CN110384491A - A kind of heart rate detection method based on common camera - Google Patents
A kind of heart rate detection method based on common camera Download PDFInfo
- Publication number
- CN110384491A CN110384491A CN201910774697.0A CN201910774697A CN110384491A CN 110384491 A CN110384491 A CN 110384491A CN 201910774697 A CN201910774697 A CN 201910774697A CN 110384491 A CN110384491 A CN 110384491A
- Authority
- CN
- China
- Prior art keywords
- signal
- frame
- heart rate
- matrix
- image
- 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
- A61B5/0077—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
- A61B5/024—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
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/50—Extraction of image or video features by performing operations within image blocks; by using histograms, e.g. histogram of oriented gradients [HoG]; by summing image-intensity values; Projection analysis
- G06V10/507—Summing image-intensity values; Histogram projection analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/56—Extraction of image or video features relating to colour
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/168—Feature extraction; Face representation
- G06V40/171—Local features and components; Facial parts ; Occluding parts, e.g. glasses; Geometrical relationships
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30048—Heart; Cardiac
Landscapes
- Health & Medical Sciences (AREA)
- Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Molecular Biology (AREA)
- Animal Behavior & Ethology (AREA)
- Theoretical Computer Science (AREA)
- Biophysics (AREA)
- Pathology (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Veterinary Medicine (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Surgery (AREA)
- General Physics & Mathematics (AREA)
- Public Health (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Physiology (AREA)
- Multimedia (AREA)
- Artificial Intelligence (AREA)
- Cardiology (AREA)
- Signal Processing (AREA)
- Psychiatry (AREA)
- Quality & Reliability (AREA)
- Radiology & Medical Imaging (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Human Computer Interaction (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
The present invention relates to biomedical engineering technology field, specifically a kind of heart rate detection method based on common camera.Face front video image is acquired using common camera first, human face region is extracted from image using Face datection algorithm and face tracking technology, it chooses and positions forehead as area-of-interest, region of interesting extraction is come out, the region as acquisition signal；Then using technologies such as primary colours separation and independent component analysis, pulse source signal is extracted from area-of-interest, and handle it using wavelet filtering, obtain pure pulse wave；Signal is finally transformed from the time domain into frequency domain using discrete fourier transform algorithm, analyzed after obtaining energy spectrum and calculates heart rate value.The present invention effectively improves detection efficiency and the usage experience of testee, is suitable for prolonged rhythm of the heart and disease prevention.
Description
Technical field
The present invention relates to biomedical engineering technology field, specifically a kind of heart rate detection based on common camera
Method.
Background technique
In recent years, video image processing was related to medical domain, and it is each to be applied to medical diagnosis and routine health monitoring etc.
Link has played powerful booster action for the progress of medicine.Heart rate is human metabolism and the important physiology of functional activity
One of parameter.The most accurate method of traditional heart rate measurement is b12extrocardiography, but electrode need to be sticked to testee's skin by b12extrocardiography
On skin, this method use it is more complex inconvenient, and this method need and direct skin contact, can cause tested
The dislike of person, therefore be very restricted in use, the heart rate detection not being suitable under common scenarios.And it is contactless
Heart rate detection only need to by common camera can automatically monitor heart rate, have the characteristics that easy to operate, at low cost.
PPG, that is, photoplethysmographic graphical method is a kind of utilization photoelectricity means Non-invasive detection blood in living tissue
The method of volume variation, it traces volumetric blood pulse (BVP) letter by measuring the intensity of reflected light after living tissue absorbs
Heart rate is calculated after number.Fu Mingzhe et al. proposes to utilize the contactless heart rate detection method of general network camera earliest.The party
Three average color traces are separated into three base source signals using independent component analysis (ICA) by method, pass through analysis second
The power Spectral Estimation heart rate of base source signal.Above method requires tester to be in cooperation and needs bright and clear situation
Lower measurement.And when light is weaker, it can include extra noise that it is difficult to extract BVP signals clean out for this method, therefore simultaneously
The contactless heart rate detection problem under varying environment light real scene is not can be well solved.
