A respiration rate estimation method, apparatus, electronic device, and storage medium

Abstract

The application discloses a breathing frequency estimation method and device, electronic equipment and storage medium. The method comprises the following steps: acquiring a radar echo signal; processing the radar echo signal to obtain a range-angle spectrum; performing target human body detection on the range-angle spectrum to obtain a target point cloud spectrum; determining the number of target human bodies and the range-angle range of target human body clusters by using the range and angle of the density spectrum in the target point cloud spectrum; determining the chest cavity range of the target human bodies based on the range-angle range of the target human body clusters, and extracting the signals in the chest cavity range of the target human bodies to obtain potential breathing phases of the target human bodies; screening the potential breathing phases of the target human bodies to determine a candidate breathing phase group; and processing the candidate breathing phase group according to the number of target human bodies to determine the breathing frequency corresponding to the number of target human bodies. According to the technical scheme, the corresponding breathing frequency can be calculated in real time according to the number of people.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of radar life detection, and in particular to a respiration rate estimation method and device, electronic equipment and a storage medium. BACKGROUND

[0002] With the acceleration of the pace of life and the increase of work pressure, people pay more and more attention to their own health status. Vital signs can be used to measure the health status of the human body, and vital signs mainly refer to respiration, heart rate, blood pressure and the like, among which respiration is one of the body sign information that can directly reflect the physiological state of the human body. Therefore, it is meaningful to detect the respiration signal of the human body.

[0003] Common human respiration rate estimation methods include: (1) a respiration rate estimation method based on PSG polysomnography; (2) a respiration rate estimation method based on a visual sensor; (3) a respiration rate estimation method based on a smart sleep pillow / smart sleep mattress; (4) a respiration rate estimation method based on an audio signal; and (5) a respiration rate estimation method based on the respiration gas change characteristics of the human body.

[0004] The PSG polysomnography is the gold standard in the industry, but it is expensive and its use is complex, and it needs to be assisted by professionals for detection, which is not suitable for daily home monitoring, and it is not friendly to detection objects in special situations such as burn patients; the respiration rate estimation method based on the visual sensor needs a series of image and signal processing technologies to extract the respiration signal in the image, the camera design has privacy problems, and the method needs good hardware to support a large amount of data processing, thereby increasing the cost; the smart sleep pillow mainly converts the pressure signal into an electrical signal through the built-in pressure sensor, and obtains the respiration signal by recording and processing the collected electrical signal, and the smart sleep mattress uses an optical fiber sensor, which places the sensor under the mattress to collect the respiration signal. The accuracy of these detection methods based on smart devices is limited by the detection range; the respiration rate estimation method based on the audio signal records the human respiration audio and other noises through a sound sensor, and uses an algorithm to identify and extract the respiration sound to estimate the respiration rate. The accuracy of this method is limited by environmental factors, and the detection error greatly increases in a noisy environment; the respiration rate estimation method based on the respiration gas change characteristics of the human body detects according to the respiration gas flow rate, gas temperature and the like, and uses a mask with a built-in vortex flow meter and other sensors to measure the speed of inhaled and exhaled gas during the respiration process. This method is a contact detection method, and the experience is poor. SUMMARY

[0005] The application provides a respiration frequency estimation method and device, electronic equipment and a storage medium, which can calculate the corresponding respiration frequency in real time according to the number of people, has the advantages of protecting personal privacy, being completely non-contact, having strong penetration, being able to work all day and all year round, and being not affected by changes in external environment.

[0006] According to an aspect of the application, a respiration frequency estimation method is provided, comprising:

[0007] acquiring a radar echo signal;

[0008] processing the radar echo signal to obtain a range-angle spectrum;

[0009] performing target human body detection on the range-angle spectrum to obtain a target point cloud spectrum;

[0010] determining a target human body number and a distance-angle range of a target human body cluster using the distance and angle of a density spectrum in the target point cloud spectrum, wherein the target human body cluster is used to represent a region with greater density in the density spectrum;

[0011] based on the distance-angle range of the target human body cluster, determining a target human body chest cavity range, and extracting signals in the target human body chest cavity range to obtain a target human body potential respiration phase;

[0012] performing screening on the target human body potential respiration phase to determine a candidate respiration phase group;

[0013] processing the candidate respiration phase group according to the target human body number to determine a respiration frequency corresponding to the target human body number.

[0014] According to another aspect of the application, a respiration frequency estimation device is provided, comprising:

[0015] a radar echo signal acquisition module configured to acquire a radar echo signal;

[0016] a range-angle spectrum obtaining module configured to process the radar echo signal to obtain a range-angle spectrum;

[0017] a target point cloud spectrum obtaining module configured to perform target human body detection on the range-angle spectrum to obtain a target point cloud spectrum;

[0018] a target human body information determining module configured to determine a target human body number and a distance-angle range of a target human body cluster using the distance and angle of a density spectrum in the target point cloud spectrum, wherein the target human body cluster is used to represent a region with greater density in the density spectrum;

[0019] The target human potential respiration phase obtaining module is configured to determine a target human chest cavity range based on the distance-angle range of the target human cluster, and extract signals in the target human chest cavity range to obtain a target human potential respiration phase.

[0020] The candidate respiration phase group determining module is configured to screen the target human potential respiration phase to determine a candidate respiration phase group.

[0021] The respiration frequency determining module is configured to process the candidate respiration phase group according to the target human number to determine a respiration frequency corresponding to the target human number.

