A method, device, equipment and storage medium for predicting flight path

Through distributed algorithm and velocity vector angle correction combined with ridge regression method, the trajectory prediction problem in strong noise and high track density scenarios is solved, the effect and calculation efficiency of the track prediction model are optimized, and false tracks and data are reduced Storage amount.

CN117198042BActive Publication Date: 2024-12-06THREE GORGES INTELLIGENT CONTROL TECHNOLOGY CO LTD
View PDF 2 Cites 0 Cited by

Patent Information

Application Number
CN202311079669.X
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2023-08-25
Publication Date
2024-12-06
Estimated Expiration
2043-08-25

AI Technical Summary

Technical Problem

The existing trajectory prediction methods are not suitable for strong noise and high track density scenarios, resulting in large data storage, slow calculation and false tracks, affecting the accuracy and efficiency of the prediction results.

Method used

Use distributed algorithm to create a track prediction model, and use the target's velocity vector angle at adjacent sensor samples to correct it, and use the ridge regression method to perform regularization processing, and allocate adaptive computing nodes for prediction to optimize track prediction. Effect and calculation efficiency.

Benefits of technology

Through denoising and reducing overfitting errors, the prediction effect of the track prediction model is improved and the computing efficiency of the distributed logic algorithm is improved.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN117198042B_ABST
    Figure CN117198042B_ABST
Patent Text Reader

Abstract

The present invention discloses a track prediction method, device, equipment and storage medium, the method comprising: creating a first track prediction model based on a distributed algorithm; using the velocity vector angle of the target at adjacent sensor sample points to correct the first track prediction model to obtain a second track prediction model; assigning a computing power node that is compatible with the current operation type to the second track prediction model for track prediction. The present invention optimizes the prediction effect of the track prediction model by creating a distributed track prediction model, and using the velocity vector angle for denoising, and reducing the overfitting error that may occur in the track prediction model based on the ridge regression method, and by assigning a suitable computing power node to the track prediction model, the operation efficiency of the distributed logic algorithm is improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a track prediction method, device, equipment and storage medium. Background Art

[0002] With the rapid development of social economy, radar monitoring technology has gradually entered the public's field of vision. The technical means of using radar to track targets can be applied to traffic business. Tracking refers to the processing of radar measurements of targets in order to estimate the target state. Measurement refers to the observed value related to the target state, so measurement can also be called measurement or observation. The track is the motion trajectory formed by the target state estimated by the set of measurements from the same target, that is, the tracking trajectory.

[0003] However, some current trajectory prediction methods split the tracks for all measurement points of the associated gate, which is not suitable for scenes with strong noise and high track density. In addition, the data storage volume is large, which is not conducive to fast start calculation. In addition, there are many false tracks, which not only affects the accuracy of the track prediction results, but also affects the efficiency of track prediction. Summary of the invention

[0004] In order to solve the above problems, the embodiments of the present application provide a track prediction method, device, equipment and storage medium.

[0005] In a first aspect, an embodiment of the present application provides a track prediction method, the method comprising:

[0006] Creating the first track prediction model based on a distributed algorithm;

[0007] The first track prediction model is corrected using the velocity vector angle of the target at adjacent sensor sample points to obtain a second track prediction model;

[0008] A computing node that matches the current operation type is allocated to the second track prediction model to perform track prediction.

[0009] Preferably, the first track prediction model is:

[0010] ;

[0011] in, is the temporary track state estimation result obtained by polynomial fitting; is the measurement result at the kth moment in the lth track sequence; R(k) is the track covariance matrix, and H(k) is the measurement matrix.

[0012] Preferably, before correcting the first track prediction model using the velocity vector angle of the target at adjacent sensor sample points, the method further includes:

[0013] The velocity vector angle of the target at adjacent sensor sampling points is obtained; the velocity vector angle θ satisfies the following equation:

[0014] ;

[0015] Among them, v(k) and v(k+1) are the velocity vectors of the target estimated using adjacent sensor samples.

[0016] Preferably, the method of using the velocity vector angle of the target at adjacent sensor sample points to correct the first track prediction model to obtain the second track prediction model includes:

[0017] If the velocity vector angle θ is greater than a preset threshold, the track initiation process of the current sensor sample point is stopped.