Summary of the invention
The present invention is intended to provide a kind of heart rate detection method based on common camera, to realize the noninvasive continuous non-of heart rate
Contact measurement, and it is at low cost, easy to operate, performance is stable, reproducible.
In order to solve the above technical problems, the technical solution adopted by the present invention are as follows: a kind of heart rate based on common camera
Detection method, comprising the following steps:
Step 1) carries out illumination compensation using the method video comprising face collected to camera of histogram equalization,
The video after illumination compensation is carried out Face datection and separates human face region to extract using AdaBoost algorithm, to obtain video
In each frame human face region image, the forehead region of the image of each frame human face region is intercepted, is obtained in video every
The image in one frame forehead region；
Step 2 carries out algorithm process to the image in each frame forehead region obtained in step 1), obtains pulse wave source signal,
Detailed process is as follows:
A, primary colours separate, and the separation of RGB triple channel are carried out to the image in each frame forehead region obtained in step 1), to each frame
The pixel value in each channel of forehead area image summed after divided by total pixel number, obtain each frame forehead area image
The corresponding numerical value in each channel, by obtained all numerical value according to chronological order connect to get arrive R, G, B tri-
Signal in a time domain；
For t frame forehead area image, it is assumed that the scale in forehead region is M × N, is owned using superposed average method in region
Three component x of pixelr,gr,brMean value is taken respectively, then the pixel value in every frame image difference channel are as follows:
,
The observation signal of t frame forehead area image can be obtained after above-mentioned processing, and, t therein is the time series of video frame；
B, independent component analysis
Using ICA algorithm in tri- time domains of R, G, B signal carry out blind source separating, and from the signal isolated choose with it is green
The maximum component of chrominance signal relevance is as PPG signal, and detailed process is as follows:
Average value processing is gone to observation signal first to simplify ICA algorithm, then to going the observation signal after mean value to carry out at albefaction
Reason, to remove the correlation of data and the extraction process of simplified isolated component in mixed signal, whitening processing needs first to ask former
Then the covariance matrix of matrix carries out Eigenvalues Decomposition, can use a n-dimensional vector X, its covariance matrix cov (X)
Following formula calculates:,
The eigenvalue matrix L and feature vector Q for seeking covariance matrix, acquire whitening matrix M:
,
Matrix is after albefaction are as follows:
,
Assuming that the color change signals generated under key role are s1(t), color change signals caused by face shakes are s2
(t), color change signals caused by illumination are s3(t), according to mixed process assumed above, it is available below formula:
,
It is rewritten into matrix form:, therein
,,It is mixing coefficient matrix；It is mutually independent that each component is found by ICA algorithm
Matrix W makesApproximate matrix, to obtain, whereinFor to source signal
Approximation；
Step 3) handles pulse wave source signal obtained in step 2 to obtain volumetric blood pulse wave by wavelet filtering；
The pulse wave signal extracted in step 3) is transformed from the time domain to frequency domain by discrete Fourier transform by step 4), is seen
The signal for examining normal heart rate range 0.7-4Hz, corresponding frequency is flat as this time when taking the range self-energy maximum
Equal heart rate, selecting frequency are located at the corresponding frequency in energy highest point in heartbeat frequency band as palmic rate, then heart rate HR
For。
Beneficial effect
The present invention fetters problem for the complicated for operation and limbs of contact heart rate measurement, proposes a kind of heart based on face video
Rate detection method.The technology can only be monitored by common camera automatically without using electrode or sensor contacts human body
Heart rate.Detection efficiency and the usage experience of testee are effectively improved, prolonged rhythm of the heart and disease prevention are suitable for；
Present invention employs independent component analysis, and carry out mean value and whitening processing to signal, simplify the extraction process of isolated component,
Arithmetic speed is effectively raised, makes contactless heart rate detection technology that there is better usage experience, there is at low cost, operation
The features such as simplicity, performance are stable, reproducible, the development for intelligent medical in the following Internet of Things are had laid a good foundation, and
Have great importance to the physiology monitoring of astronaut, improves the practical significance of the technology.
