CN107330945A - A kind of examing heartbeat fastly method based on video - Google Patents
A kind of examing heartbeat fastly method based on video Download PDFInfo
- Publication number
- CN107330945A CN107330945A CN201710543119.7A CN201710543119A CN107330945A CN 107330945 A CN107330945 A CN 107330945A CN 201710543119 A CN201710543119 A CN 201710543119A CN 107330945 A CN107330945 A CN 107330945A
- Authority
- CN
- China
- Prior art keywords
- mtd
- video
- heart rate
- frame
- mtr
- 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
- 238000000034 method Methods 0.000 title claims abstract description 33
- 238000001514 detection method Methods 0.000 claims abstract description 21
- 238000004364 calculation method Methods 0.000 claims description 12
- 238000001914 filtration Methods 0.000 claims description 12
- 238000000354 decomposition reaction Methods 0.000 claims description 8
- 239000008280 blood Substances 0.000 claims description 6
- 210000004369 blood Anatomy 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 5
- 238000001228 spectrum Methods 0.000 claims description 5
- 230000008859 change Effects 0.000 claims description 4
- 238000006243 chemical reaction Methods 0.000 claims description 4
- 230000008569 process Effects 0.000 claims description 4
- 238000013461 design Methods 0.000 claims description 3
- 238000012163 sequencing technique Methods 0.000 claims description 3
- 238000009499 grossing Methods 0.000 claims description 2
- 239000011159 matrix material Substances 0.000 claims description 2
- 230000003287 optical effect Effects 0.000 claims description 2
- 238000007689 inspection Methods 0.000 claims 1
- 230000002452 interceptive effect Effects 0.000 claims 1
- 230000007812 deficiency Effects 0.000 abstract 1
- 230000007774 longterm Effects 0.000 abstract 1
- 238000005516 engineering process Methods 0.000 description 5
- 238000012880 independent component analysis Methods 0.000 description 4
- 102000001554 Hemoglobins Human genes 0.000 description 2
- 108010054147 Hemoglobins Proteins 0.000 description 2
- 238000012937 correction Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000009532 heart rate measurement Methods 0.000 description 2
- 238000013186 photoplethysmography Methods 0.000 description 2
- 230000033764 rhythmic process Effects 0.000 description 2
- 238000010521 absorption reaction Methods 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 230000002457 bidirectional effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 230000006806 disease prevention Effects 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 230000003862 health status Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000002035 prolonged effect Effects 0.000 description 1
- 239000011435 rock Substances 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 230000003595 spectral effect Effects 0.000 description 1
- 238000007920 subcutaneous administration Methods 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/90—Determination of colour characteristics
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/10—Image enhancement or restoration using non-spatial domain filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/40—Analysis of texture
- G06T7/41—Analysis of texture based on statistical description of texture
- G06T7/42—Analysis of texture based on statistical description of texture using transform domain methods
-
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/60—Control of cameras or camera modules
- H04N23/617—Upgrading or updating of programs or applications for camera control
-
- 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
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20016—Hierarchical, coarse-to-fine, multiscale or multiresolution image processing; Pyramid transform
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Probability & Statistics with Applications (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Human Computer Interaction (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a kind of examing heartbeat fastly method based on video, implement as follows：1) video acquisition；2) data prediction；3) multithreading computing；4) heart rate detection.It this method propose a kind of algorithm of multi-threaded parallel computing and the double-linked circular list structure of data access carried out suitable for the algorithm, improve whole detection speed, solve the deficiency of the current contactless heart rate detection speed of service so that contactless heart rate detection can realize long-term continuous detection under real scene.
Description
Technical field
The invention belongs to field of video image processing, the contactless heart rate detection method more particularly under real scene.
Background technology
With the development and popularization of computer technology, increasing computer theory is related to medical domain, is applied to
The links such as medical diagnosis and routine health monitoring, are that the progress of medical science has played powerful booster action.Heart rate is reflection
One of index of human health status, is also one of physical signs for judging that angiocardiopathy is most basic.The clinical heart traditionally
Rate detection means needs multiple positions of the 12 lead linear contact lay human body using electrocardiograph, trivial operations, automaticity
It is not high, there is higher professional knowledge requirement to user, be not suitable for the heart rate detection under common scenarios.