[0022] According to another aspect of the present application, an electronic device is provided, which comprises:

[0023] at least one processor; and

[0024] a memory connected to the at least one processor in communication; wherein

[0025] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to execute a respiration frequency estimation method according to any one of the embodiments of the present application.

[0026] According to another aspect of the present application, a computer readable storage medium is provided, which stores computer instructions for enabling a processor to implement a respiration frequency estimation method according to any one of the embodiments of the present application when executed by the processor.

[0027] The technical solution of the embodiments of the present application comprises the following steps: obtaining a radar echo signal; processing the radar echo signal to obtain a distance-angle spectrum; performing target human detection on the distance-angle spectrum to obtain a target point cloud spectrum; determining a target human number and a distance-angle range of a target human cluster by using the distance and angle of the density spectrum in the target point cloud spectrum; determining a target human chest cavity range based on the distance-angle range of the target human cluster, and extracting signals in the target human chest cavity range to obtain a target human potential respiration phase; screening the target human potential respiration phase to determine a candidate respiration phase group; and processing the candidate respiration phase group according to the target human number to determine a respiration frequency corresponding to the target human number. The technical solution can determine the corresponding respiration frequency according to the number of people in real time, has the advantages of protecting personal privacy, being completely non-contact, having strong penetration, being able to work all day and all year round, and being not affected by changes in external environment.

[0028] It is to be understood that the details set forth herein do not limit the scope of the embodiments of the application to the specific embodiments described. Rather, the scope of the embodiments of the application is to be defined by the appended claims. BRIEF DESCRIPTION OF DRAWINGS

[0029] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiments description. Obviously, the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained without creative labor based on these drawings.

[0030] Figure 1 is a flow chart of a respiration rate estimation method according to the first embodiment of the present application;

[0031] Figure 2 is a flow chart of a respiration rate estimation process according to the second embodiment of the present application;

[0032] Figure 3 is a schematic diagram of a respiration rate estimation process according to the third embodiment of the present application;

[0033] Figure 4 is a structural schematic diagram of a respiration rate estimation device according to the fourth embodiment of the present application;

[0034] Figure 5 is a structural schematic diagram of an electronic device implementing a respiration rate estimation method according to the fifth embodiment of the present application. DETAILED DESCRIPTION

[0035] In order to make the technical personnel in the art better understand the present application scheme, the following will combine the drawings in the embodiments of the present application, and the technical solutions in the embodiments of the present application will be described clearly and completely. Obviously, the described embodiments are only some embodiments of the present application, not all. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor should belong to the scope of protection of the present application.

[0036] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and do not necessarily describe a specific order or sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments of the application described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device including a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but can include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0037] Embodiment one

[0038] Figure 1 is a flowchart of a respiration rate estimation method according to an embodiment one of the present application, the embodiment can be applicable to the case of estimating the respiration rate of a target human body, the method can be executed by a respiration rate estimation device, the respiration rate estimation device can be realized in the form of hardware and / or software, and the respiration rate estimation device can be configured in an electronic device. As shown in Figure 1 , the method comprises:

[0039] S110, acquiring a radar echo signal.

[0040] Wherein, the radar echo signal refers to the delay of the radar transmission signal modulated by the target, and the radar antenna receives the reflected signal.

[0041] Specifically, a multi-transmit multi-receive radar can be used to transmit a linear frequency continuous wave into space, and the echo signal scattered by the target human body, the ground and other objects in space is received by the radar receiver. After mixing and ADC (Analog-to-Digital Converter) sampling, the discrete echo signal containing distance, angle and time information is obtained, i.e. the radar echo signal, which can be represented as y(m, n, k), wherein m represents the slow time sampling index, n represents the fast time sampling index, and k represents the antenna dimension sampling index.

[0042] S120, processing the radar echo signal to obtain a range-angle spectrum.

[0043] Wherein, the range-angle spectrum can be represented as P(m, l, θ), wherein l is the distance unit index, and θ is the angle.

[0044] In this embodiment, the range-angle spectrum P(m, l, θ) can be obtained by angle estimation of the radar echo signal y(m, n, k).

[0045] Optionally, the radar echo signal is processed to obtain a range-angle spectrum, including steps A1-A2:

[0046] Step A1, Fourier transform the radar echo signal in the fast time dimension to obtain a first signal;

[0047] Specifically, the received radar echo signal y(m, n, k) is Fourier transformed in the fast time dimension, and then the signal after Fourier transform is processed by a moving average clutter suppression algorithm to filter out clutter to obtain a first signal Z(m, l, k), wherein l is a range unit index.

[0048] Step A2, angle estimation of the first signal is performed by using a capon algorithm to obtain a range-angle spectrum.

[0049] The capon algorithm is a spectrum estimation algorithm commonly used in signal processing, which can suppress noise and improve signal resolution by weighting data.

[0050] In this embodiment, the capon algorithm can be used to perform angle estimation on the first signal Z(m, r, k) to obtain a range-angle spectrum P(m, l, θ).

[0051] By performing angle estimation on the radar echo signal, the breathing frequency of the target human body can be estimated based on the range-angle spectrum.

[0052] S130, target human body detection is performed on the range-angle spectrum to obtain a target point cloud spectrum.

[0053] Each point cloud of the target point cloud spectrum is composed of a range unit and an angle unit.

