Multi-target radar body motion identification method, device, equipment and medium

Abstract

The invention discloses a multi-target radar body motion identification method, device and equipment and a medium, and relates to the technical field of radar signal processing. The method comprises the following steps: acquiring a radar echo signal acquired by a multi-input multi-output radar; performing signal processing on the radar echo signals, determining recognized targets, and generating a distance azimuth spectrogram and a distance Doppler map of each recognized target; body motion identification is carried out based on each distance Doppler map, and a to-be-confirmed body motion target is determined from each identified target; and in the distance azimuth spectrogram, if the power peak of the to-be-confirmed body moving target belongs to a preset body moving target power peak, determining the to-be-confirmed body moving target as a body moving target. According to the invention, the accuracy of multi-target body motion recognition can be improved, and the condition of false detection of multi-target body motion recognition is improved.

Description

Technical Field

[0001] The present application relates to the technical field of radar signal processing, and particularly to a multi-target radar body movement recognition method, device, equipment and medium. Background Art

[0002] Body movement mainly refers to body actions such as turning over, waving hands, and kicking legs of a human target. In the related art, based on the information of the human target movement contained in the radar echo signal, the echo signal can be processed to extract the characteristics of the human action, and then the human body movement can be recognized. Specifically, when the target has body movement, the velocity dimension characteristics of the power spectrum of the target will change significantly, so that the recognition of the target body movement can be realized based on the change of the velocity dimension characteristics.

[0003] However, in specific usage scenarios, there are often multiple targets at the same time, and the velocity dimension characteristics between multiple targets will interfere with each other, resulting in a relatively high probability of misrecognition for the body movement recognition of the target. Summary of the Invention

[0004] The main purpose of the present application is to provide a multi-target radar body movement recognition method, device, equipment and medium, aiming to solve the problem of relatively high probability of misrecognition in multi-target body movement recognition.

[0005] To achieve the above object, the present application provides a multi-target radar body movement recognition method, including:

[0006] Obtain the radar echo signal collected by a multiple-input multiple-output radar;

[0007] Perform signal processing on the radar echo signal to determine the recognized targets, and generate a range-azimuth spectrogram and a range-Doppler diagram of each recognized target;

[0008] Perform body movement recognition based on each range-Doppler diagram respectively, and determine the to-be-confirmed body movement targets from the recognized targets;

[0009] In the range-azimuth spectrogram, if the power peak of the to-be-confirmed body movement target belongs to the preset body movement target power peak, then determine the to-be-confirmed body movement target as the body movement target.

[0010] In a possible embodiment of the present application, in the range-azimuth spectrogram, if the power peak of the to-be-confirmed body movement target belongs to the preset body movement target power peak, then determining the to-be-confirmed body movement target as the body movement target includes:

[0011] Determine the power peak belonging to the to-be-confirmed body movement target from the range-azimuth spectrogram;

[0012] If the power peak is the highest power peak of the range-Doppler diagram, then determine that the power peak belongs to the preset body movement target power peak;

[0013] Determine the body movement target to be confirmed as a body movement target.

[0014] In a possible embodiment of the present application, in the range-azimuth spectrum diagram, if the power peak of the body movement target to be confirmed belongs to the preset body movement target power peak, determining the body movement target to be confirmed as a body movement target includes:

[0015] Identify all the highest power peaks from the range-Doppler diagram;

[0016] Determine the position information of each highest power peak;

[0017] If one of all the position information corresponds to the body movement target to be confirmed, determine that the power peak of the body movement target to be confirmed belongs to the preset body movement target power peak;

[0018] Determine the body movement target to be confirmed as a body movement target.

[0019] In a possible embodiment of the present application, in the range-azimuth spectrum diagram, if the power peak of the body movement target to be confirmed belongs to the preset body movement target power peak, determining the body movement target to be confirmed as a body movement target includes:

[0020] Determine the reference power peak of the stationary target among the identified targets from the range-azimuth spectrum diagram;

[0021] If the power difference between the power peak and the reference power peak is greater than the preset threshold, determine that the power peak belongs to the preset body movement target power peak;

[0022] Determine the body movement target to be confirmed as a body movement target.

[0023] In a possible embodiment of the present application, in the range-azimuth spectrum diagram, if the power peak of the body movement target to be confirmed belongs to the preset body movement target power peak, after determining the body movement target to be confirmed as a body movement target, the method further includes:

[0024] Output the position information of the body movement target and / or the number of body movement targets.

