CN109044314B - Non-contact heart rate monitoring method based on Euler video amplification - Google Patents
Non-contact heart rate monitoring method based on Euler video amplification Download PDFInfo
- Publication number
- CN109044314B CN109044314B CN201810622284.6A CN201810622284A CN109044314B CN 109044314 B CN109044314 B CN 109044314B CN 201810622284 A CN201810622284 A CN 201810622284A CN 109044314 B CN109044314 B CN 109044314B
- Authority
- CN
- China
- Prior art keywords
- video
- heart rate
- person
- sequence
- color
- 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.)
- Active
Links
- 230000003321 amplification Effects 0.000 title claims abstract description 33
- 238000003199 nucleic acid amplification method Methods 0.000 title claims abstract description 33
- 238000000034 method Methods 0.000 title claims abstract description 31
- 238000012544 monitoring process Methods 0.000 title claims abstract description 23
- 230000003287 optical effect Effects 0.000 claims abstract description 5
- 210000001061 forehead Anatomy 0.000 claims abstract description 4
- 238000001514 detection method Methods 0.000 claims description 17
- 238000000354 decomposition reaction Methods 0.000 claims description 15
- 238000004458 analytical method Methods 0.000 claims description 14
- 238000001914 filtration Methods 0.000 claims description 12
- 238000012545 processing Methods 0.000 claims description 12
- 230000008859 change Effects 0.000 claims description 7
- 238000005070 sampling Methods 0.000 claims description 6
- 235000002566 Capsicum Nutrition 0.000 claims description 3
- 239000006002 Pepper Substances 0.000 claims description 3
- 235000016761 Piper aduncum Nutrition 0.000 claims description 3
- 235000017804 Piper guineense Nutrition 0.000 claims description 3
- 235000008184 Piper nigrum Nutrition 0.000 claims description 3
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 210000000056 organ Anatomy 0.000 claims description 3
- 150000003839 salts Chemical class 0.000 claims description 3
- 238000000926 separation method Methods 0.000 claims description 3
- 230000002194 synthesizing effect Effects 0.000 claims description 3
- 244000203593 Piper nigrum Species 0.000 claims 1
- 230000036541 health Effects 0.000 description 3
- 241000722363 Piper Species 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 208000031636 Body Temperature Changes Diseases 0.000 description 1
- 208000024172 Cardiovascular disease Diseases 0.000 description 1
- 240000007651 Rubus glaucus Species 0.000 description 1
- 235000011034 Rubus glaucus Nutrition 0.000 description 1
- 235000009122 Rubus idaeus Nutrition 0.000 description 1
- 206010042434 Sudden death Diseases 0.000 description 1
- 206010003119 arrhythmia Diseases 0.000 description 1
- 230000006793 arrhythmia Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 210000004709 eyebrow Anatomy 0.000 description 1
- 230000004217 heart function Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000012806 monitoring device Methods 0.000 description 1
- 230000000284 resting effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/02—Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
- A61B5/024—Detecting, measuring or recording pulse rate or heart rate
- A61B5/02416—Detecting, measuring or recording pulse rate or heart rate using photoplethysmograph signals, e.g. generated by infrared radiation
Abstract
The invention discloses a non-contact heart rate monitoring method based on Euler video amplification, which comprises the following steps of: 1) acquiring a video sequence of a face area of a person to be monitored through a camera; 2) carrying out Euler video color amplification on a video sequence of a face area of a person to be monitored; 3) taking an initial video frame of a video sequence after the Euler video is subjected to color amplification as a reference, detecting a rectangular face region through a harr classifier to determine a forehead region of the face, determining a point d1 to be detected by using a random generation region coordinate method, and tracking the position of the point to be detected in a subsequent video sequence by using a Lukas-Kanade optical flow method to determine a color value sequence of the point to be detected; 4) the method can realize long-time non-contact monitoring of the heart rate of the user, and has high automation degree.
Description
Technical Field
The invention belongs to the field of human face video image processing, and relates to a non-contact heart rate monitoring method based on Euler video amplification.
