CN116999044A - Real-time motion full-connection bidirectional consistent optical flow field heart rate signal extraction method - Google Patents
Real-time motion full-connection bidirectional consistent optical flow field heart rate signal extraction method Download PDFInfo
- Publication number
- CN116999044A CN116999044A CN202311150859.6A CN202311150859A CN116999044A CN 116999044 A CN116999044 A CN 116999044A CN 202311150859 A CN202311150859 A CN 202311150859A CN 116999044 A CN116999044 A CN 116999044A
- Authority
- CN
- China
- Prior art keywords
- flow field
- optical flow
- heart rate
- extracting
- frame
- 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.)
- Granted
Links
- 230000003287 optical effect Effects 0.000 title claims abstract description 47
- 230000002457 bidirectional effect Effects 0.000 title claims abstract description 27
- 238000000605 extraction Methods 0.000 title abstract description 17
- 238000001514 detection method Methods 0.000 claims abstract description 14
- 238000000034 method Methods 0.000 claims description 27
- 238000006073 displacement reaction Methods 0.000 claims description 18
- 238000001914 filtration Methods 0.000 claims description 15
- 238000012545 processing Methods 0.000 claims description 10
- 238000004364 calculation method Methods 0.000 claims description 7
- 238000000926 separation method Methods 0.000 claims description 6
- 238000005311 autocorrelation function Methods 0.000 claims description 3
- 230000001427 coherent effect Effects 0.000 claims description 3
- 239000000470 constituent Substances 0.000 claims description 3
- 238000000354 decomposition reaction Methods 0.000 claims description 3
- 238000012216 screening Methods 0.000 claims description 3
- 238000012935 Averaging Methods 0.000 claims description 2
- VYZAMTAEIAYCRO-UHFFFAOYSA-N Chromium Chemical compound [Cr] VYZAMTAEIAYCRO-UHFFFAOYSA-N 0.000 abstract description 5
- 238000005259 measurement Methods 0.000 description 5
- 230000001815 facial effect Effects 0.000 description 2
- 238000013186 photoplethysmography Methods 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 230000002792 vascular Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000000747 cardiac effect Effects 0.000 description 1
- 210000001061 forehead Anatomy 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
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
-
- 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
- A61B5/02427—Details of sensor
-
- 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
- A61B5/7203—Signal processing specially adapted for physiological signals or for diagnostic purposes for noise prevention, reduction or removal
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
- A61B5/725—Details of waveform analysis using specific filters therefor, e.g. Kalman or adaptive filters
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Medical Informatics (AREA)
- Surgery (AREA)
- Biophysics (AREA)
- Pathology (AREA)
- Physiology (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Veterinary Medicine (AREA)
- Molecular Biology (AREA)
- Physics & Mathematics (AREA)
- Animal Behavior & Ethology (AREA)
- General Health & Medical Sciences (AREA)
- Public Health (AREA)
- Cardiology (AREA)
- Signal Processing (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Psychiatry (AREA)
- Image Analysis (AREA)
Abstract
The application discloses a real-time motion full-connection bidirectional consistent optical flow field heart rate signal extraction method, which comprises the following steps: the application further utilizes a fully-connected bidirectional consistent optical flow field in the original face detection and tracking area to dynamically select the ROI area, only the ROI area which is useful for heart rate signals is reserved, interference caused by movement on rPPG signals can be reduced, and the heart rate signals of a human body in a movement state can be reliably calculated by combining a CHROM model.
Description
Technical Field
The application relates to the technical field of heart rate signal extraction, in particular to a real-time motion full-connection bidirectional consistent optical flow field heart rate signal extraction method.
Background
Heart rate detection is important for determining the physiological and psychological state of a person, and traditional heart rate detection is contact type, such as electrode type electrocardiogram, and heart rate is measured by sensing the cardiac current of the human body through electrode plates; on wearable devices such as smartwatches, it is most common to make measurements with photoplethysmography (PPG), but also in close contact with the skin. Although the contact measurement mode is accurate, the contact measurement mode inevitably causes a lot of discomfort and inconvenience, and particularly in some special scenes, the contact measurement mode cannot be used.