Photoplethysmography (Photoplethysmography, PPG) is to carry out the heart using computer vision technique
Rate detects most basic method, and it is by light emitting diode subcutaneously tissue emissions feux rouges, and feux rouges is by subcutaneous capillary network
In hemoglobin absorption, reflect or be transmitted to the photistor of the other end, its signal after treatment with arterial blood
Amount of hemoglobin be proportionate, by measuring intensity of reflected light, trace volumetric blood pulse (Blood volume
Pulse, BVP) after signal, it can directly calculate heart rate.Fu Mingzhe et al. proposes to connect using the non-of general network camera earliest
Touch heart rate detection method.This method will using independent component analysis (Independent Component Analysis, ICA)
Three average color traces are separated into three base source signals, by the power Spectral Estimation heart rate for analyzing second base source signal.
However, second Ji Yuan of ICA outputs can not represent PPG signals, later Fu Mingzhe et al. is carried out to their method
Improve, add the signal behavior operation of trending and peak power spectrum spike.Qi Gang et al. has also been proposed a kind of people recently
Face rotation correction algorithm, rocks to the faint face in video acquisition and is corrected, and eliminates what a part of face motion was produced
Noise, makes the accuracy of the measurement of heart rate further improve, it is adaptable to the heart rate measurement under non-collaboration scenario.
Above method by contactless video method can accurately measure heart rate value under certain scene, but
It is that calculating process is excessively very long, for tested personnel, too high time cost will bring non-contact detection method
Convenience offset.Especially Qi Gang et al. face rotation correction algorithm, although eliminate certain motion artifacts, but with
This adds the data operation quantity of algorithm simultaneously so that the detection time and robustness of heart rate detection are substantially reduced, in actual field
Jing Zhong, does not possess preferable Consumer's Experience and operability.
The content of the invention
The purpose of the present invention is realized by following scheme：A kind of examing heartbeat fastly method based on video, its
It is characterised by, comprises the following steps：
1) video acquisition：One generic USB camera is placed in 1m positions immediately ahead of face, camera is carried out with computer
Connection, controls camera to carry out video acquisition using OpenCV/Qt programs.Synchronous Face datection can be carried out in gatherer process,
Ensure to include face information in gathered sequence of frames of video, during heart rate detection, USB is kept it turned on, and is uninterruptedly adopted
Collect video.
2) data structure is pre-processed：The frame sequence that camera is gathered is input in the chained list of a bidirectional circulating, is received
While sequence of frames of video, the pointer of a sensing current operation node is set, the node of pointer forward direction is treated as data
Acquisition node；The node of pointer backward directions, as computing node.Chained list length long enough, it is ensured that the collection of frame of video and fortune
Access conflict will not occur for calculation.The characteristic of double-linked circular list ensure that the continuity on data acquisition time, and multithreading
While the security of accessing shared data.
3) parallel heart rhythm of multithreading is calculated：After data prediction is finished, heart rate detection thread is waken up, and is entered
Enter execution state, run with video acquisition thread parallel.Video acquisition thread persistently enters data into shared data region, the heart
Rate computing thread loops calculate heart rate, substantially reduce both concurrent operations, the total time of detection.
The present invention compared with prior art, has an advantageous effect in that：
1) present invention is proposed a kind of based on video for complex operation and limbs the constraint problem of contact heart rate measurement
Examing heartbeat fastly method.The technology, only can be certainly by common camera without using electrode or sensor contacts human body
Dynamic monitor heart rate.It is effectively improved detection efficiency and the usage experience of testee, it is adaptable to prolonged rhythm of the heart and disease
Disease prevention.
2) present invention employs multi-thread design structure, the thought of concurrent operation is introduced, computing speed is effectively raised
Degree, makes contactless heart rate detection technology have more preferable usage experience, improves the practical significance of the technology.
3) data structure for employing double-linked circular list carrys out processing data, and chained list is divided into data acquisition region and computing
Two, region part so that concurrent operation is possibly realized, enables the access data that multithreading is asynchronous, parallel.
