CN113397519B - Cardiovascular health status detection device - Google Patents
Cardiovascular health status detection device Download PDFInfo
- Publication number
- CN113397519B CN113397519B CN202110898085.XA CN202110898085A CN113397519B CN 113397519 B CN113397519 B CN 113397519B CN 202110898085 A CN202110898085 A CN 202110898085A CN 113397519 B CN113397519 B CN 113397519B
- Authority
- CN
- China
- Prior art keywords
- heart rate
- ippg
- average
- value
- poincare
- 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
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 for evaluating the cardiovascular system, e.g. pulse, heart rate, blood pressure or blood flow
- A61B5/024—Measuring pulse rate or heart rate
- A61B5/02405—Determining heart rate variability
-
- 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 for evaluating the cardiovascular system, e.g. pulse, heart rate, blood pressure or blood flow
- A61B5/024—Measuring pulse rate or heart rate
- A61B5/02416—Measuring pulse rate or heart rate using photoplethysmograph signals, e.g. generated by infrared radiation
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Cardiology (AREA)
- Biomedical Technology (AREA)
- Medical Informatics (AREA)
- Biophysics (AREA)
- Pathology (AREA)
- Engineering & Computer Science (AREA)
- Physiology (AREA)
- Heart & Thoracic Surgery (AREA)
- Physics & Mathematics (AREA)
- Molecular Biology (AREA)
- Surgery (AREA)
- Animal Behavior & Ethology (AREA)
- General Health & Medical Sciences (AREA)
- Public Health (AREA)
- Veterinary Medicine (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
The invention provides a cardiovascular health state detection device, which is characterized by acquiring an original IPPG signal of a face area of a detected person; preprocessing the original IPPG signals; extracting HRV features and average periodic waveform features according to the pre-processed IPPG signals; inputting the HRV characteristics and the average periodic waveform characteristics into a pre-trained classification detection model to obtain a detection result of the cardiovascular health state of the tested person; therefore, the detection result is associated with the physiological characteristics with higher dimension, and the accuracy of the detection result is higher.
Description
Technical Field
The invention relates to the technical field of image processing, in particular to a cardiovascular health state detection device.
Background
At present, when monitoring cardiovascular health status, an electrocardiograph is generally used to acquire accurate electrocardiograph data for analysis, and the method has the defects of complex operation process and higher expertise of a user. Therefore, pavlidis et al propose a non-contact heart rate detection method using a common camera, called imaging photoplethysmography (imaging photoplethysmography, IPPG), which is to acquire IPPG signals of a face region, quickly extract various physiological index features related to functional changes of the cardiovascular system, and further judge the cardiovascular health state according to the physiological index features. However, at present, analysis and judgment are generally performed only by extracting low-dimensional HRV features (heart rate variability features) according to IPPG signals, and the accuracy of the judgment result cannot meet the actual application requirements.
Disclosure of Invention
In view of the above-mentioned shortcomings of the prior art, an object of an embodiment of the present application is to provide a method, an apparatus, an electronic device, and a storage medium for detecting a cardiovascular health status, where accuracy of a result of detecting the cardiovascular health status is high.
The embodiment of the application provides a cardiovascular health state detection device, which comprises a camera device and a processing device;
the camera device is used for collecting face videos of the tested person;
the processing device is used for acquiring an original IPPG signal of a face area of a tested person according to the face video, preprocessing the original IPPG signal, extracting HRV characteristics and average periodic waveform characteristics according to the preprocessed IPPG signal, and inputting the HRV characteristics and the average periodic waveform characteristics into a pre-trained classification detection model to obtain a detection result of cardiovascular health state of the tested person.
According to the cardiovascular health state detection device, the HRV characteristic and the average periodic waveform characteristic are extracted according to IPPG signals, the HRV characteristic and the average periodic waveform characteristic are used for detecting the cardiovascular health state, and compared with the prior art, the detection result is associated with the physiological characteristic with higher dimension, and the accuracy of the detection result is higher.
Preferably, the processing device acquires the original IPPG signals of the face area of the tested person according to the face video:
Acquiring a face video of the tested person;
Performing RGB channel separation on each frame of image of the face video, and extracting a green channel image;
selecting an ROI region for each green channel image;
and calculating the average value of the pixel values of each ROI area to obtain an original IPPG signal.
Preferably, the frame rate of the face video of the detected person collected by the camera device is 30fps.
Preferably, the preprocessing includes trending processing, moving average processing, and band-pass filtering denoising processing.