[0025] In a possible embodiment of the present application, based on each range-Doppler diagram, perform body movement recognition respectively, and determine the body movement target to be confirmed from each identified target, including:

[0026] For each identified target, extract the velocity dimension feature data of the identified target from the range-Doppler diagram;

[0027] Based on the velocity dimension feature data, perform body movement recognition to identify whether the identified target is the body movement target to be confirmed, so as to determine the body movement target to be confirmed from each identified target.

[0028] In a second aspect, the present application further provides a multi-target radar body movement recognition device, including:

[0029] A signal acquisition module, configured to acquire radar echo signals collected by a multiple-input multiple-output radar;

[0030] A signal processing module, configured to perform signal processing on the radar echo signals to determine identified targets, and generate a range-azimuth spectrogram and a range-Doppler map of each identified target;

[0031] A body movement initial identification module, configured to perform body movement identification based on each range-Doppler map respectively, and determine to-be-confirmed body movement targets from the identified targets;

[0032] A body movement confirmation module, configured to, in the range-azimuth spectrogram, if the power peak of a to-be-confirmed body movement target belongs to a preset body movement target power peak, determine the to-be-confirmed body movement target as a body movement target.

[0033] In a possible embodiment of the present application, the body movement confirmation module includes:

[0034] A first feature extraction unit, configured to determine the power peak of a to-be-confirmed body movement target from the range-azimuth spectrogram;

[0035] A first feature confirmation unit, configured to, if the power peak is the highest power peak of the range-Doppler map, determine that the power peak belongs to a preset body movement target power peak;

[0036] A first target confirmation unit, configured to determine the to-be-confirmed body movement target as a body movement target.

[0037] In a possible embodiment of the present application, the body movement confirmation module includes:

[0038] A power peak identification unit, configured to identify all the highest power peaks from the range-Doppler map;

[0039] A position determination unit, configured to determine the position information of each highest power peak;

[0040] A second feature confirmation unit, configured to, if one of all the position information corresponds to the to-be-confirmed body movement target, determine that the power peak of the to-be-confirmed body movement target belongs to a preset body movement target power peak;

[0041] A second target confirmation unit, configured to determine the to-be-confirmed body movement target as a body movement target.

[0042] In a possible embodiment of the present application, the body movement confirmation module includes:

[0043] A second feature extraction unit, configured to determine the reference power peak of a stationary target among the identified targets from the range-azimuth spectrogram;

[0044] A difference judgment module, configured to determine that a power peak belongs to a preset body movement target power peak if the power difference between the power peak and the reference power peak is greater than a preset threshold value.

[0045] A third target confirmation unit, configured to confirm the to-be-confirmed body movement target as a body movement target.

[0046] In a possible embodiment of the present application, the multi-target radar body movement recognition device further includes:

[0047] A result output module, configured to output the position information and / or the number of body movement targets.

[0048] In a possible embodiment of the present application, the body movement initial recognition module includes:

[0049] A velocity dimension extraction unit, configured to extract velocity dimension feature data of each recognized target from the range-Doppler map for each recognized target.

[0050] An initial recognition unit, configured to perform body movement recognition based on the velocity dimension feature data, determine the to-be-confirmed body movement targets from the recognized targets, and identify whether the recognized targets are the to-be-confirmed body movement targets.

[0051] In a third aspect, the present application further provides a multi-target radar body movement recognition device, including: a processor, a memory, and a computer program stored in the memory. When the computer program is run by the processor, the multi-target radar body movement recognition method as in the first aspect is implemented.

[0052] In a fourth aspect, the present application further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the multi-target radar body movement recognition method as in the first aspect is implemented.

[0053] A multi-target radar body movement recognition method provided by an embodiment of the present application includes: acquiring radar echo signals collected by a multiple-input multiple-output radar; performing signal processing on the radar echo signals to determine recognized targets, and generating a range-azimuth spectrum map and a range-Doppler map of each recognized target; performing body movement recognition based on each range-Doppler map respectively to determine to-be-confirmed body movement targets from the recognized targets; in the range-azimuth spectrum map, if the power peak of the to-be-confirmed body movement target belongs to a preset body movement target power peak, then confirm the to-be-confirmed body movement target as a body movement target.