Background
The heart rate is an important index for clinically detecting life parameters, can be mainly used for judging whether the heart is overloaded, determining exercise intensity, evaluating body temperature change, evaluating heart function, preventing sudden death caused by arrhythmia and the like, and is an important index for measuring the health condition of a human body.
In recent years, computer vision has been rapidly developed, and video image processing has begun to be involved in the field of medical science. The non-contact heart rate detection method and the non-contact heart rate detection device have good performance in the aspects of convenience in use, safety and flexibility, so the method and the device are widely concerned by the medical field and the industrial field. The non-contact heart rate detection technology based on video processing is an important application of video image processing in the field of medical science, and has an extremely important role in health management and cardiovascular disease judgment.
At present, the main heart rate monitoring devices on the market all use the contact as the main, mostly need connect special sensor, seriously restrict patient's limbs, and its comfort level is lower, is not suitable for long-time monitoring, and degree of automation is lower. Moreover, most detection devices have poor intelligent degree, and the workload of medical staff is seriously increased.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provides a non-contact heart rate monitoring method based on Euler video amplification, which can realize long-time non-contact monitoring of the heart rate of a user and has higher automation degree.
In order to achieve the purpose, the non-contact heart rate monitoring method based on Euler video amplification comprises the following steps:
1) acquiring a video sequence of a face area of a person to be monitored through a camera;
2) carrying out Euler video color amplification on the video sequence of the face area of the person to be monitored acquired in the step 1);
3) taking an initial video frame of a video sequence after the Euler video is subjected to color amplification as a reference, detecting a rectangular face region through a harr classifier, simultaneously identifying the position of a local key organ of the face to determine the forehead region of the face, determining a point to be detected d1 by using a random generation region coordinate method, and tracking the position of the point to be detected in a subsequent video sequence by using a Lukas-Kanade optical flow method to determine a color value sequence of the point to be detected, wherein the point to be detected in an ith frame video image is marked as d [ i ];
4) performing time-frequency analysis on the color value sequence of the point to be detected obtained in the step 3), calculating the heart rate value of the person to be monitored according to the result of the time-frequency analysis, and completing non-contact heart rate monitoring based on Euler video amplification.
The specific operation of the step 1) is as follows:
11) placing the camera at a front position facing the face of a person, opening the camera, and correcting the position of the face area of the person to be monitored;
12) and acquiring a video sequence of the face area of the person to be monitored by a camera at 30 frames/second, wherein the acquisition time is 10 seconds, and the video sequence is stored in an AVI video format.
The specific operation of the step 2) is as follows:
21) converting the color space of the video of the face area of the person to be monitored from RGB into YIQ, and separating the brightness information and the chrominance information of the image, wherein the Y component represents the brightness information of the image, the I component represents the color change from orange to cyan, and the Q component represents the color change from purple to yellow-green;
22) performing spatial decomposition on a video image of a face region of a person to be monitored by using a Gaussian pyramid decomposition method, performing Gaussian smooth blurring on the video image, performing down-sampling to obtain images with different resolutions, and constructing a multi-scale video subsequence of spatial decomposition according to the images with different resolutions, wherein the width and height of each resolution image are 1/2 of the width and height of the original image;
23) performing time domain filtering on the multi-scale video subsequence subjected to spatial decomposition by using an ideal band-pass filter;
24) amplifying the filtered multi-scale video subsequence subjected to spatial decomposition, wherein the amplification factor is 100, synthesizing the amplified multi-scale video subsequence into an image of a conversion signal, expanding the image to the same size as the original video image, and finally overlapping the image with the original video image to finish the Euler video color amplification of the video sequence of the face region of the person to be monitored.
The specific operation of performing time-frequency analysis on the color value sequence of the point to be detected obtained in the step 3) in the step 4) is as follows:
4a) channel separation is carried out on the YIQ color space of the point to be detected, Y, I and Q color channel subsequences are respectively generated, and then filtering processing is carried out by utilizing a one-dimensional ideal band-pass filter;
4b) performing median filtering on the Y, I and Q color channel subsequences obtained in the step 4a) through a filtering template to remove salt and pepper noise;
4c) respectively solving Y, I and the average value of the Q color channel subsequence;
4d) respectively carrying out difference processing on the Y, I and Q color channel subsequence obtained in the step 4b) and the mean value of the Y, I and Q color channel subsequence obtained in the step 4c) to obtain a difference value sequence;
4e) and carrying out peak value detection on the difference value sequence, and constructing and storing a peak value sequence in advance of a frame number i corresponding to each peak value in the difference value sequence.