In 2008, first study by verkruyse et al proves that the photo-volume pulse wave trace signal related to the heart rate can be analyzed from the face video of the person collected by the camera, so as to realize remote measurement of the heart rate, which is also called rPPG (remotePPG). However, such remote heart rate detection based on video analysis is relatively much affected by the environment and the detected object, and generally requires that the object remains stationary for a long time, since the object, once moving, will bring about a change in the ROI (hot spot area, mainly the facial area of the person) and a relative change in the distance and angle between the object and the camera, light source. These variations can affect the vascular pulse signal, giving more noise and thus affecting the accuracy of the heart rate calculation.
Disclosure of Invention
This section is intended to outline some aspects of embodiments of the application and to briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section as well as in the description of the application and in the title of the application, which may not be used to limit the scope of the application.
Therefore, the application aims to provide a real-time motion full-connection bidirectional consistent optical flow field heart rate signal extraction method, which improves the accuracy of heart rate calculation.
In order to solve the technical problems, according to one aspect of the present application, the following technical solutions are provided:
a real-time motion full-connection bidirectional consistent optical flow field heart rate signal extraction method comprises the following steps:
s1, detecting and tracking the face of a user in a video acquisition mode to acquire a face region image of the user;
s2, extracting a human face skin color region of a user, dynamically selecting an ROI region, and performing primary color separation to generate an original digital signal;
s3, performing blind source separation on the sampled digital signals to obtain independent source signals, extracting pulse after signal processing, performing FFT (fast Fourier transform), and selecting the maximum peak frequency as the frequency of the heartbeat.
As a preferable scheme of the real-time motion full-connection bidirectional consistent optical flow field heart rate signal extraction method, the signal processing is as follows: the correlation or empirical mode decomposition is used for signal screening processing, and then arithmetic average filtering or band-pass filtering signal processing is used.
As a preferable scheme of the real-time motion full-connection bidirectional consistent optical flow field heart rate signal extraction method, the method comprises the following steps of:
calculating an optical flow field of a certain characteristic point in a later frame in a video frame of L frames in total of the extracted ROI area for a period of time, reversely calculating the optical flow field at the current position according to the position of the characteristic point in the later frame, and judging consistency;
and carrying out recursion expansion, judging consistency of a certain point on the image which is expanded to the L frames by taking one frame as a distance, reserving matched characteristic points, and filtering out unmatched characteristic points.
As a preferred scheme of the real-time motion full-connection bidirectional consistent optical flow field heart rate signal extraction method, the application calculates an optical flow field of a certain characteristic point in a later frame, reversely calculates the optical flow field at the current position by the position of the characteristic point in the later frame, and carries out the specific steps of consistency judgment as follows:
inputting two continuous frames of images, namely a k frame and a k+1 frame, and an initial pixel point p_k;
calculating to obtain a displacement vector d_k (u, v) at a p_k point by using an optical flow field method;
updating the pixel point position according to the displacement vector d_k (u, v) to obtain p_ (k+1) =p_k+d_k (u, v);
calculating a displacement vector d_ (k+1)/(u, v) at a p_ (k+1) point by using a reverse optical flow field method;
and updating the position of the reverse pixel point according to the displacement vector d_ (k+1)/(u, v) to obtain p_k_ (k+1) +d_ (k+1)/(u, v).
Comparing whether the distance between p_k and p_k' is close enough, if the distance is smaller than a certain threshold, considering that the displacement of the pixel point between the continuous frames is stable, and if the distance is larger than or equal to a certain threshold, filtering out the unmatched pixel points.
