Millimeter wave radar waveform data processing method and system

Abstract

The present disclosure provides a millimeter wave radar waveform data processing method and system, belonging to the technical field of radar data processing, which comprises: performing time-frequency analysis on multiple groups of waveform arrays to obtain multiple image groups and multiple micro-Doppler features; the multiple groups of waveform arrays are obtained based on multiple millimeter wave radars monitoring a target area; generating a target identity based on target motion information and target micro-Doppler features; the target motion information is obtained based on multiple image groups identifying target personnel in the target area, and the target micro-Doppler feature is calculated based on multiple micro-Doppler features; and tracking the trajectory of the target personnel based on the target identity. The millimeter wave radar waveform data processing method and system provided by the present disclosure can analyze the waveform data of the millimeter wave radar and improve the accuracy of tracking the trajectory of the personnel.

Description

TECHNICAL FIELD

[0001] The present disclosure belongs to the technical field of radar data processing, and more particularly to a millimeter wave radar waveform data processing method and system. BACKGROUND

[0002] In the field of modern intelligent buildings and security monitoring, there is an increasing demand for accurate tracking of indoor personnel. With the advancement of building intelligence, whether it is large commercial complexes, office buildings, or public buildings such as hospitals and schools, there is a greater focus on personnel movement within the internal space to achieve efficient resource management, safety assurance, and personalized services.

[0003] However, the accuracy of analyzing and processing the waveform data received by the radar is currently low, which results in ineffective tracking of personnel. Therefore, an accurate and reliable millimeter wave radar waveform data processing method is needed to improve the accuracy and reliability of personnel tracking. SUMMARY

[0004] The purpose of the present disclosure is to provide a millimeter wave radar waveform data processing method and system to improve the accuracy and reliability of personnel trajectory tracking through analysis and processing of millimeter wave radar waveform data.

[0005] In a first aspect, the present disclosure provides a millimeter wave radar waveform data processing method, comprising:

[0006] performing time-frequency analysis on multiple groups of waveform arrays to obtain multiple image groups and multiple micro-Doppler features; the multiple groups of waveform arrays are obtained based on monitoring a target area by multiple millimeter wave radars;

[0007] generating a target identity based on target motion information and target micro-Doppler features; the target motion information is obtained by identifying target personnel in the target area based on the multiple image groups, and the target micro-Doppler features are calculated based on the multiple micro-Doppler features;

[0008] tracking the trajectory of the target personnel based on the target identity.

[0009] In a second aspect, the present disclosure provides a millimeter wave radar waveform data processing system, comprising:

[0010] a waveform analysis module configured to perform time-frequency analysis on multiple groups of waveform arrays to obtain multiple image groups and multiple micro-Doppler features; the multiple groups of waveform arrays are obtained based on monitoring a target area by multiple millimeter wave radars;

[0011] The identity generation module is configured to generate a target identity based on target motion information and target micro-Doppler features. The target motion information is obtained by identifying a target person in a target region based on a plurality of image groups, and the target micro-Doppler features are calculated based on a plurality of micro-Doppler features.

[0012] The trajectory tracking module is configured to track the trajectory of the target person based on the target identity.

[0013] In a third aspect, an electronic device is provided, which includes a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, the steps of the millimeter wave radar waveform data processing method described above are implemented.

[0014] In a fourth aspect, a computer-readable storage medium is provided, which stores a computer program. When the computer program is executed by a processor, the steps of the millimeter wave radar waveform data processing method described above are implemented.

[0015] The millimeter wave radar waveform data processing method and system provided by the embodiments of the present disclosure have the following advantages:

[0016] The present disclosure determines the motion information of the target person and the micro-Doppler features related to the motion of the target person by performing time-frequency analysis on the waveforms received by the radar, and then determines an identity for the target person based on the motion information and the micro-Doppler features. The identity is more closely related to the target person, and thus more accurate tracking of the target person is achieved. BRIEF DESCRIPTION OF DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description are only some embodiments of the present disclosure, and other drawings can be obtained by those skilled in the art without creative labor.

[0018] Figure 1 A flowchart of the millimeter wave radar waveform data processing method provided by an embodiment of the present disclosure is shown in the figure.

[0019] Figure 2 A schematic diagram of the principle of determining the position of the target person provided by an embodiment of the present disclosure is shown in the figure.

[0020] Figure 3 A structural block diagram of the millimeter wave radar waveform data processing system provided by an embodiment of the present disclosure is shown in the figure.

[0021] Figure 4 A schematic block diagram of the electronic device provided by an embodiment of the present disclosure is shown in the figure. DETAILED DESCRIPTION

[0022] In the following description, specific details such as specific system structures and techniques are provided for purposes of illustration rather than limitation to facilitate a thorough understanding of the embodiments of the present disclosure. However, it will be apparent to those skilled in the art that the present disclosure may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid obscuring the description of the present disclosure with unnecessary detail.