[0054] In this scheme, a constant false alarm detector can be used to perform target human body detection on the range-angle spectrum P(m, l, θ) to obtain a target point cloud spectrum. The ordered statistic constant false alarm rate (OS-CFAR) method can also be used to perform target human body detection to obtain a target point cloud spectrum.

[0055] S140, the range and angle of the density spectrum in the target point cloud spectrum are used to determine the number of target human bodies and the range-angle range of the target human body cluster; wherein the target human body cluster is used to represent a region with high density in the density spectrum.

[0056] In the scheme, the target human body number and the distance angle range of the target human body cluster can be determined based on the density feature. Specifically, the distance and angle of the target point cloud spectrum can be used to determine the density spectrum of the target point cloud spectrum, and the target human body number and the distance angle range of the target human body cluster can be determined according to the density spectrum of the target point cloud spectrum.

[0057] Optionally, the target human body number and the distance angle range of the target human body cluster are determined by using the distance and angle of the density spectrum in the target point cloud spectrum, including steps B1-B4.

[0058] Step B1, determining the density of each point cloud based on the distance and angle of the target point cloud spectrum;

[0059] In the embodiment, the density of each point cloud is calculated by traversing each distance unit and angle unit on the target point cloud spectrum. That is, the ratio of the number of point clouds occupied by the target human body in a certain range around the point cloud to the total number of point clouds is calculated.

[0060] Step B2, determining the density spectrum according to the density of each point cloud;

[0061] In the embodiment, the density of each point cloud can be compared with a preset threshold to determine the density spectrum. The preset threshold can be set according to the density spectrum construction requirement.

[0062] Specifically, if the density of the point cloud is less than the threshold η, it is set to 0, and if the density of the point cloud is greater than or equal to the threshold η, it is retained. The density spectrum is constructed based on the density of the retained point cloud.

[0063] Step B3, in the case where the maximum value of the density spectrum is not 0, taking the point cloud where the maximum value is located as a center point, determining the boundary of the center point, and taking the boundary of the center point as the distance angle range of the target human body cluster;

[0064] Wherein, a plurality of density points gathered together are called a cluster.

[0065] In the embodiment, the target human body cluster and the distance angle range occupied by the target human body cluster can be found based on the density spectrum.

[0066] Step B4, if the number of point clouds in the distance angle range of the target human body cluster is greater than or equal to a preset third threshold, the target human body number is determined according to the number of target human body clusters.

[0067] In the embodiment, the number of target human body clusters is the target human body number.

[0068] Further, the maximum value on the density spectrum is found, if the maximum value of the density spectrum is 0, there is no target human cluster; if the maximum value of the density spectrum is not 0, there is a possible target human cluster, and the point cloud at the maximum value is taken as the center to find the upper, lower, left and right boundaries of the cluster as the range occupied by the cluster. The number of point clouds in the range occupied by the possible target human cluster is calculated, and if the number is greater than a threshold value ξ, the cluster is considered to be the target human cluster, and then the point clouds in the range occupied by the cluster are all set to 0. Repeat the step until no cluster is found on the density spectrum, at this time the number of target human clusters and the distance and angle range occupied by the target human clusters in the density spectrum can be obtained.

[0069] Based on the distance and angle of the target point cloud spectrum, the number of target human bodies and the distance and angle range of the target human cluster are determined, the corresponding respiratory frequency can be calculated in real time according to the number of target human bodies, and the accuracy of the respiratory frequency can be improved.

[0070] S150, based on the distance and angle range of the target human cluster, the chest cavity range of the target human body is determined, and the signal in the chest cavity range of the target human body is extracted to obtain the potential respiratory phase of the target human body.

[0071] In this embodiment, for the distance and angle range where each target human cluster i is located, the maximum energy value on the distance and angle spectrum P(m, l, θ) is searched as the distance and angle of the chest cavity position, denoted as A plurality of distance units before and after the distance unit are selected as the chest cavity range of the human target l∈[a i ,b i ]. Wherein, Δl is the upper and lower boundaries centered on the distance unit index of the maximum value.

[0072] In this scheme, after determining the chest cavity range of the target human body, the signal in the chest cavity range is extracted by using a beamformer, and then the potential respiratory phase of the target human body i in the chest cavity range is extracted from the signal

[0073] Alternatively, the differential and cross-multiplication (DACM) method can also be used to extract the signal in the chest cavity range.

[0074] In this embodiment, the estimated target human potential respiratory phase may have a drift phenomenon at this time. Therefore, the target human potential respiratory phase can be corrected to improve the accuracy of the target human potential respiratory phase. Specifically, all peak values and valley values of the target human potential respiratory phase are found, and the median values of adjacent peak values and valley values are taken. The line connecting these median values is the trend of the phase. Taking the median value of the first peak value and the valley value as the reference, the difference between the second median value and the first median value is obtained. Then, the values between the two median values are all added to the difference. In this way, the last median value is calculated, and the modified target human potential respiratory phase is finally obtained.

[0075] S160, screening the target human potential respiratory phase to determine a candidate respiratory phase group.

[0076] In this scheme, the target human potential respiratory phase features can be compared with the preset respiratory phase threshold by setting the respiratory phase threshold, so as to screen the candidate respiratory phase group from the target human potential respiratory phase. The target human potential respiratory phase features can be phase shape similarity features and respiratory intensity features. The phase shape similarity features are obtained by calculating the similarity coefficient between the shapes of adjacent distance units of the target human potential respiratory phase; and the respiratory intensity features are obtained by calculating the respiratory energy intensity of the target human potential respiratory phase.