As a preferred scheme of the real-time motion full-connection bidirectional consistent optical flow field heart rate signal extraction method, the application carries out recursion expansion, uses one frame as consistency judgment of a certain point on an image which is expanded to an L frame, reserves matched characteristic points, and filters out unmatched characteristic points, wherein the method comprises the following specific steps of:
inputting a sequence [0:L-1 frame ] containing L frames of images, and an initial pixel point p_0;
defining a list all_p, adding the initial pixel point p_0 into the list, and judging the sequence length: if the sequence length is less than 2, returning to None;
calling a consistency () function, using an initial pixel point p_0 as a calculation starting point, calculating by using an optical flow field method to obtain a displacement vector, and calculating to obtain a matched pixel point position p_1 of a 1 st frame;
judging whether the length of the input sequence is equal to 2: if yes, adding the p_1 into an all_p list, returning to the all_p, and if the length of the input sequence is greater than 2, recursively calling a constituents () function to calculate the matching feature point positions of all frames after the 1 st frame, so as to obtain a matching feature point list list_p;
and adding the calculated matching feature point position list list_p into an all_p list, and storing the matching feature point positions of reserved matching among all frames.
As a preferable scheme of the real-time motion full-connection bidirectional consistent optical flow field heart rate signal extraction method, the method in the step S3 further comprises the following steps:
extracting signals from the color channels: extracting heart rate using the signals in the color channels;
extracting a pulse signal from the color signal: extracting a pulse signal from the color signal using a frequency domain filter and a peak detection algorithm;
using the calculated heart rate: heart rate is calculated using an autocorrelation function or a peak detection algorithm.
As a preferable scheme of the real-time motion full-connection bidirectional consistent optical flow field heart rate signal extraction method, the method for extracting signals from color channels further comprises preprocessing, and the method comprises the following steps:
removal of low and high frequency noise using band pass filters
Converting RGB signals into a color space such as YCbCr or HSV;
spatially averaging the signals to reduce motion artifacts and other noise;
the signals are spatially averaged to reduce motion artifacts and other noise.
Compared with the prior art, the application has the following beneficial effects: the consistency of points on all frames is obtained by further utilizing the fully-connected bidirectional consistent optical flow field in the original face detection and tracking area, the inconsistent points are filtered by reserving all consistent points, the ROI area is dynamically selected, only the ROI area which is useful for heart rate signals is reserved, the interference to rPPG signals caused by movement can be reduced, the interference to rPPG signals caused by the change of reflection angles is reduced by combining with a CHROM model, and the heart rate signals of a human body in a movement state are reliably calculated.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following detailed description will be given with reference to the accompanying drawings and detailed embodiments, it being obvious that the drawings in the following description are only some embodiments of the present application, and that other drawings may be obtained from these drawings without inventive faculty for a person skilled in the art. Wherein:
fig. 1 is a flow chart of a real-time motion full-connection bidirectional consistent optical flow field heart rate signal extraction method of the application.
Detailed Description
In order that the above objects, features and advantages of the application will be readily understood, a more particular description of the application will be rendered by reference to the appended drawings.
Next, the present application will be described in detail with reference to the drawings, wherein the sectional view of the device structure is not partially enlarged to general scale for the convenience of description, and the drawings are only examples, which should not limit the scope of the present application. In addition, the three-dimensional dimensions of length, width and depth should be included in actual fabrication.
For the purpose of making the objects, technical solutions and advantages of the present application more apparent, embodiments of the present application will be described in further detail below with reference to the accompanying drawings.
The application provides a real-time motion full-connection bidirectional consistent optical flow field heart rate signal extraction method, which improves the accuracy of heart rate calculation.
In this embodiment, rpg detection of heart rate generally requires that the subject remain stationary for a longer period of time, as the subject once moving will bring about changes in ROI (hot spot area, mainly the facial area of the person) and relative changes in distance and angle between the subject and the camera, light source. These variations can affect the vascular pulse signal, giving more noise and thus affecting the accuracy of the heart rate calculation.
For the latter variation, the CHROM model method can be sampled, and the method adopts the linear combination of R, G, B three channels, so that the influence caused by the change of the reflection angle due to the change of the angle between the object and the camera and the light source can be overcome.
For the ROI change caused by the motion, the fully-connected bidirectional consistent optical flow field can be further utilized in the original face detection and tracking area to dynamically select the ROI area, and only the ROI area which is useful for the heart rate signal is reserved. This is advantageous over methods that take only the forehead or use the entire face as the ROI area.