[0023] In order to make the purpose, technical solutions and advantages of the present disclosure more clear, specific embodiments will be described below with reference to the accompanying drawings.

[0024] Please refer to Figure 1 , Figure 1 This is a flow chart of a method for processing millimeter-wave radar waveform data according to an embodiment of the present disclosure. The method includes:

[0025] S101: performing time-frequency analysis on multiple sets of waveform arrays to obtain multiple image groups and multiple micro-Doppler features; the multiple sets of waveform arrays are obtained by monitoring the target area based on multiple millimeter-wave radars.

[0026] In this embodiment, a waveform array refers to an array of reflected waveform data received by a millimeter-wave radar when monitoring a target area. This means that a waveform array corresponds one-to-one to each millimeter-wave radar, and the number of waveform arrays matches the number of millimeter-wave radars. The number of waveform data in a waveform array is related to the monitoring frequency of the millimeter-wave radar: a higher frequency results in more waveform data, and one waveform data item corresponds to one millimeter-wave radar monitoring of the target area.

[0027] In this embodiment, time-frequency analysis is a signal processing method used to simultaneously analyze the characteristics of a signal in time and frequency.

[0028] An image group includes multiple images, which can be range-Doppler images. Image groups correspond one-to-one to waveform arrays, and the number of image groups is consistent with the number of waveform arrays. Range-Doppler images also correspond one-to-one to waveform data in the waveform array, that is, one waveform data corresponds to one range-Doppler image.

[0029] Micro-Doppler characteristics refer to the Doppler frequency shift changes caused by tiny movements of the target person, such as human limb movements. Different people or objects have unique micro-Doppler characteristics because different people have corresponding habitual movements or habitual walking postures when walking.

[0030] The echo signal received by millimeter-wave radar contains various information about the target. Micro-Doppler signatures, generated by the target's minute motion, are a time-varying frequency modulation phenomenon. Time-frequency analysis methods, such as short-time Fourier transforms or wavelet transforms, can be used to jointly analyze the waveform signal in both time and frequency dimensions to obtain micro-Doppler signatures. The same applies to range-Doppler maps.

[0031] The aforementioned multiple sets of waveform arrays can be understood as being obtained by monitoring the target area by multiple millimeter-wave radars over a period of time. The target area can be inside a shopping mall, a corporate building, or a residential unit building, and the application scenario can be indoors.

[0032] S102: Generate a target identity based on target motion information and target micro-Doppler features; the target motion information is obtained by identifying a target person in a target area based on multiple image groups, and the target micro-Doppler features are calculated based on multiple micro-Doppler features.

[0033] In this embodiment, the target motion information is the motion information of the target person, which may include the distance between the target person and the millimeter wave radar, the position or speed in the target area, etc. It may be obtained through the multiple image groups obtained in S101.

[0034] The target micro-Doppler signature is a signature obtained by calculating and processing the micro-Doppler signatures acquired by multiple millimeter-wave radars. The calculation method can be a weighted calculation of the multiple micro-Doppler signatures. The weight of the weighted calculation can be preset or set according to the distance of the target person from the radar. For example, since the closer the radar is to the target person, the more reliable the data obtained by its monitoring is, the weight of the micro-Doppler signature corresponding to the radar closest to the target person can be set to a relatively high threshold.

[0035] In one embodiment of the present disclosure, the target identity may be generated as follows:

[0036] Generate target identification based on target motion information and target micro-Doppler characteristics, including:

[0037] Generate a target feature vector based on target motion information and target micro-Doppler characteristics;

[0038] Perform encoding operation on the target feature vector to obtain the target identity.

[0039] In this embodiment, the target motion information can be distance, speed, position, etc., and the target micro-Doppler feature can be the body movement, such as arm swing, leg step, etc. The extracted distance, speed, angle and micro-Doppler features are combined to form a multi-dimensional feature vector. For example, assuming that the distance feature is The speed characteristics are expressed as Indicates that the position feature is Indicates that the micro-Doppler feature is represented by a vector Then the eigenvector can be expressed as .

[0040] The encoding operation in this embodiment can be a hash operation. For example, the MD5 hash algorithm is used as input. The MD5 algorithm performs a series of bitwise operations and transformations on the feature vector, ultimately outputting a 128-bit (16-byte) hash value. This hash value serves as the initial identity of the target person. Because the probability of different feature vectors yielding the same hash value (hash collision) after hashing is extremely low, each target person's identity can be considered unique.

[0041] In this embodiment, the millimeter wave radar waveform data processing method further includes: updating the target identity based on a first frequency, where the first frequency is determined based on a rate of change of target motion information.