Brief description of the drawings
Fig. 1 is the algorithm flow chart of the present invention
Fig. 2 is the equipment installation effect of the present invention
Fig. 3 is the structural representation of double-linked circular list
Fig. 4 is the volumetric blood pulse wave that the present invention is extracted
Embodiment
Below with reference to accompanying drawing 1 to 4, the present invention is described further, but the protection of the present invention should not be limited with this
Scope.For convenience of explanation and understand technical scheme, illustrate below used in the noun of locality with the exhibition of accompanying drawing institute
The orientation shown is defined.
Step 1, a generic USB camera is placed in 0.5m positions immediately ahead of face, camera is connected with computer
Connect, operator controls camera to carry out video acquisition using OpenCV/Qt programs, as shown in Figure 2.It can be carried out in gatherer process
Face datection, it is ensured that face information is included in the sequence of frames of video gathered, during heart rate detection, USB is kept it turned on,
Uninterrupted sampling video.The arrange parameter of camera is, 640*480 resolution ratio, 30fps frame per second and RGB color domain.
Step 2, frame sequence camera gathered is stored among the node of a double-linked circular list, the chained list node
Number is set to 300, and design of joints is two and is respectively directed to front and rear pointer field, the Mat forms of OpenCV storage images
Data field, the mark domain for indicating present node position.While circulation receives continuous frame of video, there is a pointer sensing
Current operation node, pointer forward direction is frame of video node to be deposited, as data deposit；Pointer backward directions are to have deposited
Enter frame of video node, the computing as next step, chained list length long enough, it is ensured that frame of video deposit does not interfere with frame of video
Calculate, concrete structure schematic diagram is as shown in Figure 3.The characteristic of double-linked circular list ensure that the continuity of data inputting, Yi Jiduo
The Line Procedure Mutually-exclusive of thread computing and the data safety accessed critical data.
Step 3, control variable to control the sequencing of video acquisition and heart rate computing by Boolean type, realize that thread is different
Walk and thread synchronization, specific algorithm step is：
1) video acquisition initial phase：Frame of video is not present in chained list, video acquisition thread starts, and heart rate computing enters
Circular wait state.
2) the video acquisition cycle stage：After linked list data pretreatment filling is finished, the condition of rate calculation, heart rate are met
Computing thread is waken up to running status from wait state, and video acquisition and heart rate computing are performed parallel, realize continuous, the quick heart
Rate is detected.
Step 4, start continuous heart rate detection, specifically include：
1) data input：The current pointer of chained list is obtained, continuous S frames are taken backward as calculating number from pointer present node
According to, meanwhile, inverted conversion is done to the sequence, the input of its i-th frame (i=1,2,3 ... S) is performed according to formula (1)：
Frames [i]=List [S-i] (1)
Wherein, frames [i] represents the i-th two field picture, and List [S-i] represents taken chained list subsequence corresponding node；
2) ROI region is selected：The face recognition algorithms provided using OpenCV, are carried out Face datection to each frame, obtained
To the region vector Rect (x, y, w, h) for only including face information, ROI (Region Of Interest, region of interest are used as
Domain) region, wherein Rect represents a matrix area, the initial vertex of x and y representing matrixs, the length and width of w and h representing matrixs.
3) color gamut conversion：The color space of face video is converted into YIQ by RGB, makes the monochrome information and colourity of image
Unpack, is easy to brightness and the independent processing of colourity, and wherein YIQ is NTSC (National Television Standards
Committee brightness (Luminance) information of) color space that vitascan is used, wherein Y passages storage image, I
With colourity (chrominance) information of Q passage storage images, I represents the color change from orange to cyan, and Q is represented from purple
Color is to the color change of yellow green, and RGB and YIQ transformational relation is shown below：
4) space filtering：Spatial decomposition is carried out to video using a kind of multiple dimensioned image gaussian pyramid decomposition method,
It obtains the sets of subbands of many levels, calculation procedure is such as by carrying out continuously Gaussian smoothing and down-sampled to every two field picture
Under：
1. input jth (j=1,2,3 ...) two field picture calculates Decomposition order L as the 0th layer；
2. to the advanced row gaussian filtering of previous tomographic image, rear down-sampled, picture size is changed into original 1/4, is designated as secondary one
Layer
3. by step, 2. iteration is performed L-1 times, obtains L layers of sub-band images；
4. j=j+1, circulates and performs above step, output subband sequence；