[0018] Preferably, after obtaining the second track prediction model, the method further includes:

[0019] Regularizing the second track prediction model based on the ridge regression method to obtain a data prediction fitting result;

[0020] If the fitting result indicates that the second track prediction model is overfitted, the sensor sample points are screened;

[0021] The second track prediction model is modified based on the screened sensor samples.

[0022] Preferably, before allocating a computing power node that is compatible with the current operation type to the second track prediction model for track prediction, the method further includes:

[0023] The current operation type of the second track prediction model is obtained; the operation type includes logical operation, parallel calculation and neural network calculation.

[0024] Preferably, the step of allocating a computing power node that matches the current operation type to the second track prediction model for track prediction includes:

[0025] Obtain the idle computing power corresponding to each type of computing power node of the server;

[0026] Based on the idle computing power, a computing power node that matches the current operation type is allocated to the second track prediction model for track prediction.

[0027] In a second aspect, an embodiment of the present application provides a track prediction device, the device comprising:

[0028] A creation module, used for creating a first track prediction model based on a distributed algorithm;

[0029] A correction module, used to correct the first track prediction model by using the velocity vector angle of the target at adjacent sensor sample points to obtain a second track prediction model;

[0030] The prediction module is used to allocate a computing power node that is compatible with the current operation type to the second track prediction model for track prediction.

[0031] In a third aspect, an embodiment of the present application provides an electronic 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 steps of the method provided in the first aspect or any possible implementation of the first aspect are implemented.

[0032] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method provided in the first aspect or any possible implementation manner of the first aspect.

[0033] The beneficial effects of the present invention are as follows: by creating a distributed track prediction model, using the velocity vector angle for denoising, and reducing the overfitting error that may occur in the track prediction model based on the ridge regression method, the prediction effect of the track prediction model is optimized, and by allocating appropriate computing power nodes to the track prediction model, the computing efficiency of the distributed logic algorithm is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments 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 work.

[0035] Figure 1 A schematic diagram of a flow chart of a track prediction method provided in an embodiment of the present application;

[0036] Figure 2 A schematic diagram of the structure of a track prediction device provided in an embodiment of the present application;

[0037] Figure 3 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0038] The technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application.

[0039] In the following introduction, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance. The following introduction provides multiple embodiments of the present application, and different embodiments can be replaced or combined, so the present application can also be considered to include all possible combinations of the same and / or different embodiments recorded. Therefore, if one embodiment includes features A, B, and C, and another embodiment includes features B and D, then the present application should also be considered to include embodiments containing one or more of all other possible combinations of A, B, C, and D, although the embodiment may not be clearly recorded in the following text.

[0040] The following description provides examples and does not limit the scope, applicability or examples set forth in the claims. Changes may be made to the functions and arrangements of the elements described without departing from the scope of the present application. Various processes or components may be appropriately omitted, substituted or added to each example. For example, the described method may be performed in an order different from the order described, and various steps may be added, omitted or combined. In addition, features described in some examples may be combined in other examples.

[0041] See also Figure 1 , Figure 1 : is a flow chart of a track prediction method provided in an embodiment of the present application. In an embodiment of the present application, the method includes:

[0042] Step S110: creating a first track prediction model based on a distributed algorithm.

[0043] Distributed algorithm is a method of operation for the purpose of realizing multiplication operation. When completing the multiplication and addition function, the distributed algorithm adds the partial products generated by each corresponding bit of each input data in advance to form the corresponding partial products, and then accumulates the partial products to form the final result. Distributed algorithm can greatly reduce the scale of hardware circuits, easily realize pipeline processing, and improve the execution speed of circuits.

[0044] In one example, multiple sensor sample points may be set, each sensor sample point is connected to a corresponding tracker, and the multiple trackers are connected to the same central fusion device, which processes the data collected by the sensor sample points in a unified manner.

[0045] In one possible implementation, the first track prediction model is:

[0046] ;

[0047] in, is the temporary track state estimation result obtained by polynomial fitting; is the measurement result at the kth moment in the lth track sequence; R(k) is the track covariance matrix, and H(k) is the measurement matrix. Here, the l in the lth is the lowercase letter corresponding to the letter L, representing the sequence with sequence number l in multiple flight sequences.

[0048] In this embodiment, the main idea of ​​the algorithm is to form an associated gate by predicting the state at the next moment, retain the points in the associated gate, and then perform logical judgment on the acceleration and speed of the points in the associated gate, retain the point tracks that meet the conditions, and after the preset number of moments are successfully tested continuously, the start is successful, otherwise the start fails. Here, the first track prediction model accumulates information judgment on the track and retains the track that is less than a certain threshold, thereby improving the probability of track detection and reducing false tracks. At the same time, it reduces the amount of data storage, which is more conducive to the rapid start calculation of the track.

