.
5. a kind of blood pressure data processing unit characterized by comprising
Video acquiring module, for obtaining the video image of target area；
Pulse wave obtain module, for from video image obtain pulse wave information, by the maximum value of the pulse wave information with
The ratio of mean value is as pulse wave detection information；
Characteristic parameter extraction module, for extracting the characteristic parameter in the pulse wave detection information；
Modeling module, for establishing the mathematical model of the characteristic parameter Yu real-time blood pressure by regression analysis.
6. a kind of blood pressure data processing unit according to claim 1, which is characterized in that the pulse wave obtains module packet
It includes:
Pretreatment unit is pre-processed for the grey scale signal to the video image；
Separative unit, for isolating pulse wave component from the video image by independent component analysis method；
Selecting unit, for carrying out Fourier transformation to the pulse wave component, by maximum value in Fourier transformation and mean value
Ratio is as pulse wave detection information.
7. a kind of blood pressure data processing unit according to claim 6, which is characterized in that the characteristic parameter includes: arteries and veins
Fight wave transmission time, shrink rise time, diastolic time and time interval.
8. a kind of blood pressure data processing unit according to claim 7, which is characterized in that the modeling module includes:
Modeling unit is used for founding mathematical models；
Measuring unit for measuring the real-time blood pressure of multiple groups, and obtains the corresponding characteristic parameter of the real-time blood pressure of the multiple groups；
Unit is returned, for passing through unitary nonlinear regression side according to the real-time blood pressure of the multiple groups and its corresponding characteristic parameter
Method demarcates the undetermined coefficient of the mathematical model.
9. a kind of electronic equipment, including memory, processor and at least one be stored in the memory and be configured as
The application program executed by the processor, which is characterized in that the application program is configurable for perform claim and requires 1-4
Described in any item blood pressure data processing methods.
10. a kind of readable storage medium storing program for executing, which is characterized in that computer program is stored thereon with, when which is executed by processor
Realize the blood pressure data processing method as described in claim 1-4 is any.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810332101.7A CN110367961A (en) | 2018-04-13 | 2018-04-13 | Blood pressure data processing method, device, equipment and readable storage medium storing program for executing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810332101.7A CN110367961A (en) | 2018-04-13 | 2018-04-13 | Blood pressure data processing method, device, equipment and readable storage medium storing program for executing |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110367961A true CN110367961A (en) | 2019-10-25 |
Family
ID=68242991
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810332101.7A Pending CN110367961A (en) | 2018-04-13 | 2018-04-13 | Blood pressure data processing method, device, equipment and readable storage medium storing program for executing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110367961A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2020135723A1 (en) * | 2018-12-29 | 2020-07-02 | 中兴通讯股份有限公司 | Pulse wave detection method and device, and electronic device |
| CN113349751A (en) * | 2020-03-05 | 2021-09-07 | 深圳市理邦精密仪器股份有限公司 | Inflation and deflation control method and device and medical equipment |
| CN113397505A (en) * | 2021-06-25 | 2021-09-17 | 合肥综合性国家科学中心人工智能研究院(安徽省人工智能实验室) | Physiological signal detection method and system |
| CN117017249A (en) * | 2023-10-07 | 2023-11-10 | 深圳市爱保护科技有限公司 | Blood pressure detection method, device, electronic equipment and storage medium |
| CN117907622A (en) * | 2023-12-07 | 2024-04-19 | 重庆大学 | Sample suction detection method, sample suction detection device, and analyzer |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107692993A (en) * | 2017-11-08 | 2018-02-16 | 深圳市玉成创新科技有限公司 | A kind of blood pressure instrument |
-
2018
- 2018-04-13 CN CN201810332101.7A patent/CN110367961A/en active Pending
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107692993A (en) * | 2017-11-08 | 2018-02-16 | 深圳市玉成创新科技有限公司 | A kind of blood pressure instrument |
Non-Patent Citations (6)
| Title |
|---|
| MING-ZHER POH等: "Advancements in Noncontact, Multiparameter Physiological Measurements Using a Webcam", 《IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING》 * |
| 丁有得等: "基于容积脉搏波的血压参数测量与标定的方法研究", 《中国医疗器械杂志》 * |
| 余学飞等: "《现代医学电子仪器原理与设计》", 30 September 2007, 华南理工大学出版社 * |
| 李章俊等: "基于光电容积脉搏波描记法的无创连续血压测量", 《中国生物医学工程学报》 * |
| 李顶立等: "基于脉搏波速法的无创连续血压检测***", 《航天医学与医学工程》 * |
| 韩成等: "基于脉搏波的连续血压测量方法的研究进展", 《江西医药》 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2020135723A1 (en) * | 2018-12-29 | 2020-07-02 | 中兴通讯股份有限公司 | Pulse wave detection method and device, and electronic device |
| CN113349751A (en) * | 2020-03-05 | 2021-09-07 | 深圳市理邦精密仪器股份有限公司 | Inflation and deflation control method and device and medical equipment |
| CN113397505A (en) * | 2021-06-25 | 2021-09-17 | 合肥综合性国家科学中心人工智能研究院(安徽省人工智能实验室) | Physiological signal detection method and system |
| CN117017249A (en) * | 2023-10-07 | 2023-11-10 | 深圳市爱保护科技有限公司 | Blood pressure detection method, device, electronic equipment and storage medium |
| CN117017249B (en) * | 2023-10-07 | 2024-01-12 | 深圳市爱保护科技有限公司 | Blood pressure detecting device |
| CN117907622A (en) * | 2023-12-07 | 2024-04-19 | 重庆大学 | Sample suction detection method, sample suction detection device, and analyzer |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110367961A (en) | Blood pressure data processing method, device, equipment and readable storage medium storing program for executing | |
| CN107529646B (en) | Non-contact heart rate measurement method and device based on Euler image amplification | |
| US9795306B2 (en) | Method of estimating blood pressure based on image | |
| JP6308742B2 (en) | Blood pressure information output device, blood pressure information output program, medium, blood pressure information output method | |
| He et al. | Using Eulerian video magnification framework to measure pulse transit time | |
| CN109793506B (en) | Non-contact radial artery waveform extraction method | |
| CN107595271A (en) | Method for measuring heart rate, electronic equipment, storage medium and system based on mobile phone | |
| US20140200460A1 (en) | Real-time physiological characteristic detection based on reflected components of light | |
| US9936880B2 (en) | Camera based photoplethysmogram estimation | |
| US20200015688A1 (en) | Blood pressure measurement method, device and storage medium | |
| CN108403101A (en) | A kind of model training method and device, the method and device for measuring blood pressure | |
| WO2019216417A1 (en) | Model-setting device, blood pressure-measuring apparatus, and model-setting method | |
| US7285100B2 (en) | Method and equipment for analysing biological signals representing intercranial pressure and blood pressure variations | |
| CN111820870B (en) | Biological image processing method and physiological information detection device | |
| EP3318179B1 (en) | Method for measuring respiration rate and heart rate using dual camera of smartphone | |
| WO2020210813A1 (en) | Generating imaging-based neurological state biomarkers and estimating cerebrospinal fluid (csf) dynamics based on coupled neural and csf oscillations during sleep | |
| US7160250B2 (en) | Method and equipment for analyzing biological signals representing intracranial and blood pressure fluctuations | |
| CN105852863B (en) | Respiration rate measuring method and device | |
| Zairi et al. | Intelligent system for detecting cardiac arrhythmia on FPGA | |
| CN110517229B (en) | Pulse detection method, system, electronic device and storage medium | |
| CN109303573B (en) | Method for calculating fetal heart rate of embryo in early pregnancy according to hyperchromic blood flow graph in B-ultrasonic detection | |
| US20150182140A1 (en) | Arterial pulse analysis method and system thereof | |
| CN111970965B (en) | Model setting device, noncontact blood pressure measurement device, model setting method, and recording medium | |
| CN116327133A (en) | Multi-physiological index detection method, device and related equipment | |
| Pansare et al. | Heart Rate Measurement from Face and Wrist Video |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20191025 |
|
| RJ01 | Rejection of invention patent application after publication |