[0042] The first frequency refers to how often the target identity is updated. Considering that even for the same person, their walking speed and stride length can vary with environmental changes or other influencing factors, the target identity can be updated based on the rate of change of the target's motion information. This rate of change reflects the speed of changes in the target's motion state. If the target's motion state changes rapidly, such as suddenly running from a stationary state, the rate of change of the target's motion information (such as speed and position) will be greater. In this case, a higher frequency (i.e., a shorter interval) is required to update the target identity to ensure that the identity promptly reflects the target's latest characteristics.

[0043] On the contrary, if the target person's motion state changes slowly, such as walking slowly or basically staying still, the change rate of the target motion information is small, and a lower frequency (i.e., a longer time interval) can be used to update the target identity, thereby reducing unnecessary computing and processing resource consumption.

[0044] For example, when the speed of the target person changes by more than a certain threshold in a short period of time, the first frequency is set to update the target identity every 1 second; and when the speed of the target person changes very little, the first frequency can be adjusted to update every 5 seconds.

[0045] The change rate of the target motion information can be determined based on the speed change rate or displacement change rate of the target person within a fixed time. For example, the highest change rate of the two can be used as the change rate of the target motion information or determined through weighted calculation.

[0046] S103: track the target personnel based on the target identity.

[0047] In this embodiment, after obtaining the target identity, the target personnel can be tracked according to a corresponding algorithm or based on the similarity in each frame of image. For example, if the newly detected target feature matches the target identity, it can be determined that the target is the target personnel that has been identified before, and the track record of the target personnel is updated according to the new position, speed and other information. For example, the millimeter wave radar detects the position of the target personnel A as (x1, y1) at t1, and detects the target matching the target identity of A again at t2, and the position of the target is (x2, y2). Then (x2, y2) can be added to the track record of the target personnel A, so as to gradually depict the motion track of the target personnel A at different time.

[0048] From the above, it can be concluded that the present disclosure determines the motion information of the target personnel and the micro-Doppler feature related to its own motion by performing time-frequency analysis on the waveform received by the radar, and then determines an identity for the target personnel based on the motion information and the micro-Doppler feature, so that the identity is more relevant to the target personnel, and more accurate personnel tracking is achieved.

[0049] In an embodiment of the present disclosure, each waveform array includes a plurality of waveform data; each image group includes a plurality of range-Doppler maps; the target motion information includes a distance and a position; the millimeter wave radar corresponds to the waveform array one by one; the waveform data corresponds to the range-Doppler map one by one. Figure 1 one by one;

[0050] The millimeter wave radar waveform data processing method further includes:

[0051] The abscissa of each range-Doppler map in each image group is analyzed respectively to obtain the distance of the target personnel from each radar in a first period;

[0052] The position of the target personnel in the first period is determined based on the distance of the target personnel from each radar in the first period, and the first period is a monitoring period of the millimeter wave radar.

[0053] In this embodiment, the abscissa corresponding to the peak with higher energy is the distance of the target personnel from the radar corresponding to the range-Doppler map. By analyzing the abscissa of the range-Doppler map in each image group, the specific distance value of the target personnel from each radar in the first period monitored by the millimeter wave radar can be obtained. The first period can be any period of monitoring of the target area by the millimeter wave radar, and the length of the first period is higher than a monitoring period of the millimeter wave radar.

[0054] For example, in the image group b2, by analyzing the horizontal coordinates of the range-Doppler diagram, it is known that the target person moves from one meter away from radar B to three meters away from radar B in the first time period. In the image group c2, by analyzing the horizontal coordinates of the range-Doppler diagram, it is known that the target person moves from three meters away from radar C to one meter away from radar C in the first time period. In the image group d2, by analyzing the horizontal coordinates of the range-Doppler diagram, it is known that the target person moves from five meters away from radar D to two meters away from radar D in the first time period.

[0055] Figure 2 A schematic diagram of a principle for determining the position of a target person is provided for an embodiment of the present disclosure. Referring to Figure 2 ; the distance of the target person from each radar in the first time period is obtained, and according to the distance of the target person from each radar in the first time period, the position of the target person in the target area can be determined.

[0056] As Figure 2 shown, the radars are numbered in alphabetical order, and according to the foregoing description, it can be understood that radar B monitors the target area and obtains the waveform in the first time period, which forms the waveform array b1. Time-frequency analysis is performed on the waveform array b1 to obtain the image group b2. One of the range-Doppler images in the image group b2 is analyzed, and the horizontal coordinate corresponding to the peak with higher energy is taken as the distance of the target person from radar B. Since the points at a certain distance from the radar in the three-dimensional space should form a sphere, the surface of the sphere is at the same distance from the center (i.e., the radar).