Preferably, the processing means extracts HRV features from the pre-processed IPPG signals:
carrying out peak point positioning on the pre-processed IPPG signals;
calculating the interval between adjacent peak points to obtain an RR interval sequence;
Calculating HRV characteristics according to the RR interval sequence; the HRV features include heart rate, respiratory rate, time domain features, frequency domain features, and Poincare scatter plot distribution features.
Preferably, the Poincare scatter plot distribution characteristics comprise a major axis of a quantified description ellipse of the Poincare scatter plot, a minor axis of the quantified description ellipse of the Poincare scatter plot, and a ratio of the major axis to the minor axis of the quantified description ellipse of the Poincare scatter plot;
the processing device calculates Poincare scatter diagram distribution characteristics:
sequentially taking each RR interval value as an abscissa value of a Poincare point, and taking the subsequent RR interval value as an ordinate value of the Poincare point to generate a Poincare scatter diagram;
Taking the smallest ellipse surrounding all the Poincare points in the Poincare scatter diagram as a quantitative description ellipse, acquiring the length of the long axis and the length of the short axis of the quantitative description ellipse, and calculating the ratio of the length of the long axis to the length of the short axis.
Preferably, the average periodic waveform characteristic includes a main peak amplitude Hb, a falling branch amplitude Hc, a reflection peak amplitude Hd, an average duration T, a main wave occurrence time Tab, and a main wave to counterpulsation peak interval Tbd; the processing device extracts the average periodic waveform characteristic according to the IPPG signals after pretreatment:
performing waveform inversion processing and trending processing on IPPG signals;
Dividing IPPG signals subjected to inverse processing and trending processing into a plurality of pulse waves by taking wave valley points as dividing points, and calculating the duration average value of the pulse waves to obtain average duration T;
removing the deformed pulse wave according to preset screening conditions;
The rest pulse waves are adjusted into pulse waves with the duration equal to the average duration T by means of amplifying or intercepting signal fragments;
Performing linear average superposition on all the adjusted pulse waves to obtain an average periodic waveform of the IPPG signals;
after interpolation and smoothing treatment are carried out on the average periodic waveform, a second derivative waveform is obtained;
Detecting the wave crest and the wave trough of the second derivative waveform, and taking IPPG signal values in an average periodic waveform corresponding to the first minimum value of the second derivative waveform as main peak amplitude Hb; taking IPPG signal values in the average periodic waveform corresponding to the second minimum value of the second derivative waveform as the reflection peak amplitude Hd; taking IPPG signal values in the average periodic waveform corresponding to the maximum value between the first minimum value and the second minimum value of the second derivative waveform as descending branch amplitude Hc; taking the time corresponding to the first minimum value as main wave occurrence time Tab; taking the time interval from the first minimum value to the second minimum value as the interval time Tbd from the main wave to the counterpulsation wave crest.
The average periodic waveform characteristics include main peak amplitude, falling branch amplitude, reflection peak amplitude, average duration, main wave occurrence time, and main wave to counterpulsation peak interval time.
Preferably, the device further comprises an illumination device for illuminating the face area of the person under test when the camera device collects the face video of the person under test.
The beneficial effects are that:
The cardiovascular health state detection device provided by the embodiment of the application obtains the original IPPG signals of the face area of the detected person; preprocessing the original IPPG signals; extracting HRV features and average periodic waveform features according to the pre-processed IPPG signals; inputting the HRV characteristics and the average periodic waveform characteristics into a pre-trained classification detection model to obtain a detection result of the cardiovascular health state of the tested person; therefore, the detection result is associated with the physiological characteristics with higher dimension, and the accuracy of the detection result is higher.
Drawings
Fig. 1 is a schematic structural diagram of a cardiovascular health status detection device according to an embodiment of the present application.
Fig. 2 is a schematic view of the usage state of the cardiovascular health status detection device.
Detailed Description
Embodiments of the present invention are described in detail below, examples of which are illustrated in the accompanying drawings, wherein the same or similar reference numerals refer to the same or similar elements or elements having the same or similar functions throughout. The embodiments described below by referring to the drawings are exemplary only for explaining the present invention and are not to be construed as limiting the present invention.
In the description of the present invention, it should be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", "clockwise", "counterclockwise", etc. indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings are merely for convenience in describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be configured and operated in a specific orientation, and thus should not be construed as limiting the present invention. Furthermore, the terms "first," "second," and the like, are used for descriptive purposes only and are not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include one or more of the described features. In the description of the present invention, the meaning of "a plurality" is two or more, unless explicitly defined otherwise.
