Vital signs monitoring method and apparatus

Abstract

The present application relates to the technical field of health monitoring, and provides a kind of vital sign monitoring method and device, the method comprises: obtaining the point cloud information of target area, and the target object to be monitored is located in target area;Based on the point cloud information of target area, the vital sign signal sequence of target object is determined;Based on the vital sign signal sequence of target object, the target detection position in target area is determined, and the target detection position is one of multiple detection positions in target area;Determine the vital sign signal of target detection position;Based on the vital sign signal of target detection position, the vital sign information of target object is determined.The method tracks target object through target area, and the activity and posture of target object when monitoring vital sign are not limited, and the vital sign information of target object can be accurately monitored by determining target detection position in target area, to realize full-orientation accurate vital sign monitoring in different directions, distances and human postures.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of health monitoring, in particular to a vital sign monitoring method and device. BACKGROUND

[0002] Common vital sign monitoring devices are contact devices that need to be attached to the human body or clothes for monitoring. These contact devices affect the quality of life and sleep of people, and are not suitable for people with sensitive skin or body wounds.

[0003] At present, some non-contact vital sign monitoring devices have appeared. These non-contact devices are mostly realized based on a radar system, emit electromagnetic waves, receive echoes for processing, and monitor vital signs. However, these non-contact devices have high requirements for the position of the human body when monitoring vital signs. Only when the human body is directly opposite the non-contact device or is close to the non-contact device, the vital signs can be monitored. When the human body moves or changes posture, such devices cannot accurately measure the accurate vital signs of the human body. SUMMARY

[0004] The present application aims to at least solve one of the technical problems existing in the prior art. To this end, the present application provides a vital sign monitoring method, which overcomes the limitations of the monitoring position of the non-contact vital sign monitoring device and accurately monitors the vital signs.

[0005] The vital sign monitoring method according to the first aspect of the present application comprises:

[0006] Obtaining point cloud information of a target area, wherein a target object to be monitored is located in the target area;

[0007] Determining a vital sign signal sequence of the target object based on the point cloud information of the target area;

[0008] Determining a target detection position in the target area based on the vital sign signal sequence of the target object, wherein the target detection position is one of a plurality of detection positions in the target area;

[0009] Determining a vital sign signal of the target detection position;

[0010] Determining vital sign information of the target object based on the vital sign signal of the target detection position.

[0011] According to the vital sign monitoring method of the present application, the target object is tracked by determining the target area. The target object does not need to maintain a relative position relationship with the sensor when monitoring the vital signs, and the activity of the target object is not limited. The target detection position is determined in the target area, and full-range more accurate vital sign monitoring under different orientations, distances and body postures is realized.

[0012] According to an embodiment of the present application, the target detection position is determined from the target region based on the vital sign signal sequence of the target object, comprising:

[0013] The vital sign signal frequency of each detection position in the target region is determined based on the vital sign signal sequence of the target object.

[0014] The target detection position is determined based on the vital sign signal frequency.

[0015] According to an embodiment of the present application, the target detection position is determined based on the vital sign signal frequency, comprising:

[0016] The frequency domain amplitude and confidence of the vital sign signal frequency are obtained.

[0017] A plurality of first detection positions in the target region are determined based on the frequency domain amplitude.

[0018] The target detection position is determined by voting the plurality of first detection positions according to the confidence.

[0019] According to an embodiment of the present application, the target detection position is determined from the target region based on the vital sign signal sequence of the target object, comprising:

[0020] The vital sign signal power of each detection position in the target region is determined based on the vital sign signal sequence of the target object.

[0021] The clutter in the vital sign signal sequence of the target object is removed based on the vital sign signal power.

[0022] The target detection position is determined based on the vital sign signal sequence of the target object after removing the clutter.

[0023] According to an embodiment of the present application, the clutter in the vital sign signal sequence of the target object is removed based on the vital sign signal power, comprising:

[0024] The vital sign signal power is normalized, and the mean and variance of the probability density function of the vital sign signal power are obtained.

[0025] The clutter in the vital sign signal sequence of the target object is removed based on the mean and the variance.

[0026] According to an embodiment of the present application, the vital sign signal sequence of the target object is determined based on the point cloud information of the target region, comprising:

[0027] The target phase sequence is determined based on the point cloud information of the target region.

[0028] Separate a vital sign signal sequence of the target object from the point cloud information of the target region based on the target phase sequence.

[0029] According to an embodiment of the present application, the target phase sequence is determined based on the point cloud information of the target region, comprising:

[0030] The target thermogram of the target region is synthesized by beamforming based on the point cloud information of the target region.

[0031] The target phase sequence is determined based on the target thermogram.

[0032] According to an embodiment of the present application, the point cloud information of the target region is obtained, comprising:

[0033] A plurality of frames of point cloud information of the space where the target object is located is obtained.

[0034] The target region where the target object is located is determined based on the plurality of frames of point cloud information.

[0035] The point cloud information of the target region is determined based on the target region.

[0036] According to an embodiment of the present application, the target region where the target object is located is determined based on the plurality of frames of point cloud information, comprising:

[0037] The target position where the target object is located is determined based on the plurality of frames of point cloud information.

[0038] The target region is determined based on the target position, and the target position is at the center of the target region.

