CN106236049A - Blood pressure measuring method based on video image - Google Patents
Blood pressure measuring method based on video image Download PDFInfo
- Publication number
- CN106236049A CN106236049A CN201610888102.0A CN201610888102A CN106236049A CN 106236049 A CN106236049 A CN 106236049A CN 201610888102 A CN201610888102 A CN 201610888102A CN 106236049 A CN106236049 A CN 106236049A
- Authority
- CN
- China
- Prior art keywords
- time
- blood pressure
- signal
- video image
- method based
- 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
- A61B5/0059—Measuring for diagnostic purposes; Identification of persons using light, e.g. diagnosis by transillumination, diascopy, fluorescence
- A61B5/0062—Arrangements for scanning
- A61B5/0064—Body surface scanning
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/0059—Measuring for diagnostic purposes; Identification of persons using light, e.g. diagnosis by transillumination, diascopy, fluorescence
- A61B5/0077—Devices for viewing the surface of the body, e.g. camera, magnifying lens
-
- 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
-
- 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
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7225—Details of analog processing, e.g. isolation amplifier, gain or sensitivity adjustment, filtering, baseline or drift compensation
-
- 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
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Animal Behavior & Ethology (AREA)
- Veterinary Medicine (AREA)
- Biophysics (AREA)
- Pathology (AREA)
- Public Health (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Medical Informatics (AREA)
- Molecular Biology (AREA)
- Surgery (AREA)
- General Health & Medical Sciences (AREA)
- Physiology (AREA)
- Cardiology (AREA)
- Signal Processing (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Psychiatry (AREA)
- Pulmonology (AREA)
- Power Engineering (AREA)
- Mathematical Physics (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Radiology & Medical Imaging (AREA)
- Vascular Medicine (AREA)
- Measuring Pulse, Heart Rate, Blood Pressure Or Blood Flow (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
The invention discloses a kind of blood pressure measuring method based on video image, by gathering the video image of human face, then face's video image is carried out spatial decomposition, time-domain filtering and processes in real time, it is achieved the continuous measurement of blood pressure.Specifically include: target area to be measured real-time tracking, determine ROI region;The each frame image sequence of ROI region obtained is carried out RGB triple channel separation, and the time series waveform obtained in a period of time of averaging of suing for peace;Above-mentioned time series waveform is gone trend term and is normalized, obtains time series signal;The method using empirical mode decomposition, carries out Denoising disposal to the signal after normalization, it is thus achieved that the three-channel time-domain signal that signal to noise ratio is higher;Finally ask for crest and the trough of time-domain signal, set up the relational expression of time-domain signal and blood pressure, thus obtain pressure value;For the field such as the collection of the big data of health and tele-medicine.
Description
Technical field
The present invention relates to a kind of blood pressure measuring method based on video image, for the collection and remotely of healthy big data
The fields such as medical treatment.
Background technology
The fields such as the physiological parameter acquisition of healthy big data and tele-medicine are required for the physiological parameter to human body and carry out
Long-term monitoring, these have positive effect about the data of health and fitness information to the physically and mentally healthy assessment of people.Existing physiology
Parameter (heart rate, breathing, blood pressure, blood oxygen etc.) acquisition method is to be acquired by the way of contact mostly, then passes through nothing
The data collected are transferred in computer store by the mode of line, in order to doctor carries out consulting, with reference to and assessment.Especially
It is blood pressure measurement, it is necessary to wearing cuff could measure, reaches the purpose measured through gas overcharging and venting, and measure the time relatively
Long, the metering system of this contact is the most inconvenient for monitored person, is difficulty with the continuous blood pressure monitoring of human body.
Patent of invention CN102499664B discloses the detection side of a kind of non-contact vital sign based on video image
Method and detecting system, this system can be fixed the video image of frame frequency continuous acquisition target to be measured, automatically be detected the ROI in image
(region of interesting) region, use independent component analysis signal is smoothed, then use multiple from
Method of correlation extracts frequency signal, isolates the frequency values of vital sign parameter signals from the multi channel signals that ROI region marks off, raw
Life sign frequency includes heart rate frequency signal and respiratory frequency signal.But this only obtains heart rate value and breathing
Rate value, does not obtain the pressure value of human body.Patent of invention CN105011921A discloses one and measures blood by video analysis
The method of pressure, first obtains the relation of human blood-pressure and tremulous pulse yardstick, by the tremulous pulse of side at the shallow table tremulous pulse of shooting human body
Video is also analyzed, and calculates the coefficient of association of blood pressure and tremulous pulse yardstick and then obtains blood pressure.This invention must obtain clearly
To blood-vessel image, just can obtain tremulous pulse yardstick information over time accurately, and then set up mathematical relationship with blood pressure.And
And vision sensor is required higher, need wrist type video equipment, increase measurement difficulty, be unfavorable for popularization and application.