Detailed description of the invention
Fig. 1 is the flow chart of method for measuring heart rate；
Fig. 2 is face overhaul flow chart；
Fig. 3 is the filter result of the first component in embodiment；
Fig. 4 is the filter result of second component in embodiment；
Fig. 5 is three-component filter result in embodiment；
Fig. 6 is the spectrogram of the first component in embodiment；
Fig. 7 is the spectrogram of second component in embodiment；
Fig. 8 is three-component spectrogram in embodiment.
Specific embodiment
As shown in Figure 1, a kind of heart rate detection method based on common camera of the invention, first progress Face datection,
Then it chooses forehead and reduces the interference to signal extraction such as eyes, eyebrow, hair as area-of-interest, then extract pulse
Source signal, signal denoising, finally calculate heart rate, specifically includes the following steps:
Step 1) Face datection
The face part in the shot the video image of camera is split into detection, process such as Fig. 2 institute using AdaBoost algorithm
Show, to obtain the image of each frame human face region in video.Since illumination variation will affect the effect of Face datection, in face
Before detection, need to carry out illumination compensation to image.Histogram equalization, which can eliminate illumination condition variation bring, to be influenced.Cause
This carries out illumination compensation to face video before carrying out Face datection, using the method for histogram equalization.
The video after illumination compensation is carried out Face datection and separates human face region to extract using AdaBoost algorithm, with
The image of each frame human face region in video is obtained, the forehead region of the image of each frame human face region is intercepted, is obtained
The image in each frame forehead region in video；
Step 2, pulse wave source extraction
Primary colours separation, independent composition analysis algorithm processing are carried out to the image in each frame forehead region obtained in step 1), obtained
To pulse wave source signal, detailed process is as follows:
A, primary colours separate, because the color change of face reflects the process of heartbeat, so first have to do is exactly color change
Signal extraction come out.
The separation of RGB triple channel is carried out to the image in each frame forehead region obtained in step 1), to each frame forehead area
The pixel value in each channel of area image summed after divided by total pixel number, obtain each of each frame forehead area image
The corresponding numerical value in a channel connects obtained all numerical value to get tri- time domains of R, G, B are arrived according to chronological order
On signal；
For t frame forehead area image, it is assumed that the scale in forehead region is M × N, is owned using superposed average method in region
Three component x of pixelr,gr,brMean value is taken respectively, then the pixel value in every frame image difference channel are as follows:
,
The observation signal of t frame forehead area image can be obtained after above-mentioned processing, and, t therein is the time series of video frame；
B, independent component analysis
Using ICA algorithm in tri- time domains of R, G, B signal carry out blind source separating, and from the signal isolated choose with it is green
The maximum component of chrominance signal relevance is as PPG signal, and detailed process is as follows:
Average value processing is gone to observation signal first to simplify ICA algorithm, then to going the observation signal after mean value to carry out at albefaction
Reason, to remove the correlation of data and the extraction process of simplified isolated component in mixed signal, whitening processing needs first to ask former
Then the covariance matrix of matrix carries out Eigenvalues Decomposition, can use a n-dimensional vector X, its covariance matrix cov (X)
Following formula calculates:,
This method has obtained one 3 × 3 covariance matrix, asks the eigenvalue matrix L and feature vector Q of covariance matrix, asks
Obtain whitening matrix M:
,
Matrix is after albefaction are as follows:
,
Assuming that the color change signals generated under key role are s1(t), color change signals caused by face shakes are s2
(t), color change signals caused by illumination are s3(t), according to mixed process assumed above, it is available below formula:
,
It is rewritten into matrix form:, therein
,,It is mixing coefficient matrix；The purpose of ICA algorithm is exactly that find each component mutual
Independent matrix W, makesApproximate matrix, to obtain, whereinTo believe source
NumberApproximation；
By carrying out primary colours separation, independent component analysis processing to forehead region, pulse wave source signal is obtained；
Step 3), signal denoising
It handles pulse wave source signal obtained in step 2 to obtain volumetric blood pulse wave by wavelet filtering.Due to using general
It, inevitably can (camera be unstable, light because of the influence of extraneous factor during logical camera acquisition a period of time video image
Line intensity etc.), noise is introduced, to keep collected signal contaminated, influences subsequent processing.In addition, in PPG signal in addition to
There is heart rate signal, also contain a series of low-frequency noise, as caused by breathing, the trembling of body and Skeletal Muscle Contraction etc.