The following disclosure provides embodiments or examples for implementing different configurations of the present invention. In order to simplify the present disclosure, components and arrangements of specific examples are described below. They are, of course, merely examples and are not intended to limit the invention. Furthermore, the present invention may repeat reference numerals and/or letters in the various examples, which are for the purpose of brevity and clarity, and which do not themselves indicate the relationship between the various embodiments and/or arrangements discussed. In addition, the present invention provides examples of various specific processes and materials, but one of ordinary skill in the art will recognize the application of other processes and/or the use of other materials.
Referring to fig. 1, a cardiovascular health status detection device provided by an embodiment of the present application includes a camera device 1 and a processing device 2;
the camera device 1 is used for collecting face videos of a tested person;
The processing device 2 is configured to obtain an original IPPG signal of a face area of a person to be tested according to the face video, perform preprocessing on the original IPPG signal, extract HRV features and average periodic waveform features according to the preprocessed IPPG signal, and input the HRV features and the average periodic waveform features into a pre-trained classification detection model to obtain a detection result of cardiovascular health status of the person to be tested.
According to the cardiovascular health state detection device, the HRV characteristic and the average periodic waveform characteristic are extracted according to IPPG signals, the HRV characteristic and the average periodic waveform characteristic are used for detecting the cardiovascular health state, and compared with the prior art, the detection result is associated with the physiological characteristic with higher dimension, and the accuracy of the detection result is higher.
Preferably, the processing device 2 acquires the original IPPG signals of the face region of the tested person according to the face video:
Acquiring a face video of the tested person;
Performing RGB channel separation on each frame of image of the face video, and extracting a green channel image;
Selecting a region of interest (ROI) for each green channel image;
and calculating the average value of the pixel values of each ROI area to obtain an original IPPG signal.
The video image is collected through the camera device 1, then RGB channel separation is carried out on each frame of image, the green channel image is extracted for analysis processing because the sensitivity degree of the green channel image to HRV characteristic changes such as heart rate, respiratory rate and the like is high, the skin region of the face can be selected as the ROI region according to a skin detection algorithm, and finally the pixel value average value of the ROI region is calculated on each frame of green channel image, so that a pixel value average value sequence is obtained, namely the original IPPG signal. Wherein, the pixel value mean of the ROI region can be calculated according to the following formula:
;
Wherein, For the pixel value average value of the ROI area of the i-th frame green channel image,/>The pixel value of the j-th pixel point of the ROI area of the i-th frame green channel image is given, and N is the total number of pixel points of the ROI area of the i-th frame green channel image.
The frame rate of the video image can be set according to practical needs, and is generally 25 fps-40 fps, preferably 30fps.
In some preferred embodiments, the preprocessing includes trending, moving average, and band pass filtering denoising.
The influence of the respiration rate on the extraction of the wave crest and the wave trough of the original waveform Shan Maibo can be effectively reduced through trending treatment.
The extraction of short-time stable signals can be realized through the moving average processing, and the interference of sampling abnormal values is reduced.
Noise in IPPG signals can be effectively removed through band-pass filtering noise removal processing.
In some preferred embodiments, the processing device 2 extracts HRV features from the pre-processed IPPG signals:
carrying out peak point positioning on the pre-processed IPPG signals;
calculating the interval between adjacent peak points to obtain an RR interval sequence;
Calculating HRV characteristics according to the RR interval sequence; the HRV features include heart rate, respiratory rate, time domain features, frequency domain features, and Poincare scatter plot distribution features.
Wherein, the step of carrying out peak point positioning on the pre-processed IPPG signals comprises the following steps: searching the positions of all maximum value elements (IPPG signal values), namely, the amplitude values of the position elements are larger than the values of two adjacent elements; while small spikes due to noise effects are eliminated based on screening conditions (which may be referred to as first screening conditions) that include restrictions on the characteristics of the extracted wave, such as the width of the extracted wave peak being no less than 5/60 of the estimated heart rate.
And subtracting the time corresponding to the adjacent peak value points to obtain the RR interval sequence.
Wherein the heart rate can be calculated by the following formula:
Bpm=60*K/T；
where Bpm is heart rate, K represents the number of peak points in the pre-processed IPPG signal, and T represents the duration of the pre-processed IPPG signal. The heart rate Bpm represents the number of beats per minute in the resting state.
In practice, the pre-processed IPPG signal may also be subjected to a fast fourier transform to obtain its power spectrum, from which the maximum power spectrum value is then extracted, and the heart rate is calculated by the following formula:
Bpm=60*T1*Fs/M；
Wherein T1 is the maximum power spectrum value, fs is the acquisition frame rate of the video image, and M is the total sampling point number of the pre-processed IPPG signals. Since the heart rate is calculated in this way, the accuracy of the calculation result is affected by factors such as the acquisition frame rate, the sampling length (the total number of sampling points), the window length selected during the fast fourier transform, and the like of the video image, and compared with the former way, the reliability of the calculation result is relatively low.