Summary of the invention
Present invention aims to problems of the prior art, propose a kind of contactless blood pressure measurement side
Method, by gathering the video image of human face, then carries out spatial decomposition, time-domain filtering and locates in real time face's video image
Reason, it is achieved the continuous measurement of vital sign.
A kind of blood pressure measuring method based on video image of the present invention, uses the video information at the exposed position of human body to carry out people
The blood pressure measurement of body, specifically comprises the following steps that
(1) target area to be measured real-time tracking, determines ROI region;Gather the sequence of video images of human body detected part, it is thus achieved that one
Video in the section time, chooses ROI region to be analyzed;
(2) each frame image sequence of ROI region obtained is carried out RGB triple channel separation, and summation is averaged, it is thus achieved that one section
Time series waveform in time;
(3) above-mentioned time series waveform gone trend term and is normalized, obtaining time series signal;
(4) method using empirical mode decomposition, carries out Denoising disposal to the signal after normalization, it is thus achieved that signal to noise ratio is higher
Three-channel time-domain signal;
(5) finally ask for crest and the trough of time-domain signal, set up the relational expression of time-domain signal and blood pressure, thus obtain blood pressure
Value.
In described step (1), processed by common camera shooting, gather the sequence of video images of human body detected part.
Described target area to be measured is preferably face.
Detection method can monitor heart rate, breathing rate and blood pressure in real time, be applied to the collection of healthy big data with
And the field such as tele-medicine.
Accompanying drawing explanation
Fig. 1 is the blood pressure measurement flow chart of the embodiment of the present invention;
Fig. 2 is the time series signal figure of the embodiment of the present invention;
Fig. 3 is the Wave crest and wave trough schematic diagram of the embodiment of the present invention;
Fig. 4 is time series crest and the valley value of the embodiment of the present invention.
Detailed description of the invention
The present invention is further illustrated below in conjunction with specific embodiments and the drawings.
Embodiment
First, target area to be measured selects face, and under indoor sufficient light source, tested human body is general with collection video image
Logical photographic head distance 50-60cm, allows human body head remain stationary as far as possible, carries out the collection of human face video, and acquisition frame rate is
15 frames/second, the acquisition time of human face video is 30s or 60s.If the video time gathered is 30s, then altogether obtain
450, picture;If gathering 60s, that obtains 900 pictures altogether.The pixel value of the human face each frame picture obtained is
640*480.After the video information obtaining a period of time, we do and process as follows:
(1) real-time tracking of face area, determines region ROI interested.First we use cascade classifier to obtain video
The position of face in first frame, then uses track algorithm Kanade-Lucas-Tomasi (KLT) algorithm to carry out the reality of face
Time follow the tracks of, it is thus achieved that the region of each frame face in video.ROI is a rectangular region, and 80% then taken in ROI region enters
The intercepting of row image.
(2) in each two field picture intercepted, ROI image is carried out the R three-channel separation of G B, the ROI to each frame
The pixel value of each passage carry out suing for peace again divided by total pixel number, obtain the numerical value that each frame is corresponding, finally by this
A little data values are connected according to time order and function order, obtain an one-dimensional time series waveform.Its computing formula is as follows:
In formula, i represents the frame number of image, ViRepresent the pixel average of the i-th two field picture ROI region,I ij Represent the i-th two field picture ROI
Region jth pixel value, m is the line number of ROI region, and n is the columns of ROI region.
Each passage is carried out processed as above after, respectively obtain the One-dimension Time Series of R tri-passages of G B.