Low-frequency noise, thus want to improve signal-to-noise ratio, more intuitive volumetric blood pulse waveform is obtained, needs to carry out source signal
Denoising.This method is by wavelet transformation to signal denoising.Denoising be exactly in order to by optimal signal from containing much noise
Data in separate.Signal needed for this method is low frequency signal, and detailed process is as follows:
A, Decomposition order selects:
In wavelet decomposition, it is critically important for selecting Decomposition order.Decomposition order is bigger, gets over to the differentiation effect of noise and signal
Obviously, but reconstruction signal distortion also can be bigger, and influences the effect of denoising, and it is optimal for selecting suitable Decomposition order.
B, threshold value selects:
Threshold value selects the effect for being directly related to signal denoising.Threshold value is too small, cannot completely remove noise；Threshold value is excessive, needs
Signal can also be filtered out, be distorted, therefore suitable threshold value should be selected to reach best filter effect.Threshold process point
For Soft thresholding and hard threshold method.Soft-threshold processing denoising effect is smoother and ideal, therefore selects Soft thresholding.
C, choice of mother wavelet:
Different wavelet basis functions is selected to will have a direct impact on denoising effect.The selection of wavelet basis function will consider orthogonality, tight branch
The factors such as property, symmetry, flatness, disappearance order of a matrix number, due to collected data be it is discrete, in order to carry out discrete wavelet
Transformation, selects sym8 as wavelet basis function.
The denoising effect of tri- components of the present embodiment ICA as shown in figure 3, figure 4 and figure 5, there it can be seen that logical with green
Maximally related road mixed signal is ICA second component, so this method selects second ICA component to be analyzed.
Step 4), heart rate value extract
Fourier transformation is carried out to the volumetric blood pulse wave that step 3) obtains, power spectrum is obtained, by analyzing power Spectral Estimation
Heart rate out.Detailed process is as follows:
Fourier transformation is a kind of linear integral operation, commonly used in converting frequency-region signal for time-domain signal.Assuming that there is company
Continuous periodic signal, and have for arbitrary t, enable,Fourier space can indicate are as follows:.Wherein,,WithReferred to as Fourier is
Number, periodIt is the primitive period,It is fundamental wave radian frequency.
The pulse wave signal extracted in step 3) is transformed from the time domain to frequency domain using discrete Fourier transform by this method.
Since normal heart rate range is 0.7-4Hz, the signal of heart rate range frequency is only observed now, when taking the range self-energy maximum
Average heart rate of the corresponding frequency as this time, here it is the methods that heart rate is calculated on frequency domain.Selecting frequency is located at the heart
The corresponding frequency in energy highest point in frequency hopping band is as palmic rate, then heart rate HR be。
If Fig. 6, Fig. 7, Fig. 8 are the power spectrum charts of the three-component pulse source signal of ICA, there it can be seen that 0.7-4Hz model
Enclosing the corresponding frequency in energy highest point in interior three-component power spectrum is respectively 1.09,1.211,1.09, calculate heart rate HR1=
1.09 × 60=65.4 ≈ 65, HR2=1.211 × 60=72.66 ≈ 73, HR3=1.09 × 60=65.4 ≈ 65, are surveyed by blood pressure device
The heart rate of amount is 74, so second ICA component is best.
