Millimeter wave radar secondary clustering method for short-distance traffic target

Abstract

The invention provides a millimeter wave radar secondary clustering method for a short-distance traffic target, and the method comprises the steps: obtaining the motion data of a maneuvering target, carrying out the classification of application scenes according to the motion data of the maneuvering target, and obtaining an application scene classification result; matching a merging judgment method according to the application scene classification result, and performing merging judgment according to the merging judgment method to obtain a merging judgment result; and performing attribute merging according to the merging judgment result to obtain a clustering result of the maneuvering target. According to the invention, on the basis of the first clustering, for different maneuvering target tracking scenes, the strategy of merging judgment and attribute merging is added, the traditional clustering algorithm is improved, and the influence of redundancy and noise data is reduced, so that the clustering accuracy is improved, and the tracking precision is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of maneuvering target tracking, and in particular to a millimeter-wave radar secondary clustering method for close-range traffic targets. Background Art

[0002] Millimeter-wave radar plays a vital role in numerous fields, including automotive safety, autonomous driving, and smart transportation. Clustering is a crucial step in processing and analyzing radar return data, particularly in multi-target tracking (MTT) scenarios, where it plays a crucial role. Radar sensors typically capture a large amount of raw echo data, containing signals from multiple reflected targets. Separating individual target information from this chaotic signal and effectively tracking it is a complex and crucial task.

[0003] The technical background and significance of clustering technology in radar target tracking are primarily reflected in its applications in multi-target detection, noise suppression, dynamic target tracking, and data association. However, the same clustering algorithm can achieve inconsistent results in different scenarios, significantly impacting tracking outcomes. Therefore, a well-designed clustering algorithm can effectively distinguish target signals from radar echoes and provide accurate input for subsequent target tracking algorithms. Summary of the Invention

[0004] Based on this, it is necessary to provide a millimeter-wave radar secondary clustering method for close-range traffic targets to address the above technical problems.

[0005] A millimeter wave radar secondary clustering method for close-range traffic targets includes the following steps:

[0006] Acquiring motion data of a maneuvering target, and performing application scenario classification based on the motion data of the maneuvering target to obtain an application scenario classification result;

[0007] Matching a merging determination method according to the application scenario classification result, performing a merging determination according to the merging determination method, and obtaining a merging determination result;

[0008] Attribute merging is performed according to the merging determination result to obtain a clustering result of the maneuvering target.

[0009] In one embodiment, obtaining maneuvering target motion data, and performing application scenario classification based on the maneuvering target motion data to obtain application scenario classification results include:

[0010] Obtain maneuvering target motion data and preset scene division requirements, classify the maneuvering target motion data into application scenarios according to the preset scene division requirements, and obtain application scenario classification results; wherein the application scenario classification results include: routes with overlapping tracks, routes with a small number of overlapping tracks, and routes with stationary tracks.

[0011] In one embodiment, the merging determination method is matched according to the application scenario classification result, and a merging determination is performed according to the merging determination method to obtain a merging determination result including:

[0012] For the routes with overlapping tracks, target clustering is performed using the NMS algorithm to obtain the first merging judgment result;

[0013] For a small number of routes with overlapping tracks, route data is obtained, matching routes are obtained based on the route data, and the matching routes are subjected to target clustering to obtain a second merging determination result;

[0014] For the routes with stationary tracks, target clustering is performed using the DBSCAN algorithm to obtain the third merging judgment result;

[0015] The first merging determination result, the second merging determination result, and the third merging determination result constitute the merging determination result.