In some embodiments, two heart rate values (a first heart rate and a second heart rate) may be calculated according to the two modes respectively, then, a deviation rate between the two heart rate values (a ratio of the first heart rate to the second heart rate to the first heart rate) is determined, if the deviation rate does not exceed a preset deviation rate threshold, an average value of the two heart rate values is taken as a final heart rate value, otherwise, the heart rate value calculated in the first mode (the first heart rate) is taken as the final heart rate value.
Further, the pre-processed IPPG signal may be subjected to a fast fourier transform to obtain its power spectrum, from which a second maximum power spectrum value is then extracted, and the respiratory rate is calculated by the following formula:
Br=60* T2*Fs/M；
Wherein Br is respiratory frequency, T2 is the second largest power spectrum value, fs is the acquisition frame rate of the video image, and M is the total sampling point number of the pre-processed IPPG signals. The respiratory rate Br represents the number of breaths per minute.
In this embodiment, the time domain features in the HRV features include features in the following table:
| Sequence number | Sign symbol | Meaning of |
| 1 | IBI | Average value of RR interval |
| 2 | SDNN | RR interval standard deviation |
| 3 | SDSD | Standard deviation of differences between adjacent RR intervals |
| 4 | RMSSD | Root mean square of difference between adjacent RR intervals |
| 5 | pNN20 | The ratio of the number of absolute differences between adjacent RR intervals greater than 20ms to the total number |
| 6 | pNN50 | The ratio of the number of absolute differences between adjacent RR intervals greater than 50ms to the total number |
The frequency domain features in the HRV features include features in the following table:
| Sequence number | Sign symbol | Meaning of |
| 1 | LF | The power spectrum density diagram of RR interval sequence is 0.04-0.15Hz |
| 2 | HF | The power spectrum density diagram of RR interval sequence is 0.15-0.4Hz |
| 3 | LF/HF | Area ratio of low frequency to high frequency power spectral density |
Preferably, the Poincare scatter plot distribution characteristics comprise a major axis of a quantified description ellipse of the Poincare scatter plot, a minor axis of the quantified description ellipse of the Poincare scatter plot, and a ratio of the major axis to the minor axis of the quantified description ellipse of the Poincare scatter plot;
the processing device 2 calculates the Poincare scatter diagram distribution characteristics:
sequentially taking each RR interval value as an abscissa value of a Poincare point, and taking the subsequent RR interval value as an ordinate value of the Poincare point to generate a Poincare scatter diagram;
Taking the smallest ellipse surrounding all the Poincare points in the Poincare scatter diagram as a quantitative description ellipse, acquiring the long axis length SD1 and the short axis length SD2 of the quantitative description ellipse, and calculating the ratio SD1/SD2 of the long axis length to the short axis length.
The Poincare scatter plot distribution features reflect the characteristics of heart state dynamics, such as the heart frequency, interactions with nerves, body fluids and respiration, so that the collection of Poincare scatter plot distribution features as part of HRV features herein allows for non-linear motion based heart rate variability descriptions and studies.