[0039] The vital sign monitoring device according to the second embodiment of the present application comprises:

[0040] The millimeter wave radar is used to obtain the point cloud information of the target region, and the target object to be monitored is located in the target region.

[0041] The first processing module is used to determine the vital sign signal sequence of the target object based on the point cloud information of the target region.

[0042] The second processing module is used to determine the target detection position in the target region based on the vital sign signal sequence of the target object, and the target detection position is one of a plurality of detection positions in the target region.

[0043] The third processing module is used to determine the vital sign signal of the target detection position.

[0044] The fourth processing module is configured to determine vital sign information of the target object based on the vital sign signal of the target detection position.

[0045] The electronic device according to the third aspect of the present application comprises a memory, a processor and a computer program stored in the memory and executable on the processor, and the processor implements the vital sign monitoring method according to any one of the above aspects when executing the computer program.

[0046] The non-transitory computer readable storage medium according to the fourth aspect of the present application stores a computer program, and the computer program is executable on a processor to implement the vital sign monitoring method according to any one of the above aspects.

[0047] The computer program product according to the fifth aspect of the present application comprises a computer program, and the computer program is executable on a processor to implement the vital sign monitoring method according to any one of the above aspects.

[0048] The one or more technical solutions described above in the embodiments of the present application have at least one of the following technical effects:

[0049] By determining the target detection position in the target area, the target object does not need to maintain a relative position relationship with the sensor when monitoring the vital sign, and the activity of the target object is not limited. The target detection position is determined in the target area, and the vital sign information of the target object can be accurately monitored. When the vital sign of the target object is abnormal, a warning can be issued in time or medical advice can be provided.

[0050] Further, by calculating the convolution and confidence of each detection position, the first detection position with a larger frequency domain amplitude of the vital sign signal is extracted, and the target detection position is selected by confidence voting. The vital sign signal strength of the target detection position is obviously higher than that of other detection positions, and the frequency domain amplitude maximum point of the target detection position can most truly and accurately represent the vital sign information of the target object.

[0051] Further, according to the vital sign signal power of the detection position in the target area, the clutter in the vital sign signal sequence of the target object is removed to remove the influence of non-target objects, and then the target detection position is accurately positioned in the vital sign signal sequence of the target object after removing the clutter.

[0052] Additional aspects and advantages of the present application will be given in part in the following description, become apparent from the following description, or be understood by practicing the present application. BRIEF DESCRIPTION OF DRAWINGS

[0053] In order to make the technical solutions of the embodiments of the present application or the prior art clearer, the accompanying drawings needed in the embodiments or prior art description will be briefly introduced. Obviously, the accompanying drawings in the following description only constitute some embodiments of the present application, and for those skilled in the art, other drawings can be obtained from these accompanying drawings without creative effort.

[0054] Figure 1 is one of the flowcharts of the vital sign monitoring method provided by the embodiments of the present application;

[0055] Figure 2 is another flowchart of the vital sign monitoring method provided by the embodiments of the present application;

[0056] Figure 3 is a schematic diagram of a target position where a target object is located, provided by the embodiments of the present application;

[0057] Figure 4 is a schematic diagram of a target region, provided by the embodiments of the present application;

[0058] Figure 5 is a respiratory spectrum diagram of a target detection position, provided by the embodiments of the present application;

[0059] Figure 6 is a structural schematic diagram of the vital sign monitoring device provided by the embodiments of the present application;

[0060] Figure 7 is a structural schematic diagram of the electronic device provided by the embodiments of the present application. DETAILED DESCRIPTION

[0061] The embodiments of the present application will be further described in detail below with reference to the accompanying drawings and embodiments. The following embodiments are used to illustrate the present application, but cannot be used to limit the scope of the present application.

[0062] In the description of the embodiments of the present application, it should be noted that the terms “first”, “second”, “third” are only used for description purpose, and cannot be understood as indicating or implying relative importance.

[0063] In the description of the present specification, the description of the terms "one embodiment", "some embodiments", "an example", "a specific example", or "some examples" and the like means that the specific features, structures, materials or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present application. In the present specification, the illustrative description of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any appropriate manner in any one or more embodiments or examples. In addition, the person skilled in the art can combine and combine the different embodiments or examples described in the present specification and the features of the different embodiments or examples without contradiction.

[0064] Vital signs, including body temperature, heart rate, respiratory rate, and blood pressure, are important indicators for physical health assessment. Vital sign monitoring is commonly used in medical health analysis, sleep monitoring, daily vital sign detection, and post-disaster rescue scenarios. Vital sign monitoring helps to timely detect abnormal life activities and provide early warning and treatment for diseases.

[0065] Common vital sign monitoring devices are contact devices that need to be attached to the human body or clothing for monitoring. These contact devices affect the quality of life and sleep quality, and are not suitable for people with sensitive skin or body wounds.

[0066] Currently, some non-contact vital sign monitoring devices have appeared. These non-contact devices are mostly based on radar systems and use electromagnetic waves to monitor vital signs by emitting and receiving echoes. However, these non-contact devices have high requirements for the position of the human body and can only monitor vital signs when facing the non-contact device or being close to it. When the human body moves or changes posture, these devices cannot accurately measure the accurate vital signs of the human body.

