A target track association method and device based on spatio-temporal grids

Abstract

The present invention discloses a method and device for target track association based on spatio-temporal grids. The method includes obtaining track data information at time T, track data information at time T+1, a track data set at time T, and spatio-temporal grid information, where T is a positive integer. Fusing the track data information at time T, the spatio-temporal grid information, and the track data set at time T to obtain track fusion result information at time T. Fusing the track fusion result information at time T, the spatio-temporal grid information, and the track data information at time T+1 to obtain target track information. It can be seen that by putting multi-source targets globally into spatio-temporal grids and calculating the association degree between targets, the present invention can achieve fast association of target tracks, thereby realizing full-course target tracking of multi-source targets, which is beneficial to reducing the computational complexity and improving the fusion efficiency and accuracy of multi-source target association.

Description

Technical Field

[0001] The present invention relates to the field of information fusion, and particularly to a method and device for target track association based on spatio-temporal grids. Background Art

[0002] Track association is to comprehensively process the target track information obtained by multiple radar sensors, and use methods such as information association, registration, prediction, etc. to obtain the global track of the target as accurately and comprehensively as possible, so as to achieve high-precision and continuous target tracking, and thus more comprehensively reflect the comprehensive situation of the target. Traditional information fusion methods mainly include links such as data preprocessing, coordinate transformation, spatio-temporal alignment, track association, and track filtering, and finally obtain the complete track corresponding to each target.

[0003] However, in real-time association of multi-source target tracks, it is necessary to quickly classify various point track and track data of different sensors and different targets, and then form target track association through spatio-temporal relationships, feature associations, etc., so as to cluster the track information and feature data of the same target on a target data set, which has objective requirements such as fast, stable, and accurate. When processing the situation data in the far sea and far region, it has the characteristics of a large number of targets, a large amount of data, and a high update rate. Traditional information fusion algorithms are prone to problems such as track intersection or low correct rate of association and fusion in a dense target environment, and the calculation amount increases exponentially with the number of targets, and the calculation amount is often difficult to handle. Summary of the Invention

[0004] The technical problem to be solved by the present invention is to provide a method and device for target track association based on spatio-temporal grids. By putting multi-source targets globally into spatio-temporal grids and calculating the association degree between targets, fast association of target tracks can be realized, so as to achieve full-course target tracking of multi-source targets, which is beneficial to reducing the calculation complexity and improving the fusion efficiency and correct rate of multi-source target association.

[0005] To solve the above technical problem, a first aspect of an embodiment of the present invention discloses a method for target track association based on spatio-temporal grids, and the method includes:

[0006] S1, obtaining track data information at time T, track data information at time T+1, a track data set at time T, and spatio-temporal grid information; the track data set at time T includes several pieces of fused track data information; the fused track data information includes fused track speed information, fused track average speed information, fused track position information, fused track time information, and fused track batch number value; the spatio-temporal grid information includes several time-level grid information and several space-level grid information; the time-level grid information includes several time grid information; the space-level grid information includes several space grid information; T is a positive integer;

[0007] S2. Perform fusion processing on the track data information at time T, the spatio-temporal grid information, and the track data set at time T to obtain the track fusion result information at time T;

[0008] S3. Perform fusion processing on the track fusion result information at time T, the spatio-temporal grid information, and the track data information at time T+1 to obtain the target track information.

[0009] As an optional implementation manner, in the first aspect of the embodiments of the present invention, the performing fusion processing on the track data information at time T, the spatio-temporal grid information, and the track data set at time T to obtain the track fusion result information at time T includes:

[0010] S21. Preprocess the track data information at time T to obtain the preprocessed track data information at time T;

[0011] S22. Perform an extraction operation on the preprocessed track data information at time T to obtain the track extraction data information at time T; the track extraction data information at time T includes the first track position information, the first track speed information, the first track average speed information, the first track time information, and the first track lot number value;

[0012] S23. Process the track extraction data information at time T, the spatio-temporal grid information, and the track data set at time T to obtain the track fusion result information at time T.

[0013] As an optional implementation manner, in the first aspect of the embodiments of the present invention, the processing the track extraction data information at time T, the spatio-temporal grid information, and the track data set at time T to obtain the track fusion result information at time T includes:

[0014] S231. Perform matching processing on the first track lot number value and the track data set at time T to obtain the matching result information and the fusion track matching data information;

[0015] When the matching result information is no, execute S232;

[0016] When the matching result information is yes, execute S234;

[0017] S232. Add the track extraction data information at time T to the track data set at time T;

[0018] S233. Obtain the first track data information to be processed and determine that the first track data information to be processed is the track data information at time T, and execute S2;

[0019] S234. Process the track extraction data information at time T, the spatio-temporal grid information, the fused track matching data information, and the track data set at time T to obtain the track fusion result information at time T.

[0020] As an optional implementation manner, in the first aspect of the embodiments of the present invention, the processing of the track extraction data information at time T, the spatio-temporal grid information, the fused track matching data information, and the track data set at time T to obtain the track fusion result information at time T includes:

[0021] S2341. Perform calculation processing on the track extraction data information at time T and the fused track matching data information to obtain the track correlation degree value at time T;

[0022] S2342. Determine whether the track correlation degree value at time T is greater than the first correlation threshold to obtain a first judgment result;

[0023] When the first judgment result is yes, execute S2343;

[0024] When the first judgment result is no, execute S2344;

[0025] S2343. Perform fusion processing on the track extraction data information at time T and the fused track matching data information to obtain the track result information at time T, and execute S2345;

[0026] S2344. Process the track extraction data information at time T, the spatio-temporal grid information, and the track data set at time T to obtain the track result information at time T;

[0027] S2345. Add the track result information at time T to the track fusion result information at time T;

[0028] S2346. Obtain the user's first stop receiving instruction information;

[0029] When the user's first stop receiving instruction information is yes, execute S3;

[0030] When the first user's stop receiving instruction information is no, obtain the second to-be-processed track data information, and determine the second to-be-processed track data information as the track data information at time T, and execute S2.

[0031] As an optional implementation manner, in the first aspect of the embodiments of the present invention, the performing calculation processing on the track extraction data information at time T and the fused track matching data information to obtain the track correlation degree value at time T includes:

[0032] S23411. Calculate and process the fused track position information in the first track position information and the fused track matching data information to obtain a distance correlation value;

[0033] S23412. Calculate and process the fused track speed information in the first track speed information and the fused track matching data information to obtain a speed correlation value;

[0034] S23413. Perform a weighted average calculation on the distance correlation value and the speed correlation value to obtain a motion attribute correlation value;

[0035] S23414. Calculate the average of the first track average speed information and the fused track average speed information in the fused track matching data information to obtain an average speed correlation value;

[0036] S23415. Determine whether the motion attribute correlation value is greater than the average speed correlation value to obtain a second judgment result;

[0037] When the second judgment result is yes, determine the motion attribute correlation value as the track correlation value at time T;

[0038] When the second judgment result is no, determine the average speed correlation value as the track correlation value at time T.