[0049] Step S120, using the velocity vector angle of the target at adjacent sensor sample points to correct the first track prediction model, to obtain a second track prediction model.

[0050] In this embodiment, a velocity direction constraint is added to reduce the interference of noise on the start of the flight. Here, the velocity vector angle may include the heading angle, pitch angle and roll angle corresponding to the instantaneous velocity vector. A velocity coordinate system is established according to the instantaneous velocity vector direction of the track target, and then the angles in each direction can be obtained.

[0051] In one possible implementation, before the first track prediction model is corrected using the velocity vector angle of the target at adjacent sensor sample points in step S120, the method further includes:

[0052] Get the velocity vector angle of the target at adjacent sensor sampling points; the velocity vector angle θ satisfies the following equation:

[0053] ;

[0054] Among them, v(k) and v(k+1) are the velocity vectors of the target estimated using adjacent sensor samples.

[0055] In this embodiment, the target velocity vectors estimated by adjacent sensor sample points are v(k) and v(k+1) respectively. On the premise of establishing the above-mentioned velocity coordinate system, the heading angle, pitch angle and roll angle corresponding to the instantaneous velocity vector can also be used to establish the relationship between the velocity coordinate system and the ground rectangular coordinate system, thereby obtaining the velocity vector angle of the target at the adjacent sensor sample points.

[0056] In one possible implementation, step S120, using the velocity vector angle of the target at adjacent sensor sample points to correct the first track prediction model to obtain the second track prediction model, includes:

[0057] If the velocity vector angle θ is greater than the preset threshold, the track initiation process of the current sensor sample point is stopped.

[0058] The velocity vector angle represents the change in the speed direction of the target. The larger the velocity vector angle, the faster the target turns. If the velocity vector angle exceeds the turning ability of the target, the track initiation process of the current sensor sample point needs to be stopped. By correcting the first track prediction model through the velocity vector angle, noise data can be filtered, the data storage volume can be reduced, and it is more conducive to the rapid start calculation of the track.

[0059] In one possible implementation, after obtaining the second track prediction model, the method further includes:

[0060] The second track prediction model is regularized based on the ridge regression method to obtain the data prediction fitting result;

[0061] If the fitting result indicates that the second track prediction model is overfitted, the sensor sample points are screened;

[0062] The second track prediction model is corrected based on the screened sensor samples.

[0063] When there are multiple correlated variables in a linear regression model, their coefficients become less deterministic and exhibit high variance. For example, a large positive coefficient on one variable may be offset by a similarly sized negative coefficient on its correlated variable. Ridge regression avoids this by imposing constraints on the coefficients, which can effectively reduce the probability of overfitting.

[0064] The most common linear regression method is the least squares method:

[0065] ;

[0066] Among them, X is the eigenvalue matrix, y is the target value matrix, and T is the weight constant.

[0067] Ridge regression is Add a positive constant matrix to , whose expression is:

[0068] ;

[0069] Among them, w is the ridge regression estimate and k is the ridge parameter.

[0070] Through the constraints of ridge regression, the probability of data overfitting can be effectively reduced and the prediction accuracy of the second track prediction model can be improved.

[0071] Step S130, assigning a computing node that matches the current operation type to the second track prediction model to perform track prediction.

[0072] Computing power is the key core capability of a device or platform to process business information in order to complete a certain business. It involves the computing power of the device or platform, including logical computing power, parallel computing power, neural network acceleration, etc. Depending on the algorithm being run and the type of data calculation involved, computing power can be divided into logical computing power, parallel computing power, and neural network computing power.

[0073] In one possible implementation, before step S130, assigning a computing node that matches the current operation type to the second track prediction model for track prediction, the method further includes:

[0074] Get the current operation type of the second track prediction model; the operation types include logical operation, parallel calculation and neural network calculation.

[0075] In this embodiment, the current operation type of the second track prediction model is obtained in advance. Correspondingly, the idle computing power of each computing power node can also be calculated through the relevant model.

[0076] It should be noted that for computing chips in the same device or platform, the computing power provided by different types of computing chips can be mapped to a unified dimension through a measurement function. For devices and platforms with heterogeneous computing power, assuming that there are n logic operation chips, m parallel computing chips, and p neural network acceleration chips, the computing power requirements of the business can be uniformly described as a [computing power quantization model]:

[0077]

[0078] In the formula, is the total computing power requirement; f(x) is the mapping function; , and is the mapping ratio coefficient; q1 (TOPS), q2 (FLOPS) and q3 (FLOPS) are the redundant computing power. I, j, k are the corresponding chip sequences in multiple chips.

[0079] In an example, assuming there are three different types of parallel computing chip resources, b1, b2, and b3, then It represents the mapping function of the parallel computing capability that the j-th parallel computing chip b can provide, and q2 represents the redundant computing power of parallel computing.

[0080] In one possible implementation, step S130, allocating a computing node that matches the current operation type to the second track prediction model for track prediction, includes:

[0081] Get the idle computing power corresponding to each type of computing power node on the server;

[0082] Based on the idle computing power, a computing power node that matches the current operation type is allocated to the second track prediction model for track prediction.

[0083] In this embodiment, based on pre-acquisition of the current operation type of the second track prediction model and the idle computing power corresponding to each type of current computing power node, computing power nodes with more idle computing power can be allocated to the second track prediction model to improve the utilization rate of the computing power nodes, thereby ensuring the computing efficiency of the algorithm.

[0084] The embodiment of the present application optimizes the prediction effect of the track prediction model by creating a distributed track prediction model, using the velocity vector angle for denoising, and reducing the overfitting error that may occur in the track prediction model based on the ridge regression method, and improves the computing efficiency of the distributed logic algorithm by allocating appropriate computing power nodes to the track prediction model.

[0085] The following will be combined with the attached Figure 2 , the track prediction device provided in the embodiment of the present application is introduced in detail. It should be noted that, Figure 2 A schematic diagram of a track prediction device provided in an embodiment of the present application, for executing the present application Figure 1 For the convenience of explanation, only the part related to the embodiment of the present application is shown. For the specific technical details not disclosed, please refer to the present application. Figure 1 The embodiment shown.

[0086] See also Figure 2 , Figure 2 Schematic diagram of the structure of a track prediction device provided in an embodiment of the present application. Figure 2 As shown, the track prediction device 200 includes:

[0087] A creation module 210, configured to create a first track prediction model based on a distributed algorithm;

[0088] A correction module 220, configured to correct the first track prediction model using the velocity vector angle of the target at adjacent sensor sample points to obtain a second track prediction model;

[0089] The prediction module 230 is used to allocate a computing power node that is compatible with the current operation type to the second track prediction model for track prediction.

[0090] In one possible implementation, the first track prediction model is:

[0091] ;

[0092] in, is the temporary track state estimation result obtained by polynomial fitting; is the measurement result at the kth moment in the lth track sequence; R(k) is the track covariance matrix, and H(k) is the measurement matrix.

[0093] In one possible implementation, the track prediction device 200 further includes an acquisition module, which is specifically used to:

[0094] Get the velocity vector angle of the target at adjacent sensor sampling points; the velocity vector angle θ satisfies the following equation:

[0095] ;

[0096] Among them, v(k) and v(k+1) are the velocity vectors of the target estimated using adjacent sensor samples.

[0097] In one possible implementation, the correction module 220 is specifically used to:

[0098] If the velocity vector angle θ is greater than the preset threshold, the track initiation process of the current sensor sample point is stopped.

[0099] In one possible implementation, the track prediction device 200 further includes a processing module, which is specifically used to:

[0100] The second track prediction model is regularized based on the ridge regression method to obtain the data prediction fitting result;

[0101] If the fitting result indicates that the second track prediction model is overfitted, the sensor sample points are screened;

[0102] The second track prediction model is corrected based on the screened sensor samples.

[0103] In one possible implementation, the acquisition module is further configured to:

[0104] Get the current operation type of the second track prediction model; the operation types include logical operation, parallel calculation and neural network calculation.

[0105] In one possible implementation, the prediction module 230 is specifically used to:

[0106] Obtain the idle computing power corresponding to each type of computing power node of the server;

[0107] Based on the idle computing power, a computing power node that matches the current operation type is allocated to the second track prediction model for track prediction.

[0108] Those skilled in the art can clearly understand that the technical solutions of the embodiments of the present application can be implemented with the help of software and / or hardware. The "unit" and "module" in this specification refer to software and / or hardware that can independently complete or cooperate with other components to complete specific functions, where the hardware can be, for example, a field programmable gate array (FPGA), an integrated circuit (IC), etc.

[0109] Each processing unit and / or module of the embodiments of the present application may be implemented by an analog circuit that implements the functions described in the embodiments of the present application, or may be implemented by software that executes the functions described in the embodiments of the present application.

[0110] See also Figure 3 , which shows a schematic diagram of the structure of an electronic device involved in an embodiment of the present application, the electronic device can be used to implement Figure 1 The method in the embodiment shown. Figure 3 As shown, the electronic device 300 may include: at least one central processor 301 , at least one network interface 304 , a user interface 303 , a memory 305 , and at least one communication bus 302 .

[0111] The communication bus 302 is used to realize the connection and communication between these components.

[0112] The user interface 303 may include a display screen (Display) and a camera (Camera). Optionally, the user interface 303 may also include a standard wired interface and a wireless interface.

[0113] The network interface 304 may optionally include a standard wired interface or a wireless interface (such as a WI-FI interface).

[0114] Among them, the central processing unit 301 may include one or more processing cores. The central processing unit 301 uses various interfaces and lines to connect various parts of the entire electronic device 300, and executes various functions and processes data of the terminal 300 by running or executing instructions, programs, code sets or instruction sets stored in the memory 305, and calling data stored in the memory 305. Optionally, the central processing unit 31 can be implemented in at least one hardware form of digital signal processing (Digital Signal Processing, DSP), field programmable gate array (Field-Programmable Gate Array, FPGA), and programmable logic array (Programmable Logic Array, PLA). The central processing unit 301 can integrate one or a combination of a central processing unit (Central Processing Unit, CPU), a graphics processing unit (Graphics Processing Unit, GPU) and a modem. Among them, the CPU mainly processes the operating system, user interface and application programs; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; the modem is used to process wireless communications. It can be understood that the above-mentioned modem may not be integrated into the central processing unit 301, and can be implemented separately through a chip.

[0115] Among them, the memory 305 may include a random access memory (Random Access Memory, RAM) and may also include a read-only memory (Read-Only Memory). Optionally, the memory 305 includes a non-transitory computer-readable storage medium. The memory 305 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 305 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area may store data involved in the above-mentioned various method embodiments, etc. The memory 305 may optionally be at least one storage device located away from the aforementioned central processor 301. As Figure 3 As shown, the memory 305 as a computer storage medium may include an operating system, a network communication module, a user interface module, and program instructions.

[0116] The present application also provides a computer-readable storage medium on which a computer program is stored, and when the program is executed by a processor, the steps of the above method are implemented. The computer-readable storage medium may include, but is not limited to, any type of disk, including a floppy disk, an optical disk, a DVD, a CD-ROM, a micro drive, and a magneto-optical disk, a ROM, a RAM, an EPROM, an EEPROM, a DRAM, a VRAM, a flash memory device, a magnetic card or an optical card, a nanosystem (including a molecular memory IC), or any type of medium or device suitable for storing instructions and / or data.

[0117] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present application.

[0118] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0119] In the several embodiments provided in the present application, it should be understood that the disclosed devices can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of the units, which 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 service interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0120] 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.

[0121] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0122] 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 memory. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a memory, including a number of instructions to enable a computer device (which can be a personal computer, server or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned memory includes: U disk, read-only memory (ROM), random access memory (RAM), mobile hard disk, disk or optical disk and other media that can store program codes.

[0123] A person skilled in the art may understand that all or part of the steps in the various methods of the above embodiments may be completed by entering a program to instruct related hardware, and the program may be stored in a computer-readable memory, which may include a flash drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0124] The above is only an exemplary embodiment of the present disclosure, and the scope of the present disclosure cannot be limited thereto. That is, any equivalent changes and modifications made according to the teachings of the present disclosure are still within the scope of the present disclosure. After considering the specification and practicing the disclosure here, those skilled in the art will easily think of the implementation scheme of the present disclosure. This application is intended to cover any modification, use or adaptation of the present disclosure, which follows the general principles of the present disclosure and includes common knowledge or customary technical means in the technical field not recorded in the present disclosure. The description and examples are regarded as exemplary only, and the scope and spirit of the present disclosure are defined by the claims.

Claims

1. A track prediction method, characterized in that: The method comprises: Creating the first track prediction model based on a distributed algorithm; The first track prediction model is corrected using the velocity vector angle of the target at adjacent sensor sample points to obtain a second track prediction model; Allocating a computing node compatible with the current operation type to the second track prediction model to perform track prediction; The first track prediction model is: Among them, z r(l,k) (k) is the temporary track state estimation result obtained by polynomial fitting; is the measurement result at the kth moment in the lth track sequence; R(k) is the track covariance matrix, H(k) is the measurement matrix, and the l in the lth is the lowercase letter corresponding to the letter L, representing the sequence with sequence number l in multiple flight sequences; By predicting the state at the next moment, an associated gate is formed, and the points in the associated gate are retained. Then, the points in the associated gate are logically judged for acceleration and speed, and the point traces that meet the conditions are retained. After the preset number of moments are successfully tested continuously, the start is successful, otherwise the start fails; the first track prediction model judges the track by accumulating information, and retains the track that is less than a certain threshold; Before correcting the first track prediction model using the velocity vector angle of the target at adjacent sensor sample points, the method further includes: The velocity vector angle of the target at adjacent sensor sampling points is obtained; the velocity vector angle θ satisfies the following equation: Among them, v(k) and v(k+1) are the velocity vectors of the target estimated using adjacent sensor samples; The method of correcting the first track prediction model by using the velocity vector angle of the target at adjacent sensor sample points to obtain the second track prediction model includes: If the velocity vector angle θ is greater than a preset threshold, the track initiation process of the current sensor sample point is stopped; Before allocating a computing power node that matches the current operation type to the second track prediction model for track prediction, the method further includes: Acquire the current operation type of the second track prediction model; the operation type includes logical operation, parallel calculation and neural network calculation; The step of allocating a computing power node that matches the current operation type to the second track prediction model for track prediction includes: Obtain the idle computing power corresponding to each type of computing power node of the server; Based on the idle computing power, a computing power node that matches the current operation type is allocated to the second track prediction model for track prediction.

2. The method according to claim 1, characterized in that After obtaining the second track prediction model, the method further includes: Regularizing the second track prediction model based on the ridge regression method to obtain a data prediction fitting result; If the fitting result indicates that the second track prediction model is overfitted, the sensor sample points are screened; The second track prediction model is modified based on the screened sensor samples.

3. A track prediction device, characterized in that: The device comprises: A creation module, used for creating a first track prediction model based on a distributed algorithm; A correction module, used to correct the first track prediction model using the velocity vector angle of the target at adjacent sensor sample points to obtain a second track prediction model; A prediction module, used for allocating a computing power node adapted to the current operation type to the second track prediction model for track prediction; The first track prediction model is: Among them, z r(l,k) (k) is the temporary track state estimation result obtained by polynomial fitting; is the measurement result at the kth moment in the lth track sequence; R(k) is the track covariance matrix, H(k) is the measurement matrix, and the l in the lth is the lowercase letter corresponding to the letter L, representing the sequence with sequence number l in multiple flight sequences; By predicting the state at the next moment, an associated gate is formed, and the points in the associated gate are retained. Then, the points in the associated gate are logically judged for acceleration and speed, and the point traces that meet the conditions are retained. After the preset number of moments are successfully tested continuously, the start is successful, otherwise the start fails; the first track prediction model judges the track by accumulating information, and retains the track that is less than a certain threshold; The track prediction device further includes an acquisition module, which is used to: The velocity vector angle of the target at adjacent sensor sampling points is obtained; the velocity vector angle θ satisfies the following equation: Among them, v(k) and v(k+1) are the velocity vectors of the target estimated using adjacent sensor samples; The correction module is specifically used for: If the velocity vector angle θ is greater than a preset threshold, the track initiation process of the current sensor sample point is stopped; The acquisition module is also specifically used for: Acquire the current operation type of the second track prediction model; the operation type includes logical operation, parallel calculation and neural network calculation; The prediction module is specifically used for: Obtain the idle computing power corresponding to each type of computing power node of the server; Based on the idle computing power, a computing power node that matches the current operation type is allocated to the second track prediction model for track prediction.

4. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 2 are implemented.

5. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 2 are implemented.

Citation Information

Patent Citations

  • Method for analyzing high precision 4D flight trajectory of airplane based on real-time radar data

    CN101692315A

  • Multi-ocean-robot cooperative circular scanning method based on distributed model predictive control

    CN108897215A