[0054] It can be seen that in the embodiment of the present application, the target body movement is first identified through the range-Doppler (RD) map, and then in the range-azimuth spectrum map, further discrimination and confirmation are carried out by whether the power peak of the to-be-confirmed body movement target changes accordingly, that is, whether it belongs to the preset body movement target power peak. Therefore, compared with the related art that independently analyzes based on the range-Doppler map, the embodiment of the present application combines the RD map and the range-azimuth spectrum map in space, which can improve the situation of false detection in multi-target body movement recognition. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] Figure 1 It is a schematic structural diagram of the multi-target radar body movement recognition device of the present application;

[0056] Figure 2 It is a schematic flowchart of the first embodiment of the multi-target radar body movement recognition method of the present application;

[0057] Figure 3 It is a schematic diagram of "target body movement" in the velocity dimension feature data of the RD map of the present application;

[0058] Figure 4 It is a schematic diagram of "target body movement" in the R map of the present application;

[0059] Figure 5 It is a schematic flowchart of a selection in the first embodiment of the multi-target radar body movement recognition method of the present application;

[0060] Figure 6 It is a schematic module diagram of the first embodiment of the multi-target radar body movement recognition device of the present application.

[0061] The realization, functional characteristics and advantages of the purpose of the present application will be further described with reference to the embodiments and the accompanying drawings. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0062] It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0063] Body movement mainly refers to body actions such as turning over, waving hands, kicking legs of human targets. In the related art, based on the information of the human target movement contained in the radar echo signal, necessary signal processing can be performed on the echo signal to extract the characteristics of the human action, and then human body movement recognition can be carried out. Specifically, when the target has body movement, the velocity dimension characteristics of the power spectrum of the target will change significantly, so that the recognition of the target body movement can be realized based on the change of the velocity dimension characteristics.

[0064] However, the above-mentioned recognition of target body movement based on the change of velocity dimension features is independent component analysis in a single dimension. The inventors found that when there are multiple targets, due to the limited channels of the MIMO (Multiple-Input Multiple-Output) radar, the velocity dimension features of each target in the azimuth angle direction will leak. That is, when one of the targets makes body movements such as turning over, waving, or kicking, not only the velocity dimension feature data of the moving target shows significant body movement features, but the velocity dimension features of the stationary target may also change and show significant body movement features, resulting in misdetection events where stationary targets are also recognized as moving targets. In particular, even if the azimuth angles of the stationary target and the moving target are different from each other, interference may still occur.

[0065] The inventors found that when the target makes a body movement, its power value on the range-azimuth spectrogram will also become significantly higher. Therefore, the embodiments of the present application provide a solution that combines the range-Doppler map and the range-azimuth spectrogram for body movement recognition. After body movement recognition is performed through the range-Doppler map, it is then determined whether the power peak of the to-be-confirmed target obtained by preliminary recognition on the range-azimuth spectrogram will produce the above-discovered change, that is, whether it belongs to the preset power peak of the body movement target, so as to effectively distinguish and improve the recognition accuracy and improve the misdetection situation of multi-target body movement recognition.

[0066] The inventive concept of the present application will be further elaborated below in conjunction with some specific embodiments.

[0067] Refer to Figure 1 , Figure 1 which is a schematic structural diagram of a multi-target radar body movement recognition device according to the embodiment solution of the present application.

[0068] As Figure 1 shown, the multi-target radar body movement recognition device may include: a processor 1001, such as a CPU, a user interface 1003, a memory 1005, and a communication bus 1002. Among them, the communication bus 1002 is used to realize the connection and communication between these components. Optionally, the user interface 1003 may also be a display screen (Display), an input unit such as a keyboard (Keyboard), etc. The memory 1005 may be a high-speed RAM memory or a stable memory (non-volatile memory), such as a disk memory. Optionally, the memory 1005 may also be a storage device independent of the aforementioned processor 1001.

[0069] It can be understood that the multi-target radar body movement recognition device may further include a network interface 1004, and the network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a WI-FI interface). Optionally, the multi-target radar body movement recognition device may further include an RF (Radio Frequency) circuit, sensors, an audio circuit, a WiFi module, and so on. The multi-target radar body movement recognition device may further include a display screen for displaying a UI (User Interface). The UI may include graphics, text, icons, videos, and any combination thereof. When the display screen is a touch display screen, the display screen also has the ability to collect touch signals on or above the surface of the display screen. The touch signals may be input to the processor 301 as control signals for processing.

[0070] Those skilled in the art can understand that Figure 1 the structure of the multi-target radar body movement recognition device shown in

[0071] does not constitute a limitation on the multi-target radar body movement recognition device, and may include more or fewer components than shown, or combine certain components, or have different component arrangements. Figure 2 , Figure 2 is a schematic flowchart of the first embodiment of the multi-target radar body movement recognition method of the present application.