[0067] The following will be described in conjunction with Figures 1 to 5 The vital sign monitoring method of the embodiment of the present application is described. The execution subject of the method is the controller of the device, or the cloud, or the edge server.

[0068] As Figure 1 shown, the vital sign monitoring method of the embodiment of the present application includes steps 110 to 150.

[0069] Step 110, acquiring point cloud information of a target area.

[0070] The target object is an object that needs to be monitored for vital signs. The target object is located in the target area, and the point cloud information of the target area is acquired by the sensor to analyze the vital signs of the target object.

[0071] It is understandable that vital signs such as heart rate and respiratory rate are determined based on the rise and fall of the human chest or abdomen. The point cloud information of the target area is multi-frame point cloud information, and the rise and fall displacement of the human chest or abdomen is determined based on the multi-frame point cloud information.

[0072] In practice, the sensors that collect point cloud information can be millimeter-wave radar, ultra-wideband radar, or other sensors that can collect micro-motion point cloud information of vital signs.

[0073] Taking millimeter-wave radar as an example, which is used to acquire multi-frame point cloud information.

[0074] Millimeter-wave radar's emitted waves can penetrate materials such as plastic, wall panels, and clothing, and are unaffected by environmental conditions such as rain, fog, dust, and snow, enabling non-contact monitoring of the vital signs of target objects.

[0075] The antenna of the millimeter-wave radar transmits a linear frequency modulated continuous wave signal with a wavelength on the order of millimeters. After being reflected by the target object, the echo signal is received. The transmitted signal and the tracking signal are extracted, and the transmitted signal and the echo signal are mixed and filtered. The mixed and filtered signal is tracked in each frame to obtain the point cloud information of the target area.

[0076] In this embodiment, the formula for extracting the transmitted signal is:

[0077]

[0078] Among them, f c denoted as the operating frequency of the millimeter-wave radar, μ as the frequency modulation slope, j as the complex imaginary number, and t as time.

[0079] The formula for extracting the echo received signal is:

[0080]

[0081] Among them, delay d represents the distance between the target human body and the millimeter-wave radar, and c represents the speed of light.

[0082] Subsequently, the formula for mixing and filtering the transmitted signal and the echo signal is as follows:

[0083] In this embodiment, the target area is the signal acquisition area for monitoring the vital signs of the target object, and the target area is determined according to the location of the target object.

[0084] It should be noted that when determining the target area, the target object needs to be in a relatively stationary state. When the target object moves, the position of the target object needs to be re-determined, and then the target area needs to be re-determined.

[0085] In step 120, a vital sign signal sequence of the target object is determined based on the point cloud information of the target region.

[0086] After the target region is determined from the multiple frames of point cloud information, the vital sign signal sequence of the target object is obtained based on the point cloud information of the target region.

[0087] In this embodiment, the vital sign signal sequence of the target object is a signal sequence representing the vital sign of the target object, which is separated from the point cloud information of the target region.

[0088] For example, when monitoring the respiration rate, after the target region is determined from the multiple frames of point cloud information, a signal sequence related to the respiration rate is separated from the point cloud information of the target region as the vital sign signal sequence of the target object.

[0089] In step 130, a target detection position is determined from the target region based on the vital sign signal sequence of the target object.

[0090] In this embodiment, there are multiple detection positions in the target region, and the vital sign signal sequence of the target object is separated from the point cloud information of the target region, and each detection position has a corresponding vital sign signal sequence.

[0091] According to the corresponding vital sign signal sequence of each detection position in the target region, a target detection position is selected from the multiple detection positions in the target region, and the target detection position is one of the multiple detection positions in the target region.

[0092] The target detection position is a fluctuating position on the target object, the fluctuation of the position is related to the vital sign of the target object, and the vital sign signal sequence corresponding to the target detection position can accurately reflect the vital sign of the target object.

[0093] For example, when monitoring the respiration rate, the target detection position determined from the target region can be the abdominal position or the chest position of the target object.

[0094] For another example, when monitoring the heart rate, the target detection position determined from the target region can be the chest position of the target object.

[0095] In this embodiment, in the target region, the target detection position that can accurately reflect the vital sign of the target object is searched based on the vital sign signal sequence of the target object.

[0096] For example, after the target region is determined, the target object is centered in the target region to divide the target region into a grid, which is divided into m*n grids to obtain m*n grid points, and m and n are positive integers.

[0097] Each grid point corresponds to a detection position, and a target grid point, i.e., a target detection position, is selected according to the vital sign signal sequence of the target object at the m*n grid points.

[0098] In actual implementation, the values of m and n can be determined by the size of the target region and the grid distance, and the m*n grids are of the same size and shape.

[0099] m and n can be determined by the following formula:

[0100]

[0101]

[0102] wherein m and n are the number of horizontal and vertical points of the grid, W is the width of the target region, H is the height of the target region, R is the resolution of the millimeter wave radar, and s is a multiple of the resolution of the grid distance, which can be empirically valued, and the reference value of s can be 4 times. res

[0103] As shown in FIG. 4, the target object is centered and divided into a 4*4 grid, wherein the smiley face represents the target object. Figure 4

[0104] Step 140, determining the vital sign signal of the target detection position.

[0105] In this step, the vital sign signal of the target detection position is determined according to the vital sign signal sequence of the target detection position, and the vital sign signal of the target detection position is a signal for monitoring the vital sign of the target object.