The specific operation of extracting the heart rate value of the person to be monitored according to the result of the time-frequency analysis in the step 4) is as follows:
41) the first peak-to-peak value in the peak value sequence is taken as a starting point, the time required by the starting point and the rest peak values is calculated in a traversing way, the frame numbers of the original video corresponding to the ith peak value and the j peak values are set as T [ i ] and T [ j ], and then the calculated heart rate value is as follows: (| T [ j ] -T [ i ] |)/((j-i) xfs) x60, wherein fs is the sampling rate;
42) according to the fact that the normal adult pulse is between [45,120], eliminating heart rate values which are not between [45,120], and then constructing a heart rate value sequence by using the residual heart rate values;
43) calculating the median of the heart rate value sequence, then calculating Y, I, Q the average value of the median of the heart rate value sequence corresponding to the channel subsequence, and taking the calculated result as the heart rate value of the person to be monitored.
In step 21), the corresponding relationship between RGB and YIQ is:
Y＝0.299R+0.587G+0.114B
I＝0.596R-0.274G-0.322B
Q＝0.211R-0.523G+0.312B。
the invention has the following beneficial effects:
the non-contact heart rate monitoring method based on Euler video amplification is characterized in that when the method is specifically operated, a video sequence of a face area of a person to be monitored is acquired only through a camera in a non-contact mode, Euler video color amplification is carried out on the video sequence, a point to be detected is determined by utilizing a random area coordinate generation method, the position of the point to be detected in a subsequent video sequence is tracked by utilizing a Lukas-Kanade optical flow method to determine a color value sequence of the point to be detected, the problem of shaking of a face video is effectively solved, the detection robustness is improved, then time-frequency analysis is carried out on the color value sequence, and the heart rate value of the person to be monitored is calculated according to the result of the time-frequency analysis, so that long-time non-contact monitoring of the heart rate of a user is realized, the automation degree is high.
Drawings
FIG. 1 is a flow chart of the present invention;
fig. 2 is a flow chart of signal processing according to the present invention.
Detailed Description
The invention is described in further detail below with reference to the accompanying drawings:
as shown in fig. 1 and fig. 2, the non-contact heart rate monitoring method based on euler video amplification according to the present invention includes the following steps:
1) acquiring a video sequence of a face area of a person to be monitored through a camera;
the specific operation of the step 1) is as follows:
11) placing the camera at a front position facing the face of a person, opening the camera, and correcting the position of the face area of the person to be monitored;
12) and acquiring a video sequence of the face area of the person to be monitored by a camera at 30 frames/second, wherein the acquisition time is 10 seconds, and the video sequence is stored in an AVI video format.
2) Carrying out Euler video color amplification on the video sequence of the face area of the person to be monitored acquired in the step 1);
the specific operation of the step 2) is as follows:
21) converting the color space of the video of the face area of the person to be monitored from RGB to YIQ, and separating the brightness information and the chrominance information of the image, wherein the Y component represents the brightness information of the image, the I component represents the color change from orange to cyan, and the Q component represents the color change from purple to yellow green, wherein the corresponding relation between RGB and YIQ is as follows:
Y＝0.299R+0.587G+0.114B
I＝0.596R-0.274G-0.322B
Q＝0.211R-0.523G+0.312B。
22) performing spatial decomposition on a video image of a face region of a person to be monitored by using a Gaussian pyramid decomposition method, performing Gaussian smooth blurring on the video image, performing down-sampling to obtain images with different resolutions, and constructing a multi-scale video subsequence of spatial decomposition according to the images with different resolutions, wherein the width and height of each resolution image are 1/2 of the width and height of the original image;
23) performing time domain filtering on the multi-scale video subsequence subjected to spatial decomposition by using an ideal band-pass filter, wherein the resting heart rate of a normal adult is between [0.75 and 2] Hz, and the corresponding heart rate is [45,120] beats/min;
24) amplifying the filtered multi-scale video subsequence subjected to spatial decomposition, wherein the amplification factor is 100, synthesizing the amplified multi-scale video subsequence into an image of a conversion signal, expanding the image to the same size as the original video image, and finally overlapping the image with the original video image to finish the Euler video color amplification of the video sequence of the face region of the person to be monitored.