[0072] It should be noted that although the logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than here.

[0073] In this embodiment, the multi-target radar body movement recognition method includes:

[0074] Step S100: Obtain the radar echo signal of the multiple-input multiple-output radar.

[0075] Step S200: Perform signal processing on the radar echo signal to determine the recognized targets, and generate a range-azimuth spectrogram and a range-Doppler diagram of each recognized target.

[0076] In this embodiment, the execution subject of the multi-target radar body movement recognition method is a multi-target radar body movement recognition device, and the multi-target radar body movement recognition device may be configured as a device such as a computer or a server communicatively connected to the MIMO radar, so that the multi-target radar body movement recognition device and the MIMO radar jointly form a body movement recognition environment. Of course, the multi-target radar body movement recognition device may also be configured as a virtual cluster arranged in the cloud.

[0077] After setting up the body movement recognition environment, the MIMO radar can be controlled to start working, thereby obtaining radar echo signals. After obtaining the radar echo signals, signal processing can be performed on them. It can be understood that signal processing can include target recognition to determine the recognized targets. It should be noted that since this embodiment is for body movement recognition, only the human body can be regarded as the recognized target, while other targets such as vehicles are not regarded as recognized targets.

[0078] Of course, in this embodiment, there are multiple recognized targets. It is worth mentioning that the multiple recognized targets can be distinguished from each other in the radar azimuth, that is, the azimuth angles of different recognized targets are different.

[0079] The detection result includes at least one of speed, distance, and angle. Among them, speed refers to the moving speed of the target object detected by the MIMO radar; distance refers to the distance between the target object detected by the MIMO radar and the MIMO radar; angle refers to the pose angle of the target object detected by the MIMO radar relative to the MIMO radar.

[0080] Signal processing can obtain the relevant information of each recognized target. For example, the moving speed of the recognized target detected by the MIMO radar, the distance between the recognized target detected by the MIMO radar and the MIMO radar, and the azimuth of the recognized target detected by the MIMO radar relative to the MIMO radar can be obtained. And a Range-Doppler distance-Doppler map of the recognized target is generated, that is, the RD map. It can be understood that the horizontal axis of the RD map represents distance information, the vertical axis represents speed information, and the vertical axis represents the intensity information of the target echo, that is, the power value.

[0081] In addition, information processing can also obtain the target detection information of the MIMO radar in space and generate a Range-azimuth distance-azimuth spectrum map, that is, the RA map (spatial spectrum). The horizontal axis of the RA map represents azimuth information, the vertical axis represents distance information, and the vertical axis represents the intensity information of the target echo, that is, the power value. It can be understood that the positions of the power peaks (spikes) in the RA map represent the spatial azimuth information of the detected recognized targets, and the intensity of the spikes represents the intensity of the target echo.

[0082] Step S300: Perform body movement recognition based on each distance-Doppler map, and determine the body movement target to be confirmed from each recognized target.

[0083] Specifically, after obtaining the RD maps of each identified target, it is possible to monitor whether the velocity dimension feature data shows significant body movement features, thereby preliminarily determining whether the identified target is a body movement target to be determined. For example, the CFAR (Constant False-Alarm Rate) detection algorithm can be used for body movement identification.

[0084] In a specific embodiment, when the multi-target radar body movement identification method executes step S300, for each identified target, the velocity dimension feature data of the identified target can be extracted from the range-Doppler map. Then, based on the velocity dimension feature data, body movement identification is performed to identify whether the identified target is a body movement target to be confirmed, so as to determine the body movement target to be confirmed from each identified target.

[0085] Specifically, for the RD map of a certain identified target, at any moment, its range is a known value, so it is intercepted with this known range value to extract the velocity dimension feature data of the identified target. The horizontal axis of the velocity dimension feature data is time, and the vertical axis is velocity.

[0086] Please refer to Figure 3 , in the velocity dimension feature data, when there is "target body movement", it shows a short-term severe waveform oscillation in the velocity dimension feature data. Therefore, for a certain identified target, if its velocity dimension feature data has this short-term severe waveform oscillation, that is, has the preset body movement feature, then the identified target can be preliminarily identified as a body movement target, that is, a body movement target to be confirmed.

[0087] Step S400: In the range-azimuth spectrum map, if the power peak of the body movement target to be confirmed belongs to the preset body movement target power peak, then the body movement target to be confirmed is determined as a body movement target.