[0106] It can be understood that the target detection position is a fluctuating position on the target object, and the fluctuation of the position is related to the vital sign of the target object. The vital sign signal sequence of the target object obtained according to the vital sign signal sequence corresponding to the target detection position can accurately reflect the vital sign of the target object.

[0107] Step 150, determining the vital sign information of the target object based on the vital sign signal of the target detection position.

[0108] In this embodiment, the target detection position is a position in the target region that can accurately reflect the vital sign of the target object, and the vital sign information of the target object can be determined according to the vital sign signal of the target detection position.

[0109] It can be understood that the vital sign signal measured at the target detection position can accurately reflect the vital sign of the target object, and the vital sign information of the target object is more real and accurate. ​​

[0110] In the related art, the non-contact monitoring device has high limitations, and when in use, the chest or other parts of the human body need to face the sensor of the non-contact monitoring device and keep a relatively close distance from the sensor. When the human body changes posture or is far away, the device cannot accurately measure the vital signs of the human body.

[0111] In the embodiment of the present application, the way to obtain multiple frames of point cloud information is non-contact, which does not cause harm to the human body and does not affect the quality of life and sleep. By determining the target area to track the target object, the target object does not need to maintain a relative positional relationship with the sensor when monitoring the vital signs, and the activity of the target object is not restricted. The target detection position is determined in the target area, and the vital sign information of the target object can be accurately monitored, which helps to issue a warning or provide medical advice in time when the vital signs of the target object are abnormal.

[0112] According to the vital sign monitoring method provided by the embodiment of the present application, by determining the target area to track the target object, the target object does not need to maintain a relative positional relationship with the sensor when monitoring the vital signs, and the activity of the target object is not restricted. The target detection position is determined in the target area, and the vital sign information of the target object can be accurately monitored, which helps to issue a warning or provide medical advice in time when the vital signs of the target object are abnormal.

[0113] In some embodiments, step 130 comprises:

[0114] Based on the vital sign signal sequence of the target object, the vital sign signal frequency of each detection position in the target area is determined.

[0115] Based on the vital sign signal frequency, the target detection position is determined.

[0116] The vital sign signal sequence of the target object is separated from the point cloud information of the target area, and each detection position in the target area has a corresponding vital sign signal sequence of the target object.

[0117] According to the vital sign signal sequence of the target object corresponding to each detection position, the vital sign signal frequency corresponding to the vital sign signal sequence of the target object of each detection position is calculated.

[0118] The vital sign signal frequency of the target object is the frequency of the vital sign signal sequence of the target object, and in actual execution, the vital sign signal frequency of the target object can be calculated by fast Fourier transform (FFT).

[0119] For example, the respiratory rate, a vital sign, is monitored.

[0120] The vital sign signal sequence of the target object separated from the point cloud information of the target region is a respiratory signal of the target object, and a vital sign frequency of the respiratory signal is calculated by fast Fourier transform, that is, a respiratory frequency.

[0121] In this embodiment, the target detection position is determined from the multiple detection positions of the target region according to the vital sign frequency of the target object at each detection position.

[0122] It can be understood that the target detection position is a fluctuation position on the target object, and the fluctuation of the fluctuation position is related to the vital sign of the target object. The vital sign frequency is a parameter reflecting the fluctuation of the vital sign signal, and the target detection position in the target region can be accurately determined according to the vital sign frequency.

[0123] For example, in actual implementation, the target detection position can be a position with the largest vital sign frequency among the multiple detection positions of the target region.

[0124] In some embodiments, the target detection position is determined based on the vital sign frequency, including:

[0125] The frequency domain amplitude and the confidence of the vital sign frequency are obtained.

[0126] Based on the frequency domain amplitude, a plurality of first detection positions in the target region are determined.

[0127] The target detection position is determined by voting the plurality of first detection positions according to the confidence.

[0128] In this embodiment, the frequency domain amplitude of each detection position can be obtained by calculating the convolution of the vital sign frequency of each detection position.

[0129] It can be understood that the convolution of the vital sign frequency of each detection position is a multiplication operation on the vital sign frequency of each detection position.

[0130] In this embodiment, the plurality of first detection positions are determined from the multiple detection positions of the target region according to the frequency domain amplitude of the vital sign frequency of each detection position.

[0131] The first detection position is a detection position with a frequency domain amplitude reaching a certain threshold in the target region, and the number of the first detection position is less than the number of all detection positions in the target region.

[0132] For example, there are 10 detection positions in the target region, and 5 first detection positions are determined according to the frequency domain amplitude of the vital sign frequency of the 10 detection positions.

[0133] It can be understood that the first detection position is a position with a larger frequency domain amplitude among multiple detection positions of the target region, and other positions except the first detection position in the target region have smaller frequency domain amplitudes. The size of the frequency domain amplitude represents the strength of the vital sign signal at the detection position, that is, the first detection position is a point in the target region where the vital sign signal reaches a certain strength, and the greater the strength of the vital sign signal, the higher the correlation with the vital sign of the target object.

[0134] In this embodiment, the target detection position is determined from the multiple first detection positions according to the confidence.

