A TWS radar target tracking method, device, server, and readable storage medium

Abstract

The present application is applicable to the field of radar tracking and scanning technology, and provides a TWS radar target tracking method, device, server and readable storage medium, the method comprising: within a preset range, observing the initial position point corresponding to the target to be confirmed scanned by the radar; identifying the important target and the secondary target in the target to be confirmed according to the initial position point; forming a first motion trajectory corresponding to the important target according to the first position point set and the first predicted target position point; forming a second motion trajectory corresponding to the secondary target according to the second position point set and the second predicted target position point. It can be seen that the present application distinguishes the important targets and secondary targets among the multiple targets in the terminal device, controls the radar to allocate different antenna beam energies to scan and track different targets respectively, and predicts the predicted position points of different targets, thereby obtaining the motion trajectory of all targets, ensuring the advance scanning and tracking of multiple targets, and improving the accuracy of scanning and tracking.

Description

Technical Field

[0001] The present application belongs to the field of radar tracking and scanning technology, and in particular, relates to a TWS radar target tracking method, device, server and readable storage medium. Background Art

[0002] With the rapid development of modern high technology, radar positioning and tracking technology is not only used in the military field, but also has more and more applications in some civil security fields. However, in many security fields, there are often multiple targets, which means that when the radar is tracking one target, it cannot continue to scan and track other targets in the airspace. Summary of the invention

[0003] The embodiments of the present application provide a TWS radar target tracking method, device, server and readable storage medium, which can solve the problem in the prior art that the radar cannot track and scan all targets when there are multiple targets.

[0004] In a first aspect, an embodiment of the present application provides a TWS radar target tracking method, including:

[0005] Within the preset range, observe the initial position points corresponding to the unconfirmed targets scanned by the radar; wherein each unconfirmed target corresponds to an initial position point;

[0006] Identifying the important target and the secondary target among the targets to be confirmed according to the initial position point;

[0007] Controlling the radar to scan the important target according to the first antenna beam to obtain a first position point set corresponding to the important target;

[0008] Controlling the radar to scan the secondary target according to the second antenna beam to obtain a second position point set corresponding to the secondary target;

[0009] Tracking the important target based on the first position point set, predicting a first predicted target position point of the important target, and forming a first motion trajectory corresponding to the important target according to the first position point set and the first predicted target position point;

[0010] Tracking the secondary target based on the second position point set, predicting a second predicted target position point of the secondary target, and forming a second motion trajectory corresponding to the secondary target according to the second position point set and the second predicted target position point;

[0011] The first motion trajectory and the second motion trajectory are translated to the same coordinate system to generate a target motion trajectory.

[0012] In a possible implementation manner of the first aspect, identifying the important target and the secondary target among the targets to be confirmed according to the initial position point includes:

[0013] Mapping the initial position point from the radar coordinate system to the image coordinate system;

[0014] Acquire an image to be processed corresponding to the target to be confirmed photographed by a camera according to the initial position point in the image coordinate system; wherein each target to be confirmed corresponds to one image to be processed;

[0015] The image to be processed corresponding to the target to be confirmed is input into a pre-trained target detection model, and the important target and the secondary target in the target to be confirmed are output.

[0016] In a possible implementation of the first aspect, the pre-trained target detection model includes a pre-trained feature extraction sub-model and a pre-trained determination model;

[0017] Inputting the image to be processed corresponding to the target to be confirmed into a pre-trained target detection model, and outputting the important targets and secondary targets in the target to be confirmed, including:

[0018] Inputting the image to be processed into a pre-trained feature extraction sub-model, and outputting a feature image;

[0019] Identify feature points in the feature image according to a preset feature descriptor;

[0020] Encode the feature points according to a preset encoding method to obtain a feature vector;

[0021] The feature vector is input into a pre-trained determination model to obtain important targets and secondary targets among the targets to be confirmed.

[0022] In a possible implementation manner of the first aspect, tracking the important target based on the first position point set, predicting a first predicted target position point of the important target, and forming a first motion trajectory corresponding to the important target according to the first position point set and the first predicted target position point, including:

[0023] Establishing a first target tracking model corresponding to the important target according to the first position point set;

[0024] Based on the first target tracking model, a first predicted target position point of the important target is predicted.