Fig. 1 is a flowchart of an embodiment of a real-time motion full-connection bidirectional coherent optical flow field heart rate signal extraction method of the present application, referring to fig. 1, the embodiment of the real-time motion full-connection bidirectional coherent optical flow field heart rate signal extraction method specifically includes the following steps:
s1, detecting and tracking the face of a user in a video acquisition mode to acquire a face region image of the user;
s2, extracting a human face skin color region of a user, dynamically selecting an ROI region, and performing primary color separation to generate an original digital signal;
s3, performing blind source separation on the sampled digital signals to obtain independent source signals, performing signal screening processing through correlation or empirical mode decomposition, extracting pulse after signal processing such as arithmetic average filtering or band-pass filtering, performing FFT (fast Fourier transform), and selecting the maximum peak frequency as the frequency of the heartbeat.
The step of dynamically selecting the ROI area is as follows:
calculating an optical flow field of a certain characteristic point in a later frame in a video frame of L frames in total of the extracted ROI area for a period of time, reversely calculating the optical flow field at the current position according to the position of the characteristic point in the later frame, and judging consistency; and then recursively expanding, namely judging the consistency of a certain point on the image which is expanded to the L frames by taking one frame as a distance, reserving matched characteristic points, and filtering out unmatched characteristic points.
The specific steps of calculating the optical flow field of a certain characteristic point in the following frame, reversely calculating the optical flow field at the current position according to the position of the characteristic point in the following frame, and carrying out consistency judgment are as follows:
inputting two continuous frames of images, namely a k frame and a k+1 frame, and an initial pixel point p_k; calculating to obtain a displacement vector d_k (u, v) at a p_k point by using an optical flow field method; updating the pixel point position according to the displacement vector d_k (u, v) to obtain p_ (k+1) =p_k+d_k (u, v); calculating a displacement vector d_ (k+1)/(u, v) at a p_ (k+1) point by using a reverse optical flow field method; and updating the position of the reverse pixel point according to the displacement vector d_ (k+1)/(u, v) to obtain p_k_ (k+1) +d_ (k+1)/(u, v), comparing whether the distance between p_k and p_k_ is sufficiently close, if the distance is smaller than a certain threshold value, considering that the displacement of the pixel point between the continuous frames is stable, and if the distance is larger than or equal to a certain threshold value, filtering out the unmatched pixel points.
Performing recursion expansion, namely performing consistency judgment on a certain point on an image which is expanded to an L frame by taking one frame as a distance, reserving matched characteristic points, and filtering out unmatched characteristic points, wherein the method comprises the following specific steps of:
inputting a sequence [0:L-1 frame ] containing L frames of images, and an initial pixel point p_0; defining a list all_p, adding the initial pixel point p_0 into the list, and judging the sequence length: if the sequence length is less than 2, returning to None; calling a consistency () function, using an initial pixel point p_0 as a calculation starting point, calculating by using an optical flow field method to obtain a displacement vector, and calculating to obtain a matched pixel point position p_1 of a 1 st frame; judging whether the length of the input sequence is equal to 2: if yes, adding the p_1 into an all_p list, returning to the all_p, and if the length of the input sequence is greater than 2, recursively calling a constituents () function to calculate the matching feature point positions of all frames after the 1 st frame, so as to obtain a matching feature point list list_p; and adding the calculated matching feature point position list list_p into an all_p list, and storing the matching feature point positions of reserved matching among all frames.
In step S3, a CHROM model method is further included to overcome the influence caused by the change of the reflection angle due to the change of the angle between the object and the camera, and the light source, and the specific steps are as follows:
extracting signals from the color channels: extracting heart rate using the signals in the color channels; extracting a pulse signal from the color signal: extracting a pulse signal from the color signal using a frequency domain filter and a peak detection algorithm; using the calculated heart rate: heart rate is calculated using an autocorrelation function or a peak detection algorithm.
Wherein, the extracting signal from the color channel further comprises preprocessing to improve the signal quality, and the steps are as follows:
removing low-frequency noise and high-frequency noise by using a band-pass filter, and converting RGB signals into color spaces such as YCbCr or HSV; the signals are spatially averaged to reduce motion artifacts and other noise and spatially averaged to reduce motion artifacts and other noise.