[0135] In statistics, the confidence interval of a probability sample is an interval estimate of a population parameter of the sample. The confidence interval shows the degree to which the true value of the parameter falls around the measurement result with a certain probability. The confidence interval gives the range of the confidence degree of the measured parameter, that is, the “certain probability” required above. This probability is called the confidence level or confidence.

[0136] It can be understood that, for the target region, all the detection positions in the target region constitute a complete sample, and the confidence of the vital sign frequency is the confidence of the vital sign frequency of all the detection positions in the target region.

[0137] In this embodiment, the first detection position with a larger vital sign frequency domain amplitude is extracted by calculating the convolution and confidence of each detection position, the target detection position is selected by confidence voting, the vital sign signal strength of the target detection position is obviously higher than that of other detection positions, and the frequency domain amplitude peak of the target detection position can most truly and accurately represent the vital sign information of the target object.

[0138] For example, the respiratory rate is monitored, as shown in FIG. 6, which is a respiratory spectrum corresponding to the target detection position selected by the confidence. The respiratory spectrum can accurately represent the vital sign information related to the respiratory rate of the target object. Figure 5

[0139] It can be understood that when the position and posture of the target object change, the target region needs to be reselected, and the target detection position needs to be reselected according to the confidence.

[0140] In some embodiments, step 130 comprises:

[0141] Based on the vital sign signal sequence of the target object, the vital sign signal power of each detection position in the target region is determined.

[0142] ​Remove the clutter in the vital sign signal sequence of the target object based on the vital sign signal power;

[0143] Determine the target detection position based on the vital sign signal sequence of the target object after removing the clutter.

[0144] The vital sign signal sequence of the target object is separated from the point cloud information of the target area, and each detection position in the target area has a corresponding vital sign signal sequence of the target object.

[0145] According to the vital sign signal sequence of the target object corresponding to each detection position, the vital sign signal power corresponding to the vital sign signal sequence of the target object at each detection position is calculated.

[0146] The vital sign signal power of the target object is the signal power of the vital sign signal sequence of the target object, and in actual execution, the vital sign signal power of the target object can be calculated by fast Fourier transform.

[0147] For example, the respiratory rate, a vital sign, is monitored.

[0148] The vital sign signal sequence of the target object separated from the point cloud information of the target area is the respiratory signal of the target object, and the vital sign signal power of the respiratory signal, i.e., the respiratory power, is calculated by fast Fourier transform.

[0149] In this embodiment, the clutter in the vital sign signal sequence of the target object is removed based on the vital sign signal power of the detection position in the target area to remove the influence of non-target objects, and then the target detection position is accurately positioned in the vital sign signal sequence of the target object after removing the clutter.

[0150] The clutter is an unwanted reflection source, which is generated and appears as a spatially coherent reflector in the effective bandwidth and search window. The clutter refers to the echo signal of other objects except the target object of interest, and the clutter will interfere with the signal acquisition and detection of the target object.

[0151] In some embodiments, removing the clutter in the vital sign signal sequence of the target object based on the vital sign signal power comprises:

[0152] The vital sign signal power is normalized, and the mean and variance of the probability density function of the vital sign signal power are obtained;

[0153] The clutter in the vital sign signal sequence of the target object is removed based on the mean and variance.

[0154] In this embodiment, the vital sign signal power is normalized, which can limit the vital sign signal power within a certain range, facilitate subsequent data processing, and calculate the mean and variance of the probability density function of the vital sign signal power to reflect the data difference of the vital sign signal power of each detection position.

[0155] According to the mean and variance of the vital sign signal power of each detection position, the vital sign signal power data with greater difference and greater deviation is clutter.

[0156] In actual execution, the vital sign signal power is normalized, so that Wherein, x is the vital sign signal power.

[0157] Correspondingly, the calculation formula of the mean E[X] of the probability density function of the vital sign signal power is:

[0158]

[0159] The calculation formula of the variance V[X] of the probability density function of the vital sign signal power is:

[0160]

[0161] According to the calculated mean and variance of the probability density function of the vital sign signal power, the clutter in the vital sign signal sequence of the target object is removed, and the target detection position is further determined.

[0162] In some embodiments, step 120 comprises:

[0163] Based on the point cloud information of the target region, a target phase sequence is determined;

[0164] Based on the target phase sequence, a vital sign signal sequence of a target object is separated from the point cloud information of the target region.

[0165] In this embodiment, based on the point cloud information of the target region, a target heat map of the target region is first synthesized through beamforming; based on the target heat map, a target phase sequence is determined.

[0166] Based on the point cloud information of the target region, a target heat map with distance information and azimuth information is drawn through beamforming technology, a target phase sequence is extracted from the target heat map, phase unwrapping is performed, and then a vital sign signal sequence of a target object is separated through a filter and other devices.

[0167] It can be understood that the target heat map is a heat map corresponding to the target region, there are multiple detection positions in the target region, and there are multiple detection positions in the target heat map. Multiple frames of point cloud information correspond to multiple frames of targets.

[0168] For example, each target heat map has m*n detection positions, each detection position has a region centered on it, and the region has x*y points, where x and y are positive integers, and x and y are determined by distance and azimuth angle.

[0169] The x*y points of each region are represented in the form of a complex number a+bj, where a and b are real numbers, a is called the real part of a+bj, and bj is called the imaginary part.