[0088] Specifically, the RA map can reflect the spatial positions and echo conditions of each target in the space detected by the radar. Among them, each power peak in the RA map represents a detected target. Please refer to Figure 4, for a moving target, the height (echo intensity) of its power peak A becomes larger compared to the height (echo intensity) of the power peak in the stationary state, that is, the power peak becomes significantly higher. Of course, its echo intensity becomes larger, and the height (echo intensity) of power peak A on the RA is higher than that of power peak B of other stationary targets. Thus, since the target to be confirmed is an identified target, its distance information, azimuth information, etc. are all known information. Therefore, the power peak of the target to be confirmed can be determined from the RA map based on the known distance information and azimuth information, and then it can be judged whether this power peak belongs to the preset moving target power peak, that is, whether it matches the aforementioned "its echo intensity becomes larger, and the height (echo intensity) of power peak A on the RA is higher than that of power peak B of other stationary targets". If it matches, it can be confirmed as a moving target, and if it does not match, it can be confirmed as a stationary target without body movement.

[0089] As an option of this embodiment, when the multi-target radar body movement recognition device executes step S400, it can determine the power peak belonging to the target to be confirmed as a moving target from the range-azimuth spectrogram; if the power peak is the highest power peak of the range-Doppler map, it is determined that the power peak belongs to the preset moving target power peak; the target to be confirmed as a moving target is determined as a moving target.

[0090] Specifically, in this option, first, according to the known distance information and azimuth information, the power peak of the target to be confirmed is identified from the RA map, and then it is judged whether the power peak is the highest power peak of the RA map. That is, it is judged whether the power value of this power peak is the highest peak of the RA map. If so, it is determined that the power peak matches the aforementioned "its echo intensity becomes larger, and the height (echo intensity) of power peak A on the RA is higher than that of power peak B of other stationary targets", and belongs to the preset moving target power peak. Furthermore, the target to be confirmed as a moving target can be determined as a moving target.

[0091] It is not difficult to see that in this option, directly judging whether the power value of this power peak is the highest peak of the RA map can quickly determine whether the target to be confirmed is a moving target.

[0092] Alternatively, in order to further improve the processing speed, when the multi-target radar body movement recognition device executes step S400, it can identify all the highest power peaks from the range-Doppler map; determine the position information of each highest power peak; if one of all the position information corresponds to the target to be confirmed as a moving target, it is determined that the power peak of the target to be confirmed as a moving target belongs to the preset moving target power peak; the target to be confirmed as a moving target is determined as a moving target.

[0093] Specifically, please refer to Figure 5, the multi-target radar body movement recognition device takes the radar echo signal as data input, calculates the RD spectrograms of each recognized target, and then performs body movement recognition on the RD map through the CFAR detection algorithm. When the multi-target radar body movement recognition device executes step S400, it first performs the statistics of the highest peaks of the RA map, calculates the spatial spectrum according to the power dimension, identifies all the highest power peaks from the RA map, and then determines the position information corresponding to each highest power peak, that is, the distance information and the azimuth information, so as to obtain the possible positions of the body movement targets through the statistics of the highest peak positions. If one of all the position information corresponding to all the highest power peaks is the position information of the body movement target to be confirmed, it is determined that the power peak matches the aforementioned "its echo intensity will become larger, and the height (echo intensity) of power peak A on the RA is higher than that of power peak B of other stationary targets", belonging to the preset body movement target power peak, and then the body movement target to be confirmed can be determined as a body movement target.

[0094] It is worth mentioning that the highest power peak in this embodiment can be the power peak corresponding to the highest power value in the entire RA map, or the power peak corresponding to the highest power value in a certain area of the RA map. For example, the RA map can be divided into multiple regions according to the azimuth, etc., and then the highest power value is determined within the region, so as to improve the efficiency of determining the highest power value. Of course, in order to improve the processing efficiency, the highest power peak can also be the power peak in the entire RA map whose power value is greater than a set threshold.

[0095] Of course, in this selection, the number of body movements can also be discriminated according to the statistically obtained position information to judge whether the body movement recognition based on the RD map is accurate.

[0096] However, judging by the highest peak requires a higher requirement for the target scene, which is more suitable for the in-vehicle or indoor scenes, and is easily interfered by moving objects in the outdoor scene. Therefore, as another option in this embodiment, when the multi-target radar body movement recognition device executes step S400, it can determine the reference power peak of the stationary target among the recognized targets from the range-azimuth spectrogram; if the power difference between the power peak and the reference power peak is greater than the preset threshold, it is determined that the power peak belongs to the preset body movement target power peak; the body movement target to be confirmed is determined as a body movement target.