[0016] In one embodiment, for a small number of routes with overlapping tracks, route data is obtained, matching routes are obtained based on the route data, and the matching routes are subjected to target clustering to obtain a second merging determination result, which includes:

[0017] Sort the routes of a small number of overlapping tracks according to the preset sorting requirements to obtain a track list;

[0018] Acquire route data, and calculate attribute data between each pair of routes based on the route data; wherein the attribute data includes: horizontal and vertical coordinates of the maneuvering target position, absolute speed of the maneuvering target, and difference in heading angle;

[0019] obtaining an attribute threshold, and in response to the attribute data being less than the attribute threshold, sorting the attribute data according to a preset requirement to obtain an attribute list;

[0020] Selecting a number of routes with smaller differences according to the attribute list, and saving the routes with smaller differences in a matching list;

[0021] The matching list is traversed to calculate the number of occurrences of each route. In response to the number of occurrences being greater than a preset occurrence threshold, the corresponding route is used as the second merging determination result.

[0022] In one embodiment, performing attribute merging according to the merging determination result to obtain a clustering result of the maneuvering target includes:

[0023] Acquire multiple track frames according to the merging determination result, and calculate a merged track frame and a track frame coefficient according to the track frames;

[0024] Obtaining the track speed and heading angle of the track frame, and calculating the updated track speed and updated heading angle according to the track frame coefficient;

[0025] Calculate the track center point according to the merged track frame to obtain an updated center point;

[0026] Resetting the track dynamic and static attribute counts according to the update center point, and extending the dynamic and static attribute conversion window to obtain updated dynamic and static attributes;

[0027] The merged track frame, the updated track speed, the updated heading angle, the updated center point and the updated dynamic and static attributes constitute a clustering result of the maneuvering target.

[0028] A millimeter-wave radar secondary clustering system for close-range traffic targets, used to implement the above-mentioned millimeter-wave radar secondary clustering method for close-range traffic targets, comprising:

[0029] a classification acquisition module, configured to acquire motion data of a maneuvering target, classify an application scenario according to the motion data of the maneuvering target, and obtain an application scenario classification result;

[0030] A merging and clustering module is used to match the merging determination method according to the classification result of the application scenario, perform target clustering according to the merging determination method, and obtain a clustering result;

[0031] The attribute merging module is used to merge attributes according to the clustering result to obtain a clustering result of the maneuvering target.

[0032] A device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the steps of a millimeter-wave radar secondary clustering method for close-range traffic targets described in each of the above embodiments are implemented.

[0033] A storage medium stores a computer program, which, when executed by a processor, implements the steps of a millimeter-wave radar secondary clustering method for close-range traffic targets described in each of the above embodiments.

[0034] Compared with the existing technology, the advantages and beneficial effects of the present invention are: on the basis of the first clustering, the present invention can add merging judgment and attribute merging strategies for different mobile target tracking scenarios, improve the traditional clustering algorithm, reduce the impact of redundant and noisy data, thereby improving the accuracy of clustering and improving the accuracy of tracking. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 1 is a flow chart of a millimeter-wave radar secondary clustering method for close-range traffic targets in one embodiment;

[0036] Figure 2 This is a schematic diagram of the original clustering effect in one embodiment;

[0037] Figure 3 A schematic diagram of a secondary clustering effect in one embodiment;

[0038] Figure 4 Schematic diagram of the structure of a millimeter-wave radar secondary clustering system for close-range traffic targets in one embodiment;

[0039] Figure 5 Schematic diagram of the internal structure of a device in one embodiment. DETAILED DESCRIPTION

[0040] Before describing the specific embodiments of the present invention, the overall concept of the present invention is described as follows:

[0041] This invention is primarily developed for radar target tracking. Currently, most tracking algorithms are clustering algorithms. Clustering is typically used to simplify target tracking by grouping objects or data points. In many scenarios, clustering offers robustness, flexibility, and the ability to effectively track multiple targets in complex environments. However, it also suffers from high computational complexity, difficulty handling overlapping targets, and parameter sensitivity, which can lead to a large number of tracked targets flying out of the target and causing them to split.

[0042] Therefore, the present invention proposes a millimeter-wave radar secondary clustering method for close-range traffic targets. Based on the first clustering, the traditional clustering algorithm is improved by adding merging judgment and attribute merging strategies for different maneuvering target tracking scenarios.

[0043] After introducing the overall concept of the present invention, in order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below through specific implementation methods in conjunction with the accompanying drawings.