(3) after obtaining above-mentioned One-dimension Time Series waveform, smoothing prior method is used to enter One-dimension Time Series waveform
It is 10 that row removes trend term, smoothing parameter λ, and cut-off frequency is 0.059Hz.Then the signal removing trend term is normalized place
Reason, normalized formula is as follows:
Signal after x (t) is normalization in formula,V ’ i For removing the signal after trend term,uForV ’ i Average,әForV ’ i Standard
Difference.
The time series obtained is as shown in Figure 2.
(4) after obtaining normalized signal, signal is carried out empirical mode decomposition (Empirical Mode
Decomposition, EMD).This decomposition method is that signal decomposition becomes several intrinsic mode functions (Intrinsic Mode
Functions, IMFs), by removing the IMF of upper frequency, select residue IMFs to carry out summation and reconstruct signal.Use EMD
Purpose be that normalized signal is carried out Denoising disposal, in order to obtain high s/n ratio three-channel time-domain signal.
(5) the G channel signal after selecting denoising carries out the extraction of heart rate and breathing rate.
First having to signal is carried out bandpass filtering, when asking for heart rate value, the frequency threshold of band filter is that 0.7Hz arrives
4Hz, then carries out discrete Fourier transform and obtains frequency component f of heart rate the signal after bandpass filteringh, fh× 60 just for the heart
Rate value.
When asking for breathing rate, the frequency threshold of band filter is 0.3Hz to 0.7Hz, then to bandpass filtering after
Signal carries out discrete Fourier transform and obtains frequency component f of heart rater, fr× 60 just obtain breathing rate value.
(6) blood pressure measurement.Radially resonance theory think the blood circulation of human body with pressure to transmit energy, its footpath
To pulse pressure it is:
With face for measuring object, z is the distance that face arrives heart, and c is velocity of wave, and k is harmonic wave quantity, ak, bkShaking for harmonic wave
Width, ω Hk For angular frequency.Assuming that z Yu c is fixed value, signal is the most obvious with the 0th and the 1st harmonic wave, so by after the 1st harmonic wave
Harmonic wave is ignored, and above formula can be reduced to:
In formula, a0, b0It is the amplitude of 0 subharmonic, a1, b1Being the amplitude of 1 subharmonic, Q and R is 1 subharmonic amplitude.Can from above formula
To find out, the crest of time series signal, trough that we obtain have inevitable contacting with pressure wave.Normal physiological conditions
Under, small artery is beaten.Incident illumination due to the attenuation by absorption effect by integumentary musculature and blood, then optical receiver detect anti-
Penetrate light intensity will weaken.Wherein the non-blood composition such as skin, fat, muscle, skeleton is organized in cardiac cycle basic holding not
Becoming, it also keeps invariable to absorption and the attenuation of light, and these signals are exactly constant direct current after optical receiver
Component.In arteries in Zu Zhi blood then in cardiac cycle in cyclically-varying, when the heart contracts peripheral blood hold
At most, absorbing amount is the most maximum, and the light intensity detected is the most minimum for amount;And during diastole, contrast, the light intensity detected
Degree maximum, the signal making optical receiver receive is the AC compounent of periodically pulsing.Use face's video of photographic head shooting,
Can regard as the most reflective reception.So the crest of heart rate signal can regard diastolic pressure as, trough can be regarded as
Shrink pressure.Wave crest and wave trough schematic diagram is as shown in Figure 3.
After time series waveform after acquisition processes, ask for crest quantity and the trough quantity of this waveform.Try to achieve
Crest and valley value and number after, crest and the valley value of those clutter interference will be weeded out.Frame per second here be 15 frames/
Second, gather the data of 30s, 450 data points altogether.The heart rate assuming people is one minute 120 times, then 0.5s jumps, 0.5s
The interval that can collect 0.5*15=7.5 data point, crest and trough should be 0.25, say, that when crest and trough it
Between time less than 0.25s time, it should give up to fall this pair crest, valley value.By such computing, we finally obtain institute
The crest needed and valley value, as shown in Figure 4.
Contact closely owing to the body constitution performance figure (BMI) of people has with blood pressure, introduce BMI here as revising ginseng
Number, blood pressure and time-domain signal set up following relation:
Diastolic pressure:
Wherein, HDTable crest sequential value;BMI represents body constitution quality index;A, B, C are constants.
Shrink and press:
Wherein, HLTable trough sequential value;BMI represents body constitution quality index;D, E, F are constants.n1For the number of crest, n2For ripple
The number of paddy.