[0097] Specifically, when performing signal processing, the multi-target radar body movement recognition device can perform target recognition and identify the monitored targets in advance. For example, the detected human target is determined as the recognized target, and other non-human targets are not regarded as recognized targets. At this time, the stationary targets among the recognized targets are the humans who have not made body movements such as turning over, waving, or kicking.

[0098] Then, based on the known distance information and azimuth information of the stationary target, the reference power peak of the stationary target is identified from the RA diagram, and based on the known distance information and azimuth information of the target to be confirmed, the power peak of the target to be confirmed is identified from the RA diagram. If the power difference between the power peak and the reference power peak is greater than the preset threshold, it can be considered that the power value of the target to be confirmed on the RA diagram becomes significantly higher, thus matching the aforementioned "its echo intensity will become larger, and the height (echo intensity) of the power peak A on the RA is higher than the power peak B of other stationary targets", belonging to the preset power peak of the body movement target. Furthermore, the target to be confirmed as the body movement target can be determined as the body movement target.

[0099] Among them, the specific value of the preset threshold is related to the power of the MIMO radar.

[0100] It is not difficult to see that compared with the prior art that only performs body movement analysis independently based on the velocity dimension characteristics in the range-Doppler diagram, this embodiment combines the RD diagram and the range-azimuth spectrum diagram in space. After performing body movement recognition through the range-Doppler diagram, it is determined whether the power peak of the target to be confirmed obtained by preliminary recognition on the range-azimuth spectrum diagram will have a significant increase in the power value on the range-azimuth spectrum diagram, that is, whether it belongs to the preset power peak of the body movement target for effective discrimination, thereby improving the recognition accuracy and improving the false detection situation of multi-target body movement recognition.

[0101] In addition, a second embodiment of the multi-target radar body movement recognition method of the present application is proposed. In this embodiment, the method further includes:

[0102] Step S500: Output the position information of the body movement target and / or the number of body movement targets.

[0103] Specifically, after performing body movement recognition, the position information of the recognized body movement target and / or the number of body movement targets can also be output, which is conducive to subsequent processing by the multi-target radar body movement recognition device, such as action triggering or device control.

[0104] Based on the same inventive concept, please refer to Figure 6 , the present application also provides a multi-target radar body movement recognition device.

[0105] A signal acquisition module, configured to acquire radar echo signals collected by a multiple-input multiple-output radar;

[0106] A signal processing module, configured to perform signal processing on the radar echo signals, determine the recognized targets, and generate a range-azimuth spectrum diagram and a range-Doppler diagram of each of the recognized targets;

[0107] A body movement preliminary recognition module, configured to perform body movement recognition based on each of the range-Doppler diagrams, and determine the targets to be confirmed as body movement targets from each of the recognized targets;

[0108] The body movement confirmation module is used to confirm the body movement target in the distance-azimuth spectrogram. If the power peak of the body movement target to be confirmed belongs to the preset body movement target power peak, the body movement target to be confirmed is determined as the body movement target.

[0109] In a possible embodiment of the present application, the body movement confirmation module includes:

[0110] The first feature extraction unit is used to determine the power peak belonging to the body movement target to be confirmed from the distance-azimuth spectrogram;

[0111] The first feature confirmation unit is used to determine that the power peak belongs to the preset body movement target power peak if the power peak is the highest power peak of the range-Doppler map;

[0112] The first target confirmation unit is used to determine the body movement target to be confirmed as the body movement target.

[0113] In a possible embodiment of the present application, the body movement confirmation module includes:

[0114] The power peak identification unit is used to identify all the highest power peaks from the range-Doppler map;

[0115] The position determination unit is used to determine the position information of each of the highest power peaks;

[0116] The second feature confirmation unit is used to determine that the power peak of the body movement target to be confirmed belongs to the preset body movement target power peak if one of all the position information corresponds to the body movement target to be confirmed;

[0117] The second target confirmation unit is used to determine the body movement target to be confirmed as the body movement target.

[0118] In a possible embodiment of the present application, the body movement confirmation module includes:

[0119] The second feature extraction unit is used to determine the reference power peak of the stationary target among the identified targets from the distance-azimuth spectrogram;

[0120] The difference judgment module is used to determine that the power peak belongs to the preset body movement target power peak if the power difference between the power peak and the reference power peak is greater than the preset threshold;

[0121] The third target confirmation unit is used to determine the body movement target to be confirmed as the body movement target.