[0044] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in one or more embodiments of this specification should have the usual meanings understood by people with ordinary skills in the field to which the invention belongs. The words "first", "second" and similar terms used in one or more implementations of this specification do not indicate any order, quantity or importance, but are only used to distinguish different components. Words such as "include" or "comprise" mean that the elements or objects appearing before the word include the elements or objects listed after the word and their equivalents, without excluding other elements or objects. Words such as "connect" or "connected" are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the object being described changes, the relative positional relationship may also change accordingly.

[0045] In one embodiment, Figure 1 As shown, a millimeter wave radar secondary clustering method for close-range traffic targets is provided, comprising the following steps:

[0046] Step S101 : acquiring motion data of a maneuvering target, and performing application scenario classification based on the motion data of the maneuvering target to obtain an application scenario classification result.

[0047] Specifically, firstly, the motion data of the maneuvering target is acquired, and then the application scenario is classified according to the current motion data of the maneuvering target to obtain the application scenario classification result.

[0048] On this basis, the motion data of the maneuvering target is obtained, and the application scenario classification is performed according to the motion data of the maneuvering target. The application scenario classification results obtained include:

[0049] Obtain maneuvering target motion data and preset scene division requirements, classify the maneuvering target motion data into application scenarios according to the preset scene division requirements, and obtain application scenario classification results; wherein the application scenario classification results include: routes with overlapping tracks, routes with a small number of overlapping tracks, and routes with stationary tracks.

[0050] Specifically, according to the preset scene division requirements, the maneuvering target motion data is subjected to secondary clustering. Two (or more) track frames with a high degree of overlap and roughly consistent speed and heading angle are classified as overlapping track routes; track frames with no or only a small overlap, but consistent movement direction, speed, and relative position are classified as slightly overlapping track routes; and stationary tracks are classified as stationary track routes.

[0051] Step S102 : matching a merging determination method according to the application scenario classification result, performing a merging determination according to the merging determination method, and obtaining a merging determination result.

[0052] Specifically, according to different application scenarios, different merging determination methods will be used to perform merging determination and obtain merging determination results.

[0053] On this basis, the merging determination method is matched according to the application scenario classification result, and a merging determination is performed according to the merging determination method. The merging determination results obtained include:

[0054] For the routes with overlapping tracks, target clustering is performed using the NMS algorithm to obtain the first merging judgment result;

[0055] For a small number of routes with overlapping tracks, route data is obtained, matching routes are obtained based on the route data, and the matching routes are subjected to target clustering to obtain a second merging determination result;

[0056] For the routes of stationary tracks, target clustering is performed using the DBSCAN algorithm to obtain the third merging judgment result;

[0057] The first merging determination result, the second merging determination result, and the third merging determination result constitute the merging determination result.

[0058] Specifically, for routes with overlapping tracks, when there is a high degree of overlap between two (or more) track frames and the speed and heading angle are basically the same, the non-maximum suppression algorithm (NMS) is used to eliminate redundant routes, retain the most significant routes, reduce the splitting of moving targets, and obtain the first merge judgment result.

[0059] The standard NMS suppression function is as follows:

[0060]

[0061] The intersection-union ratio is the ratio of the area of the intersection of two bounding boxes to the area of the union of the two bounding boxes, as shown below:

[0062]

[0063] Among them, S a Represents the area of the intersection, S b Represents the area of the union part. The score of the detection box whose intersection over union (IoU) exceeds the threshold is directly set to 0.

[0064] For applications where track frames overlap significantly, we consider using the non-maximum suppression (NMS) algorithm from image algorithms to calculate the intersection over union (IoU) of two (or more) track frames. Those with an IoU greater than a set threshold are recorded as merge targets. Furthermore, to prevent incorrect merging, we assess the speed attributes of the tracks, only considering merging tracks with small heading angle differences, small speed differences, and relatively mature tracks.

