Blood pressure measurement method, device, terminal equipment and storage medium based on pulse wave transit time of multi-angle polarized light

Abstract

The present application relates to the field of biomedical engineering technology. The present application discloses a blood pressure measurement method, apparatus, terminal device and storage medium based on pulse wave transmission time of multi-angle polarized light, which can improve the accuracy of blood pressure measurement. The method includes collecting an initial video of the measured part of the target user when polarized light at multiple angles is irradiated to the measured part by time division multiplexing; performing color channel signal extraction processing on the initial video to obtain a first multi-channel color signal and a second multi-channel color signal corresponding to each angle; performing phase delay identification processing on the first multi-channel color signal and the second multi-channel color signal corresponding to all angles using a first preset algorithm to obtain a target pulse wave transmission time; and calculating and processing the target pulse wave transmission time using a linear regression model to obtain a blood pressure measurement value of the measured part of the target user.

Description

Technical Field

[0001] The present application relates to the field of biomedical engineering technology. More specifically, the present application relates to a blood pressure measurement method, apparatus, terminal device, and storage medium based on pulse wave transit time of multi-angle polarized light. Background Art

[0002] The traditional blood pressure measurement method involves wrapping a wristband around the wrist; linearly pressurizing the airbag within the wristband and then nonlinearly reducing the pressure; using a pulse wave sensor to directly collect real-time pulse oscillation pressure from the radial artery to obtain a first pulse wave; detecting the gas pressure within the wristband; using this first pulse wave as a correction parameter, inferring systolic and diastolic pressures based on the gas pressure; and calculating the blood pressure value based on the systolic and diastolic pressures. This shows that the traditional method requires additional gas pressure parameters when measuring blood pressure. Errors in the collection of these gas pressure parameters will directly affect the accuracy of blood pressure measurements. Summary of the Invention

[0003] The purpose of the embodiments of the present application is to provide a blood pressure measurement method, apparatus, terminal device, and storage medium based on pulse wave transit time using multi-angle polarized light, which can improve the accuracy of blood pressure measurement. The embodiments of the present application are mainly achieved through the following technical solutions:

[0004] A first aspect of the embodiments of the present application provides a blood pressure measurement method based on pulse wave transit time using multi-angle polarized light, comprising:

[0005] Using time division multiplexing, when polarized light at multiple angles is irradiated onto the measured part of the target user, an initial video of the measured part is collected;

[0006] Performing color channel signal extraction processing on the initial video to obtain a first multi-channel color signal and a second multi-channel color signal corresponding to each angle;

[0007] Using a first preset algorithm, phase delay identification processing is performed on the first multi-channel color signal and the second multi-channel color signal corresponding to all angles to obtain a target pulse wave transmission time;

[0008] The target pulse wave transmission time is calculated and processed using a linear regression model to obtain a blood pressure measurement value of the measured part of the target user.

[0009] According to one embodiment of the present application, the step of performing color channel signal extraction processing on the initial video to obtain a first multi-channel color signal and a second multi-channel color signal corresponding to each angle includes:

[0010] Performing color channel signal extraction processing on the initial video to obtain an initial multi-channel color signal corresponding to each angle;

[0011] Performing filtering on the initial multi-channel color signals corresponding to each angle according to a first preset rule to obtain a first multi-channel color signal corresponding to each angle;

[0012] The initial multi-channel color signals corresponding to each angle are filtered according to a second preset rule to obtain second multi-channel color signals corresponding to each angle.

[0013] According to one embodiment of the present application, the step of performing phase delay identification processing on the first multi-channel color signal and the second multi-channel color signal corresponding to all angles using a first preset algorithm to obtain the target pulse wave transmission time includes:

[0014] Using the phase delay algorithm of the first preset algorithm to perform phase delay identification processing on the first multi-channel color signals corresponding to all angles to obtain a first initial pulse wave transmission time;

[0015] Using the phase delay algorithm to perform phase delay identification processing on the second multi-channel color signals corresponding to all angles to obtain a second initial pulse wave transmission time;

[0016] The first initial pulse wave transit time and the second initial pulse wave transit time are weightedly summed and calculated according to the weighted summation algorithm of the first preset algorithm to obtain the target pulse wave transit time.

[0017] According to one embodiment of the present application, the step of performing phase delay identification processing on the first multi-channel color signal corresponding to all angles using the phase delay algorithm of the first preset algorithm to obtain the first initial pulse wave transit time includes:

[0018] Using the phase delay algorithm, a phase delay identification process is performed on a first red channel color signal in the first multi-channel color signals corresponding to all angles to obtain a first red channel conduction time;

[0019] Using the phase delay algorithm, a phase delay identification process is performed on a first green channel color signal in the first multi-channel color signals corresponding to all angles to obtain a first green channel conduction time;

[0020] Using the phase delay algorithm, a phase delay identification process is performed on a first blue channel color signal in the first multi-channel color signals corresponding to all angles to obtain a first blue channel conduction time;

[0021] The first red channel transit time, the first green channel transit time, and the first blue channel transit time constitute the first initial pulse wave transit time.

[0022] According to one embodiment of the present application, the phase delay algorithm is used to perform phase delay identification processing on a first red channel color signal in a first multi-channel color signal corresponding to all angles, and the step of obtaining the first red channel conduction time includes:

[0023] Performing phase point recognition processing on the first red channel color signal in the first multi-channel color signal corresponding to each angle using the phase delay algorithm to obtain a first red channel phase point corresponding to the first red channel color signal in the first multi-channel color signal corresponding to each angle;

[0024] Phase delay identification processing is performed based on all first red channel phase points to obtain the first red channel conduction time.

[0025] According to one embodiment of the present application, the step of performing weighted sum calculation processing on the first initial pulse wave transit time and the second initial pulse wave transit time according to the weighted sum algorithm of the first preset algorithm to obtain the target pulse wave transit time includes:

[0026] performing weighted sum calculation processing on the first red channel transit time and the second initial pulse wave transit time according to the weighted summation algorithm to obtain a target red channel transit time;

[0027] performing weighted sum calculation processing on the first green channel transmission time and the second initial pulse wave transmission time according to the weighted summation algorithm to obtain a target green channel transmission time;

[0028] performing weighted sum calculation processing on the first blue channel transmission time and the second initial pulse wave transmission time according to the weighted summation algorithm to obtain a target blue channel transmission time;

[0029] The target red channel conduction time, the target green channel conduction time, and the target blue channel conduction time constitute the target pulse wave conduction time.

[0030] According to one embodiment of the present application, the step of calculating and processing the target pulse wave transit time using a linear regression model to obtain the blood pressure measurement value of the measured part of the target user includes:

[0031] Using the systolic blood pressure model of the linear regression model to perform weighted summation calculation processing on the target pulse wave transit time to obtain a target systolic blood pressure;

[0032] Using the diastolic pressure model of the linear regression model to perform weighted summation calculation processing on the target pulse wave transmission time to obtain the target diastolic pressure;

[0033] The blood pressure model of the linear regression model is used to perform ratio calculation processing on the target systolic pressure and the target diastolic pressure to obtain the blood pressure measurement value of the measured part of the target user.

[0034] A second aspect of the present application provides a blood pressure measurement device based on pulse wave transit time using multi-angle polarized light, comprising:

[0035] An initial video acquisition module is used to acquire an initial video of the measured part of the target user when polarized light at multiple angles is irradiated onto the measured part of the target user in a time-division multiplexing manner;

[0036] a signal extraction module, configured to perform color channel signal extraction processing on the initial video to obtain a first multi-channel color signal and a second multi-channel color signal corresponding to each angle;

[0037] a phase delay identification module, configured to perform phase delay identification processing on the first multi-channel color signal and the second multi-channel color signal corresponding to all angles using a first preset algorithm to obtain a target pulse wave transmission time;

[0038] The blood pressure measurement value calculation module is used to calculate and process the target pulse wave transmission time using a linear regression model to obtain the blood pressure measurement value of the measured part of the target user.

[0039] The third aspect of the embodiments of the present application provides a terminal device, including: a processor and a memory, the memory being used to store a computer program, the processor being used to call and run the computer program stored in the memory, and executing the steps of the blood pressure measurement method based on pulse wave transmission time of multi-angle polarized light provided in the first aspect of the embodiments of the present application.