Claims (1)
1. a kind of heart rate detection method based on common camera, it is characterised in that: the following steps are included:
Step 1) carries out illumination compensation using the method video comprising face collected to camera of histogram equalization,
The video after illumination compensation is carried out Face datection and separates human face region to extract using AdaBoost algorithm, to obtain video
In each frame human face region image, the forehead region of the image of each frame human face region is intercepted, is obtained in video every
The image in one frame forehead region；
Step 2 carries out algorithm process to the image in each frame forehead region obtained in step 1), obtains pulse wave source signal,
Detailed process is as follows:
A, primary colours separate, and the separation of RGB triple channel are carried out to the image in each frame forehead region obtained in step 1), to each frame
The pixel value in each channel of forehead area image summed after divided by total pixel number, obtain each frame forehead area image
The corresponding numerical value in each channel, by obtained all numerical value according to chronological order connect to get arrive R, G, B tri-
Signal in a time domain；
For t frame forehead area image, it is assumed that the scale in forehead region is M × N, is owned using superposed average method in region
Three component x of pixelr,gr,brMean value is taken respectively, then the pixel value in every frame image difference channel are as follows:
,
The observation signal of t frame forehead area image can be obtained after above-mentioned processing, and, t therein is the time series of video frame；
B, independent component analysis
Using ICA algorithm in tri- time domains of R, G, B signal carry out blind source separating, and from the signal isolated choose with it is green
The maximum component of chrominance signal relevance is as PPG signal, and detailed process is as follows:
Average value processing is gone to observation signal first to simplify ICA algorithm, then to going the observation signal after mean value to carry out at albefaction
Reason, to remove the correlation of data and the extraction process of simplified isolated component in mixed signal, whitening processing needs first to ask former
Then the covariance matrix of matrix carries out Eigenvalues Decomposition, can use a n-dimensional vector X, its covariance matrix cov (X)
Following formula calculates:,
The eigenvalue matrix L and feature vector Q for seeking covariance matrix, acquire whitening matrix M:
,
Matrix is after albefaction are as follows:
,
Assuming that the color change signals generated under key role are s1(t), color change signals caused by face shakes are s2(t),
Color change signals caused by illumination are s3(t), according to mixed process assumed above, it is available below formula:
,
It is rewritten into matrix form:, therein
,,It is mixing coefficient matrix；It is mutually independent that each component is found by ICA algorithm
Matrix W makesApproximate matrix, to obtain, whereinFor to source signal
Approximation；
Step 3) handles pulse wave source signal obtained in step 2 to obtain volumetric blood pulse wave by wavelet filtering；
The pulse wave signal extracted in step 3) is transformed from the time domain to frequency domain by discrete Fourier transform by step 4), is seen
The signal for examining normal heart rate range 0.7-4Hz, corresponding frequency is flat as this time when taking the range self-energy maximum
Equal heart rate, selecting frequency are located at the corresponding frequency in energy highest point in heartbeat frequency band as palmic rate, then heart rate HR
For。
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910774697.0A CN110384491A (en) | 2019-08-21 | 2019-08-21 | A kind of heart rate detection method based on common camera |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910774697.0A CN110384491A (en) | 2019-08-21 | 2019-08-21 | A kind of heart rate detection method based on common camera |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110384491A true CN110384491A (en) | 2019-10-29 |
Family
ID=68289043