[0065] In scenarios where the track frames of two routes do not overlap or only partially overlap, but the movement direction, speed, and relative position of two (or more) tracks are consistent, attribute analysis of the route data is performed to determine whether they are the same maneuvering target by analyzing the relative position and attribute changes of the targets, thereby obtaining the second merge judgment result.

[0066] In applications involving stationary flight paths, the DBSCAN algorithm can be used to reduce the number of generated stationary objects and improve clustering quality. First, the neighborhood radius and minimum number of points for the DBSCAN algorithm are determined based on different scenarios. Then, the stationary objects are clustered, with points with insufficient density treated as noise. Finally, densely connected point sets are merged to form clusters.

[0067] On this basis, for a small number of routes with overlapping tracks, route data is obtained, matching routes are obtained based on the route data, and the matching routes are subjected to target clustering to obtain a second merging judgment result including:

[0068] Sort the routes of a small number of overlapping tracks according to the preset sorting requirements to obtain a track list;

[0069] Acquire route data, and calculate attribute data between each pair of routes based on the route data; wherein the attribute data includes: horizontal and vertical coordinates of the maneuvering target position, absolute speed of the maneuvering target, and difference in heading angle;

[0070] obtaining an attribute threshold, and in response to the attribute data being less than the attribute threshold, sorting the attribute data according to a preset requirement to obtain an attribute list;

[0071] Selecting a number of routes with smaller differences according to the attribute list, and saving the routes with smaller differences in a matching list;

[0072] The matching list is traversed to calculate the number of occurrences of each route. In response to the number of occurrences being greater than a preset occurrence threshold, the corresponding route is used as the second merging determination result.

[0073] Specifically, first sort the route list of a small number of overlapping tracks according to the confidence level or the track life cycle to obtain a track list; then set a threshold based on the motion state of the maneuvering target and the flow density of the maneuvering target in the track list. Traverse the track list and calculate the various attributes between each route, such as the horizontal and vertical coordinates of the position, the absolute speed of the maneuvering target, and the difference in heading angle. Get the attribute threshold. If each attribute is less than the set threshold, record it in the attribute list. Then, sort the attribute list, select the three routes with the smallest difference, and store them in the matching list of the corresponding route structure. Finally, re-traverse all matching lists and calculate the number of times each route appears in each route matching list. If the number of appearances is greater than the set threshold, the corresponding route will be used as the second merge judgment result.

[0074] Step S103 : merging attributes according to the merging determination result to obtain a clustering result of the maneuvering target.

[0075] Specifically, according to the merging judgment result, the attributes of the tracks that need to be merged are merged to obtain the clustering result of the maneuvering target.

[0076] On this basis, attribute merging is performed according to the merging judgment result, and the clustering results of the maneuvering target obtained include:

[0077] Acquire multiple track frames according to the merging determination result, and calculate a merged track frame and a track frame coefficient according to the track frames;

[0078] Obtaining the track speed and heading angle of the track frame, and calculating the updated track speed and updated heading angle according to the track frame coefficient;

[0079] Calculate the track center point according to the merged track frame to obtain an updated center point;

[0080] Resetting the track dynamic and static attribute counts according to the update center point, and extending the dynamic and static attribute conversion window to obtain updated dynamic and static attributes;

[0081] The merged track frame, the updated track speed, the updated heading angle, the updated center point and the updated dynamic and static attributes constitute a clustering result of the maneuvering target.

[0082] Specifically, the track frame is first expanded to obtain the track speed and heading angle of the track frame. According to the track frame information of two (or more) tracks, the minimum and maximum values of each coordinate axis are calculated, the convex hull of all vertices is calculated, and the minimum enclosing rectangle is obtained to obtain a new track frame. The reliability of each frame (such as existence time, confidence) is weighted averaged or the maximum value is taken to calculate the track frame coefficient; then, the new track speed and heading angle are recalculated by weighted summation of a certain coefficient, and the speed and heading angle are merged; third, according to the track frame information after expansion in the first step, the position of the track center point is recalculated, because the change of the center point may affect the subsequent filter and the determination of the dynamic and static attributes of the track; finally, in order to prevent the influence of the sudden change of the center point position, the track dynamic and static attribute counts need to be reset, and the dynamic and static attribute conversion window period needs to be extended.

[0083] The clustering effect before being processed by the present invention is as follows Figure 2 As shown, the clustering effect after processing by the present invention is as follows Figure 3 shown.

[0084] The present invention provides a millimeter-wave radar secondary clustering method for close-range traffic targets. Based on the first clustering, the traditional clustering algorithm is improved by adding merging judgment and attribute merging strategies for different maneuvering target tracking scenarios. By adding merging judgment and attribute merging strategies, the secondary clustering can divide the data more finely, reduce misclassification and misclassification, optimize the results of the first clustering, reduce the impact of redundant and noisy data, thereby improving the accuracy of clustering and the accuracy of tracking. The clustering strategy and parameters can be adjusted according to the specific tracking scenario and target characteristics to better meet actual needs. The introduction of the secondary clustering method expands the application scenarios of traditional clustering algorithms. It can not only be used for maneuvering target tracking, but can also be widely used in other fields that require high-precision clustering, such as image segmentation, text clustering, etc.

[0085] It should be noted that the method of the embodiment of the present invention can be performed by a single device, such as a computer or server. The method of this embodiment can also be applied in a distributed scenario, where multiple devices cooperate to perform the method. In such a distributed scenario, one of the multiple devices may only perform one or more steps of the method of the embodiment of the present invention, and the multiple devices will interact with each other to complete the method.

[0086] It should be noted that the above description is limited to some embodiments of the present invention. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in an order different from that described in the above embodiments and still achieve the desired results. Furthermore, the processes depicted in the accompanying drawings do not necessarily require the specific order or sequential order shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0087] Based on the same inventive concept, corresponding to any of the above-mentioned embodiments and methods, the present invention also provides a millimeter-wave radar secondary clustering system for close-range traffic targets.

[0088] refer to Figure 4 The millimeter-wave radar secondary clustering system for close-range traffic targets comprises:

[0089] The classification acquisition module 401 is used to acquire the motion data of the maneuvering target, classify the application scenarios according to the motion data of the maneuvering target, and obtain the application scenario classification results;

[0090] A merging and clustering module 402 is configured to match a merging determination method according to the application scenario classification result, perform target clustering according to the merging determination method, and obtain a clustering result;

[0091] The attribute merging module 403 is configured to merge attributes according to the clustering result to obtain a clustering result of the maneuvering target.

[0092] For the convenience of description, the above system is described as being divided into various modules according to their functions. Of course, when implementing the present invention, the functions of each module can be implemented in the same or multiple software and / or hardware.

[0093] The system of the above embodiment is used to implement a corresponding millimeter-wave radar secondary clustering method for close-range traffic targets in any of the above embodiments, and has the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0094] Based on the same inventive concept, corresponding to any of the above-mentioned embodiments and methods, the present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and runnable on the processor. When the processor executes the program, it implements the millimeter-wave radar secondary clustering method for close-range traffic targets described in any of the above embodiments.

[0095] Figure 510 is a schematic diagram showing a more specific hardware structure of an electronic device provided in this embodiment. The device may include: a processor 1010, a memory 1020, an input / output interface 1030, a communication interface 1040, and a bus 1050. The processor 1010, the memory 1020, the input / output interface 1030, and the communication interface 1040 are communicatively connected to each other within the device via the bus 1050.

[0096] The processor 1010 can be implemented using a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this specification.

[0097] The memory 1020 can be implemented in the form of ROM (Read Only Memory), RAM (Random Access Memory), static storage devices, dynamic storage devices, etc. The memory 1020 can store an operating system and other application programs. When the technical solutions provided in the embodiments of this specification are implemented through software or firmware, the relevant program code is stored in the memory 1020 and is called and executed by the processor 1010.

[0098] The input / output interface 1030 is used to connect input / output modules to implement information input and output. The input / output modules can be configured as components within the device (not shown in the figure) or can be externally connected to the device to provide corresponding functions. Input devices may include a keyboard, mouse, touch screen, microphone, various sensors, etc., and output devices may include a display, speaker, vibrator, indicator light, etc.

[0099] The communication interface 1040 is used to connect to a communication module (not shown) to enable communication between the device and other devices. The communication module can communicate via a wired method (such as USB, network cable, etc.) or a wireless method (such as mobile network, WiFi, Bluetooth, etc.).

[0100] The bus 1050 comprises a path for transmitting information between the various components of the device (eg, the processor 1010 , the memory 1020 , the input / output interface 1030 , and the communication interface 1040 ).

[0101] It should be noted that although the above device only shows the processor 1010, the memory 1020, the input / output interface 1030, the communication interface 1040, and the bus 1050, in a specific implementation, the device may also include other components necessary for normal operation. In addition, it will be understood by those skilled in the art that the above device may only include the components necessary to implement the embodiments of this specification, and does not necessarily include all the components shown in the figure.

[0102] The electronic device of the above embodiment is used to implement a corresponding millimeter wave radar secondary clustering method for close-range traffic targets in any of the above embodiments, and has the beneficial effects of the corresponding method embodiment, which will not be repeated here.

[0103] Based on the same inventive concept, corresponding to any of the above-mentioned embodiments and methods, the present invention also provides a non-transitory computer-readable storage medium, wherein the non-transitory computer-readable storage medium stores computer instructions, and the computer instructions are used to enable the computer to execute a millimeter-wave radar secondary clustering method for close-range traffic targets as described in any of the above embodiments.

[0104] The computer-readable media of this embodiment include permanent and non-permanent, removable and non-removable media that can be used to store information by any method or technology. The information can be computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, read-only compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device.

[0105] The computer instructions stored in the storage medium of the above embodiment are used to enable the computer to execute a millimeter-wave radar secondary clustering method for close-range traffic targets as described in any of the above embodiments, and have the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0106] Those skilled in the art should understand that the discussion of any of the above embodiments is merely illustrative and is not intended to imply that the scope of the present invention (including the claims) is limited to these examples. Within the scope of the present invention, the technical features in the above embodiments or different embodiments may be combined, the steps may be implemented in any order, and there are many other variations of the different aspects of the embodiments of the present invention as described above, which are not provided in detail for the sake of simplicity.

[0107] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, segment or portion of code comprising one or more executable instructions for implementing the steps of a specific logical function or process, and the scope of the preferred embodiments of the present invention includes alternative implementations in which functions may be performed out of the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order depending on the functions involved, which should be understood by those skilled in the art to which the embodiments of the present invention pertain.

[0108] In addition, to simplify the description and discussion, and in order not to obscure the embodiments of the present invention, known power / ground connections to integrated circuit (IC) chips and other components may or may not be shown in the provided figures. In addition, the system may be shown in the form of a block diagram to avoid obscuring the embodiments of the present invention, and this also takes into account the fact that the details of the implementation of these block diagram systems are highly dependent on the platform on which the embodiments of the present invention will be implemented (i.e., these details should be fully within the scope of understanding of those skilled in the art). Where specific details (e.g., circuits) are set forth to describe exemplary embodiments of the present invention, it will be apparent to those skilled in the art that embodiments of the present invention may be implemented without these specific details or with variations in these specific details. Therefore, these descriptions should be considered illustrative rather than restrictive.

[0109] Although the present invention has been described in conjunction with specific embodiments thereof, many alternatives, modifications and variations of these embodiments will be apparent to those skilled in the art in light of the foregoing description. For example, other memory architectures (e.g., dynamic RAM (DRAM)) may utilize the embodiments discussed.

[0110] The embodiments of the present invention are intended to cover all such substitutions, modifications, and variations that fall within the broad scope of the appended claims. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the embodiments of the present invention should be included in the scope of protection of the present invention.

