Asynchronous track association method, device, medium and system
By employing an asynchronous track association method in a distributed multi-sensor multi-target tracking system, and utilizing statistical tests during the association and verification periods, track correlation can be directly determined, thus solving the problem of error accumulation in traditional methods and improving the accuracy of track association.
Patent Information
- Application Number
- CN202511221357.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-08-29
- Publication Date
- 2026-02-10
AI Technical Summary
In distributed multi-sensor multi-target tracking systems, asynchronous track association is difficult. Traditional methods lead to the accumulation of track data errors, which affects the performance of association algorithms, especially in cluttered environments and when multiple target tracks bifurcate or intersect.
An asynchronous track association method is adopted, and the correlation of tracks is directly judged or confirmed by association statistical tests during the association period and the review period. The association statistics are constructed by using Mahalanobis distance and k-nearest neighbor matching techniques to avoid errors caused by time registration.
It improved the accuracy of correlation of track information, ensured the originality and integrity of track information, and significantly improved the accuracy of correlation.
Smart Images
Figure CN121502179A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of distributed multi-sensor multi-target tracking track management, and more specifically, to an asynchronous track association method, device, medium, and system. Background Technology
[0002] In distributed multi-sensor multi-target tracking systems, each independently operating sensor node typically tracks multiple targets continuously. Determining whether different tracks originating from different local sensor nodes correspond to the same target is one of the key problems that the fusion center needs to solve. Furthermore, due to inconsistent sampling periods or incomplete synchronization of working periods among the local sensor nodes, the local tracks received by the fusion center are not only asynchronous but also at different rates, which significantly increases the difficulty of track correlation.
[0003] When the distance between sensor tracks is large and there is no interference, track association is relatively simple. However, in cluttered environments and when multiple target tracks bifurcate or intersect, track association becomes complex. Generally, for asynchronous track association problems, traditional association algorithms use time registration techniques to convert asynchronous tracks into synchronous tracks, and then make association decisions on the converted synchronous tracks. However, time registration techniques can lead to the accumulation of errors in track data, thus affecting the performance of track association algorithms. On the other hand, while track association algorithms based on grey relational analysis do not require tracks to be synchronous, the algorithms rely excessively on the grey relational analysis calculation methods in grey system theory, failing to truly integrate with track association. Therefore, the asynchronous track association problem in dense multi-target scenarios remains a pressing technical problem to be solved in distributed multi-sensor tracking systems. Summary of the Invention
[0004] The purpose of this invention is to overcome the shortcomings of the prior art and provide an asynchronous track association method, device, medium and system that avoids the technical problem of track error accumulation caused by time registration.
[0005] The objective of this invention is achieved through the following solution: An asynchronous track association method includes: Step S1: Perform correlation statistical test on the two received asynchronous track data during the correlation period: if the track separation quality exceeds the threshold at the end of the correlation period, the two tracks are directly judged to be unrelated; otherwise, perform correlation statistical test during the review period. Step S2: Perform a verification period correlation statistical test on the two tracks that have passed the correlation period: if the quality of track verification exceeds the threshold at the end of the verification period, the two tracks are said to be correlated; otherwise, the two tracks are judged to be uncorrelated.
[0006] Furthermore, in step S1, the correlation statistical test performed on the two received asynchronous track data specifically includes the sub-steps of: constructing the correlation statistic. ,Right now: S1-1: Receiving Track Data: When the fusion center is in the track association period... During each processing cycle, , Let be a positive integer, representing the received local node. l The first reported tracking i The track sequence is Record the received local nodes w The first reported tracking j The track sequence is ;in, and Indicates the time of the waypoint. and They represent Time and The three-dimensional track coordinates at that moment. and The measurement error covariance for the corresponding track point; S1-2: Constructing correlation statistics :say For three-dimensional spatial traces with dots Mahalanobis distance between them; Reorder from smallest to largest, denoted as Then it is called For track sequence with trackpoints Between k Nearest neighbor Mahalanobis distance; based on this, the track sequence is then... Matching track sequences Each waypoint and iterate through all possible k Nearest neighbors yield the matrix: ; So, track sequence With track sequence Correlation statistics The construct expression is: ; ,in, For matrix The row number of the largest element in the text.