[0057] In this embodiment, although theoretically the points at a certain distance from radar B form a sphere, the surface of the sphere is at the same distance from the center (i.e., the radar), but considering that in the actual monitoring scene, the target person can only appear on a fixed plane (i.e., the ground), it can be understood that the position of the target person is a circle, and any point on the circle arc can be the position of the target person. The same applies to radars C and D. After analysis by at least three radars, the position of the target person in the target area can be obtained.

[0058] In this embodiment, the number of millimeter wave radars is greater than or equal to three. It should be noted that the number of radars required is different in different scenarios. For example, when the target person can appear at any position in the target area through a rope or indoor stairs, etc., the number of millimeter wave radars required is at least four. The principle of the present disclosure will not be described again.

[0059] From the above, it can be concluded that the present disclosure can obtain the distance between the target person and each millimeter-wave radar by analyzing the horizontal coordinate of the distance-Doppler diagram, and then based on the distance between the target person and each millimeter-wave radar and the preset logic, the position of the target person in the target area can be obtained. By improving the accuracy of millimeter-wave radar data processing, the accuracy and reliability of personnel tracking are improved.

[0060] In one embodiment of the present disclosure, the target motion information includes speed;

[0061] The millimeter wave radar waveform data processing method further includes:

[0062] Analyze the vertical coordinates of multiple range-Doppler images in each image group to obtain multiple velocity arrays; the velocity arrays correspond one-to-one to the millimeter-wave radars;

[0063] Determining weighted calculation weights of each speed array based on the distance of the target person from each radar in the first time period;

[0064] A weighted calculation is performed on the multiple speed arrays based on the weighted calculation weights to obtain the speed of the target person in the first time period.

[0065] In this embodiment, the vertical axis corresponding to the peak with the highest energy represents the speed of the target person as monitored by the corresponding radar in the range-Doppler graph. By analyzing the horizontal axis of the range-Doppler graph in each image group, the speed of the target person as monitored by each radar during the first period of millimeter-wave radar monitoring can be obtained. The first period can be any period during which the millimeter-wave radar monitors the target area, and the duration of the first period is longer than one millimeter-wave radar monitoring cycle.

[0066] Considering that the speed information measured by the radar closer to the target person is more accurate and has greater reference value for finally determining the target person's true speed, it is given a higher weight; while the speed information measured by the radar farther away has a relatively large error, so the weight will be relatively lower.

[0067] Specifically, the weight setting may be calculated based on a first formula, which may be: ,in, Indicates the The weight of the velocity array corresponding to each radar, Indicates the The inverse of the distance of a radar reflects the relative reliability of the radar measurement. Indicates the number of millimeter-wave radars.

[0068] After obtaining the weighted calculation weight, the plurality of speed arrays are weighted calculated, and finally the speed of the target person in the first time period is obtained. It should be noted that the weighted calculation object is the speed data representing the same time in each speed array, that is, the scanning frequency (monitoring frequency) of each millimeter wave radar is the same and synchronous.

[0069] In an embodiment of the present disclosure, the millimeter wave radar waveform data processing method further comprises:

[0070] determining a weighted calculation weight of each micro-Doppler feature based on the distance of the target person from each radar in the first time period;

[0071] performing weighted calculation on the plurality of micro-Doppler features based on the weighted calculation weight of each micro-Doppler feature to obtain a target micro-Doppler feature.

[0072] In the present embodiment, the weighted calculation weight of each micro-Doppler feature is determined in the same way as the aforementioned weighted calculation method, and can be determined based on the first formula, for example, the weighted calculation weight of each micro-Doppler feature is determined based on the first formula as , then the target micro-Doppler feature , wherein is the target micro-Doppler feature, is the micro-Doppler feature corresponding to the i-th radar.

[0073] From the above, it can be concluded that the present disclosure introduces a weighted calculation weight, which takes into account the measurement errors of different radars due to the distance to the target person. Higher weight is given to radars that are closer to the target person, thereby improving the accuracy of speed calculation. The present disclosure also considers the synchronization and consistency of the scanning frequency between radars, ensuring the accuracy and comparability of speed calculation.

[0074] When extracting the target micro-Doppler feature, the weighted calculation method is also used, which takes into account the measurement errors of different radars due to the distance, thereby improving the accuracy of micro-Doppler feature extraction. The present disclosure optimizes the feature extraction process, thereby improving the accuracy and reliability of target identification.

[0075] In an embodiment of the present disclosure, the trajectory tracking of the target person based on the target identity identifier comprises:

[0076] In response to the presence of a first person in the target area, the target identity identifier and the first identity identifier are associated based on a joint probability data association algorithm, and the trajectory tracking of the target person is performed based on the association result. The first person is a person other than the target person, and the first identity identifier is the identity identifier of the first person.

[0077] ​In this embodiment, the first person is a person other than the target person in the target area. For example, in a shopping mall scenario, a specific customer who wants to be tracked is the target person, and other customers in the mall can be regarded as the first person.