[0122] In a possible embodiment of the present application, the multi-target radar body movement recognition device further includes:

[0123] The result output module is used to output the position information of the body movement target and / or the number of the body movement targets.

[0124] In a possible embodiment of the present application, the initial body movement recognition module includes:

[0125] A velocity dimension extraction unit, configured to extract velocity dimension feature data of each of the recognized targets from the range-Doppler map;

[0126] An initial recognition unit, configured to perform body movement recognition based on the velocity dimension feature data, determine a to-be-confirmed body movement target from each of the recognized targets, and recognize whether the recognized target is a to-be-confirmed body movement target.

[0127] It should be noted that the various embodiments of the multi-target radar body movement recognition device in this embodiment and the technical effects achieved thereby can refer to the various embodiments of the multi-target radar body movement recognition method in the foregoing embodiment, which will not be elaborated here.

[0128] In addition, an embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the multi-target radar body movement recognition method as described above are implemented. Therefore, it will not be elaborated here. In addition, the description of the beneficial effects of using the same method will not be elaborated either. For the technical details not disclosed in the embodiment of the computer-readable storage medium involved in the present application, please refer to the description of the method embodiment of the present application. By way of example, the program instructions can be deployed to be executed on one computing device, or on multiple computing devices located at one location, or on multiple computing devices distributed at multiple locations and interconnected by a communication network.

[0129] Those of ordinary skill in the art can understand that all or part of the processes of implementing the methods in the above embodiments can be completed by instructing relevant hardware through a computer program. The above program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above methods. Among them, the above storage medium can be a magnetic disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM), etc.

[0130] In addition, it should be noted that the device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. In addition, in the attached drawings of the device embodiments provided in this application, the connection relationships between the modules indicate that they have communication connections, which can be specifically implemented as one or more communication buses or signal lines. Those of ordinary skill in the art can understand and implement this without creative efforts.

[0131] Through the description of the above embodiments, those skilled in the art can clearly understand that this application can be implemented by means of software plus necessary general-purpose hardware. Of course, it can also be implemented by dedicated hardware including application-specific integrated circuits, dedicated CPUs, dedicated memories, dedicated components, etc. Generally, functions completed by computer programs can be easily implemented by corresponding hardware, and the specific hardware structures for implementing the same function can also be various, such as analog circuits, digital circuits, or dedicated circuits. However, for this application, in more cases, software program implementation is a better implementation method. Based on such an understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a readable storage medium, such as a floppy disk, USB flash drive, mobile hard disk, read-only memory (ROM), random access memory (RAM), magnetic disk, or optical disc of a computer, and includes several instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to execute the methods of various embodiments of this application.

[0132] The above are only the preferred embodiments of this application, and do not limit the scope of this application accordingly. Any equivalent structural or equivalent process transformation made by using the content of the specification and drawings of this application, or directly or indirectly applied in other related technical fields, shall be equally included in the protection scope of this application.

Claims

1. A multi-target radar body movement recognition method, characterized in that, Including: Obtain the radar echo signals collected by a multiple-input multiple-output radar; Perform signal processing on the radar echo signals to identify the recognized targets, and generate a range-azimuth spectrogram and the range-Doppler diagrams of the recognized targets; Perform body movement recognition based on the range-Doppler diagrams respectively, and determine the to-be-confirmed body movement targets from the recognized targets; In the range-azimuth spectrogram, if the power peak of the to-be-confirmed body movement target belongs to a preset body movement target power peak, then determine the to-be-confirmed body movement target as a body movement target.

2. The multi-target radar body movement recognition method according to claim 1, characterized in that, The step of, in the range-azimuth spectrogram, if the power peak of the to-be-confirmed body movement target belongs to a preset body movement target power peak, then determine the to-be-confirmed body movement target as a body movement target, includes: Determine the power peak belonging to the to-be-confirmed body movement target from the range-azimuth spectrogram; If the power peak is the highest power peak of the range-Doppler diagram, then determine that the power peak belongs to a preset body movement target power peak; Determine the to-be-confirmed body movement target as a body movement target.

3. The multi-objective radar body movement recognition method according to claim 1, wherein The step of, in the range-azimuth spectrogram, if the power peak of the to-be-confirmed body movement target belongs to a preset body movement target power peak, then determine the to-be-confirmed body movement target as a body movement target, includes: Identify all the highest power peaks from the range-Doppler diagram; Determine the position information of each of the highest power peaks; If one of all the position information corresponds to the to-be-confirmed body movement target, then determine that the power peak of the to-be-confirmed body movement target belongs to a preset body movement target power peak; Determine the to-be-confirmed body movement target as a body movement target.