[0007] Furthermore, following step S1-2, the following step is also included: S1-3: Correlation Statistical Test: In the... Each processing cycle, if Then the trajectory-related quality Decoupling from the track mass Perform the following operations: ; otherwise ; When the association period ends, if Local nodes l The first reported tracking i Tracks and local nodes w The first reported tracking j The correlation between the flight paths is not yet clear and requires further verification through statistical analysis during the review period; if Then directly determine the local node. l The first reported tracking i Tracks and local nodes w The first reported tracking j The flight paths are unrelated.
[0008] Furthermore, the step of performing a verification period correlation statistical test on the two tracks that have passed the correlation period specifically includes the following sub-steps: constructing the correlation statistic. ,Right now: S2-1: Receiving Track Data: When the fusion center is in the track review period... During each processing cycle, For the received local nodes l The first reported tracking i The sequence of tracks is still recorded as And for the received local nodes w The first reported tracking j The sequence of tracks is also denoted as ;in, and Indicates the time of the waypoint. and They represent Time and The three-dimensional track coordinates at that moment. and The measurement error covariance for the corresponding track point; S2-2: Constructing correlation statistics :say For three-dimensional spatial traces with dots Mahalanobis distance between them; Reorder from smallest to largest, denoted as Then it is called For track sequence with trackpoints Between k Nearest neighbor Mahalanobis distance; based on this, the track sequence is then... Matching track sequences Each waypoint and iterate through all possible k Nearest neighbors yield the matrix: ; So, track sequence With track sequence Correlation statistics The construct expression is: ; ,in, For matrix The row number of the largest element in the text.
[0009] Furthermore, following step S2-2, the following step is also included: S2-3: Correlation Statistical Test: In the... Each processing cycle, if Then the quality of track verification Perform the following operations: ; otherwise ; S2-4: Relationship Judgment: When the review period ends, if Then determine the local node. l The first reported tracking i Tracks and local nodes w The first reported tracking j If the flight paths are related, then the local nodes are determined. l The first reported tracking i Tracks and local nodes w The first reported tracking j The flight paths are unrelated.
[0010] An asynchronous track association device includes a processor and a memory, wherein the memory stores a computer program that, when loaded by the processor, executes the method described in any of the preceding methods.
[0011] A computer-readable storage medium storing a computer program that, when loaded by a processor, executes the method described in any of the preceding claims.
[0012] An asynchronous track association system includes the asynchronous track association device described above.
[0013] The beneficial effects of this invention include: The asynchronous track association method of the present invention directly performs association decisions on asynchronous track sequences of unequal lengths, ensuring the originality and integrity of track information and significantly improving the correct association rate. Attached Figure Description
[0014] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0015] Figure 1 This is a flowchart illustrating the asynchronous track association process according to an embodiment of the present invention. Figure 2 This is a flowchart of the correlation statistical test for the correlation period in an embodiment of the present invention; Figure 3 This is a flowchart of the correlation statistical test for the review period in an embodiment of the present invention. Detailed Implementation
[0016] All features disclosed in all embodiments of this specification, or steps in all methods or processes implied in the disclosure, may be combined and / or extended or replaced in any way, except for mutually exclusive features and / or steps.
[0017] The specific implementation process of this invention is as follows: See Figure 1 . Figure 1 The working steps of an asynchronous track association method shown mainly include "S1: Association statistical test during the association period", "S2: Association statistical test during the review period", and "Parameter initialization".
[0018] See Figure 2 and Figure 3 The parameters required for the method of this invention are: positive integers. and Processing cycle calculator Track correlation quality track departure mass Track verification quality ,as well as Right tail probability of distribution and .in, , , as well as The initial value is fixed as follows: ; , as well as and The value of is usually related to the density of the target distribution, the movement pattern, and the sensor detection cycle.