[0025] In a possible implementation manner of the first aspect, establishing a first target tracking model corresponding to the important target according to the first position point set includes:

[0026] Selecting a corresponding first basic tracking model according to the first position point set; wherein the first basic tracking model is any one of the following models: CV model, CA model, singer model or current statistical model;

[0027] The first target tracking model is generated according to the following formula:

[0028]

[0029]

[0030] Among them, X k (r1) is the first state variable of the important target r1 at time k, Z k (r1) is the first measurement of the important target r1 at time k, is the state transfer matrix of the basic tracking model j from time K-1 to time K, is the system noise sequence of the first basic tracking model j, is the measurement noise sequence of model j The covariance of The covariance of Wherein, the first state variable is a first acceleration and a first velocity of the important target, and the first measurement is a first position point of the important target;

[0031] The first target tracking model is filtered according to a preset filtering algorithm to optimize the first target tracking model.

[0032] In a possible implementation manner of the first aspect, tracking the secondary target based on the second position point set, predicting a second predicted target position point of the secondary target, and forming a second motion trajectory corresponding to the secondary target according to the second position point set and the second predicted target position point, including:

[0033] Establishing a second target tracking model corresponding to the secondary target according to the second position point set;

[0034] Based on the second target tracking model, a second predicted target position point of the secondary target is predicted.

[0035] In a possible implementation manner of the first aspect, establishing a second target tracking model corresponding to the secondary target according to the second position point set includes:

[0036] Selecting a corresponding second basic tracking model according to the second position point set; wherein the second basic tracking model is any one of the following models: CV model, CA model, singer model or current statistical model;

[0037] The second target tracking model is generated according to the following formula:

[0038]

[0039]

[0040] Among them, X k (r2) is the second state variable of the secondary target r2 at time k, Z k (r2) is the second measurement of the secondary target r2 at time k, is the state transfer matrix of the second basic tracking model m from time K-1 to time K, is the system noise sequence of the second basic tracking model m, is the measurement noise sequence of the second basic tracking model m, The covariance of The covariance of Wherein, the second state variable is a second acceleration and a second velocity of the secondary target, and the second measurement is a second position point of the secondary target;

[0041] The second target tracking model is filtered according to a preset filtering algorithm to optimize the second target tracking model.

[0042] In a second aspect, an embodiment of the present application provides a TWS radar target tracking device, including:

[0043] An observation module is used to observe the initial position points corresponding to the unconfirmed targets scanned by the radar within a preset range; wherein each unconfirmed target corresponds to an initial position point;

[0044] An identification module, used for identifying the important target and the secondary target among the targets to be confirmed according to the initial position point;

[0045] A first control module is used to control the radar to scan the important target according to the first antenna beam to obtain a first position point set corresponding to the important target;

[0046] A second control module is used to control the radar to scan the secondary target according to the second antenna beam to obtain a second position point set corresponding to the secondary target;

[0047] A first tracking prediction module is used to track the important target based on the first position point set, predict a first predicted target position point of the important target, and form a first motion trajectory corresponding to the important target according to the first position point set and the first predicted target position point;

[0048] A second tracking prediction module is used to track the secondary target based on the second position point set, predict a second predicted target position point of the secondary target, and form a second motion trajectory corresponding to the secondary target according to the second position point set and the second predicted target position point;

[0049] The translation module is used to translate the first motion trajectory and the second motion trajectory to the same coordinate system, generate and send a target motion trajectory to a user terminal, and instruct the user terminal to display the target motion trajectory to the user.

[0050] In a possible implementation of the second aspect, the identification module includes:

[0051] A mapping submodule, used for mapping the initial position point from the radar coordinate system to the image coordinate system;

[0052] A collection submodule, used for collecting the image to be processed corresponding to the target to be confirmed taken by the camera according to the initial position point in the image coordinate system; wherein each target to be confirmed corresponds to one image to be processed;

[0053] The detection submodule is used to input the to-be-processed image corresponding to the to-be-confirmed target into a pre-trained target detection model, and output the important targets and secondary targets in the to-be-confirmed target.