4. The multi-objective radar body movement recognition method according to claim 1, wherein The step of, in the range-azimuth spectrogram, if the power peak of the to-be-confirmed body movement target belongs to a preset body movement target power peak, then determine the to-be-confirmed body movement target as a body movement target, includes: Determine the reference power peak of the stationary target among the recognized targets from the range-azimuth spectrogram; If the power difference between the power peak and the reference power peak is greater than a preset threshold, then determine that the power peak belongs to a preset body movement target power peak; Determine the to-be-confirmed body movement target as a body movement target.

5. The multi-target radar body movement recognition method according to any one of claims 1 to 4, characterized in that, After the step of, in the range-azimuth spectrogram, if the power peak of the to-be-confirmed body movement target belongs to a preset body movement target power peak, then determine the to-be-confirmed body movement target as a body movement target, the method further includes: Output the position information of the body movement target and / or the number of the body movement targets.

6. The multi-objective radar body movement recognition method according to any one of claims 1 to 4, characterized in that, The step of performing body movement recognition based on the range-Doppler diagrams respectively, and determining the to-be-confirmed body movement targets from the recognized targets, includes: For each recognized target, extract the velocity dimension feature data of the recognized target from the range-Doppler diagram; Perform body movement recognition based on the velocity dimension feature data to identify whether the recognized target is a to-be-confirmed body movement target, so as to determine the to-be-confirmed body movement targets from the recognized targets.

7. A multi-target radar body movement recognition device, characterized in that, Including: A signal acquisition module, configured to obtain the radar echo signals collected by a multiple-input multiple-output radar; A signal processing module, configured to perform signal processing on the radar echo signals to identify the recognized targets, and generate a range-azimuth spectrogram and the range-Doppler diagrams of the recognized targets; The body movement initial recognition module is used to perform body movement recognition based on each of the distance-Doppler maps, and determine the body movement target to be confirmed from each of the recognized targets; The body movement confirmation module is used to, in the distance-azimuth spectrum map, if the power peak of the body movement target to be confirmed belongs to the preset body movement target power peak, determine the body movement target to be confirmed as a body movement target.

8. The multi-objective radar body movement recognition device according to claim 7, characterized in that The body movement confirmation module includes: The first feature extraction unit is used to determine the power peak belonging to the body movement target to be confirmed from the distance-azimuth spectrum map; The first feature confirmation unit is used to, if the power peak is the highest power peak of the distance-Doppler map, determine that the power peak belongs to the preset body movement target power peak; The first target confirmation unit is used to determine the body movement target to be confirmed as a body movement target; and / or The body movement confirmation module includes: The power peak recognition unit is used to recognize all the highest power peaks from the distance-Doppler map; The position determination unit is used to determine the position information of each of the highest power peaks; The second feature confirmation unit is used to, if one of all the position information corresponds to the body movement target to be confirmed, determine that the power peak of the body movement target to be confirmed belongs to the preset body movement target power peak; The second target confirmation unit is used to determine the body movement target to be confirmed as a body movement target; and / or The body movement confirmation module includes: The second feature extraction unit is used to determine the reference power peak of the stationary target among the recognized targets from the distance-azimuth spectrum map; The difference judgment module is used to, if the power difference between the power peak and the reference power peak is greater than the preset threshold, determine that the power peak belongs to the preset body movement target power peak; The third target confirmation unit is used to determine the body movement target to be confirmed as a body movement target; and / or The multi-target radar body movement recognition device further includes: The result output module is used to output the position information of the body movement target and / or the number of the body movement targets; and / or The body movement initial recognition module includes: The velocity dimension extraction unit is used to, for each of the recognized targets, extract the velocity dimension feature data of the recognized target from the distance-Doppler map; The initial recognition unit is used to perform body movement recognition based on the velocity dimension feature data, determine the body movement target to be confirmed from each of the recognized targets, and recognize whether the recognized target is the body movement target to be confirmed.

9. A multi-target radar body movement recognition device, characterized in that It includes: A processor, a memory, and a computer program stored in the memory, and when the computer program is run by the processor, it implements the multi-target radar body movement recognition method according to any one of claims 1 to 6.

10. A computer-readable storage medium, characterized in that, A computer program is stored on the computer-readable storage medium, and when the computer program is executed by the processor, it implements the multi-target radar body movement recognition method according to any one of claims 1 to 6.

Images