A method and device for dynamic multidimensional rapid trajectory association based on millimeter-wave traffic radar

Abstract

This invention discloses a dynamic multidimensional rapid track association method and device based on millimeter-wave traffic radar. The method includes: acquiring point cloud data collected by millimeter-wave traffic radar; clustering the point cloud data using the DBSCAN clustering algorithm to obtain point cloud clustering results; using the centroid algorithm to agglomerate the points in the point cloud clustering results to obtain agglomerated points; and using an association algorithm based on the optimal association coefficient to perform association calculations between the agglomerated points and currently managed tracks or historical points to obtain matched track information.

Description

Technical Field

[0001] This invention relates to the field of millimeter-wave radar application technology in the transportation sector, and more specifically, to a dynamic multidimensional rapid trajectory association method and device based on millimeter-wave traffic radar. Background Technology

[0002] Millimeter-wave radar is a high-precision measuring instrument used in the transportation field, widely applied in vehicle trajectory detection, traffic flow statistics across road sections, and event detection on highways. In vehicle trajectory detection, the data association problem in multi-target tracking is a key issue. Traditional data association algorithms, including nearest neighbor methods, probabilistic data association algorithms, and joint probabilistic data association algorithms, suffer from the following main problems:

[0003] The nearest neighbor method is suitable for single-target tracking environments, but it is not applicable in highway scenarios where there are many targets. Probabilistic data association (PDA) is suitable for sparse multi-target environments, but it is prone to association errors and trajectory deviations in dense target scenarios. Furthermore, it requires calculating the probabilities of all possible measurements, making it difficult to meet real-time requirements, thus it is also unsuitable. While joint probabilistic data association (JPDA) can be applied to dense multi-target environments, the number of joint events is an exponential function of the total number of candidate targets, increasing rapidly with target density, leading to a combinatorial explosion in computational load, making it unsuitable as well.

[0004] In summary, in dense multi-target scenarios, the traces of multiple targets often overlap or are close to each other in the radar measurement space, making it difficult to accurately determine which target trajectory a particular trace belongs to. This leads to trace contention, causing errors in the association between traces and flight paths, thus deviating from the intended path. Traditional association algorithms either have limitations in their applicability to simple scenarios or suffer from high computational complexity and poor real-time performance. Summary of the Invention

[0005] To address the shortcomings of existing technologies, this invention provides a dynamic multidimensional rapid trajectory association method and device based on millimeter-wave traffic radar.

[0006] According to one aspect of the present invention, a dynamic multidimensional fast track association method based on millimeter-wave traffic radar is provided, comprising:

[0007] Acquire point cloud data collected by millimeter-wave traffic radar;

[0008] The point cloud data is clustered using the DBSCAN clustering algorithm to obtain the point cloud clustering results;

[0009] The centroid algorithm is used to agglomerate the points in the point cloud clustering results, resulting in agglomerated points.

[0010] The association algorithm based on the optimal association coefficient performs association calculations between the aggregated points and the currently managed tracks or historical points to obtain the matched track information.

[0011] Optionally, it also includes preprocessing operations such as filtering, denoising, and extracting outliers from the point cloud data.

[0012] Optionally, the point cloud data includes the target in the radar coordinate system. X , Y Position information in the direction, radial distance, radial velocity, and scattering power.

[0013] Optionally, the condensed dots ( R, A, V The expression for ) is:

[0014]

[0015] In the formula, For a certain goal n A dot mark; r Represents the radial distance to a target. a It is the azimuth angle. v Represents radial velocity. p Represents scattering power; R , A , V These represent the radial distance, azimuth angle, and radial velocity of the condensed spot, respectively.

[0016] Optionally, the association algorithm based on the optimal association coefficient performs association calculations between the aggregated points and the currently managed tracks or historical points to obtain the matched track information, including:

[0017] Based on the location of the aggregated points, thresholds of different dimensions and the priority of each dimension threshold are selected. The dimensions include the detected target's position in the radar coordinate system. X, Y Position information in direction, radial distance R and radial velocity V Four dimensions;

[0018] The predicted value of the trajectory at the current moment is calculated based on the trajectory extrapolation;

[0019] Calculate the difference between the point trace and the predicted value in each dimension;

[0020] Determine whether the difference falls within the preset threshold.