3) Taking an initial video frame of a video sequence after the Euler video is subjected to color amplification as a reference, detecting a rectangular face region through a harr classifier, identifying the positions of local key organs of the face, including eyebrows, eyes and a nose, so as to determine the forehead region of the face, determining a point to be detected d1 by using a random generation region coordinate method, tracking the position of the point to be detected in a subsequent video sequence by using a Lukas-Kanade optical flow method so as to determine a color value sequence of the point to be detected, wherein the point to be detected in an ith frame video image is marked as d [ i ];
4) performing time-frequency analysis on the color value sequence of the point to be detected obtained in the step 3), calculating the heart rate value of the person to be monitored according to the result of the time-frequency analysis, and then displaying the heart rate value to finish non-contact heart rate monitoring based on Euler video amplification.
The specific operation of performing time-frequency analysis on the color value sequence of the point to be detected obtained in the step 3) in the step 4) is as follows:
4a) channel separation is carried out on the YIQ color space of the point to be detected, Y, I and Q color channel subsequences are respectively generated, and then filtering processing is carried out by utilizing a one-dimensional ideal band-pass filter, wherein the passband of the one-dimensional ideal band-pass filter is [0.75, 2.0] Hz;
4b) performing median filtering on the Y, I and Q color channel subsequences obtained in the step 4a) through a filtering template to remove salt and pepper noise;
4c) respectively solving Y, I and the average value of the Q color channel subsequence;
4d) respectively carrying out difference processing on the Y, I and Q color channel subsequence obtained in the step 4b) and the mean value of the Y, I and Q color channel subsequence obtained in the step 4c) to obtain a difference value sequence;
4e) and carrying out peak value detection on the difference value sequence, and constructing and storing a peak value sequence in advance of a frame number i corresponding to each peak value in the difference value sequence.
The specific operation of extracting the heart rate value of the person to be monitored according to the result of the time-frequency analysis in the step 4) is as follows:
41) the first peak-to-peak value in the peak value sequence is taken as a starting point, the time required by the starting point and the rest peak values is calculated in a traversing way, the frame numbers of the original video corresponding to the ith peak value and the j peak values are set as T [ i ] and T [ j ], and then the calculated heart rate value is as follows: (| T [ j ] -T [ i ] |)/((j-i) xfs) x60, wherein fs is the sampling rate;
42) according to the fact that the normal adult pulse is between [45,120], eliminating heart rate values which are not between [45,120], and then constructing a heart rate value sequence by using the residual heart rate values;
43) calculating the median of the heart rate value sequence, then calculating Y, I, Q the average value of the median of the heart rate value sequence corresponding to the channel subsequence, and taking the calculated result as the heart rate value of the person to be monitored.
When the method is specifically implemented, the method can be realized based on a USB camera, a Linux software and hardware platform and a QT application program interface; the Linux software and hardware platform comprises an ARM-Linux embedded platform, a raspberry pi, a mobile terminal and a Linux computer platform;
the QT application program interface is a cross-platform C + + graphical user interface application program development framework; an OpenCV computer vision library is called to realize an Euler video amplification algorithm based heart rate extraction algorithm, and a QT graphic user interface library is called to design a human-computer interaction interface;
in addition, the QT application provides two modes, a single acquisition and a continuous acquisition, wherein the single acquisition mode is used for single detection of heart rate, and can be used for normal testing and intermittent detection of heart rate; the continuous acquisition mode is used for continuously detecting the heart rate, the application program acquires video frames at regular time for 1 minute, color amplification processing and heart rate calculation are carried out, the heart rate change condition of the tested person within a period of time is recorded, and the data sample can be used for health management of the tested person, prediction of heart rate diseases and the like;
preferably, the QT application has a network communication service function and can perform a TCP/IP data transceiving function.