[0019] See Figure 2 Each implementation cycle of the correlation statistical test involving the correlation period involved in this invention can be further subdivided into the following stages: S1-1: Receive track data When the fusion center is in the trajectory correlation period During each processing cycle, record the received local nodes. l The first reported tracking i The track sequence is Record the received local nodes w The first reported tracking j The track sequence is ,in, and Indicates the time of the waypoint. and They represent Time and The three-dimensional track coordinates at that moment. and This represents the measurement error covariance for the corresponding track point.
[0020] S1-2: Constructing correlation statistics
[0021] say For three-dimensional spatial traces with dots The Mahalanobis distance between them. Reorder them from smallest to largest, let's call them as follows: Then it is called ; For track sequence with trackpoints Between k Nearest neighbor Mahalanobis distance. Based on this, the track sequence is then... Matching track sequences Each waypoint and iterate through all possible k Nearest neighbors yield the matrix: ; So, track sequence With track sequence Correlation statistics The construct expression is
[0022] Obviously, ,in, For matrix The row number of the largest element in the text.
[0023] S1-3: Correlation Statistical Test In the Each processing cycle, if Then the trajectory-related quality Decoupling from the track mass Perform the following operations: ; otherwise ; When the association period ends, if Local nodes l The first reported tracking i Tracks and local nodes w The first reported tracking j The correlation between the flight paths is not yet clear and requires further verification through statistical analysis during the review period; if Then directly determine the local node. l The first reported tracking i Tracks and local nodes w The first reported tracking j The flight paths are unrelated.
[0024] See Figure 3 Each implementation cycle of the review period correlation statistical test involved in this invention can be further subdivided into the following stages: S2-1: Receive track data See S1-1. When the fusion center is in the track review period... During each processing cycle, the received local nodes l The first reported tracking i The sequence of tracks is still recorded as And for the received local nodes w The first reported tracking j The sequence of tracks is also denoted as .
[0025] S2-2: Constructing correlation statistics
[0026] See S1-2. In this step, the correlation statistics... The construction method is the same as step S1-2.
[0027] S2-3: Correlation Statistical Test In the Each processing cycle, if Then the quality of track verification Perform the following operations: ; otherwise ; S2-4: Determination of Relationships When the review period ends, if Then determine the local node. l The first reported tracking i Tracks and local nodes w The first reported tracking j If the flight paths are related, then the local nodes are determined. l The first reported tracking i Tracks and local nodes w The first reported tracking j The flight paths are unrelated.
[0028] It should be noted that, within the scope of protection defined in the claims of this invention, the following embodiments can be combined and / or extended or replaced in any logical manner from the above specific embodiments, such as the disclosed technical principles, disclosed technical features or implicitly disclosed technical features.
[0029] Example 1 An asynchronous track association method includes: Step S1: Perform correlation statistical test on the two received asynchronous track data during the correlation period: if the track separation quality exceeds the threshold at the end of the correlation period, the two tracks are directly judged to be unrelated; otherwise, perform correlation statistical test during the review period. Step S2: Perform a verification period correlation statistical test on the two tracks that have passed the correlation period: if the quality of track verification exceeds the threshold at the end of the verification period, the two tracks are said to be correlated; otherwise, the two tracks are judged to be uncorrelated.
[0030] Example 2 Based on Example 1, step S1, which involves performing a correlation statistical test on the two received asynchronous track data, specifically includes the sub-steps of: constructing a correlation statistic. ,Right now: S1-1: Receiving Track Data: When the fusion center is in the track association period... During each processing cycle, , Let be a positive integer, representing the received local node. l The first reported tracking i The track sequence is Record the received local nodes w The first reported trackingj The track sequence is ;in, and Indicates the time of the waypoint. and They represent Time and The three-dimensional track coordinates at that moment. and The measurement error covariance for the corresponding track point; S1-2: Constructing correlation statistics :say For three-dimensional spatial traces with dots Mahalanobis distance between them; Reorder from smallest to largest, denoted as Then it is called For track sequence with trackpoints Between k Nearest neighbor Mahalanobis distance; based on this, the track sequence is then... Matching track sequences Each waypoint and iterate through all possible k Nearest neighbors yield the matrix: ; So, track sequence With track sequence Correlation statistics The construct expression is: ; ,in, For matrix The row number of the largest element in the text.