[0170] Suppose there are k target heat maps, and the phase is calculated for each target heat map, then there are (m*n)*(x*y)*k phase sequences, and the phase of each point in x*y points is a complex number, and the phase angle of the point is

[0171] Subsequently, the phase sequences are unwrapped, and the unwrapping makes the phase angle of the previous and next phases Δθ=θ i -θ i-1 In the value range [-π, π], the average value of the phase sequence of x*y points at each detection position is calculated, and finally there are (m*n)*k unwrapped target phase sequences.

[0172] Finally, the vital sign signal is separated according to the target phase sequence, each frame is separated by a filter, and then zero padding is performed at the tail of the time domain signal to increase the resolution in the frequency domain.

[0173] In some embodiments, step 110 includes:

[0174] Obtaining a plurality of frames of point cloud information of a space in which a target object is located;

[0175] Based on the plurality of frames of point cloud information, determining a target region in which the target object is located;

[0176] Based on the target region, determining point cloud information of the target region.

[0177] In this embodiment, the obtained plurality of frames of point cloud information includes point cloud information of the target object and the environment around the target object.

[0178] In actual execution, the sensor for obtaining the plurality of frames of point cloud information can be a millimeter wave radar, an ultra-wideband radar, or other sensors that can collect vital sign micro-motion point cloud information.

[0179] According to the plurality of frames of point cloud information, the target region in which the target object is located is determined, and the plurality of frames of point cloud information is a large range of point cloud information, and the target region is a part of the large range of point cloud information.

[0180] For example, as shown in FIG. 1, the obtained plurality of frames of point cloud information, Figure 3 Figure 3 ​The middle fan-shaped region is a scanning region of the millimeter wave radar, i.e., a region of multiple frames of point cloud information, Figure 3 The position of the smiley face in the middle fan-shaped region is a position of the target object.

[0181] From Figure 3 the multiple frames of point cloud information, a target region in which the target object is located is determined, and the target is a region of 16 grids as shown in FIG. 16. Figure 4

[0182] In some embodiments, determining the target region in which the target object is located based on the multiple frames of point cloud information includes:

[0183] determining a target position in which the target object is located based on the multiple frames of point cloud information;

[0184] determining the target region based on the target position.

[0185] In this embodiment, a target position in which the target object is located is first determined based on the multiple frames of point cloud information, and the target position is an approximate position of the target object. Then, a target region for acquiring a vital sign signal sequence of the target object is determined with the target position as the center.

[0186] It can be understood that in this embodiment, the target object is tracked according to an approximate target position in which the target object is located, the determination of the target region is independent of the posture of the target object, and after the target object moves, the target region is determined again based on the target position, so that the vital sign of the target object can be accurately monitored, and the activity and posture of the target object are no longer limited.

[0187] As shown in FIG. 16, a specific embodiment is introduced below. Figure 2

[0188] Step one: a millimeter wave radar antenna transmits a linear frequency modulation continuous wave signal with a wavelength of millimeter level, and receives a return signal after the target human body reflects the signal.

[0189] Step two: the transmitted signal and the return signal are mixed and filtered, and the signals are tracked and processed in each frame to generate point cloud data.

[0190] Step three: an approximate position of the human body is acquired, the target object is positioned when the target human body is in a relatively static state, a target region with the target position as the center is generated, and the target region is divided into m*n grids to search for a target detection position of a breathing signal.

[0191] Step four: a target heat map of a range and azimuth is drawn through a beamforming technology, each frame of the target heat map has m*n grid points, each grid point has a region with the grid point as the center, and the region has x(range)*y(azimuth) complex points.

[0192] ​​Step five: extract the echo phase sequence of each frame and calculate the phase angle.

[0193] Step six: phase unfolding is performed on the phase sequence extracted in step five, so that the phase angles of the front and back two are Δθ = θ i -θ i-1 between the value range of [-π, π].

[0194] Step seven: the respiratory signal of the human target object vital sign is obtained by separating the respiratory signal through the filter.

[0195] Step eight: the respiratory frequency and respiratory power of each detection position are calculated by fast Fourier transform, the respiratory power is normalized, the mean value and variance of the probability density function are calculated, and the clutter is removed.

[0196] Step nine: the convolution and confidence of each detection position are calculated to obtain the highest point of the frequency domain amplitude of the respiratory signal, and then the best position, that is, the target detection position, is selected by confidence voting, and the respiratory rate measured by the best position is the most accurate respiratory rate of the target object.

[0197] Wherein, when the target object moves or changes posture, etc. Body movement, reset positioning and re-vote are needed, and the processes of steps three to nine are repeated.

[0198] The vital sign monitoring device provided in the embodiment of the present application is described below, and the vital sign monitoring device described below can be correspondingly referred to the vital sign monitoring method described above.

[0199] As shown in Figure 6 The vital sign monitoring device provided in the embodiment of the present application comprises:

[0200] The millimeter wave radar 610 is used to obtain the point cloud information of the target region, and the target object to be monitored is located in the target region.

[0201] The first processing module 620 is used to determine the target region where the target object is located based on the multiple frames of point cloud information.

[0202] The first processing module 620 is used to determine the vital sign signal sequence of the target object based on the point cloud information of the target region.

[0203] The second processing module 630 is used to determine the target detection position in the target region based on the vital sign signal sequence of the target object, and the target detection position is one of the multiple detection positions in the target region.