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910774697.0A Pending CN110384491A (en) | 2019-08-21 | 2019-08-21 | A kind of heart rate detection method based on common camera |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110384491A (en) |
Cited By (22)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111310673A (en) * | 2020-02-20 | 2020-06-19 | 无锡市宏宇汽车配件制造有限公司 | Sleepiness prediction method, device and storage medium |
| CN111345802A (en) * | 2020-03-16 | 2020-06-30 | 南京润楠医疗电子研究院有限公司 | Device and method for acquiring double heartbeat frequency based on cardiac shock signal |
| CN111444797A (en) * | 2020-03-16 | 2020-07-24 | 五邑大学 | Non-contact heart rate detection method |
| CN111513701A (en) * | 2020-05-26 | 2020-08-11 | 上海眼控科技股份有限公司 | Heart rate detection method and device, computer equipment and readable storage medium |
| CN111767788A (en) * | 2020-05-12 | 2020-10-13 | 贵阳像树岭科技有限公司 | Non-interactive monocular in vivo detection method |
| CN111797794A (en) * | 2020-07-13 | 2020-10-20 | 中国人民公安大学 | Facial dynamic blood flow distribution detection method |
| CN112043257A (en) * | 2020-09-18 | 2020-12-08 | 合肥工业大学 | Non-contact video heart rate detection method for motion robustness |
| CN112200099A (en) * | 2020-10-14 | 2021-01-08 | 浙江大学山东工业技术研究院 | Video-based dynamic heart rate detection method |
| CN112233813A (en) * | 2020-09-28 | 2021-01-15 | 兰州大学 | Non-contact non-invasive heart rate and respiration measurement method and system based on PPG |
| CN112507930A (en) * | 2020-12-16 | 2021-03-16 | 华南理工大学 | Method for improving human face video heart rate detection by using illumination balancing method |
| CN112494026A (en) * | 2020-09-07 | 2021-03-16 | 南京云思创智信息科技有限公司 | Non-contact-based remote sudden cardiac death early warning method |
| CN112507877A (en) * | 2020-12-08 | 2021-03-16 | 北京工业大学 | System and method for detecting heart rate under condition of partial video information loss |
| CN112690771A (en) * | 2020-12-09 | 2021-04-23 | 华南理工大学 | Human face video heart rate detection method using linear regression model |
| WO2021104129A1 (en) * | 2019-11-25 | 2021-06-03 | 虹软科技股份有限公司 | Heart rate estimation method and apparatus, and electronic device applying same |
| 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 |
| CN112949349A (en) * | 2019-12-09 | 2021-06-11 | 南宁莲现健康科技有限公司 | Method and system for displaying pulse condition waveform in real time based on face video |
| CN113058110A (en) * | 2021-03-17 | 2021-07-02 | 董建成 | Method and system for detecting venous transfusion extravasation |
| CN113252929A (en) * | 2021-07-05 | 2021-08-13 | 格创东智(深圳)科技有限公司 | Rotating speed determination method and device, electronic equipment and computer readable storage medium |
| WO2021184620A1 (en) * | 2020-03-19 | 2021-09-23 | 南京昊眼晶睛智能科技有限公司 | Camera-based non-contact heart rate and body temperature measurement method |
| CN113591769A (en) * | 2021-08-10 | 2021-11-02 | 北京航空航天大学 | Non-contact heart rate detection method based on photoplethysmography |
| CN114431849A (en) * | 2022-01-10 | 2022-05-06 | 厦门大学 | Aquatic animal heart rate detection method based on video image processing |
| WO2023178957A1 (en) * | 2022-03-24 | 2023-09-28 | 全境智能有限公司 | Vital sign monitoring method, related device, and computer-readable storage medium |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2004073398A (en) * | 2002-08-14 | 2004-03-11 | Rikogaku Shinkokai | Method for estimating menstruation indica during exercise by image processor |
| CN101908140A (en) * | 2010-07-29 | 2010-12-08 | 中山大学 | Biopsy method for use in human face identification |
| CN102488508A (en) * | 2011-12-29 | 2012-06-13 | 哈尔滨工业大学 | Heart rate measuring method based on image capture |
| CN104138254A (en) * | 2013-05-10 | 2014-11-12 | 天津点康科技有限公司 | Non-contact type automatic heart rate measurement system and measurement method |
| CN104173051A (en) * | 2013-05-28 | 2014-12-03 | 天津点康科技有限公司 | Automatic noncontact respiration assessing system and assessing method |
| CN106529588A (en) * | 2016-11-02 | 2017-03-22 | 浙江工业大学 | Nonlinear manifold learning dimension reduction method based on adaptive density clustering |
| CN109101949A (en) * | 2018-08-29 | 2018-12-28 | 广州洪荒智能科技有限公司 | A kind of human face in-vivo detection method based on colour-video signal frequency-domain analysis |