[0078] The joint probabilistic data association algorithm is an algorithm widely used in the field of multi-target tracking. In the scenario of millimeter wave radar, the radar will continuously obtain measurement data (such as position, speed, etc.) of the target. There may be multiple targets (target person and first person) in the scene, and the joint probabilistic data association algorithm can associate the target identity and the first identity with the newly obtained measurement data of the radar. Specifically, the algorithm calculates the association probability between each measurement data and the target corresponding to each identity. For example, the radar obtains a set of position and speed measurement data at a certain time, and the algorithm analyzes the matching degree between this set of data and the characteristics corresponding to the identity of the target person and the first person, and calculates the probability that this set of data belongs to the target person or the first person. By considering all possible association cases, the most likely association combination is found, and it is determined whether the new measurement data belongs to the target person or the first person.

[0079] In this embodiment, after the association between the target identity and the first identity and the measurement data is completed, the trajectory information of the target person is updated according to the association result. If the association result shows that a certain measurement data belongs to the target person, the position, speed, etc. corresponding to the data is added to the trajectory record of the target person, thereby realizing continuous tracking of the motion trajectory of the target person. For example, if the joint probabilistic data association algorithm determines that the measurement data at a certain time has the highest association probability with the identity of the target person, the position and speed information of the target person at that time is updated to its trajectory record, and the motion trajectory of the target person is continuously drawn.

[0080] Based on the above implementation, the detection of personnel entry and exit and the statistics of personnel can also be realized. For example, when the millimeter wave radar starts to work to detect indoor target personnel, the detection order of the personnel is recorded. Specifically, after the radar starts, the first detected person E is recorded as the first detected target. Then, the second detected person F is recorded as the second detected target, and so on.

[0081] Secondly, the disclosure assigns an integer number as the identity of the target person according to the detection order. That is, the first detected person E is assigned ID 1, the second detected person F is assigned ID 2, and the subsequent detected person is assigned an increasing number.

[0082] Thirdly, in the case of frequent personnel access to the scene, when a person leaves the scene, the corresponding ID can be reassigned to the new person entering the scene. In order to avoid confusion caused by repeated use of ID, a management mechanism can be established. For example, an ID state table can be established to record the use of each ID, and when a person leaves the scene, the corresponding ID is marked as "available". When a new person enters, an ID in the "available" state is selected for distribution, ensuring that each ID corresponds to only one target person at the same time. At the same time, the relevant information of the target person corresponding to each ID, such as the first detection time and the last detection time, can be recorded to facilitate the tracking and management of the target person.

[0083] In an embodiment of the present disclosure, the millimeter wave radar waveform data processing method further comprises:

[0084] In response to the change rate of the target motion information being greater than a first change rate, lowering the threshold parameter of the joint probabilistic data association algorithm based on a first step size;

[0085] In response to the change rate of the target motion information being less than a second change rate, increasing the threshold parameter of the joint probabilistic data association algorithm based on a second step size;

[0086] The first change rate is greater than the second change rate.

[0087] In this embodiment, in the joint probabilistic data association algorithm, the threshold parameter is used to determine whether the measured data and the target identity can be associated.

[0088] When the association probability between the measured data and the target identity is greater than the threshold parameter, it is considered that there is an effective association between them; otherwise, if the association probability is less than the threshold parameter, it is not considered that they are related. The size of the threshold parameter will affect the strictness of the association. The higher the threshold parameter, the stricter the association requirement, the less likely the misassociation, but some real associations may be missed; the lower the threshold parameter, the easier the association, but the risk of misassociation will increase.

[0089] In this scenario, when the change rate of the target person's motion information is greater than the first change rate, it means that the target person's motion state has changed greatly, and the target person is in a fast-moving or sudden direction-changing situation. In this case, in order to capture the target person's motion information more timely, avoid missing the target person's trajectory information because the threshold parameter is too high to establish an association between new measured data and target identity, the threshold parameter of the joint probabilistic data association algorithm can be lowered based on the first step size. Make the association requirement relatively loose, increase the possibility of establishing an association between new measured data and target identity, and ensure the continuous tracking of the target person.

[0090] When the change rate of the motion information of the target person is less than the second change rate, it means that the motion state of the target person is relatively stable and changes little. At this time, in order to reduce the occurrence of false association and improve the accuracy of association, the threshold parameter of the joint probabilistic data association algorithm can be increased based on the second step size. A higher threshold parameter will make the association requirement more stringent, and only when the association probability between the measurement data and the target identity is high enough, the association will be established, thereby avoiding the error association of the measurement data not belonging to the target person to the trajectory of the target person. The first step size and the second step size can be determined based on historical experience.