[0077] S170, processing the candidate respiratory phase group according to the target human number to determine a respiratory frequency corresponding to the target human number.

[0078] In this scheme, the respiratory phase of the current target human can be screened from the candidate respiratory phase group according to the target human number, and the frequency value in the respiratory phase of the current target human is taken as the respiratory frequency of the current target human.

[0079] The technical scheme of the embodiment of the present application comprises the following steps: acquiring a radar echo signal; processing the radar echo signal to obtain a range-angle spectrum; performing target human detection on the range-angle spectrum to obtain a target point cloud spectrum; determining the target human number and the distance-angle range of the target human cluster by using the distance and angle of the density spectrum in the target point cloud spectrum; determining the target human thoracic cavity range based on the distance-angle range of the target human cluster, and extracting the signals in the target human thoracic cavity range to obtain a target human potential respiratory phase; screening the target human potential respiratory phase to determine a candidate respiratory phase group; and processing the candidate respiratory phase group according to the target human number to determine a respiratory frequency corresponding to the target human number. By executing this technical scheme, the corresponding respiratory frequency can be calculated in real time according to the number of people, which has the advantages of protecting personal privacy, being completely non-contact, having strong penetration, being able to work all day and all year round, and being not affected by changes in external environment.

[0080] Embodiment Two

[0081] Figure 2 A flow chart of a breathing rate estimation process provided for Embodiment Two of the present application, the relationship between this embodiment and the above-mentioned embodiment is a detailed description of the candidate breathing phase group determination process. As shown in FIG. 2, the method comprises: Figure 2

[0082] S210, obtaining a radar echo signal.

[0083] S220, processing the radar echo signal to obtain a range-angle spectrum.

[0084] S230, performing target human body detection on the range-angle spectrum to obtain a target point cloud spectrum.

[0085] S240, determining the number of target human bodies and the range-angle range of target human body clusters using the range and angle of the density spectrum in the target point cloud spectrum; wherein the target human body cluster is used to represent a region with higher density in the density spectrum.

[0086] S250, determining the chest cavity range of the target human body based on the range-angle range of the target human body cluster, and extracting the signal in the chest cavity range of the target human body to obtain the potential breathing phase of the target human body.

[0087] S260, calculating the similarity coefficient between the shapes of the potential breathing phases of the target human body at adjacent ranges to obtain a phase shape similarity feature, and calculating the breathing energy intensity of the potential breathing phase of the target human body to obtain a breathing intensity feature.

[0088] In this scheme, the phase shape similarity feature can be calculated using the following formula:

[0089]

[0090] wherein e i,l is the phase shape similarity feature of the lth range unit and the l+1th range unit of the ith target human body cluster.

[0091] In this embodiment, the breathing intensity feature can be calculated using the following formula:

[0092]

[0093] wherein h i,l is the breathing intensity feature of the lth range unit of the ith target human body cluster, is the power spectrum of the potential breathing phase of the lth range unit of the ith target human body cluster, f is the frequency, is the frequency range of breathing (usually 0.1-0.8 Hz), and T​r is a slow time sampling interval.

[0094] Further, the phase shape similarity feature e of the target human body cluster i is sorted from large to small, and written in the form of a vector as i,l is sorted from large to small, and written in the form of a vector as The respiratory intensity feature of the target human body cluster i is sorted from large to small, and written in the form of a vector as

[0095] S270, based on the phase shape similarity feature and the respiratory intensity feature, screening the target human body potential respiratory phase to determine a candidate respiratory phase group.

[0096] In the embodiment, the phase shape similarity feature and the respiratory intensity feature can be compared with a preset threshold, so as to realize screening of the target human body potential respiratory phase.

[0097] Optionally, based on the phase shape similarity feature and the respiratory intensity feature, screening the target human body potential respiratory phase to determine a candidate respiratory phase group includes steps C1-C3:

[0098] Step C1, determining the number of phase shape similarity feature values greater than a preset first threshold value;

[0099] The first threshold value can be set according to the candidate respiratory phase group screening requirement. Optionally, the first threshold value can be set as

[0100] Step C2, in the case where the number is greater than or equal to a preset second threshold value, screening a candidate respiratory phase group from the target human body potential respiratory phase according to the second threshold value;

[0101] The second threshold value can be set according to the candidate respiratory phase group screening requirement. Optionally, the second threshold value can be set as N P . For example, N P can be set as 5, or N P can be set as 8.

[0102] Specifically, when the number of phase shape similarity feature values greater than the threshold value is greater than or equal to N P , the target human body potential respiratory phase corresponding to the first N i distance units in e P is selected as the candidate respiratory phase group.

[0103] Step C3: If the number is less than a preset second threshold, select a first candidate respiratory phase group from the potential respiratory phases of the target human body according to the number; and select a second candidate respiratory phase group from the potential respiratory phases of the target human body according to the difference between the second threshold and the number; and use the first candidate respiratory phase group and the second candidate respiratory phase group as candidate respiratory phase groups.

[0104] Furthermore, the median of the respiratory phase shape similarity feature was greater than the threshold. The number of N b 1, and N b <N p First select e i Middle front N b The potential respiratory phase of the target human body corresponding to each distance unit is then selected, and the respiratory intensity feature h is further selected. i Middle front N p -N b The potential respiratory phases of the target human body corresponding to each distance unit are collectively formed into a candidate respiratory phase group.