[0021] If the points fall within the threshold, the total correlation coefficient of the points is calculated.

[0022] Sort all tracks and all point tracks by their total correlation coefficients, and select the point track and track with the smallest total correlation coefficient as the optimal matching relationship to obtain the matched track information;

[0023] If the trajectory does not fall within the threshold, the trajectory is associated with historical trajectories in the cache to form new trajectory information.

[0024] Optionally, the selection principles for thresholds in different dimensions and the priority of each dimension's thresholds are as follows:

[0025] When the target is within the preset distance range, use X, Y, V Three dimensions serve as the correlation threshold, among which X Dimensions have the highest priority. Y Second, and lastly V ;

[0026] When the target is outside the preset distance range, use Y, R, V Three dimensions serve as the correlation threshold, among which Y Dimensions have the highest priority. R Second, and lastly V .

[0027] Optionally, if the points fall within a threshold, the total correlation coefficient is calculated, including:

[0028] Calculate the correlation coefficient and correlation weight between the points falling within the threshold and each dimension;

[0029] The total correlation coefficient of the points is calculated based on the correlation coefficients and correlation weights of each dimension.

[0030] Optionally, the formula for calculating the correlation coefficient of each dimension is as follows:

[0031]

[0032] In the formula, for X The difference between the measured and predicted dimensional values; For all data in the track X Variance in dimensions; for X Dimensional threshold; for X Dimensional resolution; for Y The difference between the measured and predicted dimensional values; For all data in the track Y Variance in dimensions; for Y Dimensional threshold; for Y Dimensional resolution; for R The difference between the measured and predicted dimensional values; For all data in the track R Variance in dimensions; for R Dimensional threshold; for R Dimensional resolution; for V The difference between the measured and predicted dimensional values; For all data in the track V Variance in dimensions; for V Dimensional threshold; for V Dimensional resolution;

[0033] When the target is within a preset distance range, the total correlation coefficient Where A is the distance when the target is within the preset range. X Dimensional contribution; B represents the distance when the target is within a preset range. Y Dimensional contribution; C represents the distance when the target is within a preset range. V Dimensional contribution;

[0034] When the target is outside the preset distance range, the total correlation coefficient ,in D When the target is outside the preset distance range Y Dimensional contribution; E When the target is outside the preset distance range R Dimensional contribution; F When the target is outside the preset distance range V Dimensional contribution.

[0035] Optionally, the point track and track with the smallest total correlation coefficient are selected as the optimal matching relationship to obtain the matched track information, which also includes:

[0036] If there are multiple matching relationships with the smallest total correlation coefficient, then the correlation coefficients of each single dimension are compared sequentially according to the priority of each dimension until the point and track with the smallest correlation coefficient are selected as the optimal matching relationship, and the matched track information is obtained.

[0037] According to another aspect of the present invention, a dynamic multi-dimensional rapid trajectory correlation device based on millimeter-wave traffic radar is provided, comprising:

[0038] The acquisition module is used to acquire point cloud data collected by millimeter-wave traffic radar;

[0039] The clustering module is used to cluster point cloud data using the DBSCAN clustering algorithm to obtain point cloud clustering results;

[0040] The aggregation module is used to aggregate the points in the point cloud clustering results using the centroid algorithm, and obtain the aggregated points.

[0041] The calculation module is used to perform association calculations between the aggregated points and the currently managed tracks or historical points based on the association algorithm with the optimal association coefficient, and obtain the matched track information.

[0042] According to another aspect of the present invention, a computer-readable storage medium is provided, the storage medium storing a computer program for performing the methods described in any of the above aspects of the present invention.

[0043] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising: a processor; a memory for storing executable instructions of the processor; the processor being configured to read the executable instructions from the memory and execute the instructions to implement the method described in any of the preceding aspects of the present invention.