[0204] The third processing module 640 is used to determine the vital sign signal of the target detection position.

[0205] The fourth processing module 650 is configured to determine the vital sign information of the target object based on the vital sign signal of the target detection position.

[0206] In this embodiment, the millimeter wave radar 610 is a sensor for collecting point cloud information of the target object, and further acquiring position information and posture information of the target object. In actual implementation, the millimeter wave radar 810 can be replaced by other sensors that can collect point cloud information of the target object in a non-contact monitoring manner.

[0207] According to the vital sign monitoring device provided in the embodiment of the present application, the target object is tracked by determining the target region, and the target object does not need to maintain a relative position relationship with the sensor when monitoring the vital sign, and the activity of the target object is not limited. The target detection position is determined in the target region, and full-range and more accurate vital sign monitoring under different orientations, distances and human postures is realized.

[0208] In some embodiments, the second processing module 630 is configured to determine the vital sign signal frequency of each detection position in the target region based on the vital sign signal sequence of the target object; and determine the target detection position based on the vital sign signal frequency.

[0209] In some embodiments, the second processing module 630 is configured to obtain the frequency domain amplitude and the confidence of the vital sign signal frequency.

[0210] The first detection position in the target region is determined based on the frequency domain amplitude.

[0211] The target detection position is determined by voting the first detection positions according to the confidence.

[0212] In some embodiments, the second processing module 630 is configured to determine the vital sign signal power of each detection position in the target region based on the vital sign signal sequence of the target object.

[0213] The clutter in the vital sign signal sequence of the target object is removed based on the vital sign signal power.

[0214] The target detection position is determined based on the vital sign signal sequence of the target object after the clutter is removed.

[0215] In some embodiments, the second processing module 630 is configured to normalize the vital sign signal power, and obtain the mean and variance of the probability density function of the vital sign signal power.

[0216] The clutter in the vital sign signal sequence of the target object is removed based on the mean and variance.

[0217] In some embodiments, the first processing module 620 is configured to determine the target phase sequence based on the point cloud information of the target region.

[0218] Based on the target phase sequence, the vital signs information of the target object are separated from the point cloud information of the target area.

[0219] In some embodiments, the first processing module 620 is used to synthesize a target heat map of the target area by beamforming based on the point cloud information of the target area.

[0220] Based on the target heatmap, the target phase sequence is determined.

[0221] In some embodiments, the first processing module 620 is used to acquire multi-frame point cloud information of the space where the target object is located;

[0222] Based on multi-frame point cloud information, determine the target area where the target object is located;

[0223] Based on the target region, determine the point cloud information of the target region.

[0224] In some embodiments, the first processing module 620 is used to determine the target location of the target object based on multi-frame point cloud information; and to determine the target region based on the target location, wherein the target location is at the center of the target region.

[0225] Figure 7 An example is a schematic diagram of the physical structure of an electronic device, such as... Figure 7 As shown, the electronic device may include a processor 710, a communications interface 720, a memory 730, and a communication bus 740. The processor 710, communications interface 720, and memory 730 communicate with each other via the communication bus 740. The processor 710 can call logical instructions in the memory 730 to execute a vital sign monitoring method. This method includes: acquiring point cloud information of a target area, where the target object to be monitored is located in the target area; determining a sequence of vital sign signals of the target object based on the point cloud information of the target area; determining a target detection position from the target area based on the sequence of vital sign signals of the target object, where the target detection position is one of multiple detection positions within the target area; determining the vital sign signal at the target detection position; and determining the vital sign information of the target object based on the vital sign signal at the target detection position.

[0226] In addition, the logic instructions in the memory 730 described above can be implemented in the form of software functional units and sold or used as independent products, and can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application essentially or the part that contributes to the prior art or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium, and includes several instructions for making a computer device (which can be a personal computer, a server, or a network device, etc.) execute all or part of the steps of the methods described in various embodiments of the present application. The foregoing storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk or an optical disk, and various media that can store program codes.

[0227] Further, the present application also provides a computer program product, the computer program product includes a computer program, the computer program can be stored on a non-transitory computer readable storage medium, when the computer program is executed by a processor, the computer can execute the vital sign monitoring method provided by each method embodiment described above, and the method includes: acquiring point cloud information of a target region, a target object to be monitored is located in the target region; determining a vital sign signal sequence of the target object based on the point cloud information of the target region; determining a target detection position from the target region based on the vital sign signal sequence of the target object, the target detection position is one of a plurality of detection positions in the target region; determining a vital sign signal of the target detection position; and determining vital sign information of the target object based on the vital sign signal of the target detection position.

[0228] On the other hand, the present application also provides a non-transitory computer readable storage medium having a computer program stored thereon, which, when executed by a processor, implements a vital sign monitoring method provided by each embodiment described above, and the method includes: acquiring point cloud information of a target region, a target object to be monitored is located in the target region; determining a vital sign signal sequence of the target object based on the point cloud information of the target region; determining a target detection position from the target region based on the vital sign signal sequence of the target object, the target detection position is one of a plurality of detection positions in the target region; determining a vital sign signal of the target detection position; and determining vital sign information of the target object based on the vital sign signal of the target detection position.