In some preferred embodiments, the average periodic waveform characteristics include a main peak amplitude Hb, a falling branch amplitude Hc, a reflection peak amplitude Hd, an average duration T, a main occurrence time Tab, and a main to counterpulsation peak interval Tbd; the processing device 2 extracts the average periodic waveform characteristic according to the IPPG signals after pretreatment:
performing waveform inversion processing and trending processing on IPPG signals;
Dividing IPPG signals subjected to inverse processing and trending processing into a plurality of pulse waves by taking wave valley points as dividing points, and calculating the duration average value of the pulse waves to obtain average duration T;
Removing the deformed pulse wave according to a preset screening condition (the screening condition can be called a second screening condition); wherein, the preset screening conditions (second screening conditions) are as follows: if the variance of the target pulse wave is not more than m1 times of the average value of the variances of all the pulse waves, and the ratio of the duration of the target pulse wave to the average duration T is in the tolerance range, judging that the target pulse wave is a non-deformed pulse wave, otherwise, judging that the target pulse wave is a deformed pulse wave. Wherein the value of m1 can be set according to practical needs, for example m1=1.75; wherein, the tolerance range can be set according to actual needs, for example, 0.8-1.2;
The rest pulse waves are adjusted into pulse waves with the duration equal to the average duration T by means of amplifying or intercepting signal fragments; for example, if the duration of the target pulse wave is less than the average duration T, the data segment may be inserted into the target pulse wave by fitting interpolation, or one data may be inserted into the target pulse wave at intervals of several data in a linear interpolation manner, so as to amplify the duration of the target pulse wave to T; if the duration of the target pulse wave is longer than the average duration T, deleting the signal segment at the end of the target pulse wave, so as to intercept the duration of the target pulse wave as T;
Performing linear average superposition on all the adjusted pulse waves to obtain an average periodic waveform of the IPPG signals;
after interpolation and smoothing treatment are carried out on the average periodic waveform, a second derivative waveform (obtained through second differential calculation) is obtained;
Detecting the wave crest and the wave trough of the second derivative waveform, and taking IPPG signal values in an average periodic waveform corresponding to a first minimum value (namely the first minimum value) of the second derivative waveform as main peak amplitude Hb; taking IPPG signal values in the average periodic waveform corresponding to the second minimum value (namely the second minimum value) of the second derivative waveform as the reflection peak amplitude Hd; taking IPPG signal values in the average periodic waveform corresponding to the maximum value between the first minimum value and the second minimum value of the second derivative waveform as descending branch amplitude Hc; taking the time corresponding to the first minimum value as main wave occurrence time Tab; taking the time interval from the first minimum value to the second minimum value as the interval time Tbd from the main wave to the counterpulsation wave crest.
The average periodic waveform characteristics reflect the information such as the degree of arterial stiffness, peripheral resistance, elastic change and the like, and the average periodic waveform characteristics are considered when cardiovascular health status detection is carried out, so that the health status information mining based on non-transient stable pulse wave characteristics can be realized.
Through the steps, the high-dimensional HRV characteristic can be obtained to detect the cardiovascular health state of the tested person, so that the accuracy and the reliability of the detection result are improved.
In some embodiments, the classification detection model is a classification detection model formed by combining Bayesian super-parametric optimization and a random forest classifier, and can perform classification detection on the health state and the unhealthy state of the cardiovascular system of the tested person. The classification detection model is obtained by training in the following way: training with a training set comprising samples and labels, training a model by back-propagating minimal errors during the training process, and cross-verifying and evaluating the trained model by a test set comprising samples and labels. The detection result that the cardiovascular health state of the tested person is healthy or unhealthy can be obtained through the classification detection model, and the detection result is accurate and reliable.
In some embodiments, see fig. 1 and 2, the device for detecting cardiovascular health status further includes an illumination device 3, where the illumination device 3 is configured to illuminate a face area of a person under test when the image capturing device 1 captures a face video of the person under test. Therefore, the brightness of the face area can be improved, so that a clearer face video frame image can be obtained, and the detection accuracy is improved. Preferably, the light emitted by the irradiation device 3 is green light, for example, green light with a wavelength of 530nm, because the light with a wavelength of 530nm penetrates through the skin to reach the capillary vessel, and the absorption rate of the blood is higher than that of other wavelengths, so that the information of the change such as the reflected light signal is easily captured, and the pulse wave with high signal to noise ratio can be extracted.
In some embodiments, as shown in fig. 2, the cardiovascular health status detecting device comprises a cylindrical detecting frame 4, a positioning and supporting part 5 for supporting the mandible of the tested person is arranged at the lower part of the front opening of the detecting frame 4, the camera device 1 is a camera arranged at the middle part of the rear side of the detecting frame 4, and the optical axis of the camera is coaxially arranged with the detecting frame 4; the irradiation device 3 is a lamp panel surrounding the camera device 1, and a light source (such as an LED lamp bead) is uniformly arranged on the front side of the lamp panel, so as to ensure that the face area of the tested person is uniformly irradiated. The distance between the camera and the front opening of the detection frame 4 may be set according to practical needs, for example, in fig. 2, the distance is 20cm.
The above can show that the cardiovascular health status detecting device obtains the original IPPG signal of the face area of the detected person; preprocessing the original IPPG signals; extracting HRV features and average periodic waveform features according to the pre-processed IPPG signals; inputting the HRV characteristics and the average periodic waveform characteristics into a pre-trained classification detection model to obtain a detection result of the cardiovascular health state of the tested person; therefore, the detection result is associated with the physiological characteristics with higher dimension, and the accuracy of the detection result is higher.
In summary, although the present invention has been described with reference to the preferred embodiments, the preferred embodiments are not intended to limit the invention, and various modifications and alterations can be made by those skilled in the art without departing from the spirit and scope of the invention, and the aspects are substantially the same as the present invention.