[0054] In a possible implementation of the second aspect, the pre-trained target detection model includes a pre-trained feature extraction sub-model and a pre-trained determination model;

[0055] The detection submodule comprises:

[0056] An extraction unit, used for inputting the image to be processed into a pre-trained feature extraction sub-model and outputting a feature image;

[0057] A recognition unit, used for recognizing feature points in the feature image according to a preset feature descriptor;

[0058] An encoding unit, used for encoding the feature points according to a preset encoding method to obtain a feature vector;

[0059] The determination unit is used to input the feature vector into a pre-trained determination model to obtain the important target and the secondary target among the targets to be confirmed.

[0060] In a possible implementation manner of the second aspect, the first tracking prediction module includes:

[0061] A first tracking submodule, configured to establish a first target tracking model corresponding to the important target according to the first position point set;

[0062] The first prediction submodule is used to predict a first predicted target position point of the important target based on the first target tracking model.

[0063] In a possible implementation manner of the second aspect, the second tracking prediction module includes:

[0064] A second tracking submodule, establishing a second target tracking model corresponding to the secondary target according to the second position point set;

[0065] The second prediction submodule predicts a second predicted target position point of the secondary target based on a second target tracking model.

[0066] In a third aspect, an embodiment of the present application provides a terminal device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method described in the first aspect above when executing the computer program.

[0067] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method described in any one of the first aspects above is implemented.

[0068] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0069] In an embodiment of the present application, in an application scenario of multi-target scanning and tracking, the terminal device distinguishes between important targets and secondary targets, controls the radar to allocate different antenna beam energies to scan and track different targets respectively, and predicts the predicted position points of different targets, thereby obtaining the motion trajectories of all targets, ensuring the advance scanning and tracking of multiple targets, and improving the accuracy of scanning and tracking. BRIEF DESCRIPTION OF THE DRAWINGS

[0070] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0071] Figure 1 It is a flowchart of a TWS radar target tracking method provided in an embodiment of the present application;

[0072] Figure 2 It is a schematic diagram of the structure of a TWS radar target tracking device provided in an embodiment of the present application;

[0073] Figure 3It is a structural diagram of the terminal device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0074] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also 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 prevent unnecessary details from obstructing the description of the present application.

[0075] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, wholes, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or combinations thereof.

[0076] It should also be understood that the term “and / or” used in the specification and appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0077] As used in the specification and appended claims of this application, the term "if" can be interpreted as "when" or "uponce" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" can be interpreted as meaning "uponce it is determined" or "in response to determining" or "uponce [described condition or event] is detected" or "in response to detecting [described condition or event]", depending on the context.

[0078] In addition, in the description of the present application specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0079] References to "one embodiment" or "some embodiments" etc. described in the specification of this application mean that one or more embodiments of the present application include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0080] It should be noted that the TWS radar target tracking method implemented in the present application is applied to a terminal device, which is connected to a radar, wherein the radar is preferably a phased array radar.

[0081] Principle: Phased array radar divides the radar antenna into different array units of different sizes. Each unit can independently transmit signal waves, which are synthesized and transmitted together when a target needs to be detected. When different targets need to be detected, the transmission direction of the synthesized signal wave can be changed by changing the transmission frequency or phase of the signal wave, so that targets in different directions can be detected.

[0082] It should be noted that the location points of the embodiments of the present application may be in different coordinate systems, including a radar coordinate system, an image coordinate system or a world coordinate system, etc. The coordinate systems may be mapped, which will not be described in detail here.

[0083] The technical solution provided by the embodiments of the present application will be introduced below through specific examples.

[0084] See also Figure 1 , is a flow chart of a TWS radar target tracking method provided in an embodiment of the present application. As an example but not a limitation, the method can be applied to a terminal device, which is connected to a radar and a camera respectively. The method includes the following steps:

[0085] Step S101: Observe the initial position point corresponding to the target to be confirmed scanned by the radar within a preset range.

[0086] Among them, each target to be confirmed corresponds to an initial position point; the target refers to birds, unmanned aircraft, model aircraft or some floating objects in the air (such as balloons, etc.), and the preset range refers to important areas in the security field such as civil airports, border lines or nuclear power plants.

[0087] Step S102: identifying important targets and secondary targets among the targets to be confirmed according to the initial position points.

[0088] Among them, the initial position point refers to the position point where an unidentified target is first scanned within the scanning range of the radar; important targets can refer to birds, unmanned aircraft, etc.; secondary targets refer to slower floating objects in the air (such as balloons, etc.).