[0105] By utilizing the similarity features of respiratory phase shapes and candidate respiratory phase groups, candidate respiratory phase groups can be screened from the potential respiratory phases of the target human body, which can improve the accuracy of candidate respiratory phase group screening.

[0106] S280. Based on the number of target human bodies, process the candidate respiratory phase group to determine the respiratory frequency corresponding to the number of target human bodies.

[0107] The technical solution of this invention involves acquiring radar echo signals; processing the radar echo signals to obtain a range-angle spectrum; performing target human detection on the range-angle spectrum to obtain a target point cloud spectrum; using the distance and angle of the density spectrum in the target point cloud spectrum to determine the number of target human bodies and the range-angle range of target human body clusters; determining the chest cavity range of the target human bodies based on the range-angle range of the target human body clusters, and extracting signals within the chest cavity range to obtain the potential respiratory phases of the target human bodies; screening the potential respiratory phases of the target human bodies based on phase shape similarity features and respiratory intensity features to determine candidate respiratory phase groups; and processing the candidate respiratory phase groups according to the number of target human bodies to determine the respiratory frequency corresponding to the number of target human bodies. By implementing this technical solution, using respiratory phase shape similarity features and candidate respiratory phase groups to screen candidate respiratory phase groups from the potential respiratory phases of target human bodies, the accuracy of candidate respiratory phase group screening can be improved. Furthermore, it can calculate the corresponding respiratory frequency in real time based on the number of people, has low computational complexity, low processor performance requirements, and advantages such as protecting personal privacy, being completely non-contact, having strong penetration, and being able to work around the clock and unaffected by changes in the external environment.

[0108] Embodiment three

[0109] Figure 3 A schematic diagram of a breathing frequency estimation process provided for embodiment three of the present application, the relationship between this embodiment and the above-mentioned embodiments is a detailed description of the breathing frequency calculation process. As shown in the figure, the method comprises: Figure 3

[0110] S310, radar echo signals are acquired.

[0111] S320, the radar echo signals are processed to obtain a range-angle spectrum.

[0112] S330, target human body detection is performed on the range-angle spectrum to obtain a target point cloud spectrum.

[0113] S340, the range and angle of the density spectrum in the target point cloud spectrum are used to determine the number of target human bodies and the range-angle range of a target human body cluster; wherein the target human body cluster is used to represent a region with greater density in the density spectrum.

[0114] S350, based on the range-angle range of the target human body cluster, the chest cavity range of the target human body is determined, and signals in the chest cavity range of the target human body are extracted to obtain a target human body potential breathing phase.

[0115] S360, the target human body potential breathing phase is screened to determine a candidate breathing phase group.

[0116] S370, in the case where the number of target human bodies is one, the first candidate breathing phase in the candidate breathing phase group is taken as the breathing phase of the target human body, and the maximum frequency value of the breathing phase is calculated to determine the breathing frequency of the target human body.

[0117] Specifically, when there is only one person in the scene, the first candidate breathing phase in the candidate breathing phase group is screened as the breathing phase of the target human body, and then the maximum frequency value in the breathing phase is calculated, which is the breathing frequency of the target human body. Wherein, the maximum frequency value in the breathing phase can be solved by using FFT (Fast Fourier Transform), frequency-time phase regression (FTPR) and other methods.

[0118] ​S380. When there are two target human bodies, the frequency of the candidate respiratory phase group is calculated to obtain the candidate respiratory frequency group of the first target human body and the second target human body. The candidate respiratory frequency group of the first target human body and the second target human body is calculated according to the preset respiratory frequency matching criterion to determine the respiratory frequency of the first target human body and the second target human body.

[0119] In this embodiment, when there are two people in the scene, the frequencies of the candidate respiratory phase groups are calculated separately to obtain the candidate respiratory frequency groups of the first target human and the second target human, denoted as... and

[0120] In this scheme, after obtaining the candidate respiratory frequency groups of the first and second target human bodies, the respiratory frequencies of the first and second target human bodies can be obtained by analyzing the Euclidean distance between the corresponding positions of the two candidate respiratory frequency groups.

[0121] Optionally, the candidate respiratory frequency groups of the first target human body and the second target human body are calculated according to a preset respiratory frequency matching criterion to determine the respiratory frequencies of the first target human body and the second target human body, including:

[0122] The respiratory rates of the first and second target humans are calculated using the following formula:

[0123]

[0124]

[0125] Among them, f A and f B This indicates the respiratory rates of the first and second target human bodies. and It is the initial frequency of the first and second target human bodies. and This represents the candidate respiratory rate groups for the first and second target human bodies.

[0126] In this embodiment, when the respiratory rate is estimated for the first time, and The initial frequency is determined by calculating the Euclidean distance between the corresponding positions of the candidate respiratory frequency groups of the first and second target human bodies, and selecting the frequency corresponding to the farthest Euclidean distance as the initial frequency; when the respiratory frequency is not estimated for the first time, and This is the last estimated final respiratory rate value. For f A and f B The final breathing rates of targets A and B are obtained using a Kalman filter. and

[0127] According to the target human number, the respiratory frequency determination can overcome the problem of mutual influence of respiratory signals caused by different individual respiratory intensities and relative position differences, can realize two-person respiratory frequency detection in different postures and different distances, and has the characteristics of high robustness and high precision.