[0039] As an optional implementation manner, in the first aspect of the embodiments of the present invention, the processing of the track extraction data information at time T, the spatio-temporal grid information, and the track data set at time T to obtain the track result information at time T includes:

[0040] S23441. Match the first track time information, the first track position information with the spatio-temporal grid information to obtain target-level time grid information and target-level space grid information;

[0041] S23442. Match the first track time information, the first track position information, the target-level time grid information, and the target-level space grid information to obtain target time grid information and target space grid information;

[0042] S23443. Process the track data set at time T, the spatio-temporal grid information, the target time grid information, and the target space grid information to obtain a number of fused track data information to be processed;

[0043] S23444. Process a number of the fused track data information to be processed and the track extraction data information at time T to obtain the track result information at time T.

[0044] As an alternative implementation, in the first aspect of the embodiments of the present invention, the fusion processing of the track fusion result information at time T, the spatio-temporal grid information, and the track data information at time T+1 to obtain the target track information includes:

[0045] S31. Process the track fusion result information at time T to obtain the predicted fusion track information at time T+1; the predicted fusion track information at time T+1 includes a plurality of predicted track information at time T+1;

[0046] S32. Obtain the track data set at time T+1;

[0047] S33. Process the predicted fusion track information at time T+1, the spatio-temporal grid information, the track data information at time T+1, and the track data set at time T+1 to obtain the target track fusion result information and the target track information;

[0048] S34. Obtain the user's second stop receiving instruction information;

[0049] When the user's second stop receiving instruction information is no, increment T by 1, obtain the third track data information to be processed, and determine the third track data information to be processed as the track data information at time T+1, and the target track fusion result information as the target track fusion result information at time T, and execute S31;

[0050] When the user's second stop receiving instruction information is yes, end the process.

[0051] The second aspect of the embodiments of the present invention discloses a target track association device based on a spatio-temporal grid, and the device includes:

[0052] An acquisition module, configured to acquire the track data information at time T, the track data information at time T+1, the track data set at time T, and the spatio-temporal grid information; the track data set at time T includes a plurality of fused track data information; the fused track data information includes fused track speed information, fused track average speed information, fused track position information, fused track time information, and fused track lot number value; the spatio-temporal grid information includes a plurality of time-level grid information and a plurality of space-level grid information; the time-level grid information includes a plurality of time grid information; the space-level grid information includes a plurality of space grid information; T is a positive integer;

[0053] A first calculation module, configured to perform fusion processing on the track data information at time T, the spatio-temporal grid information, and the track data set at time T to obtain the track fusion result information at time T;

[0054] A second computing module, configured to perform fusion processing on the track fusion result information at time T, the spatio-temporal grid information, and the track data information at time T+1 to obtain target track information.

[0055] In a third aspect of the embodiments of the present invention, another target track association device based on spatio-temporal grids is disclosed. The device includes:

[0056] A processor;

[0057] A memory coupled to the processor and storing executable program code;

[0058] The processor calls the executable program code stored in the memory to execute some or all of the steps of the method for associating target tracks based on spatio-temporal grids disclosed in the first aspect of the embodiments of the present invention.

[0059] In a fourth aspect of the embodiments of the present invention, a computer-readable storage medium is disclosed. The computer-readable storage medium stores computer instructions, which are used to execute some or all of the steps of the method for associating target tracks based on spatio-temporal grids disclosed in the first aspect of the embodiments of the present invention when called.

[0060] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0061] In the embodiments of the present invention, track data information at time T, track data information at time T+1, a track data set at time T, and spatio-temporal grid information are obtained; the track data set at time T includes a plurality of fused track data information; the fused track data information includes fused track speed information, fused track average speed information, fused track position information, fused track time information, and a fused track batch number value; the spatio-temporal grid information includes a plurality of time-level grid information and a plurality of space-level grid information; the time-level grid information includes a plurality of time grid information; the space-level grid information includes a plurality of space grid information; T is a positive integer; the track data information at time T, the spatio-temporal grid information, and the track data set at time T are subjected to fusion processing to obtain track fusion result information at time T; the track fusion result information at time T, the spatio-temporal grid information, and the track data information at time T+1 are subjected to fusion processing to obtain target track information. It can be seen that in this embodiment, by putting multi-source targets globally into spatio-temporal grids and calculating the association degree between targets, fast association of target tracks can be realized, thereby realizing the whole-process target tracking of multi-source targets, which is beneficial to reducing the computational complexity and improving the fusion efficiency and accuracy of multi-source target association. Description of the Drawings

[0062] To more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the accompanying drawings required for the description of the embodiments. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other accompanying drawings can be obtained based on these drawings.

[0063] Figure 1 It is a schematic flowchart of a target track association method based on spatio-temporal grids disclosed in an embodiment of the present invention;

[0064] Figure 2 It is a schematic structural diagram of a target track association device based on spatio-temporal grids disclosed in an embodiment of the present invention;

[0065] Figure 3 It is a schematic structural diagram of another target track association device based on spatio-temporal grids disclosed in an embodiment of the present invention. Detailed implementation manners

[0066] In order to enable those skilled in the art to better understand the solutions of the present invention, the following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, rather than all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present invention.

[0067] The terms "first", "second", etc. in the specification and claims of the present invention and the above accompanying drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, device, product or equipment that includes a series of steps or units is not limited to the listed steps or units, but optionally further includes steps or units not listed, or optionally further includes other steps or units inherent to these processes, methods, products or equipment.

[0068] Referring to "embodiments" herein means that the specific features, structures or characteristics described in connection with the embodiments can be included in at least one embodiment of the present invention. The phrase appears in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment mutually exclusive with other embodiments. Those skilled in the art will explicitly and implicitly understand that the embodiments described herein can be combined with other embodiments.

[0069] It should be noted that the time grid in this application is the time grid information in this application.

[0070] The present invention discloses a method and device for target track association based on spatio-temporal grids. By putting multi-source targets globally into spatio-temporal grids and calculating the association degree between targets, fast association of target tracks can be achieved, thereby realizing the whole-process target tracking of multi-source targets, which is beneficial to reducing the computational complexity and improving the fusion efficiency and accuracy of multi-source target association. The following will be described in detail respectively.