Referring to table 1, the pulse detection data and manual pulse taking detection data comparison table of the invention takes a single person as a measured person, takes pulses for 1 minute during detection, and counts the heartbeat times of the measured person; meanwhile, the invention is used for monitoring the testees, and the results of data for 10 times of detection on two testees are as follows:
TABLE 1
As can be seen from the comparison of the monitoring results in Table 1, the detection result of the invention is basically consistent with the manual pulse taking detection result of the traditional Chinese medicine, and the error range is within +/-2 bpm. The invention has the advantages of high detection accuracy, good practical value, high comfort level of the detected person, low price, continuous monitoring, wide application range and the like, and greatly lightens the workload of medical staff.
The above description is only an example of the present invention, and is not intended to limit the present invention, and it is obvious to those skilled in the art that various modifications and variations can be made in the present invention. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the scope of the claims of the present invention.
Claims (5)
1. A non-contact heart rate monitoring method based on Euler video amplification is characterized by comprising the following steps:
1) acquiring a video sequence of a face area of a person to be monitored through a camera;
2) carrying out Euler video color amplification on the video sequence of the face area of the person to be monitored acquired in the step 1);
3) taking an initial video frame of a video sequence after the Euler video is subjected to color amplification as a reference, detecting a rectangular face region through a harr classifier, simultaneously identifying the position of a local key organ of the face to determine the forehead region of the face, determining a point to be detected d1 by using a random generation region coordinate method, and tracking the position of the point to be detected in a subsequent video sequence by using a Lukas-Kanade optical flow method to determine a color value sequence of the point to be detected, wherein the point to be detected in an ith frame video image is marked as d [ i ];
4) performing time-frequency analysis on the color value sequence of the point to be detected obtained in the step 3), calculating the heart rate value of the person to be monitored according to the result of the time-frequency analysis, and completing non-contact heart rate monitoring based on Euler video amplification;
the specific operation of performing time-frequency analysis on the color value sequence of the point to be detected obtained in the step 3) in the step 4) is as follows:
4a) channel separation is carried out on the YIQ color space of the point to be detected, Y, I and Q color channel subsequences are respectively generated, and then filtering processing is carried out by utilizing a one-dimensional ideal band-pass filter;
4b) performing median filtering on the Y, I and Q color channel subsequences obtained in the step 4a) through a filtering template to remove salt and pepper noise;
4c) respectively solving Y, I and the average value of the Q color channel subsequence;
4d) respectively carrying out difference processing on the Y, I and Q color channel subsequence obtained in the step 4b) and the mean value of the Y, I and Q color channel subsequence obtained in the step 4c) to obtain a difference value sequence;
4e) and carrying out peak value detection on the difference value sequence, extracting a frame number i corresponding to each peak value in the difference value sequence, and constructing and storing the peak value sequence.
2. The non-contact heart rate monitoring method based on Euler video amplification according to claim 1, characterized in that the specific operation of step 1) is:
11) placing the camera at a front position facing the face of a person, opening the camera, and correcting the position of the face area of the person to be monitored;
12) and acquiring a video sequence of the face area of the person to be monitored by a camera at 30 frames/second, wherein the acquisition time is 10 seconds, and the video sequence is stored in an AVI video format.
3. The non-contact heart rate monitoring method based on Euler video amplification according to claim 1, characterized in that the specific operation of step 2) is:
21) converting the color space of the video of the face area of the person to be monitored from RGB into YIQ, and separating the brightness information and the chrominance information of the image, wherein the Y component represents the brightness information of the image, the I component represents the color change from orange to cyan, and the Q component represents the color change from purple to yellow-green;
22) performing spatial decomposition on a video image of a face region of a person to be monitored by using a Gaussian pyramid decomposition method, performing Gaussian smooth blurring on the video image, performing down-sampling to obtain images with different resolutions, and constructing a multi-scale video subsequence of spatial decomposition according to the images with different resolutions, wherein the width and height of each resolution image are 1/2 of the width and height of the original image;
23) performing time domain filtering on the multi-scale video subsequence subjected to spatial decomposition by using an ideal band-pass filter;
24) amplifying the filtered multi-scale video subsequence subjected to spatial decomposition, wherein the amplification factor is 100, synthesizing the amplified multi-scale video subsequence into an image of a conversion signal, expanding the image to the same size as the original video image, and finally overlapping the image with the original video image to finish the Euler video color amplification of the video sequence of the face area of the person to be monitored.