[0128] The technical scheme of the embodiment of the application comprises the following steps: obtaining a radar echo signal; processing the radar echo signal to obtain a range-angle spectrum; performing target human detection on the range-angle spectrum to obtain a target point cloud spectrum; determining the number of target humans and the range-angle range of a target human cluster by using the range and angle of the density spectrum in the target point cloud spectrum; determining the chest cavity range of the target human based on the range-angle range of the target human cluster, and extracting the signal in the chest cavity range of the target human to obtain a potential respiratory phase of the target human; screening the potential respiratory phase of the target human to determine a candidate respiratory phase group; and processing the candidate respiratory phase group according to the number of target humans to determine the respiratory frequency corresponding to the number of target humans. By executing the technical scheme, the respiratory frequency is determined according to the number of target humans, which can overcome the problem of mutual influence of respiratory signals caused by different individual respiratory intensities and relative position differences, can realize two-person respiratory frequency detection in different postures and different distances, has the characteristics of high robustness and high precision, has low computational complexity, has low requirements on processor performance, has the advantages of protecting personal privacy, being completely non-contact, having strong penetration, being able to work all day and all year round, and being unaffected by changes in external environment.

[0129] In the present scheme, the radar can be set to have a height of 0.8 m from the bed head, an inclination angle of 45°, and an undetermined distance from the chest cavity of the target human. The respiratory frequency obtained by the experiment is compared with the respiratory frequency obtained by the physiological recorder of the American BIOPAC company.

[0130] For single-person experiments, there are three cases of the position of a person on a bed (located in the middle of the bed, located 20 cm away from the middle of the bed, and located 40 cm away from the middle of the bed), and two sleeping postures (lying flat and lying on one side) are considered at each position. The average accuracy of the respiratory frequency obtained by the above method in these cases is 97.3%.

[0131] For the double-person experiment, there are 5 cases of distance between the two persons (0 cm, 20 cm, 40 cm, 60 cm and 80 cm), 4 cases of sleeping posture of the two persons (both lying flat, both lying on one's side, one lying flat and the other lying on one's side, and one lying on one's side and the other lying flat), and the positions of the two persons on the bed are arbitrary and both lying flat. The average accuracy of the respiration rate obtained by the above method in these cases is 97.2%.

[0132] From the above experiment, it can be seen that the present scheme has high accuracy and strong robustness for different postures and distances of the target on the bed.

[0133] Embodiment Four

[0134] Figure 4 A structure diagram of a respiration rate estimation device provided for Embodiment Four of the present application. As shown in the figure, the device comprises: Figure 4

[0135] The radar echo signal acquisition module 410 is configured to acquire a radar echo signal.

[0136] The distance-angle spectrum obtaining module 420 is configured to process the radar echo signal to obtain a distance-angle spectrum.

[0137] The target point cloud spectrum obtaining module 430 is configured to perform target human body detection on the distance-angle spectrum to obtain a target point cloud spectrum.

[0138] The target human body information determining module 440 is configured to determine the number of target human bodies and the distance-angle range of a target human body cluster by using the distance and angle of the density spectrum in the target point cloud spectrum, wherein the target human body cluster is used to represent a region with relatively high density in the density spectrum.

[0139] The target human body potential respiration phase obtaining module 450 is configured to determine the chest cavity range of the target human body based on the distance-angle range of the target human body cluster, and extract the signal in the chest cavity range of the target human body to obtain a target human body potential respiration phase.

[0140] The candidate respiration phase group determining module 460 is configured to screen the target human body potential respiration phase to determine a candidate respiration phase group.

[0141] The respiration rate determining module 470 is configured to process the candidate respiration phase group according to the number of target human bodies to determine the respiration rate corresponding to the number of target human bodies.

[0142] Optionally, the candidate respiration phase group determining module 460 comprises: ​

[0143] a feature calculation sub-module, configured to calculate a similarity coefficient between target human potential respiratory phase shapes of adjacent distances, to obtain a phase shape similarity feature, and to calculate a respiratory energy intensity of the target human potential respiratory phase, to obtain a respiratory intensity feature;

[0144] a candidate respiratory phase group determination sub-module, configured to filter the target human potential respiratory phase based on the phase shape similarity feature and the respiratory intensity feature, to determine a candidate respiratory phase group.

[0145] Optionally, the candidate respiratory phase group determination sub-module is specifically configured to:

[0146] determine a number of values greater than a preset first threshold in the phase shape similarity feature;

[0147] in a case where the number is greater than or equal to a preset second threshold, filter a candidate respiratory phase group from the target human potential respiratory phase according to the second threshold;

[0148] in a case where the number is less than the preset second threshold, filter a first candidate respiratory phase group from the target human potential respiratory phase according to the number, and filter a second candidate respiratory phase group from the target human potential respiratory phase according to a difference between the second threshold and the number; and take the first candidate respiratory phase group and the second candidate respiratory phase group as the candidate respiratory phase group.

[0149] Optionally, the respiratory frequency determination module 470 comprises:

[0150] a respiratory frequency determination sub-module, configured to, in a case where the number of target humans is one, take a first candidate respiratory phase in the candidate respiratory phase group as a respiratory phase of the target human, and calculate a maximum frequency value of the respiratory phase, to determine a respiratory frequency of the target human;

[0151] a respiratory frequency calculation sub-module, configured to, in a case where the number of target humans is two, calculate frequencies of the candidate respiratory phase group, to obtain a candidate respiratory frequency group of a first target human and a second target human, and calculate the candidate respiratory frequency group of the first target human and the second target human according to a preset respiratory frequency matching criterion, to determine respiratory frequencies of the first target human and the second target human.