Claims (6)
1. The cardiovascular health state detection device is characterized by comprising a camera device and a processing device;
the camera device is used for collecting face videos of the tested person;
the processing device is used for acquiring an original IPPG signal of a face area of a tested person according to the face video, preprocessing the original IPPG signal, extracting HRV (high-resolution video) characteristics and average periodic waveform characteristics according to the preprocessed IPPG signal, and inputting the HRV characteristics and the average periodic waveform characteristics into a pre-trained classification detection model to obtain a detection result of cardiovascular health state of the tested person;
the processing device extracts HRV features according to the pre-processed IPPG signals:
carrying out peak point positioning on the pre-processed IPPG signals;
calculating the interval between adjacent peak points to obtain an RR interval sequence;
Calculating HRV features according to the RR interval sequence, wherein the HRV features comprise heart rate, respiratory frequency, time domain features, frequency domain features and Poincare scatter diagram distribution features;
the heart rate calculation process comprises the following steps:
The heart rate is calculated by adopting the following two modes respectively to obtain a first heart rate and a second heart rate, if the ratio of the difference between the first heart rate and the second heart rate to the first heart rate does not exceed a preset deviation rate threshold value, taking the average value of the first heart rate and the second heart rate as a final heart rate value, otherwise, taking the first heart rate as the final heart rate value:
In one mode, the heart rate is calculated as a first heart rate according to the following formula: bpm=60×k/T, where Bpm is heart rate, K represents the number of peak points in the pre-processed IPPG signal, and T represents the duration of the pre-processed IPPG signal;
in a second mode, the pre-processed IPPG signal is subjected to a fast fourier transform to obtain its power spectrum, from which the maximum power spectrum value is then extracted, and the heart rate is calculated as a second heart rate by the following formula: bpm=60×t1×fs/M, where T1 is the maximum power spectrum value, fs is the acquisition frame rate of the video image, and M is the total sampling point number of the pre-processed IPPG signals;
The average periodic waveform characteristics comprise a main peak amplitude Hb, a descending branch amplitude Hc, a reflection peak amplitude Hd, an average duration T, a main wave occurrence time Tab and an interval time Tbd from the main wave to the counterpulsation wave crest; the processing device extracts the average periodic waveform characteristic according to the IPPG signals after pretreatment:
performing waveform inversion processing and trending processing on IPPG signals;
Dividing IPPG signals subjected to inverse processing and trending processing into a plurality of pulse waves by taking wave valley points as dividing points, and calculating the duration average value of the pulse waves to obtain average duration T;
removing the deformed pulse wave according to preset screening conditions;
The rest pulse waves are adjusted into pulse waves with the duration equal to the average duration T by means of amplifying or intercepting signal fragments;
Performing linear average superposition on all the adjusted pulse waves to obtain an average periodic waveform of the IPPG signals;
after interpolation and smoothing treatment are carried out on the average periodic waveform, a second derivative waveform is obtained;
Detecting the wave crest and the wave trough of the second derivative waveform, and taking IPPG signal values in an average periodic waveform corresponding to the first minimum value of the second derivative waveform as main peak amplitude Hb; taking IPPG signal values in the average periodic waveform corresponding to the second minimum value of the second derivative waveform as the reflection peak amplitude Hd; taking IPPG signal values in the average periodic waveform corresponding to the maximum value between the first minimum value and the second minimum value of the second derivative waveform as descending branch amplitude Hc; taking the time corresponding to the first minimum value as main wave occurrence time Tab; taking the time interval from the first minimum value to the second minimum value as the interval time Tbd from the main wave to the counterpulsation wave crest.
2. The cardiovascular health status detecting device according to claim 1, wherein the processing device is configured to, when acquiring the original IPPG signal of the face region of the subject according to the face video:
Acquiring a face video of the tested person;
Performing RGB channel separation on each frame of image of the face video, and extracting a green channel image;
selecting an ROI region for each green channel image;
and calculating the average value of the pixel values of each ROI area to obtain an original IPPG signal.
3. The cardiovascular health status detecting device according to claim 1, wherein the frame rate of capturing face video of the subject by the imaging device is 30fps.
4. The cardiovascular health status detection device of claim 1, wherein the preprocessing comprises trending, moving average, and band pass filtering denoising.
5. The cardiovascular health status detection device according to claim 1, wherein the Poincare scattergram distribution feature comprises a major axis of a quantified description ellipse of a Poincare scattergram, a minor axis of a quantified description ellipse of a Poincare scattergram, and a ratio of the major axis to the minor axis of a quantified description ellipse of a Poincare scattergram;
the processing device calculates Poincare scatter diagram distribution characteristics:
sequentially taking each RR interval value as an abscissa value of a Poincare point, and taking the subsequent RR interval value as an ordinate value of the Poincare point to generate a Poincare scatter diagram;
Taking the smallest ellipse surrounding all the Poincare points in the Poincare scatter diagram as a quantitative description ellipse, acquiring the length of the long axis and the length of the short axis of the quantitative description ellipse, and calculating the ratio of the length of the long axis to the length of the short axis.
6. The cardiovascular health status detecting device according to claim 1, further comprising an illumination device for illuminating a face area of the subject when the image capturing device captures a face video of the subject.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110898085.XA CN113397519B (en) | 2021-08-05 | 2021-08-05 | Cardiovascular health status detection device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110898085.XA CN113397519B (en) | 2021-08-05 | 2021-08-05 | Cardiovascular health status detection device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113397519A CN113397519A (en) | 2021-09-17 |
| CN113397519B true CN113397519B (en) | 2024-05-28 |
Family
ID=77688472
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110898085.XA Active CN113397519B (en) | 2021-08-05 | 2021-08-05 | Cardiovascular health status detection device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113397519B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114171151A (en) * | 2021-12-10 | 2022-03-11 | 季华实验室 | Data processing method and device and electronic equipment |
| CN115990008B (en) * | 2022-11-22 | 2025-01-03 | 森思泰克河北科技有限公司 | Heart rate variability monitoring method, device, radar and readable storage medium |
| CN118051809B (en) * | 2024-04-15 | 2024-06-25 | 长春理工大学 | Non-contact state identification method based on multi-feature fusion |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105476630A (en) * | 2015-11-26 | 2016-04-13 | 北京期颐科技有限公司 | Method for detecting traditional Chinese medicine visceral functions |
| CN106037694A (en) * | 2016-05-13 | 2016-10-26 | 吉林大学 | Continuous blood pressure measuring device based on pulse waves |
| CN106539580A (en) * | 2016-11-21 | 2017-03-29 | 西安交通大学 | A kind of continuous monitoring method of autonomic nervous system dynamic change |
| CN106691425A (en) * | 2016-12-30 | 2017-05-24 | 北京工业大学 | Wrist heart rate monitoring method of sports bracelet |
| 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 |
| CN109770885A (en) * | 2019-03-25 | 2019-05-21 | 合肥工业大学 | A fast heart rate detection method based on preview frame |
| WO2019161411A1 (en) * | 2018-02-17 | 2019-08-22 | Sanmina Corporation | System and method for obtaining health data using a neural network |
| CN111714144A (en) * | 2020-07-24 | 2020-09-29 | 长春理工大学 | Mental stress analysis method based on video non-contact measurement |
| CN111839491A (en) * | 2020-06-29 | 2020-10-30 | 北京曙光易通技术有限公司 | Heart beat function monitoring method, heart beat function continuous monitoring method and electronic equipment |
| CN111870235A (en) * | 2020-08-04 | 2020-11-03 | 杭州艺兴科技有限公司 | Drug addict screening method based on IPPG |
| CN112040846A (en) * | 2018-04-23 | 2020-12-04 | 赢创运营有限公司 | Method for estimating blood pressure and degree of arteriosclerosis based on photoplethysmography (PPG) signal |
| CN112890792A (en) * | 2020-11-25 | 2021-06-04 | 合肥工业大学 | Cloud computing cardiovascular health monitoring system and method based on network camera |
| CN113080917A (en) * | 2021-03-04 | 2021-07-09 | 浙江慧养科技有限公司 | Method and device for monitoring abnormal heart rate |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7771364B2 (en) * | 2004-01-27 | 2010-08-10 | Spirocor Ltd. | Method and system for cardiovascular system diagnosis |
| CA2952485A1 (en) * | 2015-12-21 | 2017-06-21 | Robert Andre Amelard | System and method for spatial cardiovascular monitoring |
| WO2017142240A1 (en) * | 2016-02-18 | 2017-08-24 | Samsung Electronics Co., Ltd. | Method and electronic device for cuff-less blood pressure(bp) measurement |
-
2021
- 2021-08-05 CN CN202110898085.XA patent/CN113397519B/en active Active
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105476630A (en) * | 2015-11-26 | 2016-04-13 | 北京期颐科技有限公司 | Method for detecting traditional Chinese medicine visceral functions |
| CN106037694A (en) * | 2016-05-13 | 2016-10-26 | 吉林大学 | Continuous blood pressure measuring device based on pulse waves |
| CN106539580A (en) * | 2016-11-21 | 2017-03-29 | 西安交通大学 | A kind of continuous monitoring method of autonomic nervous system dynamic change |
| CN106691425A (en) * | 2016-12-30 | 2017-05-24 | 北京工业大学 | Wrist heart rate monitoring method of sports bracelet |
| WO2019161411A1 (en) * | 2018-02-17 | 2019-08-22 | Sanmina Corporation | System and method for obtaining health data using a neural network |
| CN112040846A (en) * | 2018-04-23 | 2020-12-04 | 赢创运营有限公司 | Method for estimating blood pressure and degree of arteriosclerosis based on photoplethysmography (PPG) 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 |
| CN109770885A (en) * | 2019-03-25 | 2019-05-21 | 合肥工业大学 | A fast heart rate detection method based on preview frame |
| CN111839491A (en) * | 2020-06-29 | 2020-10-30 | 北京曙光易通技术有限公司 | Heart beat function monitoring method, heart beat function continuous monitoring method and electronic equipment |
| CN111714144A (en) * | 2020-07-24 | 2020-09-29 | 长春理工大学 | Mental stress analysis method based on video non-contact measurement |
| CN111870235A (en) * | 2020-08-04 | 2020-11-03 | 杭州艺兴科技有限公司 | Drug addict screening method based on IPPG |
| CN112890792A (en) * | 2020-11-25 | 2021-06-04 | 合肥工业大学 | Cloud computing cardiovascular health monitoring system and method based on network camera |
| CN113080917A (en) * | 2021-03-04 | 2021-07-09 | 浙江慧养科技有限公司 | Method and device for monitoring abnormal heart rate |
Non-Patent Citations (2)
| Title |
|---|
| An iPPG-Based Device for Pervasive Monitoring of Multi-Dimensional Cardiovascular Hemodynamics;Jingjing Luo, et al.;sensors;第21卷(第3期);第3页第1段、第5页第2段，图2、图3 * |
| Jingjing Luo, et al..An iPPG-Based Device for Pervasive Monitoring of Multi-Dimensional Cardiovascular Hemodynamics.sensors.2021,第21卷(第3期),第3页第1段、第5页第2段，图2、图3. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113397519A (en) | 2021-09-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113397519B (en) | Cardiovascular health status detection device | |
| Li et al. | The obf database: A large face video database for remote physiological signal measurement and atrial fibrillation detection | |
| US12036021B2 (en) | Non-contact fatigue detection system and method based on RPPG | |
| Chang et al. | Detection of eye blink artifacts from single prefrontal channel electroencephalogram | |
| Banerjee et al. | Application of cross wavelet transform for ECG pattern analysis and classification | |
| ES2960027T3 (en) | Detection of abnormalities in ECG signals | |
| US20200138306A1 (en) | Feature selection for cardiac arrhythmia classification and screening | |
| Orosco et al. | An epileptic seizures detection algorithm based on the empirical mode decomposition of EEG | |
| CN110200640A (en) | Contactless Emotion identification method based on dual-modality sensor | |
| KR102482796B1 (en) | Device and method for non-contact hrv analysis using remote ppg | |
| CN103263271A (en) | Non-contact automatic blood oxygen saturation degree measurement system and measurement method | |
| CN114532994A (en) | Automatic detection method for unsupervised electroencephalogram high-frequency oscillation signals based on convolution variational self-encoder | |
| Goshvarpour et al. | Do men and women have different ECG responses to sad pictures? | |
| CN110251115B (en) | PPG signal extraction method, system, equipment and medium based on body surface video | |
| US20240315632A1 (en) | Predicting erroneous classifications of physiological parameter segments | |
| KR101996027B1 (en) | Method and system for extracting Heart Information of Frequency domain by using pupil size variation | |
| CN115067910A (en) | A heart rate variability stress detection method, device, storage medium and system | |
| CN117918805A (en) | Pulse wave quality automatic evaluation system in oscillography blood pressure measurement based on multiple indexes | |
| Jaleel et al. | Improved spindle detection through intuitive pre-processing of electroencephalogram | |
| Satija et al. | Low-complexity detection and classification of ECG noises for automated ECG analysis system | |
| Talukdar et al. | Evaluating visual photoplethysmography method | |
| Tomas et al. | Application of the R-peak detection algorithm for locating noise in ECG signals | |
| Cherif et al. | Detection of artifacts on photoplethysmography signals using random distortion testing | |
| KR20170004549A (en) | Method and system for extracting Heart Information of Frequency domain | |
| Varun et al. | Automatic seizure detection employing machine learning-based late fusion techniques over behind-the-ear and the scalp EEG signals |
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 |