4. The non-contact heart rate monitoring method based on Euler video amplification of claim 1, wherein the specific operation of extracting the heart rate value of the person to be monitored according to the result of the time-frequency analysis in step 4) is as follows:
41) the first peak-to-peak value in the peak value sequence is taken as a starting point, the time required by the starting point and the rest peak values is calculated in a traversing way, the frame numbers of the original video corresponding to the ith peak value and the j peak values are set as T [ i ] and T [ j ], and then the calculated heart rate value is as follows: (| T [ j ] -T [ i ] |)/((j-i) xfs) x60, wherein fs is the sampling rate;
42) according to the fact that the normal adult pulse is between [45,120], eliminating heart rate values which are not between [45,120], and then constructing a heart rate value sequence by using the residual heart rate values;
43) calculating the median of the heart rate value sequence, then calculating Y, I, Q the average value of the median of the heart rate value sequence corresponding to the channel subsequence, and taking the calculated result as the heart rate value of the person to be monitored.
5. The non-contact heart rate monitoring method based on Euler video amplification of claim 3, wherein in step 21), the corresponding relationship between RGB and YIQ is as follows:
Y＝0.299R+0.587G+0.114B
I＝0.596R-0.274G-0.322B
Q＝0.211R-0.523G+0.312B。
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810622284.6A CN109044314B (en) | 2018-06-15 | 2018-06-15 | Non-contact heart rate monitoring method based on Euler video amplification |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810622284.6A CN109044314B (en) | 2018-06-15 | 2018-06-15 | Non-contact heart rate monitoring method based on Euler video amplification |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109044314A CN109044314A (en) | 2018-12-21 |
| CN109044314B true CN109044314B (en) | 2021-06-08 |
Family
ID=64820358
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810622284.6A Active CN109044314B (en) | 2018-06-15 | 2018-06-15 | Non-contact heart rate monitoring method based on Euler video amplification |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109044314B (en) |
Families Citing this family (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109793506B (en) * | 2019-01-18 | 2022-03-22 | 合肥工业大学 | Non-contact radial artery waveform extraction method |
| AU2020244866A1 (en) * | 2019-03-27 | 2021-10-14 | Butler, William E | Reconstructing cardiac frequency phenomena in angiographic data |
| CN110236511A (en) * | 2019-05-30 | 2019-09-17 | 云南东巴文健康管理有限公司 | A kind of noninvasive method for measuring heart rate based on video |
| CN110236514A (en) * | 2019-07-12 | 2019-09-17 | 华东师范大学 | The real-time heart rate detection method that mode based on video is extracted and median filtering combines |
| CN110674675A (en) * | 2019-08-02 | 2020-01-10 | 杭州电子科技大学 | Pedestrian face anti-fraud method |
| CN112842257B (en) * | 2019-11-12 | 2022-12-06 | 磅客策(上海)机器人有限公司 | Blood vessel positioning method and device |
| CN111243739A (en) * | 2020-01-07 | 2020-06-05 | 四川大学 | Anti-interference physiological parameter telemetering method and system |
| CN113842128B (en) * | 2021-09-29 | 2023-09-26 | 北京清智图灵科技有限公司 | Non-contact heart rate detection device based on multiple filtering and mixed amplification |
| CN115205270B (en) * | 2022-07-25 | 2023-10-24 | 哈尔滨工业大学 | Non-contact blood oxygen saturation detection method and system based on image processing |
| CN117576091B (en) * | 2024-01-15 | 2024-04-09 | 深圳昱拓智能有限公司 | Cooling tower fan vibration detection method and system based on video detection |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105989357A (en) * | 2016-01-18 | 2016-10-05 | 合肥工业大学 | Human face video processing-based heart rate detection method |