[0091] From the above, it can be concluded that the present disclosure realizes high-precision association between target identity and radar measurement data through the joint probabilistic data association algorithm, thereby being able to accurately track the motion trajectory of the target person. This method is particularly effective in a multi-target environment, and can distinguish and track multiple targets, avoiding the problems of target confusion and trajectory interruption.

[0092] The present disclosure dynamically adjusts the threshold parameter of the joint probabilistic data association algorithm according to the change rate of the target motion information, making the adaptability of the present disclosure stronger. When the target person moves quickly or changes direction suddenly, lowering the threshold parameter can increase the possibility of establishing association between new measurement data and the target identity, ensuring continuous and accurate tracking of the target person. Conversely, when the motion state of the target person is stable, increasing the threshold parameter can reduce false association and improve the accuracy of personnel tracking.

[0093] The millimeter wave radar waveform data processing method corresponding to the above embodiment, Figure 3 The structure block diagram of the millimeter wave radar waveform data processing system provided by an embodiment of the present disclosure is shown. For ease of illustration, only parts related to the embodiments of the present disclosure are shown. For reference Figure 3 The millimeter wave radar waveform data processing system 20 includes a waveform analysis module 21, an identity generation module 22, and a trajectory tracking module 23.

[0094] The waveform analysis module 21 is configured to perform time-frequency analysis on multiple groups of waveform arrays to obtain multiple image groups and multiple micro-Doppler features; the multiple groups of waveform arrays are obtained based on multiple millimeter wave radars monitoring a target region;

[0095] The identity generation module 22 is configured to generate a target identity based on target motion information and target micro-Doppler features; the target motion information is obtained based on multiple image groups identifying a target person in a target region, and the target micro-Doppler features are calculated based on multiple micro-Doppler features;

[0096] The trajectory tracking module 23 is configured to track a trajectory of a target person based on a target identity.

[0097] In an embodiment of the present disclosure, each waveform array includes a plurality of waveform data; each image group includes a plurality of range-Doppler maps; the target motion information includes range and position; the millimeter wave radar corresponds to the waveform array one-to-one; the waveform data corresponds to the range-Doppler map one-to-one. Figure 1 In an embodiment of the present disclosure, each waveform array includes a plurality of waveform data; each image group includes a plurality of range-Doppler maps; the target motion information includes range and position; the millimeter wave radar corresponds to the waveform array one-to-one; the waveform data corresponds to the range-Doppler map one-to-one.

[0098] The millimeter wave radar waveform data processing system 20 further includes:

[0099] The position determination module is configured to analyze the horizontal coordinates of the plurality of range-Doppler maps in each image group respectively to obtain the distances of the target person from each radar in the first time period.

[0100] The position of the target person in the first time period is determined based on the distances of the target person from each radar in the first time period, and the first time period is the monitoring time period of the millimeter wave radar.

[0101] In an embodiment of the present disclosure, the target motion information includes velocity.

[0102] The millimeter wave radar waveform data processing system 20 further includes a velocity determination module configured to analyze the vertical coordinates of the plurality of range-Doppler maps in each image group respectively to obtain a plurality of velocity arrays; the velocity array corresponds to the millimeter wave radar one-to-one.

[0103] The weighted calculation weights of the velocity arrays are determined based on the distances of the target person from each radar in the first time period.

[0104] The plurality of velocity arrays are weighted calculated based on the weighted calculation weights to obtain the velocity of the target person in the first time period.

[0105] In an embodiment of the present disclosure, the millimeter wave radar waveform data processing system 20 further includes:

[0106] The micro-Doppler feature determination module is configured to determine the weighted calculation weights of the micro-Doppler features based on the distances of the target person from each radar in the first time period.

[0107] The target micro-Doppler feature is obtained by weighted calculating the plurality of micro-Doppler features based on the weighted calculation weights of the micro-Doppler features.

[0108] In an embodiment of the present disclosure, the identification generation module 22 is specifically configured to generate a target feature vector based on the target motion information and the target micro-Doppler feature.

[0109] The target feature vector is encoded to obtain a target identity.

[0110] The target identity is updated based on a first frequency, and the first frequency is determined based on the change rate of the target motion information.

[0111] In one embodiment of the present disclosure, the trajectory tracking module 23 is specifically configured to, in response to the presence of a first person in the target area, associate the target identity identifier and the first identity identifier based on a joint probabilistic data association algorithm, and track the trajectory of the target person based on the association result; wherein the first person is a person other than the target person, and the first identity identifier is the identity identifier of the first person.

[0112] In one embodiment of the present disclosure, the millimeter wave radar waveform data processing system 20 further includes:

[0113] a threshold adjustment module, configured to reduce a threshold parameter of the joint probabilistic data association algorithm based on the first step length in response to a change rate of the target motion information being greater than a first change rate;

[0114] In response to a change rate of the target motion information being less than a second change rate, increasing a threshold parameter of the joint probabilistic data association algorithm based on the second step size;

[0115] The first rate of change is greater than the second rate of change.