In application process, measure first by standard electronic sphygomanometer and visual sensing, it is thus achieved that many groups measure number simultaneously
According to, constant A, B, C, D, E, F are demarcated, it is thus achieved that can be carried out after these parameters measuring.
Use above-mentioned detection method to realize the continuous measurement of heart rate, breathing rate and blood pressure, set the video to certain time length
It is acquired processing, first obtains a frame face picture, it is carried out face tracking and identification, after face being detected, determines us
Region ROI to be analyzed, then carries out R G B triple channel and separates, the pixel of each passage is carried out summation and is averaged ROI
Value, it is judged that whether data point reaches the setting duration calculated.Without reaching, then return and read a frame picture, continue to gather
Computer Vision;If equal to the duration set, then the time series produced is carried out waveform and process, it is thus achieved that blood pressure etc.
Parameter.During measuring continuously, need more new data point, the data point of 5s the earliest will be rejected, increase the data of up-to-date 5s
Point.During measuring continuously, it is all that the video to fixing duration carries out processing acquisition vital sign parameter.By long-term prison
Survey these parameters, health analysis can be carried out for monitored person and doctor.
Claims (8)
1. a blood pressure measuring method based on video image, it is characterised in that comprise the following steps:
(1) target area to be measured real-time tracking, determines ROI region;Gather the sequence of video images of human body detected part, it is thus achieved that one
Video in the section time, chooses ROI region to be analyzed;
(2) each frame image sequence of ROI region obtained is carried out RGB triple channel separation, and summation is averaged, it is thus achieved that one section
Time series waveform in time;
(3) above-mentioned time series waveform gone trend term and is normalized, obtaining time series signal;
(4) method using empirical mode decomposition, carries out Denoising disposal to the signal after normalization, it is thus achieved that signal to noise ratio is higher
Three-channel time-domain signal;
(5) finally ask for crest and the trough of time-domain signal, set up the relational expression of time-domain signal and blood pressure, thus obtain blood pressure
Value.
Blood pressure measuring method based on video image the most according to claim 1, it is characterised in that in described step (1),
Processed by common camera shooting, gather the sequence of video images of human body detected part.
Blood pressure measuring method based on video image the most according to claim 1 and 2, it is characterised in that described mesh to be measured
Mark region is preferably face.
Blood pressure measuring method based on video image the most according to claim 3, it is characterised in that use in step (1)
Cascade classifier obtains the position of face in video the first frame, then uses KLT algorithm to carry out real-time tracking, it is thus achieved that every in video
The region of one frame face;Take in ROI region 80% intercepting carrying out image.
Blood pressure measuring method based on video image the most according to claim 4, it is characterised in that to often in step (2)
The pixel value of each passage of one frame ROI carries out suing for peace again divided by total pixel number, obtains the numerical value that each frame is corresponding, then
These data values are connected according to time order and function order, obtain an one-dimensional time series waveform.
Blood pressure measuring method based on video image the most according to claim 5, it is characterised in that to upper in step (3)
Stating One-dimension Time Series waveform uses smoothing prior method to carry out trend term, smoothing parameter λ is 10, and cut-off frequency is
0.059Hz is normalized again, and normalized formula is as follows:
Signal after x (t) is normalization in formula,V ’ i For removing the signal after trend term,uForV ’ i Average,әForV ’ i Standard
Difference.
Blood pressure measuring method based on video image the most according to claim 6, it is characterised in that in step (5), radially
Pulse pressure is:
A in formula0Being the amplitude of 0 subharmonic, Q and R is 1 subharmonic amplitude.