[0229] The device embodiments described above are merely illustrative, wherein the units described as separate components can or can not be physically separate, and the components displayed as units can or can not be physical units, i.e., can be located in one place, or can be distributed to multiple network units. Part or all of the modules can be selected to achieve the purposes of the embodiments according to actual needs. Those skilled in the art can understand and implement without creative labor.

[0230] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be realized by means of software and necessary general hardware platform, and of course can also be realized by hardware. Based on such understanding, the above technical solutions can be embodied in the form of software product, which can be stored in a computer readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes a plurality of instructions to make a computer device (which can be a personal computer, server, or network device, etc.) execute the method described in each embodiment or some part of the embodiment.

[0231] Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present application, and not to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: it can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacement to some technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

[0232] The above embodiments are only used to illustrate the present application, and not to limit the present application. Although the present application has been described in detail with reference to the embodiments, those skilled in the art should understand that various combinations, modifications or equivalent replacements of the technical solutions of the present application do not deviate from the spirit and scope of the technical solutions of the present application, and should be covered in the scope of claims of the present application.

Claims

1. A vital signs monitoring method, characterized by, The method comprises: acquiring point cloud information of a target region, wherein a target object to be monitored is located in the target region; determining a vital sign signal sequence of the target object based on the point cloud information of the target region; determining a target detection position in the target region based on the vital sign signal sequence of the target object, wherein there are multiple detection positions in the target region, and the target detection position is one of the multiple detection positions in the target region; determining a vital sign signal of the target detection position; determining vital sign information of the target object based on the vital sign signal of the target detection position, wherein the vital sign signal sequence of the target object is separated from the point cloud information of the target region, and each detection position has a corresponding vital sign signal sequence; wherein the determining of the target detection position in the target region based on the vital sign signal sequence of the target object comprises: determining a vital sign signal frequency of each detection position in the target region based on the vital sign signal sequence of the target object; determining the target detection position based on the vital sign signal frequency. wherein the determining of the target detection position based on the vital sign signal frequency comprises: acquiring a frequency domain amplitude and a confidence degree of the vital sign signal frequency; determining a plurality of first detection positions in the target region based on the frequency domain amplitude; determining the target detection position by voting the plurality of first detection positions according to the confidence degree.

2. The vital signs monitoring method of claim 1, wherein, The determining of the target detection position in the target region based on the vital sign signal sequence of the target object comprises: determining a vital sign signal power of each detection position in the target region based on the vital sign signal sequence of the target object; removing clutter in the vital sign signal sequence of the target object based on the vital sign signal power; determining the target detection position based on the vital sign signal sequence of the target object after removing the clutter.

3. The vital signs monitoring method of claim 1, wherein, The determining of the vital sign signal sequence of the target object based on the point cloud information of the target region comprises: determining a target phase sequence based on the point cloud information of the target region; separating the vital sign signal sequence of the target object from the point cloud information of the target region based on the target phase sequence.

4. The vital signs monitoring method of claim 3, wherein, The determining of the target phase sequence based on the point cloud information of the target region comprises: synthesizing a target heat map of the target region by beamforming based on the point cloud information of the target region; determining the target phase sequence based on the target heat map.

5. The vital signs monitoring method according to any of claims 1-4, characterized by, The acquiring of the point cloud information of the target region comprises: acquiring a plurality of frames of point cloud information of a space in which the target object is located; determining the target region in which the target object is located based on the plurality of frames of point cloud information; determining the point cloud information of the target region based on the target region.

6. The vital signs monitoring method of claim 5, wherein, The determining of the target region in which the target object is located based on the plurality of frames of point cloud information comprises: determining a target position in which the target object is located based on the plurality of frames of point cloud information; determining the target region based on the target position, wherein the target position is at the center of the target region.

7. A vital signs monitoring device, characterized by The method comprises: The millimeter wave radar is used to acquire point cloud information of a target area, and a target object to be monitored is located in the target area. The first processing module is configured to determine a vital sign signal sequence of the target object based on the point cloud information of the target area. The second processing module is configured to determine a target detection position in the target area based on the vital sign signal sequence of the target object, wherein a plurality of detection positions exist in the target area, and the target detection position is one of the plurality of detection positions in the target area. The third processing module is configured to determine a vital sign signal of the target detection position. The fourth processing module is configured to determine vital sign information of the target object based on the vital sign signal of the target detection position, wherein the vital sign signal sequence of the target object is separated from the point cloud information of the target area, and each detection position has a corresponding vital sign signal sequence. The second processing module is specifically configured to determine a vital sign signal frequency of each detection position in the target area based on the vital sign signal sequence of the target object, and determine the target detection position based on the vital sign signal frequency. The second processing module is specifically configured to acquire a frequency domain amplitude and a confidence degree of the vital sign signal frequency, determine a plurality of first detection positions in the target area based on the frequency domain amplitude, and determine the target detection position by voting the plurality of first detection positions according to the confidence degree.

8. An electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, The processor executes the program to implement the vital sign monitoring method of any one of claims 1 to 6. 9.A non-transitory computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to implement the vital sign monitoring method of any one of claims 1 to 6.

10. A computer program product comprising a computer program, characterized in that, The computer program is executed by the processor to implement the vital sign monitoring method of any one of claims 1 to 6.

Images