[0089] Generally, in the prior art, a matching rangefinder is set at the radar to distinguish important targets from secondary targets according to the moving speed of the target, but the distinguishing dimension is single and the targets cannot be distinguished accurately. The embodiment of the present application uses image recognition to distinguish important targets from secondary targets in the target, and distinguishes the targets from multiple dimensions in combination with image information to improve the distinction accuracy.

[0090] In a specific application, identifying the important target and the secondary target among the targets to be confirmed according to the initial position point includes the following steps:

[0091] Step S102-1: Map the initial position point from the radar coordinate system to the image coordinate system.

[0092] In a specific application, the initial position point is mapped from the radar coordinate system to the world coordinate system, and then mapped from the world coordinate system to the image coordinate system.

[0093] Step S102 - 2 : acquiring an image to be processed corresponding to the target to be confirmed and captured by the camera according to the initial position point in the image coordinate system.

[0094] Wherein, each target to be confirmed corresponds to an image to be processed, the terminal device is connected to a camera, the camera includes an infrared camera and a visible light camera, and the camera and the radar are calibrated.

[0095] It is understandable that while the radar is observing the target, the camera is also photographing the target. Then, when the terminal device needs to distinguish the target, it can map the initial position point from the radar coordinate system to the image coordinate system, so as to find the image corresponding to the target to be confirmed photographed by the acquisition camera according to the initial position point in the image coordinate system, instead of matching the image corresponding to each position point observed by the radar at the same time as the terminal device processes the position point of the target observed by the radar, thereby achieving the purpose of saving computer resources.

[0096] Optionally, calibrate the radar and the corresponding camera, calibrate the radar's external parameters, and calibrate the camera's external parameters to internal parameters. Calibration is to find the spatial transformation relationship between the radar and the camera. The conversion between different coordinate systems requires a rotation matrix R and a translation matrix T, which is prepared for the subsequent radar and camera data fusion. Specifically, the Zhang Dingyou calibration method can be used to calibrate the camera's internal parameters, and the CalibrationToolKit joint tool provided by Autoware can be used to calibrate the radar's external parameters and the camera's external parameters.

[0097] Step S102-3: input the image to be processed corresponding to the target to be confirmed into a pre-trained target detection model, and output the important targets and secondary targets in the target to be confirmed.

[0098] Among them, the pre-trained target detection model includes a pre-trained feature extraction sub-model and a pre-trained judgment model. The feature extraction sub-model is preferably a Fast R-CNN model, and of course it can also be an R-CNN model, etc. The judgment model is preferably a CAN generative adversarial model, and of course it can also be a CNN convolutional neural network model, etc.

[0099] In a specific application, the image to be processed is input into a pre-trained feature extraction sub-model, a feature image is output, feature points in the feature image are identified according to a preset feature descriptor, the feature points are encoded according to a preset encoding method, and a feature vector is obtained. The feature vector is input into a pre-trained judgment model to obtain important targets and secondary targets among the targets to be confirmed.

[0100] Among them, the preset feature descriptor can be a SIFI feature descriptor, a SURF feature descriptor or a Harris feature descriptor, etc., and the preset encoding method can be one-hot encoding or word2vec encoding.

[0101] Step S103: Control the radar to scan the important target according to the first antenna beam to obtain a first position point set corresponding to the important target.

[0102] Step S104: Control the radar to scan the secondary target according to the second antenna beam to obtain a second position point set corresponding to the secondary target.

[0103] The energy of the first antenna beam is greater than the energy of the second antenna beam.

[0104] It is understandable that the terminal device allocates the main antenna beam to important targets and the secondary antenna beam to secondary targets, so that the radar scans the important targets more frequently, which can ensure the tracking and monitor the normal scanning of other targets by the antenna.

[0105] Step S105: Track the important target based on the first position point set, predict the first predicted target position point of the important target, and form a first motion trajectory corresponding to the important target according to the first position point set and the first predicted target position point.

[0106] It can be understood that the present application establishes a corresponding mathematical model of important target pairs through partial position points of important targets, which facilitates the description of the corresponding position points of important targets at each moment, and then predicts the predicted target position points of important targets based on the instant position points obtained by the target tracking model.

[0107] In a specific application, an important target is tracked based on a first position point set, a first predicted target position point of the important target is predicted, and a first motion trajectory corresponding to the important target is formed according to the first position point set and the first predicted target position point, including:

[0108] Step S105-1: establishing a first target tracking model corresponding to the important target according to the first position point set.