[0071] Embodiment 1

[0072] Please refer to Figure 1 , Figure 1 which is a schematic flowchart of a method for target track association based on spatio-temporal grids disclosed in an embodiment of the present invention. Among them, Figure 1 the described method for target track association based on spatio-temporal grids is applied to a device for target track association based on spatio-temporal grids, such as a local server or a cloud server for optimizing management of target track association based on spatio-temporal grids, etc., which is not limited in the embodiments of the present invention. As Figure 1 shown, the method for target track association based on spatio-temporal grids may include the following operations:

[0073] S1. Obtain the track data information at time T, the track data information at time T + 1, the track data set at time T, and the spatio-temporal grid information; the track data set at time T includes several pieces of fused track data information; the fused track data information includes fused track speed information, fused track average speed information, fused track position information, fused track time information, and fused track batch number value; the spatio-temporal grid information includes several time-level grid information and several space-level grid information; the time-level grid information includes several time grid information; the space-level grid information includes several space grid information; T is a positive integer.

[0074] It should be noted that the track data information at time T is the track data information received by any one of the multi-source sensors (such as radar, camera, etc.) at time T; the track data information at time T + 1 is the track data information received by any one of the multi-source sensors at time T + 1; the track data set at time T is the track data information that has been associated with targets and processed by fusion at time T.

[0075] It should be noted that the fused track time information is the average time of the reconnaissance periods of the multi-sensors after fusion in the fused track data information. For example, if the fused track data information is obtained by associating and fusing data from 2 sensors, and the reconnaissance periods of the corresponding 2 sensors are 10s and 30s respectively, then the fused track time information is (10 + 30) / 2 = 20s.

[0076] S2. Perform fusion processing on the track data information at time T, the spatio-temporal grid information, and the track data set at time T to obtain the track fusion result information at time T.

[0077] S3. Perform fusion processing on the track fusion result information, spatio-temporal grid information, and track data information at time T+1 to obtain target track information.

[0078] It can be seen that implementing the target track association method based on spatio-temporal grid described in the embodiments of the present invention can achieve full-process target tracking of multi-source targets, which is beneficial to reducing the computational complexity and improving the fusion efficiency and accuracy of multi-source target association.

[0079] In an optional embodiment, obtaining spatio-temporal grid information includes:

[0080] S11. Use the Beidou navigation system to synchronize the time information of all sensors in the multi-source sensors and initialize the time of each sensor.

[0081] S12. Obtain the reconnaissance detection time period values of all sensors in the multi-source sensors.

[0082] S13. Calculate the least common multiple of the reconnaissance detection time period values of all sensors to obtain the least common multiple value of the sensors.

[0083] S14. Sort the reconnaissance detection time period values of all sensors in ascending order to obtain the sorted reconnaissance detection time period values.

[0084] S15. Based on the sorted reconnaissance detection time period values, determine the lower limit value of the time resolution; the lower limit value of the time resolution is the first reconnaissance detection time period value in the sorted reconnaissance detection time period values.

[0085] S16. Determine the least common multiple value of the sensors as the upper limit value of the time resolution.

[0086] S17. Divide the difference between the upper limit value of the time resolution and the lower limit value of the time resolution into several equal parts to obtain several time-level grid information.

[0087] It should be noted that the above-mentioned several equal parts division is an 8-equal parts division.

[0088] S18. Perform grid division processing on any time-level grid information to obtain several time grid information of the time-level grid information.

[0089] S19. Based on all sensors in the multi-source sensors, determine several spatial-level grid information.

[0090] Exemplarily, if the number of time-level grid information is 8, the lower limit value of time resolution is 30 ms, and the upper limit value of time resolution is 1500 ms, then the difference is 1500 ms - 30 ms = 1470 ms. Then, it is divided into 8 equal parts, which is 1470 ms / 8 = 183.75 ms. The 8 time-level grid information obtained is as follows:

[0091] The first time-level grid information: 30 ms (the lower limit value of time resolution, the highest precision);

[0092] The second time-level grid information: 30 ms + 183.75 ms = 213.75 ms;

[0093] The third time-level grid information: 213.75 ms + 183.75 ms = 397.5 ms;

[0094] ……

[0095] The eighth time-level grid information: 1500 ms (the upper limit value of time resolution, the lowest precision)

[0096] The above-mentioned grid division process for any time-level grid information to obtain several time grid information of this time-level grid information is to divide [A1, A2] within a given time interval range, such as [A1, A2], using the time-level grid information. For example, the first time-level grid information is 30 ms, to obtain the corresponding time grid information [A1, A1 + 30 ms], [A1 + 30 ms, A1 + 30 ms + 30 ms]... [A2 - 30 ms, A2] of this time-level grid information.

[0097] It should be noted that the lower limit value of time resolution is based on the shortest reconnaissance period to ensure that no sensor data is lost. The upper limit value of time resolution is based on the least common divisor to ensure that all sensor data can be aligned in the same time grid information for convenient fusion. In this way, the time region is divided into 8 different levels of time resolution, and the time resolution of each level is different, which thus allows analysis and processing for different time scales. If the shortest reconnaissance period of the sensor corresponding to the track data information at time T is small, the lower-level time-level grid information can be used to reduce the calculation amount. If the shortest reconnaissance period of the sensor corresponding to the track data information at time T is large, the higher-level time-level grid information is used to ensure accuracy.

[0098] It can be seen that implementing the target track association method based on spatio-temporal grids described in the embodiments of the present invention can achieve the full-process target tracking of multi-source targets, which is beneficial to reducing the computational complexity and improving the fusion efficiency and accuracy of multi-source target association.

[0099] In an optional embodiment, based on all sensors in the multi-source sensor, several spatial hierarchical grid information is determined, including:

[0100] S191, obtain the longitude component value, latitude component value, and elevation component value of the reconnaissance error of all sensors in the multi-source sensor;

[0101] S192, determine the minimum value of the longitude component values of all sensors as the minimum longitude grid spatial resolution, and the greatest common divisor of the longitude component values of all sensors as the maximum longitude grid spatial resolution;

[0102] S193, determine the minimum value of the latitude component values of all sensors as the minimum latitude grid spatial resolution, and the greatest common divisor of the latitude component values of all sensors as the maximum latitude grid spatial resolution;

[0103] S194, determine the minimum value of the elevation component values of all sensors as the minimum elevation grid spatial resolution, and the greatest common divisor of the elevation component values of all sensors as the maximum elevation grid spatial resolution;

[0104] S195, obtain the longitude value, latitude value of the track data information at time T, and the maximum reconnaissance range value of the sensor corresponding to the track data information at time T in the elevation component;

[0105] S196, determine the maximum reconnaissance range value as the elevation value;

[0106] S197, using the 2000 China Geodetic Coordinate System (CGCS2000) adopted by the Beidou Navigation System, equally divide the minimum longitude grid spatial resolution, maximum longitude grid spatial resolution, minimum latitude grid spatial resolution, maximum latitude grid spatial resolution, minimum elevation grid spatial resolution, and maximum elevation grid spatial resolution in three dimensions of longitude value, latitude value, and elevation value respectively, and combine them in three dimensions to obtain several spatial hierarchical grid information;

[0107] It should be noted that the above several spatial hierarchical grid information is 8 spatial hierarchical grid information;

[0108] S198, perform division processing on any one of the several spatial hierarchical grid information to obtain several spatial grid information of the spatial hierarchical grid information.

[0109] Exemplarily, the above-obtained several spatial hierarchical grid information can be processed as follows.

[0110] It should be noted that the above S197 - S198 can be divided by tools such as ArcGIS or QGIS, and specifically, the embodiments of the present invention do not make limitations.

[0111] It should be noted that, similar to the above time-level grid information, the levels of the above eight spatial-level grid information are different. The first spatial-level grid information has the smallest resolution and the highest accuracy, while the eighth spatial-level grid information has the largest resolution and the lowest accuracy.

[0112] It should be noted that by selecting the minimum value among the error components of each sensor as the minimum grid spatial resolution, it can ensure that the system has a high accuracy for the errors of all sensors, thereby enabling the refinement of the spatial grid. This can more accurately locate the position of the target in target tracking and prediction. By selecting the greatest common divisor of all sensor errors as the maximum grid resolution, it is ensured that the error ranges of all sensors can be covered in the division of the spatial range, so that no important information will be missed during data fusion, and at the same time, the compatibility and consistency of the fusion result are ensured.

[0113] It should be noted that through the spatial division of different resolutions, the computing tasks can be carried out according to a unified level and structure. Appropriate minimum and maximum resolution values are selected to optimize the computing process, avoiding over-division (too high spatial resolution) and over-simplification (too low spatial resolution). This spatial division method helps to reduce unnecessary computations and improve the operating efficiency of the system.

[0114] It can be seen that implementing the target track association method based on spatio-temporal grids described in the embodiments of the present invention can achieve the whole-process target tracking of multi-source targets, which is beneficial to reducing the computational complexity and improving the fusion efficiency and accuracy of multi-source target association.

[0115] In an alternative embodiment, the track data information, spatio-temporal grid information, and track data set at time T are fused to obtain the track fusion result information at time T, including:

[0116] S21, preprocessing the track data information at time T to obtain the preprocessed track data information at time T;

[0117] It should be noted that the above preprocessing includes data verification, time synchronization, coordinate transformation, data cleaning, etc., which can be processed by Pandas, Chrony, ArcGIS, and Pandas respectively. Specifically, the embodiments of the present invention do not make limitations.

[0118] It should be noted that the above data verification can check whether the track data information at time T contains necessary information such as the timestamp, position, and speed of the target, and at the same time can filter out invalid or abnormal data.

[0119] It should be noted that the above time synchronization calibrates the time reference of the track data information at time T using a global clock (such as GPS time). Since the data from different sensors may have different time references, time calibration is required.

[0120] It should be noted that if the data comes from different coordinate systems (such as the polar coordinates of a radar and the image coordinates of a camera), it needs to be converted to a unified global coordinate system. The above coordinate transformation can convert the track data information at time T into information in the global Cartesian coordinates.

[0121] It should be noted that the above data cleaning uses filters (such as mean filtering and Kalman filtering) to remove high-frequency noise and exclude abnormal data beyond a preset range (such as impossible speeds or distances).

[0122] S22. Perform an extraction operation on the preprocessed track data information at time T to obtain the track extraction data information at time T; the track extraction data information at time T includes the first track position information, the first track speed information, the first track average speed information, the first track time information, and the first track batch number value;

[0123] It should be noted that the above extraction operation can be performed using tools such as Numpy and MATLAB. Specifically, the embodiments of the present invention do not make limitations.

[0124] It should be noted that the first track time information is the reconnaissance cycle time value of the sensor corresponding to the preprocessed track data information at time T, such as 10 s.

[0125] S23. Process the track extraction data information at time T, the spatio-temporal grid information, and the track data set at time T to obtain the track fusion result information at time T.

[0126] It can be seen that implementing the target track association method based on spatio-temporal grids described in the embodiments of the present invention can achieve the whole-process target tracking of multi-source targets, which is beneficial to reducing the computational complexity and improving the fusion efficiency and accuracy of multi-source target association.

[0127] In another optional embodiment, processing the track extraction data information at time T, the spatio-temporal grid information, and the track data set at time T to obtain the track fusion result information at time T includes:

[0128] S231. Perform a matching process on the first track batch number value and the track data set at time T to obtain the matching result information and the fusion track matching data information;

[0129] When the matching result information is no, execute S232;

[0130] When the matching result information is yes, execute S234;

[0131] S232. Add the track extraction data information at time T to the track dataset at time T.

[0132] S233. Obtain the first track data information to be processed, determine that the first track data information to be processed is the track data information at time T, and execute S2.

[0133] It should be noted that the first track data information to be processed is the track data information received by any sensor at time T.

[0134] S234. Process the track extraction data information, spatio-temporal grid information, fused track matching data information, and track dataset at time T to obtain the track fusion result information at time T.

[0135] It can be seen that implementing the target track association method based on spatio-temporal grid described in the embodiments of the present invention can achieve the full-process target tracking of multi-source targets, which is beneficial to reducing the computational complexity and improving the fusion efficiency and accuracy of multi-source target association.

[0136] In an alternative embodiment, matching the first track batch number value with the track dataset at time T to obtain the matching result information and the fused track matching data information includes:

[0137] S2311. Preset s = 1.

[0138] S2312. Determine whether the first track batch number value is equal to the fused track batch number value in the s-th fused track data information in the track dataset at time T to obtain the third judgment result.

[0139] When the third judgment result is yes, determine that yes is the matching result information, and determine the s-th fused track data information as the fused track matching data information.

[0140] When the third judgment result is no, determine whether s is equal to the number of fused track data information in the track dataset at time T to obtain the fourth judgment result.

[0141] When the fourth judgment result is no, increment s by 1 and execute S2312.

[0142] When the fourth judgment result is yes, determine that no is the matching result information, and determine the s-th fused track data information as the fused track matching data information.

[0143] It should be noted that when the third judgment result is yes, set the matching result information to yes; when the third judgment result is no, set the matching result information to no; when the fourth judgment result is yes, set the matching result information to no.

[0144] It can be seen that implementing the target track association method based on spatio-temporal grids described in the embodiments of the present invention can achieve the full-process target tracking of multi-source targets, which is beneficial to reducing the computational complexity and improving the fusion efficiency and accuracy of multi-source target association.

[0145] In yet another optional embodiment, the track extraction data information, spatio-temporal grid information, fused track matching data information, and track data set at time T are processed to obtain the track fusion result information at time T, including:

[0146] S2341, calculate and process the track extraction data information and the fused track matching data information at time T to obtain the track correlation degree value at time T;

[0147] S2342, determine whether the track correlation degree value at time T is greater than the first correlation degree threshold to obtain the first judgment result;

[0148] When the first judgment result is yes, execute S2343;

[0149] When the first judgment result is no, execute S2344;

[0150] S2343, perform fusion processing on the track extraction data information and the fused track matching data information at time T to obtain the track result information at time T, and execute S2345;

[0151] It should be noted that for the above-mentioned fusion processing to obtain the track result information at time T, it can be processed by JPDA, multi-target tracking algorithms, etc. Specifically, the embodiments of the present invention do not make limitations.

[0152] S2344, process the track extraction data information, spatio-temporal grid information, and track data set at time T to obtain the track result information at time T;

[0153] S2345, add the track result information at time T to the track fusion result information at time T;

[0154] S2346, obtain the user's first stop receiving instruction information;

[0155] When the user's first stop receiving instruction information is yes, execute S3;

[0156] When the first user's stop receiving instruction information is no, obtain the second to-be-processed track data information, and determine the second to-be-processed track data information as the track data information at time T, and execute S2.

[0157] It should be noted that the second to-be-processed track data information is the track data information received by any sensor at time T.

[0158] It should be noted that the first correlation threshold can be set by the user or obtained based on historical data, and the embodiments of the present invention do not make specific limitations.

[0159] Judging whether the track correlation value at time T is greater than the first correlation threshold is to ensure the correct correlation of the target and avoid mis-correlation. Through threshold screening, the system can improve the accuracy of data processing, ensure the accuracy of target tracking and prediction, and at the same time avoid wrongly fusing the tracks of different targets, which helps to improve the reliability and effectiveness of the target track correlation of multi-source sensors.

[0160] It can be seen that implementing the target track correlation method based on spatio-temporal grids described in the embodiments of the present invention can achieve the whole-process target tracking of multi-source targets, which is beneficial to reducing the computational complexity and improving the fusion efficiency and accuracy of multi-source target correlation.

[0161] In an optional embodiment, calculating and processing the track extraction data information and the fused track matching data information at time T to obtain the track correlation value at time T includes:

[0162] S23411, calculating and processing the fused track position information in the first track position information and the fused track matching data information to obtain a distance correlation value;

[0163] It should be noted that using the first correlation calculation model, calculating and processing the fused track position information in the first track position information and the fused track matching data information to obtain a distance correlation value;

[0164] Among them, the first correlation calculation model is:

[0165]

[0166] 0≤δ1,δ2≤1;

[0167] δ1 + δ2 = 1;

[0168] In the formula, JL is the distance correlation value, HJ is the first track position information, RH is the fused track position information, (HJX, HJY, HJZ) are the coordinates of the first track position information, (RHX, RHY, RHZ) are the coordinates of the fused track position information, TC is the square of the standard error of the sensor corresponding to the first track position information, δ1 and δ2 respectively represent the first weight parameter and the second weight parameter, and ||·|| represents taking the modulus;

[0169] It should be noted that the first weight parameter and the second weight parameter can be set by the user or obtained based on historical data, and the embodiments of the present invention do not make limitations.

[0170] It should be noted that the standard error of the sensor corresponding to the first track position information is obtained by acquiring the parameter information of the sensor.

[0171] It should be noted that the coordinate information in this application is the coordinate information corresponding to the Cartesian coordinate system.

[0172] It should be noted that by adjusting these two weight parameters, the influence of the position similarity and the direction similarity on the correlation degree value can be flexibly controlled. Specifically, if more attention is paid to the spatial position similarity of the track, a larger δ2 can be set; if more importance is attached to the directional matching of the track, a larger δ1 can be set.

[0173] Through the first correlation degree calculation model, it is possible to effectively evaluate whether the tracks observed by different sensors belong to the same physical target.

[0174] S23412. Calculate and process the fused track speed information in the first track speed information and the fused track matching data information to obtain a speed correlation degree value;

[0175] It should be noted that the second correlation degree calculation model is used to calculate and process the fused track speed information in the first track speed information and the fused track matching data information to obtain a speed correlation degree value;

[0176] Among them, the second correlation degree calculation model is:

[0177]

[0178] 0 ≤ δ3, δ4 ≤ 1;

[0179] δ3 + δ4 = 1;

[0180] In the formula, SD is the speed correlation degree value, HS is the first track speed information, RS is the fused track speed information, ||·|| represents taking the modulus, |·| represents taking the absolute value, δ3 and δ4 represent the third weight coefficient and the fourth weight coefficient, and ρ represents a constant coefficient.

[0181] It should be noted that the third weight coefficient, the fourth weight coefficient, and the constant coefficient can be set by the user or obtained according to historical data, and the embodiments of the present invention do not make limitations.

[0182] It should be noted that the second correlation degree calculation model can reflect the matching conditions in two dimensions of the magnitude and direction of the speed. By adjusting the weight coefficients, the importance of the speed magnitude and direction in the final correlation degree value can be flexibly controlled, which helps to accurately evaluate the speed similarity of the target track in the multi-source sensor data fusion, so as to achieve more efficient target association.

[0183] It should be noted that by setting a constant coefficient, a reasonable correlation degree can be maintained under the condition of allowing slight errors, while avoiding the correlation degree being directly zero due to low confidence or boundary cases.

[0184] S23413, perform a weighted average calculation on the distance correlation degree value and the speed correlation degree value to obtain a motion attribute correlation degree value;

[0185] S23414, perform an average calculation on the average speed information of the first track and the average speed information of the fused track matching data information in the fused track to obtain an average speed correlation degree value;

[0186] S23415, determine whether the motion attribute correlation degree value is greater than the average speed correlation degree value to obtain a second judgment result;

[0187] When the second judgment result is yes, determine the motion attribute correlation degree value as the track correlation degree value at time T;

[0188] When the second judgment result is no, determine the average speed correlation degree value as the track correlation degree value at time T.

[0189] It should be noted that the motion attribute correlation degree value pays more attention to the instantaneous distance and speed matching degree, while the average speed correlation degree value reflects the long-term trend characteristics of the target motion. This judgment logic can bias towards short-term or long-term information when needed, so as to achieve comprehensive consideration; when the target motion changes violently, the system can still capture the global characteristics of the target through the average speed; in the case of stable motion, the motion attribute correlation degree is more accurate.

[0190] It can be seen that implementing the target track correlation method based on spatio-temporal grids described in the embodiments of the present invention can achieve the full-process target tracking of multi-source targets, which is beneficial to reducing the computational complexity and improving the fusion efficiency and accuracy of multi-source target correlation.

[0191] In an optional embodiment, the track extraction data information, spatio-temporal grid information, and track data set at time T are processed to obtain the track result information at time T, including:

[0192] S23441, perform a matching process on the first track time information, the first track position information, and the spatio-temporal grid information to obtain the target-level time grid information and the target-level space grid information;

[0193] It should be noted that the above matching process is to match which time-level grid information in the spatio-temporal grid information the first track time information belongs to, and which space-level grid information in the spatio-temporal grid information the first track position information belongs to, and use the matched time-level grid information and space-level grid information as the target-level time grid information and target-level space grid information. For the specific matching process, QGIS or ArcGIS can be used for matching, and specifically, the embodiments of the present invention do not make limitations.

[0194] S23442. Perform a matching process on the first track time information, the first track position information, the target-level time grid information, and the target-level space grid information to obtain the target time grid information and the target space grid information;

[0195] It should be noted that the above matching process is to match which time grid information in the target-level time grid information the first track time information belongs to, and which space grid information in the target-level space grid information the first track position information belongs to, and use the matched time grid information and space grid information as the target time grid information and the target space grid information. For the specific matching process, QGIS or ArcGIS can be used for matching, and specifically, the embodiments of the present invention do not make limitations.

[0196] S23443. Process the track data set at time T, the spatio-temporal grid information, the target time grid information, and the target space grid information to obtain a number of track data information to be processed for fusion;

[0197] It should be noted that the above process of processing the track data set at time T, the spatio-temporal grid information, the target time grid information, and the target space grid information to obtain a number of track data information to be processed for fusion is to determine whether the fused track data information in the track data set at time T exists in the target time grid information and the target space grid information. If it exists, use this fused track data information as a track data information to be processed for fusion. If it does not exist, continue to determine whether the fused track data information in the track data set at time T exists in the 8 time grid information adjacent to the target time grid information and the 8 space grid information adjacent to the target space grid information, and use the matched fused track data information as a track data information to be processed for fusion. For the specific process, QGIS or ArcGIS can be used for processing, and the embodiments of the present invention do not make limitations.

[0198] It should be noted that through the above processing, the efficient association of dynamic targets under complex spatio-temporal conditions is ensured. Direct matching is the core, and extended search is the supplement. The two complement each other, ensuring both the accuracy of matching and enhancing the adaptability to uncertainty, and guaranteeing the computational efficiency in the case of big data processing.

[0199] S23444 processes a number of fusion track data information to be processed and track extraction data information at time T to obtain track result information at time T.

[0200] It should be noted that the above processing of a number of fusion track data information to be processed and track extraction data information at time T can be carried out through JPDA and multi-target tracking algorithms. Specifically, the embodiments of the present invention do not make limitations.

[0201] It can be seen that implementing the target track association method based on spatio-temporal grids described in the embodiments of the present invention can achieve the whole-process target tracking of multi-source targets, which is beneficial to reducing the computational complexity and improving the fusion efficiency and accuracy of multi-source target association.

[0202] In an optional embodiment, the track fusion result information at time T, the spatio-temporal grid information, and the track data information at time T + 1 are fused to obtain target track information, including:

[0203] S31 processes the track fusion result information at time T to obtain predicted fusion track information at time T + 1; the predicted fusion track information at time T + 1 includes a number of predicted track information at time T + 1;

[0204] S32 obtains the track data set at time T + 1;

[0205] S33 processes the predicted fusion track information at time T + 1, the spatio-temporal grid information, the track data information at time T + 1, and the track data set at time T + 1 to obtain target track fusion result information and target track information;

[0206] S34 obtains the user's second stop receiving instruction information;

[0207] When the user's second stop receiving instruction information is no, T is incremented by 1, the third track data information to be processed is obtained, and it is determined that the third track data information to be processed is the track data information at time T + 1, and the target track fusion result information is the target track fusion result information at time T, and S31 is executed;

[0208] When the user's second stop receiving instruction information is yes, the process ends.

[0209] It can be seen that implementing the target track association method based on spatio-temporal grids described in the embodiments of the present invention can achieve the whole-process target tracking of multi-source targets, which is beneficial to reducing the computational complexity and improving the fusion efficiency and accuracy of multi-source target association.

[0210] In an optional embodiment, the track fusion result information at time T is processed to obtain predicted fusion track information at time T + 1; the predicted fusion track information at time T + 1 includes a number of predicted track information at time T + 1, including:

[0211] Using the track prediction calculation model, process the track fusion result information at time T to obtain the predicted fusion track information at time T+1;

[0212] Among them, the track prediction calculation model is:

[0213] HJS i =ZY·SDD i +KZ·KZ i +ZS1≤i≤N;

[0214] In the formula, HJS is the predicted fusion track information at time T+1, and HJS i is the i-th predicted track information at time T+1 in the predicted fusion track information at time T+1. ZY represents the state transition matrix, and SDD i is the i-th track result information at time T in the track fusion result information at time T. KZ is the control input matrix, and KZ i is the control vector corresponding to the i-th track result information at time T in the track fusion result information at time T. ZS is the noise constant vector, and N is the number of track result information at time T in the track fusion result information at time T.

[0215] It should be noted that the state transition matrix, the control input matrix, and the noise constant vector can be set by the user or obtained according to historical data, and the embodiments of the present invention do not make limitations.

[0216] It should be noted that the control vector KZ i is the acceleration vector of the i-th track result information at time T in the track fusion result information at time T.

[0217] It should be noted that by introducing the noise constant vector, in dynamic target tracking, the noise constant vector can be used to make up for the uncertainty of target movement (such as the target suddenly changing speed or direction). By introducing the noise constant vector, the predicted fusion track information at time T+1 obtained can more flexibly adapt to the non-stationary behavior of the target.

[0218] It can be seen that implementing the target track association method based on spatio-temporal grids described in the embodiments of the present invention can achieve the full-process target tracking of multi-source targets, which is beneficial to reducing the computational complexity and improving the fusion efficiency and accuracy of multi-source target association.

[0219] In an optional embodiment, process the predicted fusion track information at time T+1, the spatio-temporal grid information, the track data information at time T+1, and the track data set at time T+1 to obtain the target track fusion result information and the target track information, including:

[0220] S331. Process the track data information, spatio-temporal grid information, and the track data set at time T+1 to obtain the target track fusion result information.

[0221] It should be noted that processing the track data information, spatio-temporal grid information, and the track data set at time T+1 to obtain the target track fusion result information can be achieved according to step S2 of the present invention.

[0222] S332. Perform calculation processing on the track fusion result information at time T+1 and the predicted fusion track information at time T+1 to obtain the target track information.

[0223] It should be noted that performing calculation processing on the track fusion result information at time T+1 and the predicted fusion track information at time T+1 to obtain the target track information can be processed through JPDA, multi-target tracking algorithms, which are not limited in the embodiments of the present invention. Specifically, it is to perform association processing within the time grid information and space grid information where the track fusion result information at time T+1 and the predicted fusion track information at time T+1 are located. If there is only one target to be associated within the current time grid information and space grid information, directly associate the fusion target with the original track. If there is no target to be associated within the current grid, expand the search range to the 8 adjacent time grid information and space grid information of the current time grid information and space grid information for association. If there are multiple targets to be associated within the search range (the current time grid information and space grid information or the 8 adjacent time grid information and space grid information of the current grid), calculate the Euclidean distance between the track fusion result information at time T+1 and each target to be associated, and associate it with the target to be associated with the smallest distance. After completing the target association, select the track result information at time T in the track fusion result information at time T that matches the target to be associated for fusion processing to obtain the target fusion track information. And add the target fusion track information to the target track information.

[0224] It should be noted that selecting the track result information at time T in the track fusion result information at time T that matches the target to be associated for fusion processing to obtain the target fusion track information is to perform fusion processing on the track result information at time T+1 in the track fusion result information at time T+1 and the track result information at time T in the track fusion result information at time T to obtain the target fusion track information. The fusion processing is processed through JPDA, multi-target tracking algorithms, which are not limited in the embodiments of the present invention.

[0225] It can be seen that implementing the target track association method based on spatio-temporal grid described in the embodiments of the present invention can achieve the full-process target tracking of multi-source targets, which is beneficial to reducing the computational complexity and improving the fusion efficiency and accuracy of multi-source target association.

[0226] Embodiment 2

[0227] Please refer to Figure 2 , Figure 2 which is a schematic structural diagram of a target track association device based on spatio-temporal grids disclosed in an embodiment of the present invention. Among them, Figure 2 the described target track association device based on spatio-temporal grids is applied to a target track association optimization system based on spatio-temporal grids, such as a local server or a cloud server for target track association based on spatio-temporal grids, etc., which is not limited in the embodiments of the present invention. As Figure 2 shown, the target track association device based on spatio-temporal grids includes:

[0228] An acquisition module 201, configured to acquire track data information at time T, track data information at time T+1, a track data set at time T, and spatio-temporal grid information; the track data set at time T includes a plurality of fused track data information; the fused track data information includes fused track speed information, fused track average speed information, fused track position information, fused track time information, and a fused track batch number value; the spatio-temporal grid information includes a plurality of time-level grid information and a plurality of space-level grid information; the time-level grid information includes a plurality of time grid information; the space-level grid information includes a plurality of space grid information; T is a positive integer;

[0229] A first calculation module 202, configured to perform fusion processing on the track data information at time T, the spatio-temporal grid information, and the track data set at time T to obtain track fusion result information at time T;

[0230] A second calculation module 203, configured to perform fusion processing on the track fusion result information at time T, the spatio-temporal grid information, and the track data information at time T+1 to obtain target track information.

[0231] It can be seen that implementing the target track association device based on spatio-temporal grids described in the embodiments of the present invention can achieve full-process target tracking of multi-source targets, which is beneficial to reducing the computational complexity and improving the fusion efficiency and accuracy of multi-source target association.

[0232] Embodiment 3

[0233] Please refer to Figure 3 , Figure 3 which is a schematic structural diagram of another target track association device based on spatio-temporal grids disclosed in an embodiment of the present invention. Among them, Figure 3 the described target track association device based on spatio-temporal grids is applied to a target track association optimization system based on spatio-temporal grids, such as a local server or a cloud server for target track association based on spatio-temporal grids, etc., which is not limited in the embodiments of the present invention.

[0234] As Figure 3As shown in the figure, the target track association device based on spatio-temporal grids includes:

[0235] A processor 301;

[0236] A memory 302 coupled to the processor 301 and storing executable program code;

[0237] The processor 301 calls the executable program code stored in the memory 302 and executes some or all of the steps of the method for target track association based on spatio-temporal grids in the first embodiment.

[0238] It can be seen that implementing the target track association device based on spatio-temporal grids described in the embodiments of the present invention can achieve full-process target tracking of multi-source targets, which is beneficial to reducing the computational complexity and improving the fusion efficiency and accuracy of multi-source target association.

[0239] Embodiment Four

[0240] The embodiments of the present invention disclose a computer-readable storage medium. When the computer instructions stored in the computer-readable storage medium are called, they are used to execute some or all of the steps of the method for target track association based on spatio-temporal grids in the first embodiment.

[0241] Embodiment Five

[0242] The embodiments of the present invention disclose a computer program product. The computer program product includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to execute some or all of the steps of the method for target track association based on spatio-temporal grids described in the first embodiment.

[0243] The system embodiments described above are only illustrative. The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical modules, that is, they may be located in one place or distributed to multiple network modules. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art can understand and implement it without creative labor.

[0244] Through the specific descriptions of the above embodiments, those skilled in the art can clearly understand that each implementation can be realized by means of software plus a necessary general hardware platform, and of course, it can also be realized by hardware. Based on such an understanding, the essence of the above technical solution, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, and the storage medium includes Read-Only Memory (ROM), Random Access Memory (RAM), Programmable Read-only Memory (PROM), Erasable Programmable Read Only Memory (EPROM), One-time Programmable Read-Only Memory (OTPROM), Electrically-Erasable Programmable Read-Only Memory (EEPROM), Compact Disc Read-Only Memory (CD-ROM) or other optical disc memories, magnetic disk memories, tape memories, or any other computer-readable medium that can be used to carry or store data.

[0245] Finally, it should be noted that: What is disclosed in an object track association method and device based on spatio-temporal grids according to an embodiment of the present invention is only a preferred embodiment of the present invention, and is only used to illustrate the technical solution of the present invention, rather than limiting it; Although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: They can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some of the technical features; And these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A target track association method based on a spatiotemporal grid, characterized in that: The method comprises: S1, obtain track data information at time T, track data information at time T+1, track data set at time T and space-time grid information; the track data set at time T includes a number of fused track data information; the fused track data information includes fused track speed information, fused track average speed information, fused track position information, fused track time information and fused track batch number value; the space-time grid information includes a number of time level grid information and a number of space level grid information; the time level grid information includes a number of time grid information; the space level grid information includes a number of space grid information; T is a positive integer; the fused track time information is the average time of the reconnaissance cycle of the multi-sensor fused in the fused track data information; S2, fusing the track data information at time T, the spatiotemporal grid information and the track data set at time T to obtain track fusion result information at time T; S3, fusing the track fusion result information at time T, the spatiotemporal grid information and the track data information at time T+1 to obtain target track information.

2. The target track association method based on time-space grid according to claim 1 is characterized in that: The fusing process of the track data information at time T, the spatiotemporal grid information and the track data set at time T to obtain the track fusion result information at time T includes: S21, preprocessing the track data information at time T to obtain preprocessed track data information at time T; S22, extracting the pre-processed track data information at time T to obtain the track extraction data information at time T; the track extraction data information at time T includes first track position information, first track speed information, first track average speed information, first track time information and first track batch number value; the first track time information is the reconnaissance cycle time value of the sensor corresponding to the pre-processed track data information at time T; S23, processing the track extraction data information at time T, the spatiotemporal grid information and the track data set at time T to obtain track fusion result information at time T.

3. The target track association method based on time-space grid according to claim 2 is characterized in that: The processing of the track extraction data information at time T, the spatiotemporal grid information and the track data set at time T to obtain the track fusion result information at time T includes: S231, performing matching processing on the first track batch number value and the track data set at time T to obtain matching result information and fused track matching data information; When the matching result information is negative, execute S232; When the matching result information is yes, execute S234; S232, adding the track extraction data information at time T to the track data set at time T; S233, obtaining first track data information to be processed, and determining that the first track data information to be processed is the track data information at time T, and executing S2; S234, processing the track extraction data information at time T, the spatiotemporal grid information, the fused track matching data information and the track data set at time T to obtain track fusion result information at time T; The matching process of the first track batch number value and the track data set at time T to obtain matching result information and fused track matching data information includes: S2311, preset s=1; S2312, judging whether the first track batch number value is equal to the fused track batch number value in the s-th fused track data information in the track data set at time T, and obtaining a third judgment result; When the third judgment result is yes, it is determined to be matching result information, and the s-th fused track data information is determined to be fused track matching data information; When the third judgment result is no, determine whether s is equal to the amount of the fused track data information in the track data set at time T, and obtain a fourth judgment result; When the fourth judgment result is no, s is increased by 1 and S2312 is executed; When the fourth judgment result is yes, it is determined whether it is the matching result information, and the s-th fused track data information is determined to be the fused track matching data information.

4. The target track association method based on time-space grid according to claim 3 is characterized in that: The processing of the track extraction data information at time T, the spatiotemporal grid information, the fused track matching data information and the track data set at time T to obtain the track fusion result information at time T includes: S2341, calculating and processing the track extraction data information at time T and the fused track matching data information to obtain a track correlation value at time T; S2342, determining whether the track correlation value at time T is greater than a first correlation threshold, and obtaining a first determination result; When the first judgment result is yes, execute S2343; When the first judgment result is no, executing S2344; S2343, fusing the track extraction data information at time T with the fused track matching data information to obtain the track result information at time T, and executing S2345; S2344, processing the track extraction data information at time T, the spatiotemporal grid information and the track data set at time T to obtain the track result information at time T; S2345, adding the track result information at time T to the track fusion result information at time T; S2346, obtaining the user's first stop receiving instruction information; When the user first stops receiving the instruction information, the answer is yes, executing S3; When the user's first stop receiving instruction information is no, the second track data information to be processed is obtained, and it is determined that the second track data information to be processed is the track data information at time T, and S2 is executed.

5. The target track association method based on time-space grid according to claim 4 is characterized in that: The calculating and processing the track extraction data information at time T and the fused track matching data information to obtain the track correlation value at time T includes: S23411, calculating and processing the first track position information and the fused track position information in the fused track matching data information to obtain a distance correlation value; S23412, calculating and processing the first track speed information and the fused track speed information in the fused track matching data information to obtain a speed correlation value; S23413, performing weighted average calculation processing on the distance correlation value and the speed correlation value to obtain a motion attribute correlation value; S23414, performing average calculation processing on the first track average speed information and the fused track average speed information in the fused track matching data information to obtain an average speed correlation value; S23415, determining whether the motion attribute association value is greater than the average speed association value, and obtaining a second determination result; When the second judgment result is yes, determining the motion attribute association value as the track association value at time T; When the second judgment result is no, the average speed correlation value is determined to be the track correlation value at the time T.

6. The target track association method based on time-space grid according to claim 4 is characterized in that: The processing of the track extraction data information at time T, the spatiotemporal grid information and the track data set at time T to obtain the track result information at time T includes: S23441, matching the first track time information, the first track position information and the space-time grid information to obtain target-level time grid information and target-level space grid information; S23442, performing matching processing on the first track time information, the first track position information, the target level time grid information and the target level space grid information to obtain target time grid information and target space grid information; S23443, processing the track data set at time T, the spatiotemporal grid information, the target time grid information and the target space grid information to obtain a plurality of fused track data information to be processed; S23444, processing a plurality of the fused track data information to be processed and the track extraction data information at time T to obtain the track result information at time T.

7. The target track association method based on time-space grid according to claim 1 is characterized in that: The step of fusing the track fusion result information at time T, the space-time grid information and the track data information at time T+1 to obtain target track information includes: S31, processing the track fusion result information at time T to obtain predicted fused track information at time T+1; the predicted fused track information at time T+1 includes a plurality of predicted track information at time T+1; S32, obtaining the track data set at time T+1; S33, processing the predicted fused track information at time T+1, the spatiotemporal grid information, the track data information at time T+1 and the track data set at time T+1 to obtain target track fusion result information and target track information; S34, obtaining the user's second stop receiving instruction information; When the second stop receiving instruction information of the user is no, T is increased by 1, the third track data information to be processed is obtained, and the third track data information to be processed is determined to be the track data information at time T+1, and the target track fusion result information is the target track fusion result information at time T, and S31 is executed; When the user's second stop receiving instruction information is yes, the process ends.

8. A target track association device based on a time-space grid, characterized in that: The device comprises: An acquisition module is used to acquire track data information at time T, track data information at time T+1, track data set at time T and time-space grid information; the track data set at time T includes a plurality of fused track data information; the fused track data information includes fused track speed information, fused track average speed information, fused track position information, fused track time information and fused track batch number value; the time-space grid information includes a plurality of time level grid information and a plurality of space level grid information; the time level grid information includes a plurality of time grid information; the space level grid information includes a plurality of space grid information; T is a positive integer; the fused track time information is the average time of the reconnaissance cycle of the multi-sensor after fusion in the fused track data information; A first calculation module is used to fuse the track data information at time T, the spatiotemporal grid information and the track data set at time T to obtain track fusion result information at time T; The second calculation module is used to fuse the track fusion result information at time T, the space-time grid information and the track data information at time T+1 to obtain the target track information.

9. A target track association device based on a time-space grid, characterized in that: The device comprises: processor; a memory coupled to the processor and storing executable program code; The processor calls the executable program code stored in the memory to execute the target track association method based on the space-time grid as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and when the computer instructions are called, they are used to execute the target track association method based on the space-time grid according to any one of claims 1 to 7.

Images