[0116] See also Figure 4 , Figure 4 This is a schematic block diagram of an electronic device provided by an embodiment of the present disclosure. Figure 4 The electronic device 300 in the embodiment shown may include: one or more processors 301, one or more input devices 302, one or more output devices 303, and one or more memories 304. The processors 301, input devices 302, output devices 303, and memories 304 communicate with each other via a communication bus 305. The memory 304 is used to store computer programs, which include program instructions. The processor 301 is used to execute the program instructions stored in the memory 304. The processor 301 is configured to call the program instructions to execute the functions of the modules / units in the above-mentioned device embodiments, such as Figure 3 The functions of the waveform analysis module 21, the identification generation module 22 and the trajectory tracking module 23 are shown.

[0117] It should be appreciated that in the embodiments of the present disclosure, the processor 301 can be a central processing unit (CPU), and can also be other general-purpose processors, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components, or the like. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor.

[0118] The input device 302 can include a touchpad, a fingerprint collection sensor (for collecting fingerprint information and direction information of a fingerprint of a user), a microphone, and the like, and the output device 303 can include a display (LCD, etc.), a speaker, and the like.

[0119] The memory 304 can include a read-only memory and a random access memory, and provide instructions and data for the processor 301. A portion of the memory 304 can also include a non-volatile random access memory. For example, the memory 304 can also store device type information.

[0120] In specific implementations, the processor 301, the input device 302, and the output device 303 described in the embodiments of the present disclosure can perform the implementation manners described in the first and second embodiments of the millimeter wave radar waveform data processing method provided by the embodiments of the present disclosure, and can also perform the implementation manners of the electronic device described in the embodiments of the present disclosure, which will not be described here.

[0121] In another embodiment of the present disclosure, a computer readable storage medium is provided, which stores a computer program. The computer program includes program instructions, which, when executed by a processor, implement all or part of the processes of the above-mentioned embodiment methods. The computer program can also instruct related hardware to complete the above-mentioned processes. The computer program can be stored in a computer readable storage medium. When the computer program is executed by the processor, the steps of the above-mentioned various method embodiments can be implemented. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or some intermediate form. The computer readable medium can include any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal, and software distribution medium, etc.

[0122] The computer readable storage medium can be an internal storage unit of the electronic device, such as a hard disk or a memory of the electronic device. The computer readable storage medium can also be an external storage device of the electronic device, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. Further, the computer readable storage medium can include both the internal storage unit and the external storage device of the electronic device. The computer readable storage medium is used to store the computer program and other programs and data required by the electronic device. The computer readable storage medium can also be used to temporarily store data that has been output or will be output.

[0123] Those skilled in the art can appreciate that the units and algorithm steps of the examples described in conjunction with the embodiments disclosed herein can be realized in electronic hardware, computer software or a combination of both. In order to clearly illustrate the interchangeability of hardware and software, the components and steps of the examples have been described in general terms in the above description. Whether the functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. A person skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present disclosure.

[0124] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the electronic device and the units described above can refer to the corresponding processes in the above-mentioned method embodiments, which will not be described here.

[0125] In several embodiments provided in the present application, it should be understood that the disclosed electronic device and method can be implemented in other manners. For example, the embodiments of the apparatus described above are merely illustrative. For example, the division of the units is only a logical function division. There can be another division manner for the actual implementation, for example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the displayed or discussed coupling or direct coupling or communication connection between the units can be indirect coupling or communication connection through some interfaces, or can be in electrical, mechanical or other forms.

[0126] The units described as separated components can or can not be physically separated, 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 on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purposes of the embodiments of the present disclosure.

[0127] In addition, each functional unit in the various embodiments of the present disclosure can be integrated in one processing unit, or each unit can exist physically, or two or more units can be integrated in one unit. The integrated unit can be implemented in the form of hardware, or in the form of a software functional unit.

[0128] The above is merely specific embodiments of the present disclosure, but the protection scope of the present disclosure is not limited thereto, and any skilled person in the art can easily think of various equivalent modifications or replacements within the technical scope disclosed by the present disclosure, and these modifications or replacements should be covered in the protection scope of the present disclosure. Therefore, the protection scope of the present disclosure should be subject to the protection scope of the claims.