[0109] Exemplarily, establishing a first target tracking model corresponding to the important target according to the first position point set includes:

[0110] Step S105-1-1: Select a corresponding first basic tracking model according to the first position point set.

[0111] The first basic tracking model is any one of the following models: CV model, CA model, Singer model or current statistical model. The CV model refers to a uniform linear motion model, the CA model refers to a uniformly accelerated motion model, the Singer model refers to a first-order time-dependent model with a zero acceleration mean, and the current statistical model refers to a first-order time-dependent model with a non-zero acceleration mean.

[0112] Step S105-1-2: Generate a first target tracking model according to the following formula:

[0113]

[0114]

[0115] Among them, X k (r1) is the first state variable of the important target r1 at time k, Z k (r1) is the first measurement of the important target r1 at time k, is the state transfer matrix of the basic tracking model j from time K-1 to time K, is the system noise sequence of the first basic tracking model j, is the measurement noise sequence of model i The covariance of The covariance of The first state variable is a first acceleration and a first velocity of the important target, and the first measurement is a first position point of the important target;

[0116] Step S105-1-3: filter the first target tracking model according to a preset filtering algorithm to optimize the first target tracking model.

[0117] The preset filtering algorithm includes a Kalman filtering algorithm or a smoothing filtering algorithm.

[0118] Step S105-2: predicting a first predicted target position point of an important target based on a first target tracking model.

[0119] Exemplarily, predicting a first predicted target position point of an important target based on a first target tracking model includes:

[0120] Step S105-2-1: Determine the first instant location point of the important target based on the first tracking target model.

[0121] Step S105-2-1, input the first instant position point into the pre-trained SVM regression model to obtain the first predicted target point of the important target.

[0122] In specific applications, the first tracking target model can be used to determine the first instant position point corresponding to the important target at each moment, and then the position point corresponding to the important target at each moment is regressed and fitted based on the pre-trained SVM regression model. The coordinate points at each moment are substituted into each regression path of the pre-trained SVM regression model, and the curve that fits the motion trajectory of the important target is found according to the regression fitting degree of each regression equation, and the predicted target point of the important target, that is, the final destination, is predicted based on the fitted curve.

[0123] Step S106: Track the secondary target based on the second position point set, predict a second predicted target point of the secondary target, and form a second motion trajectory corresponding to the secondary target based on the second position point set and the second predicted target point.

[0124] It can be understood that the present application establishes a mathematical model corresponding to the important target through partial position points of the secondary target, which facilitates the description of the corresponding position points of the secondary target at each moment, and then predicts the predicted target point of the secondary target based on the instant position point obtained by the target tracking model.

[0125] In a specific application, tracking a secondary target based on a second position point set, predicting a second predicted target point of the secondary target, and forming a second motion trajectory corresponding to the secondary target according to the second position point set and the second predicted target point include:

[0126] Step S106-1: Establish a second target tracking model corresponding to the secondary target according to the second position point set.

[0127] Exemplarily, establishing a second target tracking model corresponding to the secondary target according to the second position point set includes:

[0128] Step S106-1-1, select a corresponding second basic tracking model according to the second position point set; wherein the second basic tracking model is any one of the following models: CV model, CA model, Singer model or current statistical model. Among them, the CV model refers to a uniform linear motion model, the CA model refers to a uniformly accelerated motion model, the Singer model refers to a first-order time-correlated model with a zero acceleration mean, and the current statistical model refers to a first-order time-correlated model with a non-zero acceleration mean.

[0129] Step S106-1-2: Generate a second target tracking model according to the following formula:

[0130]

[0131]

[0132] Among them, X k (r2) is the second state variable of the secondary target r2 at time k, Z k (r2) is the second measurement of the secondary target r2 at time k, is the state transfer matrix of the second basic tracking model m from time K-1 to time K, is the system noise sequence of the second basic tracking model m, is the measurement noise sequence of the second basic tracking model m, The covariance of The covariance of The second state variable is a second acceleration and a second velocity of the secondary target, and the second measurement is a second position point of the secondary target.

[0133] Step S106-1-3: filter the second target tracking model according to a preset filtering algorithm to optimize the second target tracking model.

[0134] The preset filtering algorithm includes a Kalman filtering algorithm or a smoothing filtering algorithm.

[0135] Step S106 - 2 : predicting a second predicted target point of the secondary target based on the second target tracking model.

[0136] In a specific application, based on the second target tracking model, predicting the second predicted target point of the secondary target includes:

[0137] Step S106-2-1: Determine the second instant position point of the important target based on the second tracking target model.

[0138] Step S106-2-2: input the second instant location point into the pre-trained SVM regression model to obtain the second predicted target point of the secondary target.

[0139] In specific applications, the second tracking target model can be used to determine the second instant position point corresponding to the secondary target at each moment, and then the position point corresponding to the important target at each moment is regressed and fitted based on the pre-trained SVM regression model. The coordinate points at each moment are substituted into each regression path of the pre-trained SVM regression model, and the curve that fits the motion trajectory of the important target is found according to the regression fitting degree of each regression equation, and the predicted target point of the secondary target, that is, the final destination, is predicted based on the fitted curve.

[0140] Step S107 : translating the first motion trajectory and the second motion trajectory to the same coordinate system to generate a target motion trajectory.

[0141] It can be understood that the first motion trajectory of the important target and the first motion trajectory of the secondary target are translated to the same coordinate system, that is, the radar coordinate system, and merged into the target motion trajectory, which is subsequently displayed for user viewing.

[0142] In an embodiment of the present application, in an application scenario of multi-target scanning and tracking, the terminal device distinguishes between important targets and secondary targets, controls the radar to allocate different antenna beam energies to scan and track different targets respectively, and predicts the predicted position points of different targets, thereby obtaining the motion trajectories of all targets, ensuring the advance scanning and tracking of multiple targets, and improving the accuracy of scanning and tracking.

[0143] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0144] Corresponding to the TWS radar target tracking method described in the above embodiment, Figure 2 A structural block diagram of a TWS radar target tracking device provided in an embodiment of the present application is shown. For ease of explanation, only the parts related to the embodiment of the present application are shown.

[0145] Reference Figure 2 , the device comprises:

[0146] The observation module 21 is used to observe the initial position points corresponding to the unconfirmed targets scanned by the radar within a preset range; wherein each unconfirmed target corresponds to an initial position point;

[0147] An identification module 22, used for identifying the important target and the secondary target among the targets to be confirmed according to the initial position point;

[0148] A first control module 23, used to control the radar to scan the important target according to the first antenna beam to obtain a first position point set corresponding to the important target;

[0149] A second control module 24 is used to control the radar to scan the secondary target according to the second antenna beam to obtain a second position point set corresponding to the secondary target;

[0150] A first tracking prediction module 25 is used to track the important target based on the first position point set, predict a first predicted target position point of the important target, and form a first motion trajectory corresponding to the important target according to the first position point set and the first predicted target position point;

[0151] A second tracking prediction module 26, configured to track the secondary target based on the second position point set, predict a second predicted target position point of the secondary target, and form a second motion trajectory corresponding to the secondary target according to the second position point set and the second predicted target position point;

[0152] The translation module 27 is used to translate the first motion trajectory and the second motion trajectory to the same coordinate system, generate and send a target motion trajectory to the user terminal, and instruct the user terminal to display the target motion trajectory to the user.

[0153] In one possible implementation, the identification module includes:

[0154] A mapping submodule, used for mapping the initial position point from the radar coordinate system to the image coordinate system;

[0155] A collection submodule, used for collecting the image to be processed corresponding to the target to be confirmed taken by the camera according to the initial position point in the image coordinate system; wherein each target to be confirmed corresponds to one image to be processed;

[0156] The detection submodule is used to input the to-be-processed image corresponding to the to-be-confirmed target into a pre-trained target detection model, and output the important targets and secondary targets in the to-be-confirmed target.

[0157] In a possible implementation, the pre-trained target detection model includes a pre-trained feature extraction sub-model and a pre-trained determination model;

[0158] The detection submodule comprises:

[0159] An extraction unit, used for inputting the image to be processed into a pre-trained feature extraction sub-model and outputting a feature image;

[0160] A recognition unit, used for recognizing feature points in the feature image according to a preset feature descriptor;

[0161] An encoding unit, used for encoding the feature points according to a preset encoding method to obtain a feature vector;

[0162] The determination unit is used to input the feature vector into a pre-trained determination model to obtain the important target and the secondary target among the targets to be confirmed.

[0163] In a possible implementation manner, the first tracking prediction module includes:

[0164] A first tracking submodule, configured to establish a first target tracking model corresponding to the important target according to the first position point set;

[0165] The first prediction submodule is used to predict a first predicted target position point of the important target based on the first target tracking model.

[0166] In a possible implementation manner, the second tracking prediction module includes:

[0167] A second tracking submodule, establishing a second target tracking model corresponding to the secondary target according to the second position point set;

[0168] The second prediction submodule predicts a second predicted target position point of the secondary target based on a second target tracking model.

[0169] It should be noted that the information interaction, execution process, etc. between the above-mentioned devices / units are based on the same concept as the method embodiment of the present application. Their specific functions and technical effects can be found in the method embodiment part and will not be repeated here.

[0170] Figure 3 This is a schematic diagram of the structure of the terminal device provided in this application. Figure 3 As shown, the terminal device 3 of this embodiment includes: at least one processor 30, a memory 31, and a computer program 32 stored in the memory 31 and executable on the at least one processor 30, and when the processor 30 executes the computer program 32, the steps in any of the above-mentioned method embodiments are implemented.

[0171] The terminal device 3 may be a computing device such as a desktop computer, a notebook, a PDA, or a cloud server. The terminal device may include, but is not limited to, a processor 30 and a memory 31. Those skilled in the art will appreciate that Figure 3 It is only an example of the terminal device 3 and does not constitute a limitation on the terminal device 3. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, it may also include input and output devices, network access devices, etc.

[0172] The processor 30 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0173] In some embodiments, the memory 31 may be an internal storage unit of the terminal device 3, such as a hard disk or memory of the terminal device 3. In other embodiments, the memory 31 may also be an external storage device of the terminal device 3, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the terminal device 3. Further, the memory 31 may also include both an internal storage unit and an external storage device of the terminal device 3. The memory 31 is used to store an operating system, an application program, a boot loader (BootLoader), data, and other programs, such as the program code of the computer program. The memory 31 may also be used to temporarily store data that has been output or is to be output.

[0174] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0175] An embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in the above-mentioned method embodiments can be implemented.

[0176] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, which can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may at least include: any entity or device capable of carrying the computer program code to the terminal device, a recording medium, a computer memory, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), an electric carrier signal, a telecommunication signal and a software distribution medium. For example, a USB flash drive, a mobile hard disk, a magnetic disk or an optical disk. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electric carrier signals and telecommunication signals.

[0177] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0178] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0179] In the embodiments provided in the present application, it should be understood that the disclosed devices / network equipment and methods can be implemented in other ways. For example, the device / network equipment embodiments described above are merely schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0180] 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 on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0181] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A TWS radar target tracking method, characterized in that: include: Observe the initial position points corresponding to the unconfirmed targets scanned by the radar within the preset range; each unconfirmed target corresponds to one initial position point; Identifying the important target and the secondary target among the targets to be confirmed according to the initial position point; Controlling the radar to scan the important target according to the first antenna beam to obtain a first position point set corresponding to the important target; controlling the radar to scan the secondary target according to the second antenna beam to obtain a second position point set corresponding to the secondary target; Tracking the important target based on the first position point set, predicting a first predicted target position point of the important target, and forming a first motion trajectory corresponding to the important target based on the first position point set and the first predicted target position point; Tracking the secondary target based on the second position point set, predicting a second predicted target position point of the secondary target, and forming a second motion trajectory corresponding to the secondary target based on the second position point set and the second predicted target position point; The first motion trajectory and the second motion trajectory are translated to the same coordinate system to generate a target motion trajectory.

2. The TWS radar target tracking method according to claim 1, wherein: Identifying the important target and the secondary target among the targets to be confirmed according to the initial position point includes: Mapping the initial position point from the radar coordinate system to the image coordinate system; Acquire an image to be processed corresponding to the target to be confirmed, taken by a camera, according to the initial position point in the image coordinate system; wherein each target to be confirmed corresponds to one image to be processed; The image to be processed corresponding to the target to be confirmed is input into a pre-trained target detection model, and the important targets and secondary targets among the targets to be confirmed are output.

3. The TWS radar target tracking method according to claim 2, wherein: The pre-trained target detection model includes a pre-trained feature extraction sub-model and a pre-trained decision model; Inputting the image to be processed corresponding to the target to be confirmed into a pre-trained target detection model, and outputting the important targets and secondary targets in the target to be confirmed, including: Inputting the image to be processed into a pre-trained feature extraction sub-model and outputting a feature image; Identify feature points in the feature image according to a preset feature descriptor; Encode the feature points according to a preset encoding method to obtain a feature vector; The feature vector is input into a pre-trained judgment model to obtain the important targets and secondary targets among the targets to be confirmed.

4. The TWS radar target tracking method according to any one of claims 1 to 3, wherein: Tracking the important target based on the first position point set, predicting a first predicted target position point of the important target, and forming a first motion trajectory corresponding to the important target based on the first position point set and the first predicted target position point, including: Establishing a first target tracking model corresponding to the important target according to the first position point set; Based on the first target tracking model, a first predicted target position point of the important target is predicted.

5. The TWS radar target tracking method according to claim 4, wherein: Establishing a first target tracking model corresponding to the important target according to the first position point set includes: Selecting a corresponding first basic tracking model according to the first set of position points; wherein the first basic tracking model is any one of the following models: CV model, CA model, Singer model or current statistical model; The first target tracking model is generated according to the following formula: Among them, X k (r1) is the first state variable of the important target r1 at time k, Z k (r1) is the first measurement of the important target r1 at time k, is the state transfer matrix of the basic tracking model j from time K-1 to time K, is the system noise sequence of the first basic tracking model j, is the measurement noise sequence of model j The covariance of The covariance of Wherein, the first state variable is the first acceleration and the first velocity of the important target, and the first measurement is the first position point of the important target; The first target tracking model is filtered according to a preset filtering algorithm to optimize the first target tracking model.

6. The TWS radar target tracking method according to any one of claims 1 to 3, wherein: Tracking the secondary target based on the second position point set, predicting a second predicted target position point of the secondary target, and forming a second motion trajectory corresponding to the secondary target based on the second position point set and the second predicted target position point, including: Establishing a second target tracking model corresponding to the secondary target according to the second position point set; Based on the second target tracking model, a second predicted target position point of the secondary target is predicted.

7. The TWS radar target tracking method according to claim 6, wherein: Establishing a second target tracking model corresponding to the secondary target according to the second position point set includes: Selecting a corresponding second basic tracking model according to the second position point set; wherein the second basic tracking model is any one of the following models: CV model, CA model, Singer model or current statistical model; The second target tracking model is generated according to the following formula: Among them, X k (r2) is the second state variable of the secondary target r2 at time k, Z k (r2) is the second measurement of the secondary target r2 at time k, is the state transition matrix of the second basic tracking model m from time K-1 to time K, is the system noise sequence of the second basic tracking model m, is the measurement noise sequence of the second basic tracking model m, The covariance of The covariance of The second state variable is a second acceleration and a second velocity of the secondary target, and the second measurement is a second position point of the secondary target; The second target tracking model is filtered according to a preset filtering algorithm to optimize the second target tracking model.

8. A TWS radar target tracking device, characterized in that: include: An observation module is used to observe the initial position points corresponding to the unconfirmed targets scanned by the radar within a preset range; wherein each unconfirmed target corresponds to an initial position point; an identification module, configured to identify the important target and the secondary target among the targets to be confirmed according to the initial position point; a first control module, configured to control the radar to scan the important target according to a first antenna beam, and obtain a first set of position points corresponding to the important target; a second control module, configured to control the radar to scan the secondary target according to the second antenna beam to obtain a second position point set corresponding to the secondary target; a first tracking and prediction module, configured to track the important target based on the first position point set, predict a first predicted target position point of the important target, and form a first motion trajectory corresponding to the important target based on the first position point set and the first predicted target position point; a second tracking and prediction module, configured to track the secondary target based on the second position point set, predict a second predicted target position point of the secondary target, and form a second motion trajectory corresponding to the secondary target based on the second position point set and the second predicted target position point; The translation module is used to translate the first motion trajectory and the second motion trajectory to the same coordinate system, generate and send a target motion trajectory to the user terminal, and instruct the user terminal to display the target motion trajectory to the user.

9. A terminal device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the method according to any one of claims 1 to 7 is implemented.

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

Images