[0152] Optionally, the respiratory frequency calculation sub-module is specifically configured to:

[0153] calculate the respiratory frequencies of the first target human and the second target human by using the following formula:

[0154]

[0155]

[0156] wherein f A and f B denote the breathing frequencies of the first target human body and the second target human body, and are initial frequencies of the first target human body and the second target human body, and denote candidate breathing frequency groups of the first target human body and the second target human body.

[0157] Optionally, the target human body information determination module 440 is specifically configured to:

[0158] determine the density of each point cloud based on the distance and angle of the target point cloud spectrum;

[0159] determine a density spectrum according to the density of each point cloud;

[0160] in a case where the maximum value of the density spectrum is not 0, determine a boundary of a point cloud at which the maximum value is located as a center point, and take the boundary of the center point as a distance-angle range of a target human body cluster;

[0161] if the number of point clouds in the distance-angle range of the target human body cluster is greater than or equal to a preset third threshold value, determine the number of target human bodies according to the number of target human body clusters.

[0162] Optionally, the distance-angle spectrum obtaining module 420 is specifically configured to:

[0163] perform Fourier transform on the radar echo signal in the fast time dimension to obtain a first signal;

[0164] perform angle estimation on the first signal by using a capon algorithm to obtain a distance-angle spectrum.

[0165] The breathing frequency estimation device provided in the embodiment of the present application can execute the breathing frequency estimation method provided in any embodiment of the present application, and has the corresponding function modules and beneficial effects of the execution method.

[0166] Embodiment five

[0167] Figure 5A structural diagram of an electronic device 10 that can be used to implement embodiments of the present application is shown. The electronic device is intended to represent various forms of digital computers, such as laptops, desktops, tablets, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device can also represent various forms of mobile devices, such as personal digital assistants, cellular telephones, smartphones, wearable devices (e.g., headsets, glasses, watches, etc.), and other similar computing devices. The components shown here, their connections and relationships, and their functions, are meant to be examples only, and are not intended to limit the implementations of the present application described and / or claimed in this document.

[0168] As shown in Figure 5 The electronic device 10 includes at least one processor 11, and a memory, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., communicatively connected to the at least one processor 11, where the memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes according to the computer programs stored in the read-only memory (ROM) 12 or loaded into the random access memory (RAM) 13 from the storage unit 18. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0169] Various components in the electronic device 10 are connected to the I / O interface 15, including an input unit 16, such as a keyboard, a mouse, etc., an output unit 17, such as various types of displays, a speaker, etc., a storage unit 18, such as a magnetic disk, an optical disk, etc., and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network, such as the Internet, and / or various telecommunication networks.

[0170] The processor 11 can be various general and / or special purpose processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 performs various methods and processes described above, such as a respiration rate estimation method.

[0171] In some embodiments, a respiration rate estimation method can be implemented as a computer program tangibly embodied in a computer readable storage medium, e.g., storage unit 18. In some embodiments, parts or all of the computer program can be loaded and / or installed onto electronic device 10 via, e.g., ROM 12 and / or communication unit 19. When the computer program is loaded onto RAM 13 and executed by processor 11, one or more steps of a respiration rate estimation method as described above can be performed. Alternatively, in other embodiments, processor 11 can be configured to perform a respiration rate estimation method by other means, e.g., with the aid of firmware.

[0172] Various implementations of the systems and techniques described above can be realized in digital electronic circuitry, integrated circuitry, a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), a system on a chip (SOC), a programmable logic device (PLD), a computer hardware, firmware, software, and / or combinations thereof. These various implementations can include implementation in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which can be special or general purpose, coupled to receive data and instructions from, and to transmit data and instructions to, a storage system, at least one input device, and at least one output device.

[0173] Computer programs used to implement the processes of the present application can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the computer program, when executed, can implement the functions / acts specified in the flowcharts and / or block diagrams. The computer program can be executed entirely on a machine, partially on a machine, partially on a machine as part of a standalone software package, partially on a machine and partially on a remote machine or entirely on a remote machine or server.

[0174] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0175] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0176] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0177] The computing system can include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system, to solve the defects of large management difficulty and weak business scalability in traditional physical host and VPS service.

[0178] It should be understood that the various forms of flow shown above can be reordered, added to, or have steps deleted. For example, the steps described in the present application can be performed in parallel, in series, or in a different order, as long as the desired results of the technical solutions of the present application can be achieved, which are not limited herein.

[0179] The above detailed description does not constitute a limitation on the protection scope of the present application. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent replacements, and improvements made within the spirit and principles of the present application shall be included in the protection scope of the present application.