Claims

1. A millimeter wave radar waveform data processing method, characterized in that: include: Performing time-frequency analysis on multiple waveform arrays to obtain multiple image groups and multiple micro-Doppler features; The multiple sets of waveform arrays are obtained by monitoring the target area based on multiple millimeter wave radars; A waveform array refers to an array of reflected waveform data received by a millimeter-wave radar when monitoring a target area. The waveform array corresponds one-to-one to the millimeter-wave radar, and the number of waveform arrays is the same as the number of millimeter-wave radars. generating a target identity based on target motion information and target micro-Doppler features; wherein the target motion information is obtained by identifying a target person in the target area based on the multiple image groups, and the target micro-Doppler features are calculated based on the multiple micro-Doppler features; Tracking the target person based on the target identity; Each waveform array includes a plurality of waveform data; each image group includes a plurality of range-Doppler images; the target motion information includes distance and position; the millimeter wave radar corresponds to the waveform array in a one-to-one manner; The waveform data corresponds one-to-one to the range-Doppler map; The millimeter wave radar waveform data processing method further includes: Analyzing the horizontal coordinates of the multiple range-Doppler graphs in each image group respectively to obtain the distance of the target person from each radar in the first time period; the number of millimeter-wave radars is greater than or equal to three; Determining the position of the target person in the first time period based on the distance of the target person from each radar in the first time period, where the first time period is a monitoring period of the millimeter wave radar; Tracking the target person based on the target identity includes: In response to a first person being present in the target area, associating the target identity with the first identity based on a joint probabilistic data association algorithm, and tracking the trajectory of the target person based on the association result; wherein the first person is a person other than the target person, and the first identity is the identity of the first person; In response to a change rate of the target motion information being greater than a first change rate, reducing a threshold parameter of the joint probabilistic data association algorithm based on a first step length; In response to a change rate of the target motion information being less than a second change rate, increasing a threshold parameter of the joint probabilistic data association algorithm based on a second step size; The first change rate is greater than the second change rate.

2. The millimeter wave radar waveform data processing method according to claim 1, wherein: The target motion information includes speed; The millimeter wave radar waveform data processing method further includes: Analyzing the vertical coordinates of the multiple range-Doppler images in each image group to obtain multiple velocity arrays; the velocity arrays correspond one-to-one to the millimeter-wave radars; Determine the weighted calculation weights of each speed array based on the distance of the target person from each radar within the first time period; The plurality of speed arrays are weightedly calculated based on the weighted calculation weights to obtain the speed of the target person in the first time period.

3. The millimeter wave radar waveform data processing method according to claim 1, wherein: Also includes: Determining weighted calculation weights of each micro-Doppler feature based on the distance of the target person from each radar within the first time period; The target micro-Doppler feature is obtained by performing weighted calculation on the multiple micro-Doppler features based on the weighted calculation weights of the respective micro-Doppler features.

4. The millimeter wave radar waveform data processing method according to claim 1, wherein: Generating a target identity based on target motion information and target micro-Doppler characteristics includes: generating a target feature vector based on the target motion information and the target micro-Doppler feature; Perform encoding operation on the target feature vector to obtain a target identity.

5. A millimeter wave radar waveform data processing system, characterized in that: include: The waveform analysis module is used to perform time-frequency analysis on multiple waveform arrays to obtain multiple image groups and multiple micro-Doppler features; The multiple sets of waveform arrays are obtained based on multiple millimeter-wave radars monitoring the target area; a waveform array refers to an array of reflected waveform data received by a millimeter-wave radar monitoring the target area. The waveform arrays correspond one-to-one to the millimeter-wave radars, and the number of waveform arrays is consistent with the number of millimeter-wave radars. an identification generation module, configured to generate a target identity based on target motion information and target micro-Doppler features; the target motion information is obtained by identifying a target person in the target area based on the multiple image groups, and the target micro-Doppler features are calculated based on the multiple micro-Doppler features; A trajectory tracking module, configured to track the target person based on the target identity; Each waveform array includes multiple waveform data; each image group includes multiple range-Doppler images; target motion information includes distance and position; Millimeter-wave radars correspond one-to-one to waveform arrays; The waveform data corresponds one-to-one with the range-Doppler map; The millimeter wave radar waveform data processing system also includes: a position determination module, configured to analyze the abscissas of the multiple range-Doppler images in each image group to obtain the distance of the target person from each radar within a first time period; the number of millimeter-wave radars being greater than or equal to three; Determining the position of the target person in the first time period based on the distance of the target person from each radar in the first time period, where the first time period is a monitoring period of the millimeter wave radar; a trajectory tracking module, specifically configured to, in response to the presence of a first person in the target area, associate the target identity with the first identity based on a joint probabilistic data association algorithm, and track the trajectory of the target person based on the association result; wherein the first person is a person other than the target person, and the first identity is the identity of the first person; a threshold adjustment module, configured to reduce a threshold parameter of the joint probabilistic data association algorithm based on the first step length in response to a change rate of the target motion information being greater than a first change rate; In response to a change rate of the target motion information being less than a second change rate, increasing a threshold parameter of the joint probabilistic data association algorithm based on the second step size; The first rate of change is greater than the second rate of change.

6. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 4 are implemented.

7. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 4 are implemented.

Images