Blood pressure measuring method based on video image the most according to claim 7, it is characterised in that in step (5), crest
For diastolic pressure, trough is contraction pressure, diastolic pressure:
Wherein, HDTable crest sequential value;BMI represents body constitution quality index;A, B, C are constants, n1Number for crest;
Shrink and press:
Wherein, HLTable trough sequential value;BMI represents body constitution quality index;D, E, F are constants, n2Number for trough.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610888102.0A CN106236049A (en) | 2016-10-12 | 2016-10-12 | Blood pressure measuring method based on video image |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610888102.0A CN106236049A (en) | 2016-10-12 | 2016-10-12 | Blood pressure measuring method based on video image |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106236049A true CN106236049A (en) | 2016-12-21 |
Family
ID=57611450
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610888102.0A Pending CN106236049A (en) | 2016-10-12 | 2016-10-12 | Blood pressure measuring method based on video image |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106236049A (en) |
Cited By (15)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107910072A (en) * | 2017-12-11 | 2018-04-13 | 创业软件股份有限公司 | For equal line trend parameter determination method in the medical data mining process that preventives treatment of disease |
CN109247923A (en) * | 2018-11-15 | 2019-01-22 | 中国科学院自动化研究所 | Contactless pulse real-time estimation method and equipment based on video |
CN110236508A (en) * | 2019-06-12 | 2019-09-17 | 云南东巴文健康管理有限公司 | A kind of non-invasive blood pressure continuous monitoring method |
CN111281367A (en) * | 2018-12-10 | 2020-06-16 | 绍兴图聚光电科技有限公司 | Anti-interference non-contact heart rate detection method based on face video |
CN111358455A (en) * | 2020-03-17 | 2020-07-03 | 乐普(北京)医疗器械股份有限公司 | Blood pressure prediction method and device with multiple data sources |
CN111554398A (en) * | 2020-05-11 | 2020-08-18 | 济南浪潮高新科技投资发展有限公司 | Remote vital sign evaluation method and system based on 5G |
CN111854920A (en) * | 2020-07-24 | 2020-10-30 | 贵州电网有限责任公司 | Preprocessing method and system based on DVS vibration monitoring signal |
CN112244796A (en) * | 2020-11-09 | 2021-01-22 | 联合维度(广州)科技有限公司 | Method for intelligently detecting human body physiological indexes and nursing equipment |
CN112597789A (en) * | 2019-09-03 | 2021-04-02 | 株式会社东书产业 | Blood pressure estimation system, blood pressure estimation method, learning device, learning method, and program |
CN113040734A (en) * | 2021-03-04 | 2021-06-29 | 西北工业大学 | Non-contact blood pressure estimation method based on signal screening |
CN113712526A (en) * | 2021-09-30 | 2021-11-30 | 四川大学 | Pulse wave extraction method and device, electronic equipment and storage medium |
CN114081464A (en) * | 2021-10-25 | 2022-02-25 | 北京极豪科技有限公司 | Heart rate detection method and device and electronic equipment |
CN116098598A (en) * | 2022-12-27 | 2023-05-12 | 北京镁伽机器人科技有限公司 | Heart-like wave crest detection and heart rate determination methods and related products |
CN116433538A (en) * | 2023-06-15 | 2023-07-14 | 加之创(厦门)科技有限公司 | Image processing method, medium and device for video image health monitoring |
WO2023184832A1 (en) * | 2022-03-31 | 2023-10-05 | 上海商汤智能科技有限公司 | Physiological state detection method and apparatus, electronic device, storage medium, and program |
-
2016
- 2016-10-12 CN CN201610888102.0A patent/CN106236049A/en active Pending
Cited By (19)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107910072A (en) * | 2017-12-11 | 2018-04-13 | 创业软件股份有限公司 | For equal line trend parameter determination method in the medical data mining process that preventives treatment of disease |
CN109247923A (en) * | 2018-11-15 | 2019-01-22 | 中国科学院自动化研究所 | Contactless pulse real-time estimation method and equipment based on video |
CN109247923B (en) * | 2018-11-15 | 2020-12-15 | 中国科学院自动化研究所 | Non-contact type pulse real-time estimation method and device based on video |
CN111281367A (en) * | 2018-12-10 | 2020-06-16 | 绍兴图聚光电科技有限公司 | Anti-interference non-contact heart rate detection method based on face video |
CN110236508A (en) * | 2019-06-12 | 2019-09-17 | 云南东巴文健康管理有限公司 | A kind of non-invasive blood pressure continuous monitoring method |
CN112597789A (en) * | 2019-09-03 | 2021-04-02 | 株式会社东书产业 | Blood pressure estimation system, blood pressure estimation method, learning device, learning method, and program |