| CN109993068A (en) * | 2019-03-11 | 2019-07-09 | 华南理工大学 | A kind of contactless human emotion's recognition methods based on heart rate and facial characteristics |
-
2019
- 2019-08-21 CN CN201910774697.0A patent/CN110384491A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2004073398A (en) * | 2002-08-14 | 2004-03-11 | Rikogaku Shinkokai | Method for estimating menstruation indica during exercise by image processor |
| CN101908140A (en) * | 2010-07-29 | 2010-12-08 | 中山大学 | Biopsy method for use in human face identification |
| CN102488508A (en) * | 2011-12-29 | 2012-06-13 | 哈尔滨工业大学 | Heart rate measuring method based on image capture |
| CN104138254A (en) * | 2013-05-10 | 2014-11-12 | 天津点康科技有限公司 | Non-contact type automatic heart rate measurement system and measurement method |
| CN104173051A (en) * | 2013-05-28 | 2014-12-03 | 天津点康科技有限公司 | Automatic noncontact respiration assessing system and assessing method |
| CN106529588A (en) * | 2016-11-02 | 2017-03-22 | 浙江工业大学 | Nonlinear manifold learning dimension reduction method based on adaptive density clustering |
| CN109101949A (en) * | 2018-08-29 | 2018-12-28 | 广州洪荒智能科技有限公司 | A kind of human face in-vivo detection method based on colour-video signal frequency-domain analysis |
| CN109993068A (en) * | 2019-03-11 | 2019-07-09 | 华南理工大学 | A kind of contactless human emotion's recognition methods based on heart rate and facial characteristics |
Non-Patent Citations (2)
| Title |
|---|
| 李肃义等: "一种光电容积脉搏信号的峰值点自动识别方法", 《光谱学与光谱分析》 * |
| 赵海等: "自适应脉搏波信号主峰定位方法", 《控制与决策》 * |
Cited By (32)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2021104129A1 (en) * | 2019-11-25 | 2021-06-03 | 虹软科技股份有限公司 | Heart rate estimation method and apparatus, and electronic device applying same |
| CN112949349B (en) * | 2019-12-09 | 2022-08-05 | 南宁莲现健康科技有限公司 | Method and system for displaying pulse condition waveform in real time based on face video |
| CN112949349A (en) * | 2019-12-09 | 2021-06-11 | 南宁莲现健康科技有限公司 | Method and system for displaying pulse condition waveform in real time based on face video |
| CN111310673A (en) * | 2020-02-20 | 2020-06-19 | 无锡市宏宇汽车配件制造有限公司 | Sleepiness prediction method, device and storage medium |
| CN111310673B (en) * | 2020-02-20 | 2022-02-08 | 无锡市宏宇汽车配件制造有限公司 | Sleepiness prediction method, device and storage medium |
| CN111444797B (en) * | 2020-03-16 | 2023-03-17 | 五邑大学 | Non-contact heart rate detection method |
| CN111444797A (en) * | 2020-03-16 | 2020-07-24 | 五邑大学 | Non-contact heart rate detection method |
| CN111345802A (en) * | 2020-03-16 | 2020-06-30 | 南京润楠医疗电子研究院有限公司 | Device and method for acquiring double heartbeat frequency based on cardiac shock signal |
| WO2021184620A1 (en) * | 2020-03-19 | 2021-09-23 | 南京昊眼晶睛智能科技有限公司 | Camera-based non-contact heart rate and body temperature measurement method |
| CN111767788A (en) * | 2020-05-12 | 2020-10-13 | 贵阳像树岭科技有限公司 | Non-interactive monocular in vivo detection method |
| CN111513701A (en) * | 2020-05-26 | 2020-08-11 | 上海眼控科技股份有限公司 | Heart rate detection method and device, computer equipment and readable storage medium |
| CN111797794A (en) * | 2020-07-13 | 2020-10-20 | 中国人民公安大学 | Facial dynamic blood flow distribution detection method |
| CN112494026B (en) * | 2020-09-07 | 2023-08-29 | 南京云思创智信息科技有限公司 | Non-contact-based remote sudden cardiac death early warning method |
| CN112494026A (en) * | 2020-09-07 | 2021-03-16 | 南京云思创智信息科技有限公司 | Non-contact-based remote sudden cardiac death early warning method |
| CN112043257A (en) * | 2020-09-18 | 2020-12-08 | 合肥工业大学 | Non-contact video heart rate detection method for motion robustness |
| CN112043257B (en) * | 2020-09-18 | 2022-12-20 | 合肥工业大学 | Non-contact video heart rate detection method for motion robustness |
| CN112233813A (en) * | 2020-09-28 | 2021-01-15 | 兰州大学 | Non-contact non-invasive heart rate and respiration measurement method and system based on PPG |
| CN112200099A (en) * | 2020-10-14 | 2021-01-08 | 浙江大学山东工业技术研究院 | Video-based dynamic heart rate detection method |
| 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 |
| CN112507877A (en) * | 2020-12-08 | 2021-03-16 | 北京工业大学 | System and method for detecting heart rate under condition of partial video information loss |