The application further utilizes the fully-connected bidirectional consistent light flow field in the original face detection and tracking area to obtain the consistency of points on all frames, and dynamically selects the ROI area by reserving all consistent points, filtering non-consistent points and reserving only the ROI area which is useful for heart rate signals, thereby reducing the interference to the rPPG signals caused by movement, reducing the interference to the rPPG signals caused by the change of reflection angles by combining with a CHROM model and reliably calculating the heart rate signals of the human body in a movement state.
Although the application has been described hereinabove with reference to embodiments, various modifications thereof may be made and equivalents may be substituted for elements thereof without departing from the scope of the application. In particular, the features of the disclosed embodiments may be combined with each other in any manner as long as there is no structural conflict, and the exhaustive description of these combinations is not given in this specification merely for the sake of omitting the descriptions and saving resources. Therefore, it is intended that the application not be limited to the particular embodiment disclosed, but that the application will include all embodiments falling within the scope of the appended claims.
Claims (7)
1. The method for extracting the heart rate signal of the real-time motion full-connection bidirectional consistent optical flow field is characterized by comprising the following steps of:
s1, detecting and tracking the face of a user in a video acquisition mode to acquire a face region image of the user;
s2, extracting a human face skin color region of a user, dynamically selecting an ROI region, and performing primary color separation to generate an original digital signal;
s3, performing blind source separation on the sampled digital signals to obtain independent source signals, extracting pulse after signal processing, performing FFT (fast Fourier transform), and selecting the maximum peak frequency as the frequency of the heartbeat.
2. The method for extracting the heart rate signal from the real-time motion fully-connected bidirectional consistent optical flow field according to claim 1, wherein the signal processing is as follows: the correlation or empirical mode decomposition is used for signal screening processing, and then arithmetic average filtering or band-pass filtering signal processing is used.
3. The method for extracting the heart rate signal from the fully-connected bidirectional coherent optical flow field in real time according to claim 1, wherein the step of dynamically selecting the ROI area is as follows:
calculating an optical flow field of a certain characteristic point in a later frame in a video frame of L frames in total of the extracted ROI area for a period of time, reversely calculating the optical flow field at the current position according to the position of the characteristic point in the later frame, and judging consistency;
and carrying out recursion expansion, judging consistency of a certain point on the image which is expanded to the L frames by taking one frame as a distance, reserving matched characteristic points, and filtering out unmatched characteristic points.
4. The method for extracting the heart rate signal of the real-time motion fully-connected bidirectional consistent optical flow field according to claim 2, wherein the specific steps of calculating the optical flow field of a certain characteristic point in a subsequent frame, calculating the optical flow field at the current position reversely according to the position of the characteristic point in the subsequent frame, and carrying out consistency judgment are as follows:
inputting two continuous frames of images, namely a k frame and a k+1 frame, and an initial pixel point p_k;
calculating to obtain a displacement vector d_k (u, v) at a p_k point by using an optical flow field method;
updating the pixel point position according to the displacement vector d_k (u, v) to obtain p_ (k+1) =p_k+d_k (u, v);
calculating a displacement vector d_ (k+1)/(u, v) at a p_ (k+1) point by using a reverse optical flow field method;
updating the position of the reverse pixel point according to the displacement vector d_ (k+1)/(u, v) to obtain p_k_ (k+1) +d_ (k+1)/(u, v);
comparing whether the distance between p_k and p_k' is close enough, if the distance is smaller than a certain threshold, considering that the displacement of the pixel point between the continuous frames is stable, and if the distance is larger than or equal to a certain threshold, filtering out the unmatched pixel points.