| CN107529646A (en) * | 2017-05-02 | 2018-01-02 | 广东工业大学 | A kind of non-contact type method for measuring heart rate and device based on Euler's image zoom |
| EP3427640A1 (en) * | 2017-07-11 | 2019-01-16 | Tata Consultancy Services Limited | Serial fusion of eulerian and lagrangian approaches for real-time heart rate estimation |
-
2018
- 2018-06-15 CN CN201810622284.6A patent/CN109044314B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105989357A (en) * | 2016-01-18 | 2016-10-05 | 合肥工业大学 | Human face video processing-based heart rate detection method |
| CN107529646A (en) * | 2017-05-02 | 2018-01-02 | 广东工业大学 | A kind of non-contact type method for measuring heart rate and device based on Euler's image zoom |
| EP3427640A1 (en) * | 2017-07-11 | 2019-01-16 | Tata Consultancy Services Limited | Serial fusion of eulerian and lagrangian approaches for real-time heart rate estimation |
Non-Patent Citations (3)
| Title |
|---|
| 基于人脸图像的非接触式心率测量方法;皮慧;《中国优秀硕士学位论文全文数据库 医药卫生科技辑》;20180415(第4期);论文正文第11、17-19、26-28、31、45页 * |
| 基于欧拉影像放大的非接触式心率测量方法;苏培权等;《计算机应用》;20180310;第38卷(第3期);论文全文 * |
| 基于视频的非接触式心率测量研究;陈丹丹;《中国优秀硕士学位论文全文数据库 信息科技辑》;20170215(第2期);论文正文第21、28-34、43、61页） * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109044314A (en) | 2018-12-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109044314B (en) | Non-contact heart rate monitoring method based on Euler video amplification | |
| CN107529646B (en) | Non-contact heart rate measurement method and device based on Euler image amplification | |
| CN105266772B (en) | A kind of measurement method of physiological parameter | |
| Kwon et al. | Validation of heart rate extraction using video imaging on a built-in camera system of a smartphone | |
| CN103702014B (en) | Non-contact physiological parameter detection method, system and device | |
| CN111728602A (en) | Non-contact blood pressure measuring device based on PPG | |
| CN107506716A (en) | A kind of contactless real-time method for measuring heart rate based on video image | |
| CN106793962A (en) | Method and apparatus for continuously estimating human blood-pressure using video image | |
| KR101738278B1 (en) | Emotion recognition method based on image | |
| McDuff et al. | Fusing partial camera signals for noncontact pulse rate variability measurement | |
| Casado et al. | Face2PPG: An unsupervised pipeline for blood volume pulse extraction from faces | |
| JP6115263B2 (en) | Pulse wave detection device, pulse wave detection method, and pulse wave detection program | |
| CN109009052A (en) | The embedded heart rate measurement system and its measurement method of view-based access control model | |
| CN111275018B (en) | Non-contact heart rate signal extraction method based on annular region of interest weighting | |
| CA2882080A1 (en) | Real-time physiological characteristic detection based on reflected components of light | |
| CN111387959A (en) | Non-contact physiological parameter detection method based on IPPG | |
| Przybyło | A deep learning approach for remote heart rate estimation | |
| JP2017029318A (en) | Method for processing image for stress-monitoring and program of the same | |
| CN108937905B (en) | Non-contact heart rate detection method based on signal fitting | |
| JP2021534948A (en) | Pre-processing method and storage device for fundus image quantitative analysis | |
| Suriani et al. | Non-contact Facial based Vital Sign Estimation using Convolutional Neural Network Approach | |
| US10631727B2 (en) | Method and system for detecting time domain cardiac parameters by using pupillary response | |
| CN110584638A (en) | Non-contact heart rate measurement method based on CMOR wavelet | |
| Sarkar et al. | Evaluation of video magnification for nonintrusive heart rate measurement | |
| TW202247816A (en) | Non-contact heart rhythm category monitoring system and method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |