Global optimal association method and system based on target topological characteristic relation graph

Abstract

The invention belongs to the field of target association, and particularly discloses a global optimal association method and system based on a target topological characteristic relation graph. According to the target matching method and device, the target topological features of the associated target set and the to-be-associated target set are extracted, all combinations of the associated target topological features and the to-be-associated target topological features are traversed, and the maximum combination of the relation degrees of the two target topological features is determined, so that the target matching relation is obtained, and the overall relation degree in each combination is fully considered; therefore, the problem that multi-target confusion is difficult to distinguish in target association in a dense multi-target scene is solved.

Description

Technical Field

[0001] This application belongs to the field of target association, and more specifically, relates to a global optimal association method and system based on a target topological feature relationship graph. Background Art

[0002] Multi-radar detection target association refers to the process of fusing detection data from different radars in a multi-radar system to determine whether these data belong to the same target and establishing a unified trajectory of the target. The core task of target association is to match the data of the target to be associated with the data of the existing associated targets to determine whether they belong to the same actual target. The associated target refers to the radar detection data that has been confirmed and successfully associated with a specific target in the multi-radar system. The target to be associated refers to the radar detection data that has not been confirmed or associated with a specific target in the multi-radar system. These data may be new target detections or unconfirmed detections of existing targets. Target association is the basis of target tracking, which can improve the accuracy of target tracking and enhance the stability of target tracking.

[0003] However, when the distance between multiple targets is very close, the resolution of the radar may not be sufficient to distinguish them, resulting in target confusion and inability to clearly identify individual targets. Target confusion refers to the situation in a multi-radar system where, due to the similar or close signal characteristics of multiple targets, the radar cannot accurately distinguish these targets, and thus misassociates the signals of different targets to the same target. Summary of the Invention

[0004] Aiming at the defects of the prior art, the purpose of this application is to provide a global optimal association method and system based on a target topological feature relationship graph, aiming to solve the problem that it is difficult to distinguish multi-target confusion in target association in a dense multi-target scenario.

[0005] The first aspect of this application relates to a global optimal association method based on a target topological feature relationship graph. This method is applied to multi-radar detection target association and includes: Obtain an associated target set and a target set to be associated, and each target includes its own position and speed; Construct the target topological features of the associated target set and the target set to be associated respectively. The construction method is as follows: for a single target set, select any target as the center point, and other targets as nodes. Calculate the relative distance, relative azimuth, relative speed, and relative heading of each node relative to the center point as the edge between the node and the center point, so as to obtain the target topological feature corresponding to the center point. Traverse the entire target set until all targets are selected as the center point; Traverse all combinations of associated target topological features and target topological features to be associated, determine the combination that maximizes the relationship degree between the two target topological features, and obtain the target matching relationship. The relationship degree between the two target topological features is the sum of the relationship degrees of each node in the target topological feature and each node in the target topological feature to be associated. The relationship degree between two nodes is the weighted sum of four factors: relative distance, relative orientation, relative velocity, and relative heading. Conduct a relevance test on the target matching relationship. If the test is successful, determine that the targets are associated; otherwise, they are not associated.

[0006] Preferably, for the target topological feature with the center point and the target topological feature to be associated with the center point , the formula for calculating the relationship degree between two nodes is as follows:

[0007] where is the node in the target topological feature, is the node in the target topological feature to be associated, are the weight vectors corresponding to the similarity factors , determined according to the importance degree of the factors , and ; the similarity factor , represents the similarity of the th factor between the node of the target topological feature with the center point and the node of the target topological feature to be associated with the center point ; , respectively represent the relative distance, relative orientation, relative velocity, and relative heading of the node relative to the center point ; is the th element in ; , respectively represent the relative distance, relative orientation, relative velocity, and relative heading of the node relative to the center point ; is the th element in ; is the maximum value between each node of the target topological feature with the center point and each node of the target topological feature to be associated with the center point ; is the maximum value between each node of the target topological feature with the center point and each node of the target topological feature to be associated with the center point Among the nodes of the target topological features to be associated The minimum value.

[0008] Preferably, traverse all combinations of associated target topological features and target topological features to be associated, determine the combination that maximizes the relationship degree between the two target topological features, and obtain the target matching relationship, specifically as follows:

[0009]

[0010] Among them, , Indicates that the relationship between target topological features is closer, Indicates that the relationship between target topological features is looser.

[0011] Preferably, based on Algorithm for optimal solution to obtain the target matching relationship.

[0012] Preferably, the following threshold clustering method is used to determine the mutual support degree relationship: Step1: Given the clustering threshold , randomly select the relationship degree Mark it as the seed value to form a cluster , and search for the target relationship degree outside the cluster respectively. If there exists , then the relationship degree is marked as a non-seed value and enters the cluster ; otherwise, go to Step2; Step2: Mark the relationship degree as the new seed value to form a new cluster , until there are no other target intimacy values outside ; Step3: If there are still non-seed values in each cluster , return to Step1; otherwise, the clustering ends and enters Step4; Step4: Find the largest cluster. If the number within this cluster exceeds 50% of the total, it is determined that the association is successful; otherwise, the association is unsuccessful.

[0013] Preferably, the value range of the clustering threshold is 0.1 - 0.35.

[0014] The second aspect of the present application relates to a global optimal association system based on a target topological feature relationship graph, including: at least one memory for storing programs; at least one processor for accessing the programs stored in the memory, and when the programs stored in the memory are accessed, the processor is used to implement the global optimal association method as described in the first aspect.

[0015] The third aspect of the present application relates to a computer-readable storage medium storing a computer program, and when the computer program runs on a processor, it causes the processor to implement the global optimal association method as described in the first aspect.

[0016] It can be understood that the beneficial effects of the above second aspect to the third aspect can be referred to the relevant descriptions in the first aspect, and will not be elaborated here.

[0017] Generally speaking, compared with the prior art, the above technical solution conceived by the present application has the following beneficial effects: The present application proposes a global optimal association method based on a target topological feature relationship graph. By extracting the respective target topological features of the associated target set and the target set to be associated, and then traversing all combinations of the associated target topological features and the target topological features to be associated, the combination with the maximum relationship degree between the two target topological features is determined, so as to obtain the target matching relationship, fully considering the overall relationship degree in each combination, thereby solving the problem that it is difficult to distinguish multiple targets in the target association in a dense multi-target scenario. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 FIG. is a flowchart of a global optimal association method based on a target topological feature relationship graph provided by the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0019] In order to make the objectives, technical solutions and advantages of the present application clearer, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0020] The term "and / or" in the present application is a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone. The symbol " / " in the present application represents an "or" relationship between associated objects. For example, A / B represents A or B.

[0021] In the specification and claims of this application, the terms "first" and "second" are used to distinguish different objects, rather than to describe a specific order of objects. For example, "first response message" and "second response message" are used to distinguish different response messages, rather than to describe a specific order of response messages.

[0022] In the embodiments of this application, words such as "exemplary" or "for example" are used to indicate examples, illustrations, or descriptions. Any embodiment or design described as "exemplary" or "for example" in the embodiments of this application should not be interpreted as being preferred or advantageous over other embodiments or designs. Rather, the use of words such as "exemplary" or "for example" is intended to present the relevant concepts in a concrete manner.

[0023] In the description of the embodiments of the present application, unless otherwise specified, "multiple" means two or more, for example, multiple processing units means two or more processing units, etc.; multiple elements means two or more elements, etc.

[0024] The embodiments of the present application are described below in conjunction with the drawings in the embodiments of the present application.

[0025] like Figure 1 As shown, the present application discloses a global optimal association method based on a target topology feature relationship graph, which is applied to multi-radar detection target association, including: Step 1: Obtain the associated target set and the target set to be associated, each target including its own position and speed.

[0026] Step 2: Construct the target topology features of the associated target set and the target set to be associated respectively. The construction method is as follows: for a single target set, select one target as the center point and the other targets as nodes. Calculate the relative distance, relative orientation, relative speed and relative heading of each node relative to the center point as the edge between the node and the center point, thereby obtaining the target topology features corresponding to the center point. Traverse the entire target set until all targets are selected as center points.

[0027] The relative distance, relative orientation, relative speed and relative heading can be mathematically calculated based on the positions and speeds of the two nodes, the details of which belong to the existing technology and will not be elaborated here.

[0028] Step 3: traverse all combinations of associated target topological features and target topological features to be associated, determine the maximum combination of the relationship between the two target topological features, and obtain the target matching relationship. The relationship between the two target topological features is the sum of the relationship between each node in the target topological feature and each node in the target topological feature to be associated. The relationship between the two nodes is the weighted sum of four factors: relative distance, relative orientation, relative speed, and relative heading.

[0029] Preferably, for the center point The target topological features and center points are For the topological characteristics of the target to be associated, the relationship degree calculation formula between two nodes is as follows:

[0030] in, is the node in the target topology feature, is the node in the target topology feature to be associated, Similarity factors The corresponding weight vector, according to the factors The importance is determined, and ; Similarity factor , indicating that the center point is Nodes of target topological features and the center point is Node of the target topological feature to be associated Intermediate The similarity of factors, , respectively represent nodes Relative to the center point The relative distance, relative position, relative speed and relative heading of for Middle elements, , respectively represent nodes Relative to the center point The relative distance, relative position, relative speed and relative heading of for Middle elements; The center point is The target topological features of each node and the center point are Between the nodes of the target topology feature to be associated The maximum value of The center point is The target topological features of each node and the center point are Between the nodes of the target topology feature to be associated The minimum value of .

[0031] Preferably, the traversal of all combinations of associated target topological features and to-be-associated target topological features to determine the maximum combination of the relationship between the two target topological features and obtain the target matching relationship is as follows:

[0032]

[0033] in, , indicates that the target topological feature relationship is closer, indicating that the target topological feature relationship is sparser. The constraint condition is used to ensure that "if it can be associated, a target to be associated has one and only one associated target". represents the number of topological feature nodes of the associated target, represents the number of topological feature nodes of the target to be associated, and .

[0034] This application transforms the matching calculation of the standard topological feature quantity into an optimal linear programming problem of a single objective function, that is, finding a combination relationship in the relationship degree matrix of the two target topological feature quantities to maximize the sum of the relationship metrics of the two target topological feature quantities.

[0035] Preferably, based on the algorithm performs optimal solution to obtain the target matching relationship.

[0036] The KM algorithm, that is, the Kuhn-Munkres algorithm, in a weighted bipartite graph, finds a matching that maximizes the sum of the weights of all edges in the matching. Specifically, by assigning a vertex label (weight value) to each vertex, the maximum weight matching problem is transformed into a problem of finding a complete matching. The goal of the algorithm is to find an equal subgraph (a subgraph composed of edges that meet specific conditions) and find a complete matching in this subgraph.

[0037] Step 4: Conduct an association test on the target matching relationship. If the test is successful, determine that the targets are associated; otherwise, they are not associated.

[0038] Preferably, the following threshold clustering method is used to discriminate the mutual support degree relationship: Step1: Given a clustering threshold , randomly select a relationship degree and mark it as the seed value to form a cluster . Respectively search for the target relationship degree outside the cluster . If there exists , then the relationship degree is marked as a non-seed value and enters the cluster ; otherwise, go to Step2; Step2: Mark the relationship degree as the new seed value to form a new cluster , until there are no other target intimacy values outside ; Step3: If there are still non-seed values in each cluster , return to Step1; otherwise, the clustering ends and enter Step4; Step 4: Find the largest cluster. If the number within this cluster exceeds 50% of the total, it is determined that the association is successful; otherwise, the association is unsuccessful.

[0039] Preferably, the value range of the clustering threshold is 0.1 - 0.35.

[0040] Embodiment Step 1: Obtain the associated target set and the target set to be associated. Each target includes its own position and speed.

[0041] This embodiment is used in a marine multi-radar system. The associated target set = {A, B, C, D}, and the target set to be associated = {a, b, c, e, f, g}. Each target includes its own position and speed.

[0042] Step 2: Construct the target topological features of the associated target set and the target set to be associated respectively. The construction method is as follows: For a single target set, select any target as the center point, and other targets as nodes. Calculate the relative distance, relative azimuth, relative speed, and relative heading of each node relative to the center point, and use them as the edges between the node and the center point, so as to obtain the target topological features corresponding to the center point. Traverse the entire target set until all targets are selected as the center point.

[0043] For the associated target set, there are four targets. First, take A as the center point, calculate the relative distance, relative azimuth, relative speed, and relative heading of B relative to A and C relative to A, and use them as the edges between B and A. Similarly, construct the edges between C and A and between D and A, and obtain a target topological feature graph with A as the root node and three edges. In the same way, obtain the target topological feature graphs corresponding to B, C, and D.

[0044] For the target set to be associated, in the same way, obtain six target topological feature graphs corresponding to each node.

[0045] Step 3: Traverse all combinations of the associated target topological features and the target topological features to be associated, determine the combination with the maximum relationship degree between the two target topological features, and obtain the target matching relationship. The relationship degree between the two target topological features is the sum of the relationship degrees of each node in the target topological feature and each node in the target topological feature to be associated. The relationship degree between two nodes is the weighted sum value of four factors: relative distance, relative azimuth, relative speed, and relative heading.

[0046] The number of combinations of all target topological features and target topological features to be associated is Taking the target topological feature maps corresponding to A and the target topological feature maps corresponding to a as examples, calculate the relationship degrees between B and b, c, e, f, g, between C and b, c, e, f, g, and between D and b, c, e, f, g under different association modes respectively, and sum them as the relationship degree between the two target topological features of this target topological feature combination under this association mode.

[0047] Find the combination with the maximum relationship degree between the two target topological features from all combinations. At this time, according to the corresponding to this combination, obtain the target matching relationship. Specifically, consider that two targets with all have a matching relationship.

[0048] Step 4: Conduct a relevance test on the target matching relationship. If the test is successful, determine that the targets are associated; otherwise, they are not associated.

[0049] Successful association means meeting the threshold clustering and the number of clusters exceeding 50%. In this embodiment, it is obtained that a is associated with A, b is associated with B, c is associated with C, and the new associated target set = {a, b, c, e, f, g, D}.

[0050] It should be understood that the above device is used to execute the method in the above embodiment. For the corresponding program modules in the device, their implementation principles and technical effects are similar to those described in the above method. The working process of the device can refer to the corresponding process in the above method, and will not be elaborated here.

[0051] Based on the method in the above embodiment, an electronic device is provided in an embodiment of the present application. The electronic device may include: a processor (Processor), a communication interface (Communications Interface), a memory (Memory), and a communication bus. Among them, the processor, the communication interface, and the memory complete communication with each other through the communication bus. The processor can call the logical instructions in the memory to execute the method in the above embodiment.

[0052] In addition, when the logical instructions in the above memory are implemented in the form of a software functional unit and sold or used as an independent product, they can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art or a part of this technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions to enable a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application.

[0053] Based on the method in the above embodiments, an embodiment of the present application provides a computer-readable storage medium. The computer-readable storage medium stores a computer program. When the computer program runs on a processor, the processor is caused to execute the method in the above embodiments.

[0054] Based on the method in the above embodiments, an embodiment of the present application provides a computer program product. When the computer program product runs on a processor, the processor is caused to execute the method in the above embodiments.

[0055] It can be understood that the processor in the embodiments of the present application may be a central processing unit (CPU), or may be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field programmable gate arrays (FPGAs), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. The general-purpose processor may be a microprocessor or any conventional processor.

[0056] The method steps in the embodiments of the present application may be implemented in a hardware manner or by a processor executing software instructions. The software instructions may be composed of corresponding software modules. The software modules may be stored in a random access memory (RAM), flash memory, read-only memory (ROM), programmable ROM (PROM), erasable PROM (EPROM), electrically erasable PROM (EEPROM), registers, hard disk, removable hard disk, CD-ROM, or any other form of storage medium well known in the art. An exemplary storage medium is coupled to the processor so that the processor can read information from the storage medium and write information to the storage medium. Of course, the storage medium may also be a component of the processor. The processor and the storage medium may be located in an ASIC.

[0057] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the processes or functions described in the embodiments of the present application are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transmitted through the computer-readable storage medium. The computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center in a wired manner (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or a wireless manner (such as infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or a data center that includes one or more integrated available media. The available medium can be a magnetic medium (such as a floppy disk, a hard disk, a magnetic tape), an optical medium (such as a DVD), or a semiconductor medium (such as a solid state disk (SSD)), etc.

[0058] It can be understood that the various numerical numbers involved in the embodiments of the present application are only for the convenience of description and are not used to limit the scope of the embodiments of the present application.

[0059] It is easy for those skilled in the art to understand that the above are only the preferred embodiments of the present application and are not intended to limit the present application. Any modifications, equivalent replacements, and improvements made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A global optimal association method based on a target topological feature relationship graph, characterized in that The method is applied to multi-radar detection target association and includes: Obtaining an associated target set and a target set to be associated, where each target includes its own position and speed; Respectively constructing the target topological features of the associated target set and the target set to be associated. The construction method is as follows: For a single target set, select any target as the center point, and other targets as nodes. Calculate the relative distance, relative azimuth, relative speed, and relative heading of each node relative to the center point as the edge between the node and the center point, so as to obtain the target topological features corresponding to the center point. Traverse the entire target set until all targets are selected as the center point; Traverse all combinations of the associated target topological features and the target topological features to be associated, determine the combination that maximizes the degree of relationship between the two target topological features, and obtain the target matching relationship. The degree of relationship between the two target topological features is the sum of the degrees of relationship of each node in the target topological features and each node in the target topological features to be associated. The degree of relationship between two nodes is the weighted sum of four factors: relative distance, relative azimuth, relative speed, and relative heading; Conduct an association test on the target matching relationship. If the test is successful, determine that the targets are associated; otherwise, they are not associated.

2. The global optimal association method according to claim 1, wherein For the target topological feature with the center point being and the target topological feature to be associated with the center point being the relationship degree calculation formula for the two nodes is as follows: Among them, is the node in the target topological feature, is the node in the target topological feature to be associated, are the similarity factors corresponding weight vectors respectively, determined according to the importance degree of the factor and ; the similarity factor indicates the similarity of the -th factor between the node of the target topological feature with the center point and the node of the target topological feature to be associated with the center point ; , respectively represent the relative distance, relative azimuth, relative speed and relative heading of the node relative to the center point , is the -th element in , , respectively represent the relative distance, relative azimuth, relative speed and relative heading of the node relative to the center point ; is the -th element in ; is the maximum value of between each node of the target topological feature with the center point and each node of the target topological feature to be associated with the center point , is the minimum value of between each node of the target topological feature with the center point and each node of the target topological feature to be associated with the center point .

3. The global optimal association method according to claim 1, characterized in that, The process of traversing all combinations of the associated target topological features and the target topological features to be associated, determining the combination that maximizes the degree of relationship between the two target topological features, and obtaining the target matching relationship is as follows: Among them, , indicates that the target topological feature relationship is closer, indicates that the target topological feature relationship is looser.

4. The global optimal association method according to claim 3, characterized in that Based on the algorithm, the optimal solution is obtained to get the target matching relationship.

5. The global optimal association method according to claim 1, wherein Use the following threshold clustering method to judge the mutual support degree relationship: Step1: Given the clustering threshold , randomly select a relationship degree and mark it as the seed value to form a cluster . Then, for the target relationship degrees outside the cluster , conduct a search. If there exists , then mark the relationship degree as a non-seed value and add it to the cluster ; Otherwise, go to Step2; Step 2: Mark the relationship degree as a new seed value to form a new cluster , until there are no other target intimacy values outside; Step 3: If there are still non-seed values in each cluster return to Step 1; otherwise, the clustering ends and proceed to Step 4; Step4: Find the largest cluster. If the number within this cluster exceeds 50% of the total, it is determined that the association is successful; otherwise, the association is not successful.

6. The global optimal association method according to claim 5, wherein The value range of the clustering threshold is 0.1 - 0.

35.

7. A global optimal association system based on a target topological feature relationship graph, characterized in that Includes: At least one memory for storing programs; At least one processor for accessing the program stored in the memory. When the program stored in the memory is accessed, the processor is used to execute the global optimal association method according to any one of claims 1 to 6.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program. When the computer program runs on the processor, it causes the processor to execute the global optimal association method according to any one of claims 1 to 6.

Images