5. The method for extracting the heart rate signal from the full-connection bidirectional uniform optical flow field of real-time motion according to claim 4, wherein the steps of recursively expanding, taking one frame as a consistency judgment of a certain point on an image which is expanded to an L frame, reserving matched characteristic points and filtering out unmatched characteristic points are as follows:
inputting a sequence [0:L-1 frame ] containing L frames of images, and an initial pixel point p_0;
defining a list all_p, adding the initial pixel point p_0 into the list, and judging the sequence length: if the sequence length is less than 2, returning to None;
calling a consistency () function, using an initial pixel point p_0 as a calculation starting point, calculating by using an optical flow field method to obtain a displacement vector, and calculating to obtain a matched pixel point position p_1 of a 1 st frame;
judging whether the length of the input sequence is equal to 2: if yes, adding the p_1 into an all_p list, returning to the all_p, and if the length of the input sequence is greater than 2, recursively calling a constituents () function to calculate the matching feature point positions of all frames after the 1 st frame, so as to obtain a matching feature point list list_p;
and adding the calculated matching feature point position list list_p into an all_p list, and storing the matching feature point positions of reserved matching among all frames.
6. The method for extracting the heart rate signal of the real-time motion fully-connected bidirectional consistent optical flow field according to claim 1, wherein in the step S3, the method further comprises the following steps:
extracting signals from the color channels: extracting heart rate using the signals in the color channels;
extracting a pulse signal from the color signal: extracting a pulse signal from the color signal using a frequency domain filter and a peak detection algorithm;
using the calculated heart rate: heart rate is calculated using an autocorrelation function or a peak detection algorithm.
7. The method for extracting the real-time motion fully-connected bidirectional consistent optical flow field heart rate signal according to claim 6, wherein the step of extracting the signal from the color channel further comprises the following steps:
removing low frequency and high frequency noise using a band pass filter;
converting RGB signals into a color space such as YCbCr or HSV;
spatially averaging the signals to reduce motion artifacts and other noise;
the signals are spatially averaged to reduce motion artifacts and other noise.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311150859.6A CN116999044B (en) | 2023-09-07 | 2023-09-07 | Real-time motion full-connection bidirectional consistent optical flow field heart rate signal extraction method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311150859.6A CN116999044B (en) | 2023-09-07 | 2023-09-07 | Real-time motion full-connection bidirectional consistent optical flow field heart rate signal extraction method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116999044A true CN116999044A (en) | 2023-11-07 |
| CN116999044B CN116999044B (en) | 2024-04-16 |
Family
ID=88565678
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311150859.6A Active CN116999044B (en) | 2023-09-07 | 2023-09-07 | Real-time motion full-connection bidirectional consistent optical flow field heart rate signal extraction method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116999044B (en) |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| WO2016187776A1 (en) * | 2015-05-25 | 2016-12-01 | 北京大学深圳研究生院 | Video frame interpolation method and system based on optical flow method |
| CN106447696A (en) * | 2016-09-29 | 2017-02-22 | 郑州轻工业学院 | Bidirectional SIFT (scale invariant feature transformation) flow motion evaluation-based large-displacement target sparse tracking 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 |
| CN107330945A (en) * | 2017-07-05 | 2017-11-07 | 合肥工业大学 | A kind of examing heartbeat fastly method based on video |
| DE102017118636B3 (en) * | 2017-08-15 | 2018-12-06 | Technische Universität Chemnitz | Method for contactless determination of the heart rate of a person |
| CN109350030A (en) * | 2018-08-17 | 2019-02-19 | 西安电子科技大学 | System and method based on phase enhanced processing face video heart rate signal |
| CN109480808A (en) * | 2018-09-27 | 2019-03-19 | 深圳市君利信达科技有限公司 | A kind of heart rate detection method based on PPG, system, equipment and storage medium |
| CN113951855A (en) * | 2021-02-01 | 2022-01-21 | 南京云思创智信息科技有限公司 | Non-contact heart rate measuring method based on human face |