CN111358455B (en) * | 2020-03-17 | 2022-07-29 | 乐普(北京)医疗器械股份有限公司 | Blood pressure prediction method and device with multiple data sources |
CN111358455A (en) * | 2020-03-17 | 2020-07-03 | 乐普(北京)医疗器械股份有限公司 | Blood pressure prediction method and device with multiple data sources |
CN111554398A (en) * | 2020-05-11 | 2020-08-18 | 济南浪潮高新科技投资发展有限公司 | Remote vital sign evaluation method and system based on 5G |
CN111854920A (en) * | 2020-07-24 | 2020-10-30 | 贵州电网有限责任公司 | Preprocessing method and system based on DVS vibration monitoring signal |
CN112244796A (en) * | 2020-11-09 | 2021-01-22 | 联合维度(广州)科技有限公司 | Method for intelligently detecting human body physiological indexes and nursing equipment |
CN113040734A (en) * | 2021-03-04 | 2021-06-29 | 西北工业大学 | Non-contact blood pressure estimation method based on signal screening |
CN113040734B (en) * | 2021-03-04 | 2024-05-03 | 西北工业大学 | Non-contact blood pressure estimation method based on signal screening |
CN113712526A (en) * | 2021-09-30 | 2021-11-30 | 四川大学 | Pulse wave extraction method and device, electronic equipment and storage medium |
CN113712526B (en) * | 2021-09-30 | 2022-12-30 | 四川大学 | Pulse wave extraction method and device, electronic equipment and storage medium |
CN114081464A (en) * | 2021-10-25 | 2022-02-25 | 北京极豪科技有限公司 | Heart rate detection method and device and electronic equipment |
WO2023184832A1 (en) * | 2022-03-31 | 2023-10-05 | 上海商汤智能科技有限公司 | Physiological state detection method and apparatus, electronic device, storage medium, and program |
CN116098598A (en) * | 2022-12-27 | 2023-05-12 | 北京镁伽机器人科技有限公司 | Heart-like wave crest detection and heart rate determination methods and related products |
CN116433538A (en) * | 2023-06-15 | 2023-07-14 | 加之创(厦门)科技有限公司 | Image processing method, medium and device for video image health monitoring |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106236049A (en) | Blood pressure measuring method based on video image | |
Fan et al. | Robust blood pressure estimation using an RGB camera | |
RU2675036C2 (en) | Device and method for obtaining information about vital signs of subject | |
CN102499664B (en) | Video-image-based method and system for detecting non-contact vital sign | |
CN106413533B (en) | Apparatus, system and method for detecting apnea of a subject | |
US20160317041A1 (en) | System and methods for measuring physiological parameters | |
CN107358220A (en) | A kind of human heart rate and the contactless measurement of breathing | |
Fan et al. | Non-contact remote estimation of cardiovascular parameters | |
CN103826532A (en) | Remote monitoring of vital signs | |
CN112233813A (en) | Non-contact non-invasive heart rate and respiration measurement method and system based on PPG | |
CN110647815A (en) | Non-contact heart rate measurement method and system based on face video image | |
Chen et al. | Respiratory rate estimation from face videos | |
CN110236508A (en) | A kind of non-invasive blood pressure continuous monitoring method | |
Zhou et al. | The noninvasive blood pressure measurement based on facial images processing | |
CN111275018A (en) | Non-contact heart rate signal extraction method based on annular region of interest weighting | |
Karthick et al. | Analysis of vital signs using remote photoplethysmography (RPPG) | |
KR101996027B1 (en) | Method and system for extracting Heart Information of Frequency domain by using pupil size variation | |
Wiede et al. | Signal fusion based on intensity and motion variations for remote heart rate determination | |
Malasinghe et al. | A comparative study of common steps in video-based remote heart rate detection methods | |
Hu et al. | Study on Real-Time Heart Rate Detection Based on Multi-People. | |
Carter et al. | Deep Learning-Enabled Sleep Staging From Vital Signs and Activity Measured Using a Near-Infrared Video Camera | |
Ben Salah et al. | Contactless heart rate estimation from facial video using skin detection and multi-resolution analysis | |
CN114246570A (en) | Near-infrared heart rate detection method with peak signal-to-noise ratio and Pearson correlation coefficient fused | |
Wang et al. | KLT algorithm for non-contact heart rate detection based on image photoplethysmography | |
Hassan et al. | Towards health monitoring in visual surveillance |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | 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: 20161221 |
|
RJ01 | Rejection of invention patent application after publication |