[0040] In a fourth aspect of an embodiment of the present application, a computer-readable storage medium is provided, wherein the computer-readable storage medium is used to store a computer program, and the computer program enables a computer to execute the steps of the blood pressure measurement method based on pulse wave transmission time of multi-angle polarized light provided in the first aspect of the embodiment of the present application.

[0041] The beneficial effects of the embodiments of the present application include:

[0042] The embodiment of the present application uses a time-division multiplexing method to capture an initial video of a target user's measured part when polarized light at multiple angles is irradiated onto the measured part of the target user; performs color channel signal extraction processing on the initial video to obtain a first multi-channel color signal and a second multi-channel color signal corresponding to each angle; uses a first preset algorithm to perform phase delay identification processing on the first multi-channel color signal and the second multi-channel color signal corresponding to all angles to obtain a target pulse wave transit time; and uses a linear regression model to calculate and process the target pulse wave transit time to obtain a blood pressure measurement value for the measured part of the target user. Compared to the prior art, the embodiment of the present application does not require the use of additional gas pressure parameters to achieve blood pressure measurement. Therefore, the embodiment of the present application can effectively reduce the impact of errors in additional parameters on the blood pressure measurement value, thereby improving the accuracy of blood pressure measurement. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the conventional technology, the following briefly introduces the drawings required for use in the embodiments or the conventional technology descriptions. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0044] Figure 1 A flowchart of a blood pressure measurement method based on pulse wave transit time of multi-angle polarized light of the present application in some embodiments;

[0045] Figure 2 A schematic diagram showing the formation of PPG signals corresponding to shallow tissue and deep tissue in this application;

[0046] Figure 3 A reference graph for target pulse wave transit time and blood pressure measurement values ​​in some embodiments of the present application;

[0047] Figure 4 This is a principle block diagram of a blood pressure measurement device based on pulse wave transit time of multi-angle polarized light of the present application in some embodiments;

[0048] Figure 5 This is a principle block diagram of the terminal device of the present application in some embodiments. DETAILED DESCRIPTION

[0049] To make the above-mentioned objects, features, and advantages of the present application more clearly understood, the specific embodiments of the present application are described in detail below with reference to the accompanying drawings. The following description sets forth many specific details to facilitate a full understanding of the present application. However, the present application can be implemented in many other ways than those described herein, and those skilled in the art can make similar improvements without violating the scope of the present application. Therefore, the present application is not limited to the specific embodiments disclosed below.

[0050] It should be noted that the terms "first" and "second" are used for descriptive purposes only and should not be understood to indicate or imply relative importance or implicitly specify the number of the technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include at least one of such features. In the description of this application, "plurality" means at least two, for example, two, three, etc., unless otherwise specifically defined.

[0051] The terms "exemplary" or "for example" are used to indicate an example, illustration, or description. Any embodiment or design described as "exemplary" or "for example" in the embodiments of this application should not be construed as being preferred or advantageous over other embodiments or designs. Rather, the use of words such as "exemplary" or "for example" is intended to present the relevant concepts in a concrete manner.

[0052] The terms "comprises," "comprising," or any other variations thereof are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, product, or apparatus.

[0053] Unless otherwise defined, all technical and scientific terms used in the specification of this application have the same meaning as commonly understood by those skilled in the art to which this application belongs. The terms used in the specification of this application are only for the purpose of describing specific embodiments and are not intended to limit this application. The term "and / or" used in the specification of this application includes any and all combinations of one or more of the relevant listed items.

[0054] The specific implementation of this application is further described below with reference to the accompanying drawings.

[0055] refer to Figure 1 FIG. 1 is a flow chart of a blood pressure measurement method based on pulse wave transit time of multi-angle polarized light provided in the first aspect of the embodiment of the present application. Figure 1 The blood pressure measurement method based on pulse wave transit time of multi-angle polarized light includes:

[0056] S1. When polarized light at multiple angles is irradiated onto a target user's measured part in a time division multiplexing manner, an initial video of the measured part is collected.

[0057] In the embodiment of the present application, the multiple angles are 0° and 90°. In other embodiments, those skilled in the art can set the number of angles or specific values ​​of the angles according to actual needs.

[0058] When capturing the initial video, the embodiment of the present application uses 0° polarized light and 90° polarized light to alternately illuminate the measured part of the target user in a time sequence.

[0059] The initial video is captured by a sensor with a resolution of 608px × 368px (px is a unit of pixels), 8-bit depth, and a capture frame rate of 250 FPS (frames per second). The sensor is an RGB camera. It is exposed to polarized light at different angles to ensure that each frame contains optical information about the skin at a specific polarization angle.

[0060] When the polarized light incident on the sensor is 0° polarized light, the 0° polarized light is Figure 2 The first set of LED lights emits light and passes through a first polarizer to form a 0° polarizer. The first set of LED lights consists of 16 white light LEDs with a wavelength of 400-780 nm (nm is nanometers), a color temperature of 6000-6500 K (K is Kelvin), and a rated power of 5 W (W is watts).

[0061] When the polarized light incident on the sensor is 90° polarized light, the 90° polarized light is Figure 2 The second set of LED lights emits light that passes through a second polarizer to form a 90° polarizer. The second set of LED lights consists of 16 white light LEDs with a wavelength of 400-780nm, a color temperature of 6000-6500K, and a rated power of 5W.

[0062] The light emitted by the first group of LED lamps and the light emitted by the second group of LED lamps are lights of the same wavelength.

[0063] When the polarized light incident on the sensor is 0° polarized light, the photons received by the sensor primarily originate from the superficial tissue of the measured area because these photons are less depolarized. When the polarized light incident on the sensor is 90° polarized light, the reflected light from the superficial tissue of the measured area is blocked by the third polarizer placed in front of the sensor. However, the scattering effect in the deeper tissue of the measured area causes stronger depolarization, generating scattered photons in random directions, including photons in the 0° direction. Therefore, these 0° photons can pass through the third polarizer.

[0064] The 0° polarized light and the 90° polarized light are both green wavelength polarized light. In other embodiments, the 0° polarized light and the 90° polarized light can also be polarized light of other colors, or polarized light of different wavelengths, which can be specifically set by those skilled in the art according to actual needs.

[0065] The detected part is the face area of ​​the target user. In other embodiments, the detected part may also be a skin area without any external objects such as a palm or a leg. When the detected part is the face area, the initial video is a face video.

[0066] S2. Perform color channel signal extraction processing on the initial video to obtain a first multi-channel color signal and a second multi-channel color signal corresponding to each angle.

[0067] All of the first multi-channel color signals and the second multi-channel color signals are pulse wave signals.

[0068] Furthermore, step S2 includes: performing color channel signal extraction processing on the initial video to obtain an initial multi-channel color signal corresponding to each angle; performing filtering processing on the initial multi-channel color signal corresponding to each angle according to a first preset rule to obtain a first multi-channel color signal corresponding to each angle; performing filtering processing on the initial multi-channel color signal corresponding to each angle according to a second preset rule to obtain a second multi-channel color signal corresponding to each angle.

[0069] Furthermore, the steps of performing color channel signal extraction processing on the initial video to obtain an initial multi-channel color signal corresponding to each angle include: extracting images corresponding to the polarized light of each angle from the initial video, and reconstructing all images corresponding to the polarized light of each angle in time sequence to obtain a reconstructed video corresponding to the polarized light of each angle; and performing color channel signal extraction processing on the reconstructed video corresponding to the polarized light of each angle using an optical flow method to obtain an initial multi-channel color signal corresponding to each angle.

[0070] Furthermore, the optical flow method is used to perform color channel signal extraction processing on the reconstructed video corresponding to the polarized light at each angle, and the steps of obtaining the initial multi-channel color signal corresponding to each angle include: performing color channel separation processing on the reconstructed video corresponding to the polarized light at each angle to obtain a red channel reconstructed video, a green channel reconstructed video and a blue channel reconstructed video corresponding to each angle; performing signal extraction processing on the red channel reconstructed video corresponding to each angle by the optical flow method to obtain the initial red channel color signal corresponding to each angle; performing signal extraction processing on the green channel reconstructed video corresponding to each angle by the optical flow method to obtain the initial green channel color signal corresponding to each angle; performing signal extraction processing on the blue channel reconstructed video corresponding to each angle by the optical flow method to obtain the initial blue channel color signal corresponding to each angle; the initial red channel color signal, the initial green channel color signal and the initial blue channel color signal corresponding to each angle constitute the initial multi-channel color signal corresponding to each angle.

[0071] The color channel separation process can be implemented by OpenCV (OpenCV is a cross-platform computer vision and machine learning software library released under the Apache 2.0 license) in Python (Python is a computer programming language).

[0072] Furthermore, the optical flow method is used to perform signal extraction processing on the red channel reconstructed video corresponding to each angle, and the step of obtaining the initial red channel color signal corresponding to each angle includes: using the optical flow method to estimate the first target features of each pixel point in the first target area of ​​interest in multiple first predetermined directions between consecutive frames in the red channel reconstructed video corresponding to each angle; accumulating and calculating all the first target features of each pixel point in each first predetermined direction between consecutive frames in the first target area of ​​interest to obtain the first displacement signal corresponding to each pixel point in each first predetermined direction between consecutive frames; calculating the average value of all the first displacement signals in each first predetermined direction to obtain the physiological motion signal corresponding to each first predetermined direction; and fusing the physiological motion signals of all the first predetermined directions to obtain the initial red channel color signal corresponding to each angle.

[0073] The first target region of interest is the forehead region. In other embodiments, the first target region of interest may also be the face region, which may be specifically set by those skilled in the art according to actual needs.

[0074] The plurality of first predetermined directions are horizontal directions and vertical directions. In other embodiments, those skilled in the art can set other directions according to actual needs.

[0075] The first target feature is a velocity component. In other embodiments, those skilled in the art may set it to other features according to actual needs, such as an acceleration component.

[0076] The fusion processing operation is implemented by using a signal fusion method, which may be a principal component analysis method.

[0077] Furthermore, the optical flow method is used to perform signal extraction processing on the green channel reconstructed video corresponding to each angle, and the step of obtaining the initial green channel color signal corresponding to each angle includes: using the optical flow method to estimate the second target features of each pixel point in the second target area of ​​interest in multiple second predetermined directions between consecutive frames in the green channel reconstructed video corresponding to each angle; accumulating and calculating all the second target features of each pixel point in each second predetermined direction between consecutive frames in the second target area of ​​interest to obtain the second displacement signal corresponding to each pixel point in each second predetermined direction between consecutive frames; calculating the average value of all the second displacement signals in each second predetermined direction to obtain the physiological motion signal corresponding to each second predetermined direction; and fusing the physiological motion signals of all the second predetermined directions to obtain the initial green channel color signal corresponding to each angle.

[0078] The second target region of interest is the same as the first target region of interest, the multiple second predetermined directions are the same as the multiple first predetermined directions, and the second target feature is the same as the first target feature. In other embodiments, the second target region of interest and the first target region of interest, the multiple second predetermined directions and the multiple first predetermined directions, and the second target feature and the first target feature may also be set to different contents, which can be specifically set by those skilled in the art according to actual needs.

[0079] Furthermore, the optical flow method is used to perform signal extraction processing on the blue channel reconstructed video corresponding to each angle, and the step of obtaining the initial blue channel color signal corresponding to each angle includes: using the optical flow method to estimate the third target features of each pixel point in the third target area of ​​interest in multiple third predetermined directions between consecutive frames in the blue channel reconstructed video corresponding to each angle; accumulating and calculating all the third target features of each pixel point in each third predetermined direction between consecutive frames in the third target area of ​​interest to obtain a third displacement signal corresponding to each pixel point in each third predetermined direction between consecutive frames; calculating the average value of all the third displacement signals in each third predetermined direction to obtain a physiological motion signal corresponding to each third predetermined direction; and fusing the physiological motion signals of all the third predetermined directions to obtain the initial blue channel color signal corresponding to each angle.

[0080] The third target region of interest is the same as the first target region of interest, the multiple third predetermined directions are the same as the multiple first predetermined directions, and the third target feature is the same as the first target feature. In other embodiments, the third target region of interest and the first target region of interest, the multiple third predetermined directions and the multiple first predetermined directions, and the third target feature and the first target feature may also be set to different contents, which can be specifically set by those skilled in the art according to actual needs.

[0081] In other embodiments, a pulsating skin tracking algorithm can be used to automatically and accurately track the area with the strongest pulsation, and then the area with the strongest pulsation is used as the first target region of interest, the second target region of interest, and the third target region of interest. The pulsating skin tracking algorithm can be a YOLO (You Only Look Once) algorithm or an SSD (Single Shot MultiBox Detector) algorithm, both of which are existing technologies.

[0082] The initial red channel color signal, the initial green channel color signal, and the initial blue channel color signal are all color traces.

[0083] Furthermore, the initial multi-channel color signals corresponding to each angle are filtered according to the first preset rule to obtain the first multi-channel color signals corresponding to each angle, including the following steps: using the first filter to filter the initial red channel color signals corresponding to each angle to obtain the first filtered red channel color signals corresponding to each angle; using the filtfilt function (also known as the bidirectional filtering function) in Matlab (Matlab is a commercial mathematical software used in data analysis, wireless communication, deep learning, image processing and computer vision, signal processing, quantitative finance and risk management, robotics, control systems and other fields) to perform zero-phase high-pass filtering on the first filtered red channel color signals corresponding to each angle to obtain the first multi-channel color signals corresponding to each angle. red channel color signal; using the first filter to filter the initial green channel color signal corresponding to each angle to obtain the first filtered green channel color signal corresponding to each angle; using the filtfilt function to perform zero-phase high-pass filtering on the first filtered green channel color signal corresponding to each angle to obtain the first green channel color signal of the first multi-channel color signal corresponding to each angle; using the first filter to filter the initial blue channel color signal corresponding to each angle to obtain the first filtered blue channel color signal corresponding to each angle; using the filtfilt function to perform zero-phase high-pass filtering on the first filtered blue channel color signal corresponding to each angle to obtain the first blue channel color signal of the first multi-channel color signal corresponding to each angle.

[0084] The first filter is an eighth-order Butterworth high-pass filter with a cutoff frequency of 0.5 Hz (Hz is Hertz). This first filter can remove DC and low-frequency components from the initial multi-channel color signal corresponding to each angle, while preserving the signal's dynamics. This is very effective in removing interference from slow physiological changes such as baseline drift and respiration from the initial multi-channel color signal corresponding to each angle.

[0085] In other implementations, the first filter may also be other filters, which may be specifically set by those skilled in the art according to actual needs.

[0086] The above-mentioned specific implementation method of filtering the initial multi-channel color signal corresponding to each angle according to the first preset rule to obtain the first multi-channel color signal corresponding to each angle can eliminate phase distortion, ensure the consistency of the signal phase before and after filtering, and improve the accuracy and stability of signal processing.

[0087] Furthermore, the steps of filtering the initial multi-channel color signals corresponding to each angle according to the second preset rule to obtain the second multi-channel color signals corresponding to each angle include: using the regular least squares method to remove the baseline drift of the initial red channel color signals corresponding to each angle to obtain the second filtered red channel color signals corresponding to each angle; using the second filter to smooth the second filtered red channel color signals corresponding to each angle to obtain the second red channel color signals of the second multi-channel color signals corresponding to each angle; using the regular least squares method to remove the baseline drift of the initial green channel color signals corresponding to each angle to obtain the second filtered red channel color signals corresponding to each angle; Baseline drift processing is performed to obtain a second filtered green channel color signal corresponding to each angle; the second filtered green channel color signal corresponding to each angle is smoothed using the second filter to obtain a second green channel color signal of the second multi-channel color signal corresponding to each angle; the initial blue channel color signal corresponding to each angle is subjected to baseline drift removal processing using the regularized least squares method to obtain a second filtered blue channel color signal corresponding to each angle; the second filtered blue channel color signal corresponding to each angle is smoothed using the second filter to obtain a second blue channel color signal of the second multi-channel color signal corresponding to each angle.

[0088] The second filter is a Savitzky-Golay (SG) filter. In other implementations, the second filter may also be other filters, which may be specifically configured by those skilled in the art according to actual needs.

[0089] The baseline drift removal process can eliminate low-frequency interference in the signal. The smoothing process can reduce high-frequency noise in the signal without reducing the waveform of the signal, while maintaining the local characteristics and dynamic changes of the signal.

[0090] The implementation of the step of filtering the initial multi-channel color signals corresponding to each angle according to the second preset rule to obtain the second multi-channel color signals corresponding to each angle can effectively remove baseline drift and low-frequency noise in the signal and improve the signal-to-noise ratio of the signal.

[0091] In some embodiments, before filtering the initial multi-channel color signals corresponding to each angle according to a first preset rule to obtain the first multi-channel color signals corresponding to each angle, the step of extracting the color channel signals from the initial video to obtain the first multi-channel color signals and the second multi-channel color signals corresponding to each angle further includes: performing data whitening on the first multi-channel color signals and the second multi-channel color signals corresponding to each angle, subtracting the mean of each signal after the data whitening process from all signals after the data whitening process, then translating all signals after the mean subtraction to the origin and normalizing them according to the time standard deviation of each channel. The operation of removing the mean and performing the normalization process can reduce the impact of light intensity changes on the signal.

[0092] S3. Use a first preset algorithm to perform phase delay identification processing on the first multi-channel color signals and the second multi-channel color signals corresponding to all angles to obtain a target pulse wave transmission time.

[0093] Furthermore, step S3 includes: using the phase delay algorithm of the first preset algorithm to perform phase delay identification processing on the first multi-channel color signal corresponding to all angles to obtain a first initial pulse wave conduction time; using the phase delay algorithm to perform phase delay identification processing on the second multi-channel color signal corresponding to all angles to obtain a second initial pulse wave conduction time; and performing weighted summation calculation processing on the first initial pulse wave conduction time and the second initial pulse wave conduction time according to the weighted summation algorithm of the first preset algorithm to obtain the target pulse wave conduction time.

[0094] When all angles are 0° and 90°, the first multi-channel color signal corresponding to 0° is a phase-delayed signal. The corresponding first multi-channel color signal is a phase-advanced signal. Lag is primarily caused by the circulation path of arterial blood flow, which first flows through deep tissues (such as arteries) before reaching superficial tissues (such as capillaries). Phase lag reflects the time required for the pulse wave to travel from deep tissue to superficial tissues, or PTT. To ensure the accuracy of blood pressure measurements, the valid pulse wave transit time interval is defined as (0, 96] ms (ms is milliseconds) before the peak of the phase lag signal system, thereby eliminating pulse wave transit times that do not conform to physiological principles. This valid pulse wave transit time interval can be determined by referring to physiological plausibility methods and sampling rate compatibility methods. The physiological plausibility method uses an upper limit of 96 ms within the valid pulse wave transit time interval to eliminate unreasonable cross-cardiac cycle mismatches (such as incorrect alignment of adjacent cardiac cycle peaks) when measuring pulse wave transit time at different skin depths within the same measured site (e.g., superficial microvessels and subcutaneous arterioles). The sampling rate compatibility method uses a 96 ms time window at a sampling rate of 125 Hz (8 ms / sample point), covering 12 discrete sampling points, thereby achieving accurate and reliable peak alignment without introducing interpolation errors. This sampling rate compatibility method ensures accurate detection of time delays from superficial to deep vessels while avoiding quantization artifacts.

[0095] Furthermore, the phase delay algorithm of the first preset algorithm is used to perform phase delay identification processing on the first multi-channel color signals corresponding to all angles, and the step of obtaining the first initial pulse wave conduction time includes: using the phase delay algorithm to perform phase delay identification processing on the first red channel color signal in the first multi-channel color signals corresponding to all angles to obtain the first red channel conduction time; using the phase delay algorithm to perform phase delay identification processing on the first green channel color signal in the first multi-channel color signals corresponding to all angles to obtain the first green channel conduction time; using the phase delay algorithm to perform phase delay identification processing on the first blue channel color signal in the first multi-channel color signals corresponding to all angles to obtain the first blue channel conduction time; the first red channel conduction time, the first green channel conduction time and the first blue channel conduction time constitute the first initial pulse wave conduction time.

[0096] Furthermore, the phase delay algorithm is used to perform phase delay identification processing on the first red channel color signal in the first multi-channel color signal corresponding to all angles, and the step of obtaining the first red channel conduction time includes: using the phase delay algorithm to perform phase point identification processing on the first red channel color signal in the first multi-channel color signal corresponding to each angle to obtain the first red channel phase point corresponding to the first red channel color signal in the first multi-channel color signal corresponding to each angle; and performing phase delay identification processing based on all the first red channel phase points to obtain the first red channel conduction time.

[0097] The phase delay algorithm is Matlab's findpeaks (i.e., peak detection) function. In other embodiments, the phase delay algorithm may also be other peak detection methods, which can be specifically configured by those skilled in the art according to actual needs.

[0098] When all angles are 0° and 90°, the first red channel color signal in the first multi-channel color signal corresponding to the 0° angle can be referred to Figure 2 The PPG (PhotoPlethysmoGraphy) signal corresponding to the superficial tissue in the image; the first red channel color signal in the first multi-channel color signal corresponding to the 90° angle can be referred to Figure 2 The PPG signal corresponding to the deep tissue in the .

[0099] Furthermore, the phase delay algorithm is used to perform phase delay identification processing on the first green channel color signal in the first multi-channel color signal corresponding to all angles to obtain the first green channel conduction time, which includes: using the phase delay algorithm to perform phase point identification processing on the first green channel color signal in the first multi-channel color signal corresponding to each angle to obtain the first green channel phase point corresponding to the first green channel color signal in the first multi-channel color signal corresponding to each angle; and performing phase delay identification processing based on all the first green channel phase points to obtain the first green channel conduction time.

[0100] Furthermore, the phase delay algorithm is used to perform phase delay identification processing on the first blue channel color signal in the first multi-channel color signal corresponding to all angles, and the step of obtaining the first blue channel conduction time includes: using the phase delay algorithm to perform phase point identification processing on the first blue channel color signal in the first multi-channel color signal corresponding to each angle to obtain the first blue channel phase point corresponding to the first blue channel color signal in the first multi-channel color signal corresponding to each angle; and performing phase delay identification processing based on all the first blue channel phase points to obtain the first blue channel conduction time.

[0101] The first red channel phase point, the first green channel phase point, and the first blue channel phase point are all contraction peaks. In other embodiments, the first red channel phase point, the first green channel phase point, and the first blue channel phase point can also be other phase points, which can be specifically set by those skilled in the art according to actual needs.

[0102] Furthermore, the step of using the phase delay algorithm to perform phase delay identification processing on the second multi-channel color signals corresponding to all angles to obtain the second initial pulse wave transit time includes: using the phase delay algorithm to perform phase delay identification processing on the second red channel color signal in the second multi-channel color signals corresponding to all angles to obtain the second red channel transit time; using the phase delay algorithm to perform phase delay identification processing on the second green channel color signal in the second multi-channel color signals corresponding to all angles to obtain the second green channel transit time; using the phase delay algorithm to perform phase delay identification processing on the second blue channel color signal in the second multi-channel color signals corresponding to all angles to obtain the second blue channel transit time; the second red channel transit time, the second green channel transit time, and the second blue channel transit time constitute the second initial pulse wave transit time.

[0103] Furthermore, the phase delay algorithm is used to perform phase delay identification processing on the second red channel color signal in the second multi-channel color signal corresponding to all angles, and the step of obtaining the second red channel conduction time includes: using the phase delay algorithm to perform phase point identification processing on the second red channel color signal in the second multi-channel color signal corresponding to each angle to obtain the second red channel phase point corresponding to the second red channel color signal in the second multi-channel color signal corresponding to each angle; and performing phase delay identification processing based on all the second red channel phase points to obtain the second red channel conduction time.

[0104] Furthermore, the phase delay algorithm is used to perform phase delay identification processing on the second green channel color signal in the second multi-channel color signal corresponding to all angles to obtain the second green channel conduction time, which includes: using the phase delay algorithm to perform phase point identification processing on the second green channel color signal in the second multi-channel color signal corresponding to each angle to obtain the second green channel phase point corresponding to the second green channel color signal in the second multi-channel color signal corresponding to each angle; and performing phase delay identification processing based on all the second green channel phase points to obtain the second green channel conduction time.

[0105] Furthermore, the phase delay algorithm is used to perform phase delay identification processing on the second blue channel color signal in the second multi-channel color signal corresponding to all angles, and the step of obtaining the second blue channel conduction time includes: using the phase delay algorithm to perform phase point identification processing on the second blue channel color signal in the second multi-channel color signal corresponding to each angle to obtain the second blue channel phase point corresponding to the second blue channel color signal in the second multi-channel color signal corresponding to each angle; and performing phase delay identification processing based on all the second blue channel phase points to obtain the second blue channel conduction time.

[0106] The second red channel phase point, the second green channel phase point, and the second blue channel phase point are all contraction peaks. In other embodiments, the second red channel phase point, the second green channel phase point, and the second blue channel phase point can also be other phase points, which can be specifically set by those skilled in the art according to actual needs.

[0107] Furthermore, the step of performing weighted summation calculation processing on the first initial pulse wave transit time and the second initial pulse wave transit time according to the weighted summation algorithm of the first preset algorithm to obtain the target pulse wave transit time includes: performing weighted summation calculation processing on the first red channel transit time and the second red channel transit time of the second initial pulse wave transit time according to the weighted summation algorithm to obtain a target red channel transit time; performing weighted summation calculation processing on the first green channel transit time and the second green channel transit time of the second initial pulse wave transit time according to the weighted summation algorithm to obtain a target green channel transit time; performing weighted summation calculation processing on the first blue channel transit time and the second blue channel transit time of the second initial pulse wave transit time according to the weighted summation algorithm to obtain a target blue channel transit time; the target red channel transit time, the target green channel transit time, and the target blue channel transit time constitute the target pulse wave transit time, with reference to Figure 3 As shown, in Figure 3 In the image, R stands for red channel, B stands for blue channel, and G stands for green channel.

[0108] The above step of obtaining the target pulse wave transmission time can improve the stability and anti-interference performance of the signal while ensuring the real-time performance, smoothness and low-frequency drift removal effect of the signal.

[0109] Furthermore, the weighted summation algorithm is used to calculate the second red channel transit time of the first red channel transit time and the second initial pulse wave transit time, and the calculation formula for obtaining the target red channel transit time is:

[0110] PTT R3 =WR1 / (W R1 +W R2 )×PTT R1 +W R2 / (W R1 +W R2 )×PTT R2 ;

[0111] Among them, PTT R3 is the target red channel conduction time; W R1 is a first weight coefficient, which is the average value of the signal-to-noise ratio of the first red channel color signal of the first multi-channel color signal corresponding to all angles, or the average value of the signal-to-noise ratio of the first multi-channel color signal corresponding to all angles; W R2 is a second weight coefficient, which is an average value of the signal-to-noise ratios of the second red channel color signal of the second multi-channel color signal corresponding to all angles, or an average value of the signal-to-noise ratios of the second multi-channel color signal corresponding to all angles; PTT R1 is the first red channel transit time; PTT R2 It should be understood that in all calculation formulas of the present application, the “ / ” symbol is understood as a division operator symbol in mathematics.

[0112] At all angles between 0° and 90°, PTT R3 Can be expressed as PTT R0°_R90° .

[0113] Furthermore, the first green channel transmission time and the second initial pulse wave transmission time are weighted and summed according to the weighted summation algorithm to obtain the target green channel transmission time using the following calculation formula:

[0114] PTT G3 =W G1 / (W G1 +W G2 )×PTT G1 +W G2 / (W G1 +W G2 )×PTT G2 ;

[0115] Among them, PTT G3 is the target green channel conduction time; W G1 is a third weight coefficient, and the third weight coefficient is an average value of the signal-to-noise ratio of the first green channel color signal of the first multi-channel color signal corresponding to all angles, or an average value of the signal-to-noise ratio of the first multi-channel color signal corresponding to all angles; W G2is a fourth weight coefficient, the fourth weight coefficient being an average value of the signal-to-noise ratios of the second green channel color signal of the second multi-channel color signal corresponding to all angles, or an average value of the signal-to-noise ratios of the second multi-channel color signal corresponding to all angles; PTT G1 is the first green channel transit time; PTT G2 It is the second green channel conduction time.

[0116] At all angles between 0° and 90°, PTT G3 Can be expressed as PTT G0°_G90° .

[0117] Furthermore, the weighted summation algorithm is used to calculate the weighted sum of the first blue channel conduction time and the second initial pulse wave conduction time to obtain the target blue channel conduction time using the following calculation formula:

[0118] PTT B3 =W B1 / (W B1 +W B2 )×PTT B1 +W B2 / (W B1 +W B2 )×PTT B2 ;

[0119] Among them, PTT B3 is the target blue channel conduction time; W B1 is a fifth weight coefficient, which is an average value of the signal-to-noise ratios of the first blue channel color signal of the first multi-channel color signal corresponding to all angles, or an average value of the signal-to-noise ratios of the first multi-channel color signal corresponding to all angles; W B2 is a sixth weight coefficient, the sixth weight coefficient being an average value of the signal-to-noise ratios of the second blue channel color signal of the second multi-channel color signal corresponding to all angles, or an average value of the signal-to-noise ratios of the second multi-channel color signal corresponding to all angles; PTT B1 is the first blue channel conduction time; PTT B2 is the second blue channel conduction time.

[0120] At all angles between 0° and 90°, PTT B3 Can be expressed as PTT B0°_B90° .

[0121] The implementation of the specific embodiment of the step of performing weighted summation calculation processing on the first initial pulse wave transit time and the second initial pulse wave transit time according to the weighted summation algorithm of the first preset algorithm to obtain the target pulse wave transit time has both the real-time and smoothing effects of the method of performing filtering processing using the first preset rule and the low-frequency drift removal and waveform retention capabilities of the method of performing filtering processing using the second preset rule. At the same time, it effectively copes with interference from motion artifacts and ambient light, thereby improving signal quality and stability.

[0122] In other embodiments, the target pulse wave transit time can also be extracted by using the single polarization multi-band PTT (ie, pulse wave transit time) feature. B0°_R0° 、PTT G0°_R0° 、PTT B0°_G0° 、PTT B90°_R90° 、PTT G90°_R90° 、PTT B90°_G90° , and finally PTT B0°_R0° 、PTT G0°_R0° 、PTT B0°_G0° 、PTT B90°_R90° 、PTT G90°_R90° and PTT B90°_G90° In other embodiments, the target pulse wave transit time can also be extracted by multi-polarization multi-band PTT features to obtain PTT. B0°_R90° 、PTT G0°_R90° 、PTT B0°_G90° 、PTT B90°_R0° 、PTT G90°_R0° 、PTT B90°_G0° , and finally PTT B0°_R90° 、PTT G0°_R90° 、PTT B0°_G90° 、PTT B90°_R0° 、PTT G90°_R0° 、PTT B90°_G0° Fusion is the target pulse wave transit time. Wherein, R is the red channel; B is the blue channel; G is the green channel; 0° and 90° are the angles at which the polarized light is irradiated to the measured part.

[0123] PTT B0°_R0°The first channel conduction time is obtained by: using the phase delay algorithm to perform phase point identification processing on a first blue channel color signal in a first multi-channel color signal corresponding to an angle of 0° to obtain a first phase point corresponding to the first blue channel color signal in the first multi-channel color signal corresponding to the angle of 0°; using the phase delay algorithm to perform phase point identification processing on a second red channel color signal in a second multi-channel color signal corresponding to an angle of 0° to obtain a second phase point corresponding to the second red channel color signal in the second multi-channel color signal corresponding to the angle of 0°; and performing phase delay identification processing based on the first phase point and the second phase point to obtain the first channel conduction time.

[0124] PTT G0°_R0° The second channel conduction time is obtained by: performing phase point identification processing on a first green channel color signal in a first multi-channel color signal corresponding to an angle of 0° using the phase delay algorithm to obtain a third phase point corresponding to the first green channel color signal in the first multi-channel color signal corresponding to the angle of 0°; performing phase point identification processing on a second red channel color signal in a second multi-channel color signal corresponding to an angle of 0° using the phase delay algorithm to obtain a fourth phase point corresponding to the second red channel color signal in the second multi-channel color signal corresponding to the angle of 0°; and performing phase delay identification processing based on the third phase point and the fourth phase point to obtain the second channel conduction time.

[0125] PTT B0°_G0° The third channel conduction time is obtained by: performing phase point identification processing on a first blue channel color signal in a first multi-channel color signal corresponding to an angle of 0° using the phase delay algorithm to obtain a fifth phase point corresponding to the first blue channel color signal in the first multi-channel color signal corresponding to the angle of 0°; performing phase point identification processing on a second green channel color signal in a second multi-channel color signal corresponding to an angle of 0° using the phase delay algorithm to obtain a sixth phase point corresponding to the second green channel color signal in the second multi-channel color signal corresponding to the angle of 0°; and performing phase delay identification processing based on the fifth phase point and the sixth phase point to obtain the third channel conduction time.

[0126] PTT B90°_R90°The fourth channel conduction time is obtained by: performing phase point identification processing on a first blue channel color signal in a first multi-channel color signal corresponding to a 90° angle using the phase delay algorithm to obtain a seventh phase point corresponding to the first blue channel color signal in the first multi-channel color signal corresponding to the 90° angle; performing phase point identification processing on a second red channel color signal in a second multi-channel color signal corresponding to the 90° angle using the phase delay algorithm to obtain an eighth phase point corresponding to the second red channel color signal in the second multi-channel color signal corresponding to the 90° angle; and performing phase delay identification processing based on the seventh phase point and the eighth phase point to obtain the fourth channel conduction time.

[0127] PTT G90°_R90° The fifth channel conduction time is obtained by: performing phase point identification processing on a first green channel color signal in a first multi-channel color signal corresponding to a 90° angle using the phase delay algorithm to obtain a ninth phase point corresponding to the first green channel color signal in the first multi-channel color signal corresponding to the 90° angle; performing phase point identification processing on a second red channel color signal in a second multi-channel color signal corresponding to the 90° angle using the phase delay algorithm to obtain a tenth phase point corresponding to the second red channel color signal in the second multi-channel color signal corresponding to the 90° angle; and performing phase delay identification processing based on the ninth phase point and the tenth phase point to obtain the fifth channel conduction time.

[0128] PTT B90°_G90° The sixth channel conduction time is obtained by: performing phase point identification processing on a first blue channel color signal in a first multi-channel color signal corresponding to a 90° angle using the phase delay algorithm to obtain an eleventh phase point corresponding to the first blue channel color signal in the first multi-channel color signal corresponding to the 90° angle; performing phase point identification processing on a second green channel color signal in a second multi-channel color signal corresponding to the 90° angle using the phase delay algorithm to obtain a twelfth phase point corresponding to the second green channel color signal in the second multi-channel color signal corresponding to the 90° angle; and performing phase delay identification processing based on the eleventh phase point and the twelfth phase point to obtain the sixth channel conduction time.

[0129] PTT B0°_R90°The seventh channel conduction time is obtained by: performing phase point identification processing on a first blue channel color signal in a first multi-channel color signal corresponding to an angle of 0° using the phase delay algorithm to obtain a thirteenth phase point corresponding to the first blue channel color signal in the first multi-channel color signal corresponding to the angle of 0°; performing phase point identification processing on a second red channel color signal in a second multi-channel color signal corresponding to an angle of 90° using the phase delay algorithm to obtain a fourteenth phase point corresponding to the second red channel color signal in the second multi-channel color signal corresponding to the angle of 90°; and performing phase delay identification processing based on the thirteenth phase point and the fourteenth phase point to obtain the seventh channel conduction time.

[0130] PTT G0°_R90° The eighth channel conduction time is obtained by: performing phase point identification processing on a first green channel color signal in a first multi-channel color signal corresponding to an angle of 0° using the phase delay algorithm to obtain a fifteenth phase point corresponding to the first green channel color signal in the first multi-channel color signal corresponding to the angle of 0°; performing phase point identification processing on a second red channel color signal in a second multi-channel color signal corresponding to an angle of 90° using the phase delay algorithm to obtain a sixteenth phase point corresponding to the second red channel color signal in the second multi-channel color signal corresponding to the angle of 90°; and performing phase delay identification processing based on the fifteenth phase point and the sixteenth phase point to obtain the eighth channel conduction time.

[0131] PTT B0°_G90° The ninth channel conduction time is obtained by: performing phase point identification processing on a first blue channel color signal in a first multi-channel color signal corresponding to an angle of 0° using the phase delay algorithm to obtain a seventeenth phase point corresponding to the first blue channel color signal in the first multi-channel color signal corresponding to the angle of 0°; performing phase point identification processing on a second green channel color signal in a second multi-channel color signal corresponding to an angle of 90° using the phase delay algorithm to obtain an eighteenth phase point corresponding to the second green channel color signal in the second multi-channel color signal corresponding to the angle of 90°; and performing phase delay identification processing based on the seventeenth phase point and the eighteenth phase point to obtain the ninth channel conduction time.

[0132] PTT B90°_R0°The tenth channel conduction time is obtained by: performing phase point identification processing on a first blue channel color signal in a first multi-channel color signal corresponding to an angle of 90° using the phase delay algorithm to obtain a nineteenth phase point corresponding to the first blue channel color signal in the first multi-channel color signal corresponding to the 90° angle; performing phase point identification processing on a second red channel color signal in a second multi-channel color signal corresponding to an angle of 0° using the phase delay algorithm to obtain a twentieth phase point corresponding to the second red channel color signal in the second multi-channel color signal corresponding to the 0° angle; and performing phase delay identification processing based on the nineteenth phase point and the twenty-first phase point to obtain the tenth channel conduction time.

[0133] PTT G90°_R0° The eleventh channel conduction time is obtained by: performing phase point identification processing on a first green channel color signal in a first multi-channel color signal corresponding to an angle of 90° using the phase delay algorithm to obtain a twenty-first phase point corresponding to the first green channel color signal in the first multi-channel color signal corresponding to the 90° angle; performing phase point identification processing on a second red channel color signal in a second multi-channel color signal corresponding to an angle of 0° using the phase delay algorithm to obtain a twenty-second phase point corresponding to the second red channel color signal in the second multi-channel color signal corresponding to the 0° angle; and performing phase delay identification processing based on the twenty-first phase point and the twenty-second phase point to obtain the eleventh channel conduction time.

[0134] PTT B90°_G0° The twelfth channel conduction time is obtained by: performing phase point identification processing on a first blue channel color signal in a first multi-channel color signal corresponding to an angle of 90° using the phase delay algorithm to obtain a twenty-third phase point corresponding to the first blue channel color signal in the first multi-channel color signal corresponding to the 90° angle; performing phase point identification processing on a second green channel color signal in a second multi-channel color signal corresponding to an angle of 0° using the phase delay algorithm to obtain a twenty-fourth phase point corresponding to the second green channel color signal in the second multi-channel color signal corresponding to the 0° angle; and performing phase delay identification processing based on the twenty-third phase point and the twenty-fourth phase point to obtain the twelfth channel conduction time.

[0135] The first phase point, the second phase point, the third phase point, the fourth phase point, the fifth phase point, the sixth phase point, the seventh phase point, the eighth phase point, the ninth phase point, the tenth phase point, the eleventh phase point, the twelfth phase point, the thirteenth phase point, the fourteenth phase point, the fifteenth phase point, the sixteenth phase point, the seventeenth phase point, the eighteenth phase point, the nineteenth phase point, the twentieth phase point, the twenty-first phase point, the twenty-second phase point, the twenty-third phase point and the twenty-fourth phase point can all be contraction peaks.

[0136] S4. Calculate and process the target pulse wave transmission time using a linear regression model to obtain a blood pressure measurement value of the measured part of the target user.

[0137] The linear regression model includes a systolic pressure model, a diastolic pressure model and a blood pressure model.

[0138] Furthermore, step S4 includes: using the systolic pressure model of the linear regression model to perform weighted summation calculation processing on the target pulse wave transmission time to obtain the target systolic pressure; using the diastolic pressure model of the linear regression model to perform weighted summation calculation processing on the target pulse wave transmission time to obtain the target diastolic pressure; using the blood pressure model of the linear regression model to perform ratio calculation processing on the target systolic pressure and the target diastolic pressure to obtain the blood pressure measurement value of the measured part of the target user.

[0139] Furthermore, the target pulse wave transit time is weighted and calculated using the systolic pressure model of the linear regression model to obtain the target systolic pressure as follows:

[0140] SBP=A1×PTT R3 +A2×PTT G3 +A3×PTT B3 +C;

[0141] Wherein, SBP is the target systolic blood pressure; A1 is the first regression coefficient; A2 is the second regression coefficient; A3 is the third regression coefficient; C is the fourth regression coefficient; the first regression coefficient, the second regression coefficient, the third regression coefficient and the fourth regression coefficient are all estimated by the least squares method.

[0142] Furthermore, the diastolic pressure model of the linear regression model is used to perform weighted summation calculation processing on the target pulse wave transit time, and the calculation formula for obtaining the target diastolic pressure is:

[0143] DBP=B1×PTT R3 +B2×PTT G3 +B3×PTT B3 +D;

[0144] Wherein, DBP is the target diastolic pressure; B1 is the fifth regression coefficient; B2 is the sixth regression coefficient; B3 is the seventh regression coefficient; D is the eighth regression coefficient; the fifth regression coefficient, the sixth regression coefficient, the seventh regression coefficient and the eighth regression coefficient are all estimated by the least squares method.

[0145] Furthermore, the blood pressure model of the linear regression model is used to perform ratio calculation processing on the target systolic pressure and the target diastolic pressure, and the calculation formula for obtaining the blood pressure measurement value of the measured part of the target user is: BP=SBP / DBP; wherein, BP is the blood pressure measurement value.

[0146] Through the above-mentioned implementation, compared with the prior art, the embodiment of the present application does not require the use of additional gas pressure parameters to achieve the measurement of blood pressure measurement values. Therefore, the embodiment of the present application can effectively reduce the impact of errors in additional parameters on blood pressure measurement values, thereby improving the accuracy of blood pressure measurement.

[0147] In the embodiments of the present application, the multi-angle polarized light imaging technology based on time division multiplexing can simultaneously capture the first multi-channel color signal and the second multi-channel color signal corresponding to a 0° angle from the shallow tissue under parallel polarization, as well as the first multi-channel color signal and the second multi-channel color signal corresponding to a 90° angle from the deep tissue under cross polarization. The multi-angle polarized light imaging technology based on time division multiplexing can reduce the interference caused by arterial vascular characteristics and the distance between the measurement points, significantly improving signal quality. The target pulse wave transit time (MP-PTT) required for the pulse wave to transmit from the deep layer to the shallow layer can be calculated using all the first multi-channel color signals and all the second multi-channel color signals. Using this target pulse wave transit time can optimize blood pressure estimation and achieve more accurate measurement.

[0148] The embodiments of the present application not only meet the requirements for efficient blood pressure measurement at a single wavelength and a single measured site, but also significantly reduce the complexity and cost of the measurement equipment, while improving the signal quality and measurement stability.

[0149] refer to Figure 4 As shown in FIG, it is a principle block diagram of a blood pressure measurement device based on pulse wave transit time of multi-angle polarized light provided in the second aspect of the embodiment of the present application. Figure 4 In the embodiment of the present invention, the blood pressure measurement device 100 based on pulse wave transit time of multi-angle polarized light includes:

[0150] The initial video acquisition module 101 is configured to acquire an initial video of the measured part of the target user by using a time division multiplexing method when polarized light at multiple angles is irradiated onto the measured part.

[0151] The signal extraction module 102 is configured to perform color channel signal extraction processing on the initial video to obtain a first multi-channel color signal and a second multi-channel color signal corresponding to each angle.

[0152] The phase delay identification module 103 is configured to perform phase delay identification processing on the first multi-channel color signal and the second multi-channel color signal corresponding to all angles using a first preset algorithm to obtain a target pulse wave transmission time.

[0153] The blood pressure measurement value calculation module 104 is used to calculate and process the target pulse wave transmission time using a linear regression model to obtain the blood pressure measurement value of the measured part of the target user.

[0154] The third aspect of the embodiment of the present application provides a terminal device, the principle block diagram of the terminal device can be as follows: Figure 5 As shown. The terminal device includes a processor, a memory, a network interface, a display screen and a temperature sensor connected via a system bus. The processor is used to provide computing and control capabilities. The memory includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the terminal device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, a blood pressure measurement method based on the pulse wave transmission time of multi-angle polarized light is implemented. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the temperature sensor is pre-set inside the terminal device to detect the operating temperature of the internal device.

[0155] Those skilled in the art will understand that Figure 5 The principle block diagram shown in the figure is only a block diagram of a partial structure related to the solution of the present invention, and does not constitute a limitation on the terminal device to which the solution of the present invention is applied. The specific terminal device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0156] In some embodiments, embodiments of the present application provide a terminal device comprising a processor and a memory, the memory being configured to store a computer program, the processor being configured to call and execute the computer program stored in the memory to perform the steps of the blood pressure measurement method based on pulse wave transit time using multi-angle polarized light, as provided in the first aspect of the embodiments of the present application. A fourth aspect of the embodiments of the present application provides a computer-readable storage medium, the computer-readable storage medium being configured to store a computer program that causes a computer to perform the steps of the blood pressure measurement method based on pulse wave transit time using multi-angle polarized light, as provided in the first aspect of the embodiments of the present application.

[0157] Those skilled in the art will appreciate that all or part of the processes in the above-described method embodiments can be implemented by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the above-described method embodiments. Any reference to memory, storage, database, or other media used in the various embodiments provided herein may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct RAMbus dynamic RAM (DRDRAM), and RAMbus dynamic RAM (RDRAM).

[0158] The technical features of the above embodiments can be combined without changing the basic principles of this application. In order to make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0159] The above embodiments merely illustrate several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the patent application. It should be noted that a person skilled in the art could make various modifications and improvements without departing from the spirit of the present application, all of which fall within the scope of protection of the present application. Therefore, the scope of patent protection for the present application shall be determined by the appended claims.

Claims

1. A blood pressure measurement method based on pulse wave transit time using multi-angle polarized light, characterized in that: include: Using time division multiplexing, when polarized light at multiple angles is irradiated onto the measured part of the target user, an initial video of the measured part is collected; Performing color channel signal extraction processing on the initial video to obtain a first multi-channel color signal and a second multi-channel color signal corresponding to each angle; Using a first preset algorithm, phase delay identification processing is performed on the first multi-channel color signal and the second multi-channel color signal corresponding to all angles to obtain a target pulse wave transmission time; Calculating and processing the target pulse wave transmission time using a linear regression model to obtain a blood pressure measurement value of the measured part of the target user; The step of performing phase delay identification processing on the first multi-channel color signals and the second multi-channel color signals corresponding to all angles using a first preset algorithm to obtain a target pulse wave transit time includes: performing phase delay identification processing on the first multi-channel color signals corresponding to all angles using a phase delay algorithm of the first preset algorithm to obtain a first initial pulse wave transit time; performing phase delay identification processing on the second multi-channel color signals corresponding to all angles using the phase delay algorithm to obtain a second initial pulse wave transit time; and performing weighted sum calculation processing on the first initial pulse wave transit time and the second initial pulse wave transit time using a weighted summation algorithm of the first preset algorithm to obtain the target pulse wave transit time. The step of using the phase delay algorithm of the first preset algorithm to perform phase delay identification processing on the first multi-channel color signals corresponding to all angles to obtain a first initial pulse wave transit time includes: using the phase delay algorithm to perform phase delay identification processing on the first red channel color signal in the first multi-channel color signals corresponding to all angles to obtain a first red channel transit time; using the phase delay algorithm to perform phase delay identification processing on the first green channel color signal in the first multi-channel color signals corresponding to all angles to obtain a first green channel transit time; using the phase delay algorithm to perform phase delay identification processing on the first blue channel color signal in the first multi-channel color signals corresponding to all angles to obtain a first blue channel transit time; the first red channel transit time, the first green channel transit time, and the first blue channel transit time constitute the first initial pulse wave transit time; The step of performing weighted summation calculation processing on the first initial pulse wave transit time and the second initial pulse wave transit time according to the weighted summation algorithm of the first preset algorithm to obtain the target pulse wave transit time includes: performing weighted summation calculation processing on the first red channel transit time and the second red channel transit time of the second initial pulse wave transit time according to the weighted summation algorithm to obtain a target red channel transit time; performing weighted summation calculation processing on the first green channel transit time and the second green channel transit time of the second initial pulse wave transit time according to the weighted summation algorithm to obtain a target green channel transit time; performing weighted summation calculation processing on the first blue channel transit time and the second blue channel transit time of the second initial pulse wave transit time according to the weighted summation algorithm to obtain a target blue channel transit time; the target red channel transit time, the target green channel transit time, and the target blue channel transit time constitute the target pulse wave transit time; The weighted summation algorithm is used to calculate the weighted sum of the first red channel transfer time and the second initial pulse wave transfer time to obtain the target red channel transfer time using the following calculation formula: PTT R3 =W R1 / (IN R1 +W R2 )×PTT R1 +W R2 / (IN R1 +W R2 )×PTT R2 ; Among them, PTT R3 is the target red channel conduction time; W R1 is a first weight coefficient, which is the average value of the signal-to-noise ratio of the first red channel color signal of the first multi-channel color signal corresponding to all angles, or the average value of the signal-to-noise ratio of the first multi-channel color signal corresponding to all angles; W R2 is a second weight coefficient, which is an average value of the signal-to-noise ratios of the second red channel color signal of the second multi-channel color signal corresponding to all angles, or an average value of the signal-to-noise ratios of the second multi-channel color signal corresponding to all angles; PTT R1 is the first red channel transit time; PTT R2 is the second red channel conduction time.

2. The blood pressure measurement method based on pulse wave transit time using multi-angle polarized light according to claim 1, characterized in that: The step of performing color channel signal extraction processing on the initial video to obtain a first multi-channel color signal and a second multi-channel color signal corresponding to each angle includes: Performing color channel signal extraction processing on the initial video to obtain an initial multi-channel color signal corresponding to each angle; Performing filtering on the initial multi-channel color signals corresponding to each angle according to a first preset rule to obtain a first multi-channel color signal corresponding to each angle; The initial multi-channel color signals corresponding to each angle are filtered according to a second preset rule to obtain second multi-channel color signals corresponding to each angle.

3. The blood pressure measurement method based on pulse wave transit time using multi-angle polarized light according to claim 1, wherein: The step of performing phase delay identification processing on the first red channel color signal in the first multi-channel color signals corresponding to all angles using the phase delay algorithm to obtain the first red channel conduction time includes: Performing phase point recognition processing on the first red channel color signal in the first multi-channel color signal corresponding to each angle using the phase delay algorithm to obtain a first red channel phase point corresponding to the first red channel color signal in the first multi-channel color signal corresponding to each angle; Phase delay identification processing is performed based on all first red channel phase points to obtain the first red channel conduction time.

4. The blood pressure measurement method based on pulse wave transit time using multi-angle polarized light according to claim 1, wherein: The step of calculating and processing the target pulse wave transit time using a linear regression model to obtain the blood pressure measurement value of the measured part of the target user includes: Using the systolic blood pressure model of the linear regression model to perform weighted summation calculation processing on the target pulse wave transit time to obtain a target systolic blood pressure; Using the diastolic pressure model of the linear regression model to perform weighted summation calculation processing on the target pulse wave transmission time to obtain the target diastolic pressure; The blood pressure model of the linear regression model is used to perform ratio calculation processing on the target systolic pressure and the target diastolic pressure to obtain the blood pressure measurement value of the measured part of the target user.

5. A blood pressure measurement device based on pulse wave transit time using multi-angle polarized light, characterized in that: include: An initial video acquisition module is used to acquire an initial video of the measured part of the target user when polarized light at multiple angles is irradiated onto the measured part of the target user in a time-division multiplexing manner; a signal extraction module, configured to perform color channel signal extraction processing on the initial video to obtain a first multi-channel color signal and a second multi-channel color signal corresponding to each angle; a phase delay identification module, configured to perform phase delay identification processing on the first multi-channel color signal and the second multi-channel color signal corresponding to all angles using a first preset algorithm to obtain a target pulse wave transmission time; a blood pressure measurement value calculation module, configured to calculate and process the target pulse wave transit time using a linear regression model to obtain a blood pressure measurement value of a measured part of the target user; The phase delay identification module is further configured to perform phase delay identification processing on first multi-channel color signals corresponding to all angles using the phase delay algorithm of the first preset algorithm to obtain a first initial pulse wave transit time; perform phase delay identification processing on second multi-channel color signals corresponding to all angles using the phase delay algorithm to obtain a second initial pulse wave transit time; and perform weighted sum calculation processing on the first initial pulse wave transit time and the second initial pulse wave transit time using the weighted summation algorithm of the first preset algorithm to obtain the target pulse wave transit time; The phase delay identification module is further configured to perform phase delay identification processing on a first red channel color signal in the first multi-channel color signals corresponding to all angles using the phase delay algorithm to obtain a first red channel conduction time; perform phase delay identification processing on a first green channel color signal in the first multi-channel color signals corresponding to all angles using the phase delay algorithm to obtain a first green channel conduction time; and perform phase delay identification processing on a first blue channel color signal in the first multi-channel color signals corresponding to all angles using the phase delay algorithm to obtain a first blue channel conduction time. The first red channel conduction time, the first green channel conduction time, and the first blue channel conduction time constitute the first initial pulse wave conduction time. The phase delay identification module is further configured to perform weighted summation calculation processing on the first red channel transit time and the second red channel transit time of the second initial pulse wave transit time according to the weighted summation algorithm to obtain a target red channel transit time; perform weighted summation calculation processing on the first green channel transit time and the second green channel transit time of the second initial pulse wave transit time according to the weighted summation algorithm to obtain a target green channel transit time; and perform weighted summation calculation processing on the first blue channel transit time and the second blue channel transit time of the second initial pulse wave transit time according to the weighted summation algorithm to obtain a target blue channel transit time; the target red channel transit time, the target green channel transit time, and the target blue channel transit time constitute the target pulse wave transit time; The weighted summation algorithm is used to calculate the weighted sum of the first red channel transfer time and the second initial pulse wave transfer time to obtain the target red channel transfer time using the following calculation formula: PTT R3 =W R1 / (IN R1 +W R2 )×PTT R1 +W R2 / (IN R1 +W R2 )×PTT R2 ; Among them, PTT R3 is the target red channel conduction time; W R1 is a first weight coefficient, which is the average value of the signal-to-noise ratio of the first red channel color signal of the first multi-channel color signal corresponding to all angles, or the average value of the signal-to-noise ratio of the first multi-channel color signal corresponding to all angles; W R2 is a second weight coefficient, which is an average value of the signal-to-noise ratios of the second red channel color signal of the second multi-channel color signal corresponding to all angles, or an average value of the signal-to-noise ratios of the second multi-channel color signal corresponding to all angles; PTT R1 is the first red channel transit time; PTT R2 is the second red channel conduction time.

6. A terminal device, characterized in that: include: A processor and a memory, the memory being used to store a computer program, the processor being used to call and run the computer program stored in the memory to execute the steps of the blood pressure measurement method based on pulse wave transit time of multi-angle polarized light as described in any one of claims 1 to 4.

7. A computer-readable storage medium, characterized in that Used to store a computer program, wherein the computer program causes a computer to execute the steps of the blood pressure measurement method based on pulse wave transit time of multi-angle polarized light as claimed in any one of claims 1 to 4.

Images