[0031] Example 3 Based on Example 1, after steps S1-2, the following step is also included: S1-3: Correlation Statistical Test: In the... Each processing cycle, if Then the trajectory-related quality Decoupling from the track mass Perform the following operations: ; otherwise ; When the association period ends, if Local nodes l The first reported tracking iTracks and local nodes w The first reported tracking j The correlation between the flight paths is not yet clear and requires further verification through statistical analysis during the review period; if Then directly determine the local node. l The first reported tracking i Tracks and local nodes w The first reported tracking j The flight paths are unrelated.
[0032] Example 4 Based on Example 1, the step of performing a verification period correlation statistical test on two flight paths that have passed the correlation period specifically includes the following sub-steps: constructing the correlation statistic. ,Right now: S2-1: Receiving Track Data: When the fusion center is in the track review period... During each processing cycle, For the received local nodes l The first reported tracking i The sequence of tracks is still recorded as And for the received local nodes w The first reported tracking j The sequence of tracks is also denoted as ;in, and Indicates the time of the waypoint. and They represent Time and The three-dimensional track coordinates at that moment. and The measurement error covariance for the corresponding track point; S2-2: Constructing correlation statistics :say For three-dimensional spatial traces with dots Mahalanobis distance between them; Reorder from smallest to largest, denoted as Then it is called For track sequence with trackpoints Between k Nearest neighbor Mahalanobis distance; based on this, the track sequence is then... Matching track sequences Each waypoint and iterate through all possible k Nearest neighbors yield the matrix: ; So, track sequence With track sequence Correlation statistics The construct expression is: ; ,in, For matrix The row number of the largest element in the text.
[0033] Example 5 Based on Example 4, after step S2-2, the following step is also included: S2-3: Correlation Statistical Test: In the... Each processing cycle, if Then the quality of track verification Perform the following operations: ; otherwise ; S2-4: Relationship Judgment: When the review period ends, if Then determine the local node. l The first reported tracking i Tracks and local nodes w The first reported tracking j If the flight paths are related, then the local nodes are determined. l The first reported tracking i Tracks and local nodes w The first reported tracking j The flight paths are unrelated.
[0034] Example 6 An asynchronous track association device includes a processor and a memory, wherein the memory stores a computer program that, when loaded by the processor, executes the method described in any of the preceding methods.
[0035] Example 7 A computer-readable storage medium storing a computer program that, when loaded by a processor, executes the method described in any of the preceding claims.
[0036] Example 8 An asynchronous track association system includes the asynchronous track association device described above.
[0037] The units described in the embodiments of the present invention can be implemented in software or hardware, and the described units can also be located in a processor. The names of these units do not necessarily limit the specific unit itself.
[0038] According to one aspect of the present invention, a computer program product or computer program is provided, the computer program product or computer program including computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and executes the computer instructions, causing the computer device to perform the methods provided in the various optional implementations described above.
[0039] In another aspect, embodiments of the present invention also provide a computer-readable medium, which may be included in the electronic device described in the above embodiments; or it may exist independently and not assembled into the electronic device. The computer-readable medium carries one or more programs, which, when executed by the electronic device, cause the electronic device to perform the methods described in the above embodiments.
Claims
1. An asynchronous track association method, characterized in that, include: Step S1: Perform correlation statistical test on the two received asynchronous track data during the correlation period: if the track separation quality exceeds the threshold at the end of the correlation period, the two tracks are directly judged to be unrelated; otherwise, perform correlation statistical test during the review period. Step S2: Perform a verification period correlation statistical test on the two tracks that have passed the correlation period: if the quality of track verification exceeds the threshold at the end of the verification period, the two tracks are said to be correlated; otherwise, the two tracks are judged to be uncorrelated.