Claims

1. A millimeter-wave radar secondary clustering method for close-range traffic targets, characterized in that: include: Acquiring motion data of a maneuvering target, and performing application scenario classification based on the motion data of the maneuvering target to obtain an application scenario classification result; Matching a merging determination method according to the application scenario classification result, performing a merging determination according to the merging determination method, and obtaining a merging determination result; Attribute merging is performed according to the merging determination result to obtain a clustering result of the maneuvering target.

2. The millimeter-wave radar secondary clustering method for close-range traffic targets according to claim 1, characterized in that: The acquiring of the maneuvering target motion data, and performing application scenario classification according to the maneuvering target motion data to obtain the application scenario classification result include: Obtain maneuvering target motion data and preset scene division requirements, classify the maneuvering target motion data into application scenarios according to the preset scene division requirements, and obtain application scenario classification results; wherein the application scenario classification results include: routes with overlapping tracks, routes with a small number of overlapping tracks, and routes with stationary tracks.

3. The millimeter wave radar secondary clustering method for close-range traffic targets according to claim 2, characterized in that: The matching merging determination method according to the application scenario classification result and performing merging determination according to the merging determination method to obtain a merging determination result include: For the routes with overlapping tracks, target clustering is performed using the NMS algorithm to obtain the first merging judgment result; For a small number of routes with overlapping tracks, route data is obtained, matching routes are obtained based on the route data, and the matching routes are subjected to target clustering to obtain a second merging determination result; For the routes of stationary tracks, target clustering is performed using the DBSCAN algorithm to obtain the third merging judgment result; The first merging determination result, the second merging determination result, and the third merging determination result constitute the merging determination result.

4. The millimeter wave radar secondary clustering method for close-range traffic targets according to claim 3, characterized in that: For the routes with a small number of overlapping tracks, obtaining route data, obtaining matching routes based on the route data, and performing target clustering on the matching routes to obtain a second merging determination result includes: Sort the routes of a small number of overlapping tracks according to the preset sorting requirements to obtain a track list; Acquire route data, and calculate attribute data between each pair of routes based on the route data; wherein the attribute data includes: horizontal and vertical coordinates of the maneuvering target position, absolute speed of the maneuvering target, and difference in heading angle; obtaining an attribute threshold, and in response to the attribute data being less than the attribute threshold, sorting the attribute data according to a preset requirement to obtain an attribute list; Selecting a number of routes with smaller differences according to the attribute list, and saving the routes with smaller differences in a matching list; The matching list is traversed to calculate the number of occurrences of each route. In response to the number of occurrences being greater than a preset occurrence threshold, the corresponding route is used as the second merging determination result.

5. The millimeter wave radar secondary clustering method for close-range traffic targets according to claim 1, characterized in that: Merging attributes according to the merge determination result to obtain a clustering result of the maneuvering target includes: Acquire multiple track frames according to the merging determination result, and calculate a merged track frame and a track frame coefficient according to the track frames; Obtaining the track speed and heading angle of the track frame, and calculating the updated track speed and updated heading angle according to the track frame coefficient; Calculate the track center point according to the merged track frame to obtain an updated center point; Resetting the track dynamic and static attribute counts according to the update center point, and extending the dynamic and static attribute conversion window to obtain updated dynamic and static attributes; The merged track frame, the updated track speed, the updated heading angle, the updated center point and the updated dynamic and static attributes constitute a clustering result of the maneuvering target.

6. A millimeter wave radar secondary clustering system for close-range traffic targets, characterized by: A millimeter-wave radar secondary clustering method for close-range traffic targets according to any one of claims 1 to 5 is implemented, comprising: a classification acquisition module, configured to acquire motion data of a maneuvering target, classify an application scenario according to the motion data of the maneuvering target, and obtain an application scenario classification result; A merging and clustering module is used to match the merging determination method according to the classification result of the application scenario, perform target clustering according to the merging determination method, and obtain a clustering result; The attribute merging module is used to merge attributes according to the clustering result to obtain a clustering result of the maneuvering target.

7. A device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 5 are implemented.

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

Images