| CN112690771B (en) * | 2020-12-09 | 2022-05-24 | 华南理工大学 | Human face video heart rate detection method using linear regression model |
| CN112690771A (en) * | 2020-12-09 | 2021-04-23 | 华南理工大学 | Human face video heart rate detection method using linear regression model |
| CN112507930A (en) * | 2020-12-16 | 2021-03-16 | 华南理工大学 | Method for improving human face video heart rate detection by using illumination balancing method |
| CN112507930B (en) * | 2020-12-16 | 2023-06-20 | 华南理工大学 | Method for improving human face video heart rate detection by utilizing illumination equalization method |
| CN113058110B (en) * | 2021-03-17 | 2022-06-21 | 董建成 | Method and system for detecting venous transfusion extravasation |
| CN113058110A (en) * | 2021-03-17 | 2021-07-02 | 董建成 | Method and system for detecting venous transfusion extravasation |
| CN113252929A (en) * | 2021-07-05 | 2021-08-13 | 格创东智(深圳)科技有限公司 | Rotating speed determination method and device, electronic equipment and computer readable storage medium |
| CN113591769A (en) * | 2021-08-10 | 2021-11-02 | 北京航空航天大学 | Non-contact heart rate detection method based on photoplethysmography |
| CN113591769B (en) * | 2021-08-10 | 2023-09-15 | 北京航空航天大学 | Non-contact heart rate detection method based on photoplethysmography |
| CN114431849A (en) * | 2022-01-10 | 2022-05-06 | 厦门大学 | Aquatic animal heart rate detection method based on video image processing |
| CN114431849B (en) * | 2022-01-10 | 2023-08-11 | 厦门大学 | Aquatic animal heart rate detection method based on video image processing |
| WO2023178957A1 (en) * | 2022-03-24 | 2023-09-28 | 全境智能有限公司 | Vital sign monitoring method, related device, and computer-readable storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110384491A (en) | A kind of heart rate detection method based on common camera | |
| CN109157202B (en) | Cardiovascular disease early warning system based on multi-physiological signal deep fusion | |
| Bousefsaf et al. | Continuous wavelet filtering on webcam photoplethysmographic signals to remotely assess the instantaneous heart rate | |
| CN110269600B (en) | Non-contact video heart rate detection method based on multivariate empirical mode decomposition and combined blind source separation | |
| US10398327B2 (en) | Non-contact assessment of cardiovascular function using a multi-camera array | |
| CN105678780B (en) | A kind of video heart rate detection method for removing ambient light change interference | |
| US20160317041A1 (en) | System and methods for measuring physiological parameters | |
| CN108471989A (en) | The equipment, system and method for the photo-plethysmographic image of vital sign information for generating carrying object | |
| CN105989357A (en) | Human face video processing-based heart rate detection method | |
| CN110662480A (en) | Device, system and method for measuring and processing physiological signals of a subject | |
| Fan et al. | Non-contact remote estimation of cardiovascular parameters | |
| CN106580301A (en) | Physiological parameter monitoring method, device and hand-held device | |
| CN111387959A (en) | Non-contact physiological parameter detection method based on IPPG | |
| CN111714105A (en) | Human vital sign perception system based on IPPG | |
| CN112294282A (en) | Self-calibration method of emotion detection device based on RPPG | |
| CN113591769B (en) | Non-contact heart rate detection method based on photoplethysmography | |
| CN114387479A (en) | Non-contact heart rate measurement method and system based on face video | |
| Lin et al. | Development of a FPGA-based contactless pulse rate detection system | |
| 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 | |
| Gauci et al. | PCA-driven detection and enhancement of microchanges in video data associated with heart rate | |
| Zhang et al. | A novel motion and Noise Artifacts Reduction Mechanism (MNARM) for wearable PPG-based heart rate extraction | |
| Khong et al. | Analysis of heart beat rate through video imaging techniques | |
| Zhuang et al. | Remote blood pressure measurement via spatiotemporal mapping of a short-time facial video | |
| CN109770885A (en) | A kind of examing heartbeat fastly method based on preview frame |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20191029 |