Claims

1. A method for estimating respiratory rate, characterized in that, include: Acquire radar echo signals; The radar echo signal is processed to obtain the range angle spectrum; Target human detection is performed on the distance angle spectrum to obtain the target point cloud spectrum; The number of target human bodies and the range of distance and angle of target human body clusters are determined by using the distance and angle of the density spectrum in the target point cloud spectrum; wherein, the target human body clusters are used to characterize the regions with higher density in the density spectrum. Based on the distance and angle range of the target human body cluster, the range of the target human body's chest cavity is determined, and the signal within the range of the target human body's chest cavity is extracted to obtain the potential respiratory phase of the target human body. The potential respiratory phases of the target human body are screened to determine candidate respiratory phase groups; Based on the number of target human bodies, the candidate respiratory phase groups are processed to determine the respiratory frequency corresponding to the number of target human bodies; Specifically, based on the number of target human bodies, the candidate respiratory phase groups are processed to determine the respiratory frequency corresponding to the number of target human bodies, including: When there is only one target human body, the first candidate respiratory phase in the candidate respiratory phase group is taken as the respiratory phase of the target human body, and the maximum frequency value of the respiratory phase is calculated to determine the respiratory frequency of the target human body. When there are two target human bodies, the frequency of the candidate respiratory phase group is calculated to obtain the candidate respiratory frequency group of the first target human body and the second target human body. The candidate respiratory frequency group of the first target human body and the second target human body is calculated according to the preset respiratory frequency matching criterion to determine the respiratory frequency of the first target human body and the second target human body. The process includes calculating the candidate respiratory frequency groups of the first and second target humans according to a preset respiratory frequency matching criterion to determine the respiratory frequencies of the first and second target humans, including: The respiratory rates of the first and second target humans are calculated using the following formula: ； ； in, and This indicates the respiratory rates of the first and second target human bodies. and It is the initial frequency of the first and second target human bodies. and This represents the candidate respiratory rate groups for the first and second target human bodies.

2. The method according to claim 1, characterized in that, The potential respiratory phases of the target human body are screened to determine candidate respiratory phase groups, including: Calculate the similarity coefficient between the potential respiratory phase shapes of adjacent target human bodies to obtain the phase shape similarity feature, and calculate the respiratory energy intensity of the potential respiratory phase of the target human body to obtain the respiratory intensity feature; Based on the phase shape similarity feature and the breathing intensity feature, the potential breathing phases of the target human body are screened to determine the candidate breathing phase group.

3. The method according to claim 2, characterized in that, Based on the phase shape similarity features and the respiratory intensity features, the potential respiratory phases of the target human body are screened to determine candidate respiratory phase groups, including: Determine the number of phase shape similarity features whose median value is greater than a preset first threshold; If the number is greater than or equal to a preset second threshold, candidate respiratory phase groups are selected from the potential respiratory phases of the target human body according to the second threshold. If the number is less than a preset second threshold, a first candidate respiratory phase group is selected from the potential respiratory phases of the target human body based on the number; and a second candidate respiratory phase group is selected from the potential respiratory phases of the target human body based on the difference between the second threshold and the number; the first candidate respiratory phase group and the second candidate respiratory phase group are used as candidate respiratory phase groups.

4. The method according to claim 1, characterized in that, Using the distance and angle of the density spectrum in the target point cloud spectrum, the number of target human bodies and the range of distance and angle for target human body clusters are determined, including: The density of each point cloud is determined based on the distance and angle of the target point cloud spectrum; Determine the density spectrum based on the density of each point cloud; When the maximum value of the density spectrum is not 0, the point cloud where the maximum value is located is taken as the center point, the boundary of the center point is determined, and the boundary of the center point is taken as the distance angle range of the target human body cluster. If the number of point clouds within the distance angle range of the target human body cluster is greater than or equal to a preset third threshold, then the number of target human bodies is determined based on the number of target human body clusters.

5. The method according to claim 1, characterized in that, The radar echo signal is processed to obtain a range angle spectrum, including: The radar echo signal is subjected to a Fourier transform in the fast time dimension to obtain the first signal; The first signal is used to estimate its angle using the Capon algorithm to obtain the range-angle spectrum.

6. A respiratory rate estimation device, characterized in that, include: Radar echo signal acquisition module, used to acquire radar echo signals; The range angle spectrum acquisition module is used to process the radar echo signal to obtain the range angle spectrum; The target point cloud spectrum acquisition module is used to perform target human body detection on the distance angle spectrum to obtain the target point cloud spectrum; The target human information determination module is used to determine the number of target human bodies and the distance and angle range of target human body clusters by using the distance and angle of the density spectrum in the target point cloud spectrum; wherein, the target human body cluster is used to characterize the region with higher density in the density spectrum; The target human potential respiratory phase acquisition module is used to determine the range of the target human chest cavity based on the distance and angle range of the target human cluster, and extract the signal within the range of the target human chest cavity to obtain the target human potential respiratory phase. The candidate respiratory phase group determination module is used to screen the potential respiratory phases of the target human body and determine the candidate respiratory phase group. The respiratory rate determination module is used to process the candidate respiratory phase groups according to the number of target human bodies and determine the respiratory rate corresponding to the number of target human bodies; The respiratory rate determination module includes: The respiratory rate determination submodule is used to determine the respiratory rate of the target human body by taking the first candidate respiratory phase in the candidate respiratory phase group as the respiratory phase of the target human body when the number of target human bodies is one, and calculating the maximum frequency value of the respiratory phase. The respiratory rate calculation submodule is used to calculate the frequency of the candidate respiratory phase group when there are two target human bodies, to obtain the candidate respiratory rate group of the first target human body and the second target human body, and to calculate the candidate respiratory rate group of the first target human body and the second target human body according to the preset respiratory rate matching criterion, so as to determine the respiratory rate of the first target human body and the second target human body. The respiratory rate calculation submodule is specifically used for: The respiratory rates of the first and second target humans are calculated using the following formula: ； ； in, and This indicates the respiratory rates of the first and second target human bodies. and It is the initial frequency of the first and second target human bodies. and This represents the candidate respiratory rate groups for the first and second target human bodies.

7. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform a respiratory rate estimation method according to any one of claims 1-5.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute a respiratory rate estimation method according to any one of claims 1-5.

Images