2. The asynchronous track association method according to claim 1, characterized in that, In step S1, the correlation statistical test on the two received asynchronous track data specifically includes the sub-steps of: constructing the correlation statistic. ,Right now: S1-1: Receiving Track Data: When the fusion center is in the track association period... During each processing cycle, , Let be a positive integer, representing the received local node. l The first reported tracking i The track sequence is Record the received local nodes w The first reported tracking j The track sequence is ;in, and Indicates the time of the waypoint. and They represent Time and The three-dimensional track coordinates at that moment. and The measurement error covariance for the corresponding track point; S1-2: Constructing correlation statistics :say For three-dimensional spatial traces with dots Mahalanobis distance between them; Reorder from smallest to largest, denoted as Then it is called For track sequence with trackpoints Between k Nearest neighbor Mahalanobis distance; based on this, the track sequence is then... Matching track sequences Each waypoint and iterate through all possible k Nearest neighbors yield the matrix: ； So, track sequence With track sequence Correlation statistics The construct expression is: ； ,in, For matrix The row number of the largest element in the text.
3. The asynchronous track association method according to claim 1, characterized in that, Following step S1-2, the following step is also included: S1-3: Correlation Statistical Test: In the... Each processing cycle, if Then the trajectory-related quality Decoupling from the track mass Perform the following operations: ； otherwise ； When the association period ends, if Local nodes l The first reported tracking i Tracks and local nodes w The first reported tracking j The correlation between the flight paths is not yet clear and requires further verification through statistical analysis during the review period; if Then directly determine the local node. l The first reported tracking i Tracks and local nodes w The first reported tracking j The flight paths are unrelated.
4. The asynchronous track association method according to claim 1, characterized in that, The verification period correlation statistical test for two flight paths that have passed the correlation period specifically includes the following sub-steps: constructing the correlation statistic. ,Right now: S2-1: Receiving Track Data: When the fusion center is in the track review period... During each processing cycle, For the received local nodes l The first reported tracking i The sequence of tracks is still recorded as And for the received local nodes w The first reported tracking j The sequence of tracks is also denoted as ;in, and Indicates the time of the waypoint. and They represent Time and The three-dimensional track coordinates at that moment. and The measurement error covariance for the corresponding track point; S2-2: Constructing correlation statistics :say For three-dimensional spatial traces with dots Mahalanobis distance between them; Reorder from smallest to largest, denoted as Then it is called For track sequence with trackpoints Between k Nearest neighbor Mahalanobis distance; based on this, the track sequence is then... Matching track sequences Each waypoint and iterate through all possible k Nearest neighbors yield the matrix: ； So, track sequence With track sequence Correlation statistics The construct expression is: ； ,in, For matrix The row number of the largest element in the text.
5. The asynchronous track association method according to claim 4, characterized in that, Following step S2-2, the following step is also included: S2-3: Correlation Statistical Test: In the... Each processing cycle, if Then the quality of track verification Perform the following operations: ； otherwise ； S2-4: Relationship Judgment: When the review period ends, if Then determine the local node. l The first reported tracking i Tracks and local nodes w The first reported tracking j If the flight paths are related, then the local nodes are determined. l The first reported tracking i Tracks and local nodes w The first reported tracking j The flight paths are unrelated.
6. An asynchronous track association device, characterized in that, It includes a processor and a memory, wherein the memory stores a computer program that, when loaded by the processor, executes the method as described in any one of claims 1 to 5.
7. A computer-readable storage medium, characterized in that, A computer program is stored in a readable storage medium, which, when loaded by a processor, executes the method as described in any one of claims 1 to 5.
8. An asynchronous track association system, characterized in that, Includes the asynchronous track association device as described in claim 6.