5) time-domain filtering：The frame sequence after pyramid decomposition is carried out using a kind of preferable bandpass filtering based on optical flow method
Preferable bandpass filtering, calculation procedure is as follows：
1. input whole image frame sequence, the common S frames of the sequence, size is w*h；
2. take each frame (x, y) put pixel (x=1,2,3 ... w, y=1,2,3 ... h) are used as this in the value of 1~S frames
The light stream sequence perFrame [x] [y] of point；
3. Fast Fourier Transform (FFT) is carried out to perFrame [x] [y], obtains (x, y) and put the time domain in sequence of frames of video
Component, the preferable bandpass filtering that passband is 0.83~2.00Hz is carried out to the component, and inverse Fourier transform is carried out, and obtains the
The pure volumetric blood pulse BVP signals BVP [x] [y] [i] of i two field pictures (x, y) pixel；
4. x=x+1, y=y+1, circulation execution above step, export the BVP signals of all pixels；
6) spectra calculation heart rate：By calculating BVP [x] [y] [i], heart rate value is drawn, calculation procedure is as follows：
1. the BVP values of all pixels point of the i-th frame (i=1,2,3 ... S) are summed, obtains one-dimensional BVP semaphores B
[i]；
2. Fast Fourier Transform (FFT) is carried out to B [i], obtains its power spectrum PBvp：
F (t)=fft (B (t)) (3)
PBvp(t)=| F (t) |2 (4)
Wherein, fft is Fast Fourier Transform (FFT) function.
3. heart rate value HRCalculating：
T=max { PBvp(t)} (5)
Wherein, fpsFor the frame per second of video.
So far, the heart rate detection once based on face video processing is basically completed.
The announcement and teaching of book according to the above description, those skilled in the art in the invention can also be to above-mentioned embodiment party
Formula is changed and changed.Therefore, the invention is not limited in embodiment disclosed and described above, to the present invention's
Some modifications and changes should also be as falling into the scope of the claims of the present invention.Although in addition, being used in this specification
Some specific terms, but these terms are merely for convenience of description, do not constitute any limitation to the present invention.
Claims (5)
1. a kind of examing heartbeat fastly method based on video, it is characterised in that comprise the following steps：
(1) frame of video is gathered；
(2) frame of video to the collection carries out data prediction；
(3) variable is controlled to realize the sequencing of video acquisition and heart rate computing by Boolean type；
(4) start heart rate computing thread, using multi-threaded parallel structure, detect heart rate, obtain heart rate value.
2. examing heartbeat fastly method according to claim 1, it is characterised in that the collection of the frame of video specifically,
One generic USB camera is placed in 0.5m positions immediately ahead of face, the USB camera is attached with computer, is operated
Person controls camera to carry out that in video acquisition, gatherer process Face datection can be carried out using OpenCV/Qt programs, it is ensured that adopted
Face information is included in the sequence of frames of video of collection, during heart rate detection, the USB camera is kept it turned on, uninterruptedly
Video is gathered, the arrange parameter of camera is：640*480 resolution ratio, 30fps frame per second and RGB color domain space.
3. examing heartbeat fastly method according to claim 1, it is characterised in that the data prediction will be specifically, will
The frame sequence of the USB camera collection is stored among the node of a double-linked circular list, and the chained list node number is set to
300, design of joints is two and is respectively directed to front and rear pointer field, the data field of the Mat forms of OpenCV storage images, uses
In the mark domain for indicating present node position, while circulation receives continuous frame of video, there is a pointer to point to current operation
Node, pointer forward direction is frame of video node to be deposited, as data deposit；Pointer backward directions are to be stored in frame of video
Node, the computing as next step, chained list length long enough, it is ensured that frame of video is stored in the calculating for not interfering with frame of video, double
Ensure that the continuity of data inputting to the characteristic of circular linked list, and multithreading computing Line Procedure Mutually-exclusive and critical data is visited
The data safety asked.
4. examing heartbeat fastly method according to claim 1, it is characterised in that it is described by Boolean type control variable come
Realize the sequencing of video acquisition and heart rate computing specifically,
1) video acquisition initial phase：Frame of video is not present in chained list, video acquisition thread starts, and heart rate computing enters circulation
Wait state.
2) the video acquisition cycle stage：After the filling of linked list data first pass is finished, the condition of rate calculation, heart rate computing are met
Thread is changed into running status from wait state, and video acquisition and heart rate computing are alternately performed, and realizes continuous, quick heart rate inspection
Survey.
5. examing heartbeat fastly method according to claim 1, it is characterised in that the heart rate computing thread starts it
Afterwards, using multi-threaded parallel structure, detect heart rate, obtain heart rate value rate calculation specifically,
1) data input：The current pointer of chained list is obtained, continuous S frames are taken backward as data are calculated from pointer present node, together
When, inverted conversion is done to the sequence, the deposit formula of its i-th frame (i=1,2,3 ... S) is：
Frames [i]=List [S-i]
Wherein, frames [i] represents the i-th two field picture, and List [S-i] represents taken chained list subsequence corresponding node；
2) ROI region is selected：The face recognition algorithms provided using OpenCV, Face datection is carried out to each frame, is obtained only
Region vector Rect (x, y, w, h) comprising face information, as ROI area-of-interests, wherein Rect represents a matrix area
Domain, the initial vertex of x and y representing matrixs, the length and width of w and h representing matrixs；
3) color gamut conversion：The color space of face video is converted into YIQ by RGB, makes the monochrome information and chrominance information of image
Separate, be easy to brightness and the independent processing of colourity, wherein YIQ is the color space that NTSC vitascans are used, and wherein Y leads to
The monochrome information of road storage image, the chrominance information of I and Q passage storage images, I represents the color change from orange to cyan, Q
Color change of the expression from purple to yellow green, RGB and YIQ transformational relation are shown below：
<mrow>
<mfenced open = "[" close = "]">
<mtable>
<mtr>
<mtd>
<mi>Y</mi>
</mtd>
</mtr>
<mtr>
<mtd>
<mi>I</mi>
</mtd>
</mtr>
<mtr>
<mtd>
<mi>Q</mi>
</mtd>
</mtr>
</mtable>
</mfenced>
<mo>=</mo>
<mfenced open = "[" close = "]">
<mtable>
<mtr>
<mtd>
<mn>0.299</mn>
</mtd>
<mtd>
<mn>0.587</mn>
</mtd>
<mtd>
<mn>0.114</mn>
</mtd>
</mtr>
<mtr>
<mtd>
<mn>0.596</mn>
</mtd>
<mtd>
<mrow>
<mo>-</mo>
<mn>0.274</mn>
</mrow>
</mtd>
<mtd>
<mrow>
<mo>-</mo>
<mn>0.322</mn>
</mrow>
</mtd>
</mtr>
<mtr>
<mtd>
<mn>0.211</mn>
</mtd>
<mtd>
<mrow>
<mo>-</mo>
<mn>0.523</mn>
</mrow>
</mtd>
<mtd>
<mn>0.312</mn>
</mtd>
</mtr>
</mtable>
</mfenced>
<mfenced open = "[" close = "]">
<mtable>
<mtr>
<mtd>
<mi>R</mi>
</mtd>
</mtr>
<mtr>
<mtd>
<mi>G</mi>
</mtd>
</mtr>
<mtr>
<mtd>
<mi>B</mi>
</mtd>
</mtr>
</mtable>
</mfenced>
</mrow>
4) space filtering：Spatial decomposition is carried out to video using a kind of multiple dimensioned image gaussian pyramid decomposition method, it leads to
Cross and continuously Gaussian smoothing is carried out to every two field picture and down-sampled, obtain the sets of subbands of many levels, calculation procedure is as follows：
1. input jth (j=1,2,3 ...) two field picture calculates Decomposition order L as the 0th layer；
2. to the advanced row gaussian filtering of previous tomographic image, rear down-sampled, picture size is changed into original 1/4, is designated as secondary one layer
3. by step, 2. iteration is performed L-1 times, obtains L layers of sub-band images；
4. j=j+1, circulates and performs above step, output subband sequence；
5) time-domain filtering：The frame sequence after pyramid decomposition is carried out using a kind of preferable bandpass filtering based on optical flow method preferable
Bandpass filtering, calculation procedure is as follows：
1. input whole image frame sequence, the common S frames of the sequence, size is w*h；
2. take each frame (x, y) put pixel (x=1,2,3 ... w, y=1,2,3 ... h) are used as the point in the value of 1~S frames
Light stream sequence perFrame [x] [y]；
3. Fast Fourier Transform (FFT) is carried out to perFrame [x] [y], obtains (x, y) and put the time domain component in sequence of frames of video,
Passband is carried out to the component and is 0.83~2.00Hz preferable bandpass filtering, and carries out inverse Fourier transform, the i-th frame figure is obtained
As the pure volumetric blood pulse BVP signals BVP [x] [y] [i] of (x, y) pixel；
4. x=x+1, y=y+1, circulation execution above step, export the BVP signals of all pixels；
6) spectra calculation heart rate：By calculating BVP [x] [y] [i], heart rate value is drawn, calculation procedure is as follows：
1. the BVP values of all pixels point of the i-th frame (i=1,2,3 ... S) are summed, obtains one-dimensional BVP semaphores B [i]；
2. Fast Fourier Transform (FFT) is carried out to B [i], obtains its power spectrum PBvp：
F (t)=fft (B (t))
PBvp(t)=| F (t) |2
Wherein, fft is Fast Fourier Transform (FFT) function,
3. heart rate value HRCalculating：
T=max { PBvp(t)}
<mrow>
<msub>
<mi>H</mi>
<mi>R</mi>
</msub>
<mo>=</mo>
<mfrac>
<mi>T</mi>
<mi>S</mi>
</mfrac>
<msub>
<mi>f</mi>
<mrow>
<mi>p</mi>
<mi>s</mi>
</mrow>
</msub>
</mrow>
Wherein, fpsFor the frame per second of video.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710543119.7A CN107330945A (en) | 2017-07-05 | 2017-07-05 | A kind of examing heartbeat fastly method based on video |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710543119.7A CN107330945A (en) | 2017-07-05 | 2017-07-05 | A kind of examing heartbeat fastly method based on video |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107330945A true CN107330945A (en) | 2017-11-07 |
Family
ID=60196200
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710543119.7A Pending CN107330945A (en) | 2017-07-05 | 2017-07-05 | A kind of examing heartbeat fastly method based on video |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107330945A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109770885A (en) * | 2019-03-25 | 2019-05-21 | 合肥工业大学 | A kind of examing heartbeat fastly method based on preview frame |
| CN110501363A (en) * | 2019-08-30 | 2019-11-26 | 中国科学院长春应用化学研究所 | X-ray diffractometer multithreading sample test 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 |
| CN112395464A (en) * | 2020-11-18 | 2021-02-23 | 扬州船用电子仪器研究所(中国船舶重工集团公司第七二三研究所) | Electronic information intermediate frequency data processing method based on openmp acceleration |
| CN112954423A (en) * | 2020-04-08 | 2021-06-11 | 深圳市明源云客电子商务有限公司 | Animation playing method, device and equipment |
| CN113052115A (en) * | 2021-04-06 | 2021-06-29 | 合肥工业大学 | Unmanned aerial vehicle airborne vital sign detection method based on video method |
| CN116999044A (en) * | 2023-09-07 | 2023-11-07 | 南京云思创智信息科技有限公司 | Real-time motion full-connection bidirectional consistent optical flow field heart rate signal extraction method |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN100334919C (en) * | 2005-03-25 | 2007-08-29 | 北京北方烽火科技有限公司 | Managing method for user contex of multi-object positioning in GMLC |
| CN103077057A (en) * | 2012-12-31 | 2013-05-01 | 浙江创佳数字技术有限公司 | Android intelligent set-top box-based Loader method |
| US20160132732A1 (en) * | 2014-11-10 | 2016-05-12 | Utah State University | Remote Heart Rate Estimation |
| CN105989357A (en) * | 2016-01-18 | 2016-10-05 | 合肥工业大学 | Human face video processing-based heart rate detection method |
| CN106778695A (en) * | 2017-01-19 | 2017-05-31 | 北京理工大学 | A kind of many people's examing heartbeat fastly methods based on video |
| CN106725411A (en) * | 2017-02-15 | 2017-05-31 | 成都皓图智能科技有限责任公司 | A kind of contactless heartbeat detecting method accelerated based on GPU |
-
2017
- 2017-07-05 CN CN201710543119.7A patent/CN107330945A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN100334919C (en) * | 2005-03-25 | 2007-08-29 | 北京北方烽火科技有限公司 | Managing method for user contex of multi-object positioning in GMLC |
| CN103077057A (en) * | 2012-12-31 | 2013-05-01 | 浙江创佳数字技术有限公司 | Android intelligent set-top box-based Loader method |
| US20160132732A1 (en) * | 2014-11-10 | 2016-05-12 | Utah State University | Remote Heart Rate Estimation |
| CN105989357A (en) * | 2016-01-18 | 2016-10-05 | 合肥工业大学 | Human face video processing-based heart rate detection method |
| CN106778695A (en) * | 2017-01-19 | 2017-05-31 | 北京理工大学 | A kind of many people's examing heartbeat fastly methods based on video |
| CN106725411A (en) * | 2017-02-15 | 2017-05-31 | 成都皓图智能科技有限责任公司 | A kind of contactless heartbeat detecting method accelerated based on GPU |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109770885A (en) * | 2019-03-25 | 2019-05-21 | 合肥工业大学 | A kind of examing heartbeat fastly method based on preview frame |
| CN110501363A (en) * | 2019-08-30 | 2019-11-26 | 中国科学院长春应用化学研究所 | X-ray diffractometer multithreading sample test method |
| CN112954423A (en) * | 2020-04-08 | 2021-06-11 | 深圳市明源云客电子商务有限公司 | Animation playing method, device and equipment |
| 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 |
| CN112395464A (en) * | 2020-11-18 | 2021-02-23 | 扬州船用电子仪器研究所(中国船舶重工集团公司第七二三研究所) | Electronic information intermediate frequency data processing method based on openmp acceleration |
| CN113052115A (en) * | 2021-04-06 | 2021-06-29 | 合肥工业大学 | Unmanned aerial vehicle airborne vital sign detection method based on video method |
| CN116999044A (en) * | 2023-09-07 | 2023-11-07 | 南京云思创智信息科技有限公司 | Real-time motion full-connection bidirectional consistent optical flow field heart rate signal extraction method |
| CN116999044B (en) * | 2023-09-07 | 2024-04-16 | 南京云思创智信息科技有限公司 | Real-time motion full-connection bidirectional consistent optical flow field heart rate signal extraction method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107330945A (en) | A kind of examing heartbeat fastly method based on video | |
| McDuff | Camera measurement of physiological vital signs | |
| Wang et al. | A comparative survey of methods for remote heart rate detection from frontal face videos | |
| Fan et al. | Robust blood pressure estimation using an RGB camera | |
| McDuff et al. | Remote detection of photoplethysmographic systolic and diastolic peaks using a digital camera | |
| De Haan et al. | Improved motion robustness of remote-PPG by using the blood volume pulse signature | |
| US10004410B2 (en) | System and methods for measuring physiological parameters | |
| Casado et al. | Face2PPG: An unsupervised pipeline for blood volume pulse extraction from faces | |
| CN110384491A (en) | A kind of heart rate detection method based on common camera | |
| CN106580301A (en) | Physiological parameter monitoring method, device and hand-held device | |
| CN110269600A (en) | Based on polynary empirical mode decomposition and the contactless video heart rate detection method for combining blind source separating | |
| McDuff et al. | Fusing partial camera signals for noncontact pulse rate variability measurement | |
| CN102973253A (en) | Method and system for monitoring human physiological indexes by using visual information | |
| CN106999116A (en) | Apparatus and method for skin detection | |
| Alnaggar et al. | Video-based real-time monitoring for heart rate and respiration rate | |
| CN104688184A (en) | Vein imaging method for visible-light skin images | |
| Przybyło | A deep learning approach for remote heart rate estimation | |
| KR20150016903A (en) | Method and Device for measuring PPG signal by using mobile device | |
| Qi et al. | Non-contact driver cardiac physiological monitoring using video data | |
| CN106264554A (en) | A kind of method for detecting blood oxygen saturation based on visible ray and system | |
| CN108272449A (en) | Contactless monitoring of blood pressure method and system | |
| Karthick et al. | Analysis of vital signs using remote photoplethysmography (RPPG) | |
| Yin et al. | Heart rate estimation based on face video under unstable illumination | |
| Zheng et al. | Heart rate prediction from facial video with masks using eye location and corrected by convolutional neural networks | |
| Hu et al. | Contactless blood oxygen estimation from face videos: A multi-model fusion method based on deep learning |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20171107 |