| CN114569101A (en) * | 2022-03-09 | 2022-06-03 | 成都信息工程大学 | Non-contact heart rate detection method and device and electronic equipment |
| CN115376179A (en) * | 2021-12-14 | 2022-11-22 | 山东大学齐鲁医院 | Non-contact heart rate measuring method and system |
| CN116385495A (en) * | 2023-04-20 | 2023-07-04 | 大连海事大学 | Moving target closed-loop detection method of infrared video under dynamic background |
-
2023
- 2023-09-07 CN CN202311150859.6A patent/CN116999044B/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| WO2016187776A1 (en) * | 2015-05-25 | 2016-12-01 | 北京大学深圳研究生院 | Video frame interpolation method and system based on optical flow method |
| CN106447696A (en) * | 2016-09-29 | 2017-02-22 | 郑州轻工业学院 | Bidirectional SIFT (scale invariant feature transformation) flow motion evaluation-based large-displacement target sparse tracking 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 |
| CN107330945A (en) * | 2017-07-05 | 2017-11-07 | 合肥工业大学 | A kind of examing heartbeat fastly method based on video |
| DE102017118636B3 (en) * | 2017-08-15 | 2018-12-06 | Technische Universität Chemnitz | Method for contactless determination of the heart rate of a person |
| CN109350030A (en) * | 2018-08-17 | 2019-02-19 | 西安电子科技大学 | System and method based on phase enhanced processing face video heart rate signal |
| CN109480808A (en) * | 2018-09-27 | 2019-03-19 | 深圳市君利信达科技有限公司 | A kind of heart rate detection method based on PPG, system, equipment and storage medium |
| CN113951855A (en) * | 2021-02-01 | 2022-01-21 | 南京云思创智信息科技有限公司 | Non-contact heart rate measuring method based on human face |
| CN115376179A (en) * | 2021-12-14 | 2022-11-22 | 山东大学齐鲁医院 | Non-contact heart rate measuring method and system |
| CN114569101A (en) * | 2022-03-09 | 2022-06-03 | 成都信息工程大学 | Non-contact heart rate detection method and device and electronic equipment |
| CN116385495A (en) * | 2023-04-20 | 2023-07-04 | 大连海事大学 | Moving target closed-loop detection method of infrared video under dynamic background |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116999044B (en) | 2024-04-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107529646B (en) | Non-contact heart rate measurement method and device based on Euler image amplification | |
| Feng et al. | Dynamic ROI based on K-means for remote photoplethysmography | |
| CN110662480B (en) | Device, system and method for measuring and processing physiological signals of a subject | |
| CN103908236B (en) | A kind of automatic blood pressure measurement system | |
| McDuff et al. | Remote detection of photoplethysmographic systolic and diastolic peaks using a digital camera | |
| CN111728602A (en) | Non-contact blood pressure measuring device based on PPG | |
| Gudi et al. | Efficient real-time camera based estimation of heart rate and its variability | |
| CN110647815A (en) | Non-contact heart rate measurement method and system based on face video image | |
| CN110269600A (en) | Based on polynary empirical mode decomposition and the contactless video heart rate detection method for combining blind source separating | |
| CN105147274A (en) | Method for extracting heart rate from visible spectrum section face video signal | |
| WO2011127487A2 (en) | Method and system for measurement of physiological parameters | |
| CN111387959A (en) | Non-contact physiological parameter detection method based on IPPG | |
| CN111345803B (en) | Heart rate variability measuring method based on mobile device camera | |
| CN110236511A (en) | A kind of noninvasive method for measuring heart rate based on video | |
| Huang et al. | A motion-robust contactless photoplethysmography using chrominance and adaptive filtering | |
| Jiang et al. | Real-time quantifying heart beat rate from facial video recording on a smart phone using Kalman filters | |
| CN112294282A (en) | Self-calibration method of emotion detection device based on RPPG | |
| CN112200099A (en) | Video-based dynamic heart rate detection method | |
| CN111839488A (en) | Non-invasive continuous blood pressure measuring device and method based on pulse wave | |
| Zhang et al. | Using rear smartphone cameras as sensors for measuring heart rate variability | |
| CN116999044B (en) | Real-time motion full-connection bidirectional consistent optical flow field heart rate signal extraction method | |
| CN114929101A (en) | System and method for physiological measurement based on optical data | |
| CN104688199B (en) | A kind of contactless pulses measure method based on skin pigment concentration difference | |
| Wang et al. | KLT algorithm for non-contact heart rate detection based on image photoplethysmography | |
| CN114387479A (en) | Non-contact heart rate measurement method and system based on face video |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |