Flight path fusion method and system

Abstract

The invention discloses a track fusion method and system. The method comprises the following steps: receiving a reported track with a timestamp of a detection target; and estimating the positioning mean square error of each piece of reported track data, and carrying out data fusion on the track according to the estimated positioning mean square error. According to the method, the problem that it is difficult to determine a target track curve with small errors and quantitatively calculate track errors in a traditional multi-base fusion sensing method is solved, and the track accuracy is improved.

Description

Technical Field

[0001] The present application belongs to the field of wireless communication and system perception technology, and specifically relates to a track fusion method and system. Background Art

[0002] In 5G-A and future 6G systems, base stations will use integrated communication and perception technology to detect the surrounding environment while providing communication coverage, and form point tracks and tracks to report to the central unit; in the integrated communication and perception cellular system, the cell covered by each base station is divided into three uniform sectors; the maximum range radius of perception detection is generally larger than the radius of communication coverage, which makes several adjacent base stations have a large area of ​​overlapping coverage perception area, so that when multiple adjacent base stations detect the overlapping perception area, they will report independent detection results for the same target; the fusion center needs to determine whether it is the same target based on the reported target motion information (including positioning and motion speed during the motion process, etc.), and perform track fusion on the tracks obtained by several independent detections of the same target to obtain a more accurate fused track;

[0003] However, due to the lack of an estimation method for performance metrics such as the mean square error of target point tracks / tracks obtained by filtering, traditional multi-base fusion perception methods find it difficult to determine the detection cases with smaller errors among several curves, as well as the quantitative performance metrics of each curve, based solely on the point track / track coordinates, and it is difficult to ensure the point track / track fusion performance. Summary of the invention

[0004] In order to solve the deficiencies in the prior art, the present application proposes a track fusion method and system.

[0005] In a first aspect, the present application proposes a track fusion method, comprising:

[0006] Receive the time-stamped track of the detected target reported;

[0007] The positioning mean square error is estimated from each reported track data, and data fusion of the track is performed based on the estimated positioning mean square error.

[0008] Optionally, after data fusion is performed on the track, the method further includes:

[0009] For the tracks collected based on the statistical model method, use a deep learning-based method to filter the fused tracks; and / or,

[0010] For the tracks collected based on the deep learning method, the fused tracks are filtered using a statistical model-based method.

[0011] Optionally, estimating the mean square error of positioning from each reported track data, and fusing the tracks according to the estimated mean square error of positioning, comprises:

[0012] Perform spatial and temporal registration of tracks;

[0013] Calculate the mean square error of the positioning track;

[0014] Arrange the tracks that have been time-space registered in ascending order according to the mean square error of track positioning;

[0015] Select the first N ranked tracks as candidate fusion tracks;

[0016] Based on the minimum mean square error criterion, the point coordinates of the candidate fusion track at time t are weighted using the inverse of the positioning mean square error of the candidate fusion track to obtain the fused track point;

[0017] To T m The fused track points are filtered to obtain the fused track.

[0018] Optionally, the step of performing spatiotemporal registration of the track includes:

[0019] The point coordinates of the track collected in the local coordinate system are linearly transformed into the global coordinate system with the fusion center unit as the center origin coordinates;

[0020] The collected tracks are interpolated using the Lagrange three-point interpolation method, and the reported tracks are unified to the synchronized time points.

[0021] Optionally, calculate the mean square error of the positioning of the track, the steps are as follows:

[0022] Calculate t from any three consecutive coordinate points with timestamps n The instantaneous speed v n and acceleration a n ;

[0023] Assume that the total number of tracks is T m coordinate points with timestamps, then T is obtained for the mth reported track m -2 groups (v n ,a n ) value;

[0024] Calculate the variance of the speed change of the mth reported track;

[0025] The mean square error of the positioning track is calculated based on the variance of the velocity change.

[0026] Optionally, the calculation formula for the variance of the speed change is as shown in formula (1).

[0027] Optionally, the positioning mean square error of the track is obtained by multiplying the positioning mean square error of the point track and the empirical coefficient looked up in the interpolation table.

[0028] The mean square error of the positioning of the point track is obtained by multiplying the variance of the speed change of the track by the empirical parameters obtained by field tests.

[0029] In a second aspect, a track fusion system is proposed, which is implemented by the track fusion method described in the first aspect, and includes:

[0030] At least two inter-sensory base stations for reporting the time-stamped tracks of detected targets to a fusion center unit;

[0031] The fusion center unit is used to perform data fusion on the track by using the positioning mean square error.

[0032] Optionally, when the track fusion unit adopts the statistical model method for filtering, it is processed based on the CPU architecture; when the deep learning method for filtering is adopted, it is processed based on the GPU architecture.

[0033] In a third aspect, an embodiment of the present application further provides a track fusion device for implementing the method described in any embodiment of the first aspect of the present application, including:

[0034] An acquisition module, used for receiving the track with time stamp of the reported detected target;

[0035] The determination module is used to estimate the mean square error of the positioning from each reported track data, and perform data fusion on the track according to the estimated mean square error of the positioning.

[0036] In one embodiment of the present application, a generation module is also included for

[0037] For the tracks collected based on the statistical model method, use a deep learning-based method to filter the fused tracks; and / or,

[0038] For the tracks collected based on the deep learning method, the fused tracks are filtered using a statistical model-based method.

[0039] In a fourth aspect, an embodiment of the present application further proposes a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements a method as described in any embodiment of the first aspect of the present application.

[0040] In a fifth aspect, an embodiment of the present application further proposes 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 method described in any embodiment of the first aspect of the present application is implemented.

[0041] The beneficial effects brought about by the technical solutions provided by some embodiments of the present application include at least:

[0042] The track fusion method provided in the present application solves the problem that it is difficult to determine a target track curve with a smaller error and quantitatively calculate its track error in the traditional multi-base fusion perception method, thereby improving the track accuracy and track fusion accuracy.

[0043] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, preferred embodiments are specifically cited below and described in detail with reference to the attached drawings.

[0044] Advantages of additional aspects of the present application will be given in part in the following description, and in part will become apparent from the following description, or will be learned through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments of the present application or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0046] Figure 1 This is a flow chart of the track fusion method shown in an embodiment of the present application;

[0047] Figure 2 This is a schematic diagram of time registration shown in an embodiment of the present application;

[0048] Figure 3 This is a schematic diagram of a multi-base collaborative synaesthesia integrated point track / track fusion system scenario shown in an embodiment of the present application;

[0049] Figure 4 This is a flow chart of multi-base collaborative synaesthesia integrated track fusion shown in the embodiment of the present application;

[0050] Figure 5 This is an embodiment of a track fusion device of the present application;

[0051] Figure 6 This is another embodiment of a track fusion device of the present application. DETAILED DESCRIPTION

[0052] In order to make the objectives, technical solutions and advantages of the present application more clear, the embodiments of the present application will be further described in detail below with reference to the accompanying drawings.

[0053] When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. Instead, they are only examples of methods and devices consistent with some aspects of the present application as detailed in the attached claims.

[0054] In the description of this application, it should be understood that the term "plurality" refers to two or more than two. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the associated objects before and after are in an "or" relationship.

[0055] The present application proposes a track fusion method and system, which detects the same space to be detected by using multiple telepathic base stations with different physical space positions; each base station reports the detected track to a fusion center unit; the fusion center unit fuses the information reported by multiple stations to obtain a more accurate target motion track; the track fusion system can identify the target based on the fused target track. The method and system of the present application are applicable to various perception technology scenarios, including emerging communication perception integrated technologies such as drone detection and tracking scenarios, vehicle network vehicle detection scenarios, etc.

[0056] This application only requires each distributed collaborative base station to report its own detected point tracks / tracks and its own base station ID, without reporting other prior information. This allows the fusion center to quantitatively determine the accuracy quality of each reported track, and select candidate point tracks / tracks with higher accuracy to fuse the target's point tracks / tracks and obtain a more accurate fused track.

[0057] The following is further described in conjunction with the embodiments and drawings.

[0058] Embodiment 1

[0059] The following will be combined with the attached Figure 1 , a track fusion method provided in an embodiment of the present application is introduced in detail.

[0060] The flow chart of the track fusion method provided in the embodiment of the present application is as follows: Figure 1 As shown, the method of the embodiment of the present application may include the following steps:

[0061] Step S1: receiving the track with time stamp of the reported detected target;

[0062] The point track is the original coordinate point of the detected target position, and the track is the T of the detected target. m The target motion trajectory is obtained after filtering the original coordinate points; in this embodiment, m synaesthesia base stations are used to report the track of the detected target, and the fusion center unit is used to receive the track.

[0063] Step S2: estimating the mean square error of positioning from each reported track data, and performing data fusion on the track according to the estimated mean square error of positioning;

[0064] Specifically, the fusion process includes the following steps:

[0065] Step S2.1: perform spatiotemporal registration of the track;

[0066] It can be understood that spatiotemporal registration is divided into spatial registration and temporal registration. Temporal registration is a necessary step introduced to deal with the incomplete synchronization of timestamps when collecting data. Figure 2 This is a schematic diagram of the time registration of the track;

[0067] Specifically, the process of temporal and spatial registration of the track is as follows:

[0068] Step S2.1.1: linearly transform the point coordinates of the track collected in the local coordinate system into the global coordinate system with the fusion center unit as the center origin coordinates;

[0069] Specifically in this embodiment, the point coordinates of the tracks of the m synaesthesia base stations in the local coordinate system are linearly translated and transformed into the global coordinate system with the fusion center unit as the center origin coordinates;

[0070] Step S2.1.2: Use the Lagrange three-point interpolation method to interpolate the collected tracks and unify the reported tracks to the synchronized time points.

[0071] Specifically in this embodiment, the tracks of the target collected by the m synaesthesia base stations are interpolated, and the reported tracks of the m synaesthesia base stations are unified to a synchronized time point.

[0072] Step S2.2: Calculate the mean square error of the positioning of the track;

[0073] Both point tracks and flight tracks are a series of coordinate points with time stamps. Assuming that the time interval between two adjacent coordinate points reported is Δt, the instantaneous speed v at that moment can be calculated from any three consecutive coordinate points with time stamps. t and acceleration a t ;

[0074] In a feasible implementation, the steps are as follows:

[0075] Step S2.2.1: Calculate t from any three consecutive coordinate points with time stamps n The instantaneous speed v n and acceleration a n ;

[0076] Assume that the three consecutive moments are t n , t n+1 =t n +Δt',t n+2 =t n+2Δt' (Δt' can be several times of Δt, i.e., interval value selection) are respectively l n ,l n+1 ,l n+2 , then t n The speed at a moment can be expressed as: The acceleration can be expressed as:

[0077] Step S2.2.2: Assume that the total number of tracks is T m coordinate points with timestamps, then T is obtained for the mth reported track m -2 groups (v n ,a n ) value;

[0078] Step S2.2.3: Calculate the variance of the speed change of the mth reported track;

[0079] According to (v n , a n ) The variance of the speed change of the mth reported track is calculated as σ Δv,m 2 , specifically, the calculation formula is:

[0080]

[0081] Where n is the nth point of the mth reported track;

[0082] Step S2.2.4: Calculate the mean square error of the track positioning based on the variance of the velocity change.

[0083] Specifically, the calculation formula for calculating the mean square error of the track positioning based on the variance of the speed change is as follows:

[0084]

[0085] in, is the mean square error of the track positioning, is the mean square error of point location, α m To pass α m The empirical coefficients for interpolation table lookup.

[0086] Specifically in this embodiment, it is necessary to obtain α through Monte Carlo simulation or field testing. m Interpolation table of ;

[0087] Specifically, the target of the type to be tested is placed in the rasterized spatial coordinate points with the radar of the telepathic base station as the coordinate center. The distance and direction angle of each point are different. The distance and angle parameters α are calculated under these distance and angle parameters. m The value of

[0088] When applied, interpolation is performed to obtain α at a certain coordinate point m The fitted value of .

[0089] In the case of reporting the track, in this embodiment, the target track is uploaded by each synesthesia base station. The track is actually obtained by filtering the point tracks collected by the synesthesia base station. The mean square error of the positioning of the point tracks is calculated as follows:

[0090]

[0091] in, is the mean square error of the positioning of the point trace, α is an empirical parameter obtained through field tests, and σ Δv,m 2 is the variance of the velocity change of the mth reported track.

[0092] Step S2.3: Arrange the tracks that have been time-space registered in ascending order according to the mean square error of the track positioning;

[0093] Specifically, the mean square error (MSE) of all the point location of the synaesthesia base station is obtained through step S2.2: Or track positioning MSE Afterwards, the m tracks that have been time-space registered are arranged in ascending order according to the positioning MSE from small to large. The smaller the MSE value, the higher the accuracy of the track.

[0094] Step S2.4: Select the first N arranged tracks as candidate fusion tracks;

[0095] In the specific implementation process, the CU (Central Unit) selects the top N tracks with the best spatial and temporal registration quality as candidate fusion tracks, and the MSE set of candidate fusion tracks is recorded as The point coordinate set of the track at time t is

[0096] Step S2.5: Based on the minimum mean square error criterion, the point coordinates of the candidate fused track at time t are weighted using the inverse of the positioning mean square error of the candidate fused track to obtain the fused track point;

[0097] Specifically, the fused track points are recorded as Based on the minimum MSE criterion, the inverse of the track MSE is used Weighted, we get

[0098] Step S2.6: T m The fused track points are filtered to obtain the fused track.

[0099] Specifically, for all T m After fusing the points, we get the fused track.

[0100] In a feasible implementation, after data fusion of the track, it also includes: filtering the fused track collected based on the statistical model method using a deep learning-based method; the deep learning method includes a convolutional neural network or any similar method.

[0101] In a feasible implementation, after data fusion of the track, it also includes: for the track collected based on the deep learning method, using a statistical model-based method to filter the fused track. The statistical model method includes support vector machine or any similar method. The above method is applicable to the track fusion system. At this time, the track reported at the collection site is after point track filtering. The field signal acquisition device (the synaesthesia base station in this embodiment) outputs the track, and the point track is only a state in the internal intermediate processing process; the above method is also applicable to the field signal acquisition device reporting the fusion center unit as a point track. At this time, the reported point track is fused by the same method. The system for point track fusion is that each synaesthesia base station reports the point track, and the fusion center unit filters the fused point track to produce a fused track; the filtering method in this embodiment is Kalman filtering;

[0102] The track fusion method disclosed in the present application solves the problems that traditional multi-base fusion perception methods find it difficult to determine detection cases with smaller errors among several curves in the detection target solely by relying on point track / track coordinates, as well as find it difficult to quantitatively measure the performance of each curve and to ensure the point track / track fusion performance, thereby improving the track accuracy and track fusion accuracy.

[0103] It should be noted that the execution subject of each step of the method provided in Example 1 can be the same device, or the method can be executed by different devices. For example, the execution subject of step S1 and step S2 can be device 1; for another example, the execution subject of step S1 can be device 1, and the execution subject of step S2 can be device 2; and so on.

[0104] Embodiment 2

[0105] The present application proposes a track fusion system, which is implemented by the track fusion method in the first embodiment, and includes:

[0106] At least two inter-sensing base stations are used to report the time-stamped track of the detected target to the fusion center unit, such as Figure 3 As shown;

[0107] Specifically, the ISAC (Integrated Sensing And Communication) base station is a base station such as Figure 2 As shown in the figure, BS (Base Station) is used to represent each ISAC base station, which includes AAU (Active Antenna Unit) and BBU (Building Base band Unite) modules. Each base station can use any frequency band. AAU transmits and receives RF signals and echo signals, and BBU processes the echo signals to obtain the target's track sequence information and uploads it to the fusion center unit.

[0108] The specific working process is that m adjacent synaesthesia base stations report tracks with timestamps to the fusion center unit, and the fusion center unit first performs spatiotemporal registration and track MSE estimation on the reported tracks simultaneously; the point track refers to the original coordinate point information of the target position detected by the synaesthesia base station, and the track refers to the target motion trajectory obtained by filtering the original target point data detected in continuous time (for example, using methods such as Kalman filtering).

[0109] A fusion center unit, used for estimating the mean square error of positioning from each reported track data, and performing data fusion on the track according to the estimated mean square error of positioning;

[0110] Specifically, the positioning accuracy index of the track sequence reported by all distributed ISAC base stations is evaluated, the quality of the reported track sequence is sorted according to the index evaluation, the track set is track associated, the tracks belonging to the same target are determined, and several tracks with higher quality of the same target are selected for fusion and filtering; this process can be regarded as the process of obtaining the fused track by the first filtering;

[0111] In the specific implementation process, Figure 4 As shown, the fusion center unit can continue to use secondary filtering and prediction modules to filter the fused track. The specific process is as follows:

[0112] The secondary filtering and prediction module will continue to filter the incoming fused track to obtain a more accurate target track; at this time, if the base station radar uses a method based on statistical models, then the secondary filtering and prediction module uses a method based on deep learning; conversely, if the base station radar uses a method based on deep learning, then the secondary filtering and prediction module uses a method based on statistical models.

[0113] The specific cooperation process between the fusion center unit and the synaesthesia base station is as follows: CU (Centralized Unit) is the fusion center unit, which will receive the track information reported by multiple neighboring BSs after independent detection. Each reported track information should carry the identification ID of the BS that completed the target detection.

[0114] The CU first performs data fusion on the tracks reported by the connected m adjacent synaesthesia base stations, and then inputs the fused target track into a track fusion unit based on statistical model methods or deep learning methods for track fusion.

[0115] During the specific implementation process, when the track fusion unit adopts the statistical model method for filtering, it is processed based on the CPU architecture; when the deep learning method for filtering is adopted, it is processed based on the GPU architecture.

[0116] It can be understood that the track fusion system may also include a terminal unit for receiving and displaying the track fusion result of the fusion center unit;

[0117] Specifically, the fusion track result information transmitted by the fusion center unit is received, the track fusion classification result transmitted by the fusion center unit is received, and the received information is displayed on the display screen of the terminal unit.

[0118] Specifically in this embodiment, the track fusion module realizes the track fusion unit function, and is combined with the data fusion processing module as a fusion center unit to jointly realize the track fusion function of the system; the terminal unit is a visualization and control unit, which is composed of a visualization display module, a human-computer interaction module, a remote automatic control module, etc.

[0119] The visualization display module receives the fusion track results transmitted by the CU data fusion processing module, receives the track fusion classification results transmitted by the CU track fusion unit module, and displays the above information received on the display screen; the human-computer interaction module provides an interactive interface between humans and the remote control module; the remote automatic control module controls the external system to perform flight control, network configuration and other operations according to the human-computer interaction instructions.

[0120] The track fusion system provided in this embodiment is applicable to various perception technology scenarios, including emerging communication perception integrated technologies such as drone detection and tracking scenarios, Internet of Vehicles vehicle detection scenarios, etc. It is implemented through the track fusion method provided in Example 1, and has the same technical features as the track fusion method provided in Example 1, so it can also solve the same technical problems and achieve the same technical effects, so it is also applicable to point track fusion systems.

[0121] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific implementation process of the system and unit functions described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0122] Embodiment 3

[0123] Figure 5 This is an embodiment of a track fusion device of the present application, which is used to implement the track fusion method of the present application and further implement the fusion center unit of the present application. The device includes:

[0124] The acquisition module 510 is used to receive the track with a time stamp of the reported detection target;

[0125] The determination module 520 is used to estimate the mean square error of positioning from each reported track data, and perform data fusion on the track according to the estimated mean square error of positioning.

[0126] In one embodiment of the present application, a generating module 530 is further included for generating the T m The fused track points are filtered to obtain the fused track.

[0127] In one embodiment of the present application, the generation module is also used to: filter the fused track using a deep learning-based method for the track collected based on the statistical model method; and / or filter the fused track using a statistical model-based method for the track collected based on the deep learning method.

[0128] In one embodiment of the present application, the device further includes a registration module for performing time-controlled registration on the track. Preferably, the point coordinates of the track collected in the local coordinate system are linearly transformed into a global coordinate system with the fusion center unit as the center origin coordinate; the collected track is interpolated using the Lagrange three-point interpolation method, and the reported track is unified to a synchronized time point.

[0129] In one embodiment of the present application, the determination module further includes an estimation submodule, and the estimation submodule is used to calculate the mean square error of the positioning of the track. In one embodiment, the mean square error of the positioning of the track is obtained by multiplying the mean square error of the positioning of the point track and the empirical coefficients found in the interpolation table; in one embodiment, the mean square error of the positioning of the point track is obtained by multiplying the variance of the speed change of the track and the empirical parameters obtained by field testing. Preferably, t is calculated from any three consecutive coordinate points with timestamps. n The instantaneous speed v n and acceleration a n ; Assume that the total number of tracks is T m coordinate points with timestamps, then T is obtained for the mth reported track m-2 groups (v n ,a n ) value; calculate the variance of the speed change of the mth reported track; calculate the mean square error of the positioning of the track according to the variance of the speed change.

[0130] In one embodiment of the present application, the determination module further includes a fusion submodule, and the fusion submodule is used to determine the fused track point. Preferably, in one embodiment, the tracks that have been time-space registered are arranged in ascending order according to the mean square error of the positioning of the track; the first N arranged tracks are selected as candidate fused tracks; based on the minimum mean square error criterion, the point coordinates of the candidate fused track at time t are weighted by the inverse of the mean square error of the positioning of the candidate fused track to obtain the fused track point. It should be understood by those skilled in the art that the embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, some embodiments of the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0131] Therefore, the present application also proposes a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the method described in any embodiment of the present application is implemented.

[0132] Furthermore, the present application also proposes an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method described in any embodiment of the present application when executing the computer program.

[0133] For example, the first embodiment of the present invention is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present invention. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0134] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0135] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0136] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory. The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. Memory is an example of a computer-readable medium.

[0137] Figure 6 6 is a schematic diagram of the structure of an electronic device provided for another embodiment of a track fusion device of the present application. The electronic device 600 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiment of the present application. It includes: one or more processors 620; a storage device 610, which is used to store one or more programs. When the one or more programs are run by the one or more processors 620, the one or more processors 620 implement the track fusion method provided in the embodiment of the present application. The method includes:

[0138] Receive the time-stamped track of the detected target reported;

[0139] The mean square error of positioning is estimated from each reported track data, and the estimated mean square error of positioning is used to perform data fusion on the track.

[0140] A further embodiment of the method is as described in steps S1 to S2.

[0141] The electronic device 600 further includes an input device 630 and an output device 640; the processor 620, storage device 610, input device 630 and output device 640 in the electronic device can be connected via a bus or other means, and the figure takes the connection via a bus 650 as an example.

[0142] The storage device 610, as a computer-readable storage medium, can be used to store software programs, computer executable programs and module units, such as program instructions corresponding to the track fusion method in the embodiment of the present application. The storage device 610 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created according to the use of the terminal, etc. In addition, the storage device 610 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some instances, the storage device 610 may further include a memory remotely arranged relative to the processor 620, and these remote memories may be connected via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0143] The input device 630 may be used to receive input numbers, character information or voice information, and generate key signal input related to user settings and function control of the electronic device. The output device 640 may include electronic devices such as a display screen and a speaker.

[0144] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0145] Finally, it should be noted that the above-described embodiments are only specific implementation methods of the present application, which are used to illustrate the technical solutions of the present application, rather than to limit them. The protection scope of the present application is not limited thereto. Although the present application is described in detail with reference to the above-mentioned embodiments, ordinary technicians in the field should understand that any technician familiar with the technical field can still modify the technical solutions recorded in the above-mentioned embodiments within the technical scope disclosed in the present application, or can easily think of changes, or make equivalent replacements for some of the technical features therein; and these modifications, changes 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 application, and should be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be based on the protection scope of the claims.

[0146] The applicant of this application has made a detailed explanation and description of the implementation examples of this application in conjunction with the drawings in the specification. However, those skilled in the art should understand that the above implementation examples are only preferred implementation schemes of this application, and the detailed description is only to help readers better understand the spirit of this application, and it is not a limitation on the scope of protection of this application. On the contrary, any improvements or modifications based on the inventive spirit of this application should fall within the scope of protection of this application.

Claims

1. A track fusion method, characterized in that: include: Receive the time-stamped track of the detected target reported; The mean square error of positioning is estimated from each reported track data, and the estimated mean square error of positioning is used to perform data fusion on the track.

2. The track fusion method according to claim 1, characterized in that: After data fusion is performed on the track, the method further includes: For the tracks collected based on the statistical model method, use a deep learning-based method to filter the fused tracks; and / or, For the tracks collected based on the deep learning method, the fused tracks are filtered using a statistical model-based method.

3. The track fusion method according to claim 1, characterized in that: The method of estimating the mean square error of positioning from each reported track data and fusing the track data according to the estimated mean square error of positioning comprises: Perform spatial and temporal registration of tracks; Calculate the mean square error of the positioning track; Arrange the tracks that have been time-space registered in ascending order according to the mean square error of track positioning; Select the first N ranked tracks as candidate fusion tracks; Based on the minimum mean square error criterion, the point coordinates of the candidate fusion track at time t are weighted using the inverse of the positioning mean square error of the candidate fusion track to obtain the fused track point; To T m The fused track points are filtered to obtain the fused track.

4. The track fusion method according to claim 1, characterized in that: It also includes the steps of temporal and spatial registration of the tracks: The point coordinates of the track collected in the local coordinate system are linearly transformed into the global coordinate system with the fusion center unit as the center origin coordinates; The collected tracks are interpolated using the Lagrange three-point interpolation method, and the reported tracks are unified to the synchronized time points.

5. The track fusion method according to claim 1, characterized in that: Calculate the mean square error of the track positioning. The steps are as follows: Calculate t from any three consecutive coordinate points with timestamps n The instantaneous speed v n and acceleration a n ; Assume that the total number of tracks is T m coordinate points with timestamps, then T is obtained for the mth reported track m -2 groups (v n ,a n ) value; Calculate the variance of the speed change of the mth reported track; The mean square error of the positioning track is calculated based on the variance of the velocity change.

6. The track fusion method according to claim 5, characterized in that: The calculation formula of the variance of the speed variation is: Among them, σ Δv,m 2 is the variance of the speed change, and n is the nth point of the mth reported track.

7. The track fusion method according to claim 1, characterized in that: The positioning mean square error of the track is obtained by multiplying the positioning mean square error of the point track by the empirical coefficient found in the interpolation table.

8. The track fusion method according to claim 7, characterized in that: The mean square error of the positioning of the point track is obtained by multiplying the variance of the speed change of the track by the empirical parameters obtained by field tests.

9. A track fusion system, implemented by the track fusion method according to any one of claims 1 to 8, characterized in that: include: At least two inter-sensory base stations for reporting the time-stamped tracks of detected targets to a fusion center unit; The fusion center unit is used to estimate the mean square error of positioning from each reported track data, and perform data fusion on the track according to the estimated mean square error of positioning.

10. The track fusion system according to claim 9, characterized in that: When the track fusion unit adopts the statistical model method for filtering, it is processed based on the CPU architecture; when the deep learning method for filtering is adopted, it is processed based on the GPU architecture.

11. A track fusion device, used to implement the method according to any one of claims 1 to 8, characterized in that: include: An acquisition module, used for receiving the track with time stamp of the reported detected target; The determination module is used to estimate the mean square error of the positioning from each reported track data, and perform data fusion on the track according to the estimated mean square error of the positioning.

12. A track fusion device as claimed in claim 11, characterized in that: Also contains generation modules for For the tracks collected based on the statistical model method, use a deep learning-based method to filter the fused tracks; and / or, For the tracks collected based on the deep learning method, the fused tracks are filtered using a statistical model-based method.

13. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 8 is implemented.

14. 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 method according to any one of claims 1 to 8 is implemented.

Images