[0044] Therefore, this invention provides a dynamic multi-dimensional rapid trajectory association method and apparatus based on millimeter-wave traffic radar. This method involves dynamically analyzing the distance to and from the target's location within the detected area. X, Y Distance, speed V and distance R A threshold is selected based on equal dimensions for joint association. For dense multi-target scenarios, an association algorithm based on the optimal association coefficient is proposed to solve the problem of associating the traces of multiple targets with the tracks within the same threshold, as well as the problem of associating multiple tracks with the same trace. Attached Figure Description

[0045] Exemplary embodiments of the present invention can be more fully understood by referring to the following figures:

[0046] Figure 1 This is a flowchart illustrating a dynamic multidimensional rapid trajectory association method based on millimeter-wave traffic radar provided in an exemplary embodiment of the present invention.

[0047] Figure 2 This is a flowchart of the detection device based on a dynamic multidimensional fast track association method provided in an exemplary embodiment of the present invention;

[0048] Figure 3 This is an overall workflow diagram of a dynamic multi-dimensional rapid trajectory association method based on millimeter-wave traffic radar provided by an exemplary embodiment of the present invention;

[0049] Figure 4This is a schematic diagram of track extrapolation detection values ​​and predicted values ​​provided in an exemplary embodiment of the present invention;

[0050] Figure 5 This is a schematic diagram of multiple flight paths competing for the same point, provided by an exemplary embodiment of the present invention;

[0051] Figure 6 This is a schematic diagram of multiple points competing for the same flight path provided by an exemplary embodiment of the present invention;

[0052] Figure 7 This is a schematic diagram of the structure of a dynamic multi-dimensional rapid trajectory association device based on millimeter-wave traffic radar provided in an exemplary embodiment of the present invention;

[0053] Figure 8 This is the structure of an electronic device provided in an exemplary embodiment of the present invention. Detailed Implementation

[0054] Hereinafter, exemplary embodiments according to the present invention will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are merely some embodiments of the present invention, and not all embodiments of the present invention. It should be understood that the present invention is not limited to the exemplary embodiments described herein.

[0055] It should be noted that, unless otherwise specifically stated, the relative arrangement, numerical expressions, and values ​​of the components and steps described in these embodiments do not limit the scope of the invention.

[0056] Those skilled in the art will understand that the terms "first," "second," etc., in the embodiments of the present invention are only used to distinguish different steps, devices, or modules, and do not represent any specific technical meaning, nor do they indicate a necessary logical order between them.

[0057] It should also be understood that in the embodiments of the present invention, "multiple" can refer to two or more, and "at least one" can refer to one, two or more.

[0058] It should also be understood that any component, data or structure mentioned in the embodiments of the present invention can generally be understood as one or more unless explicitly defined or given contrary instructions in the context.

[0059] Furthermore, the term "and / or" in this invention is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Additionally, the character " / " in this invention generally indicates that the preceding and following related objects have an "or" relationship.

[0060] It should also be understood that the description of the various embodiments in this invention emphasizes the differences between the various embodiments, and the similarities or similarities can be referred to each other. For the sake of brevity, they will not be described in detail.

[0061] At the same time, it should be understood that, for ease of description, the dimensions of the various parts shown in the accompanying drawings are not drawn according to actual scale.

[0062] The following description of at least one exemplary embodiment is merely illustrative and is in no way intended to limit the invention or its application or use.

[0063] Techniques, methods, and equipment known to those skilled in the art may not be discussed in detail, but where appropriate, they should be considered part of the specification.

[0064] It should be noted that similar labels and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be discussed further in subsequent figures.

[0065] The embodiments of this invention can be applied to electronic devices such as terminal devices, computer systems, and servers, and can operate together with a wide range of other general-purpose or special-purpose computing system environments or configurations. Well-known examples of terminal devices, computing systems, environments, and / or configurations suitable for use with electronic devices such as terminal devices, computer systems, and servers include, but are not limited to: personal computer systems, server computer systems, thin clients, thick clients, handheld or laptop devices, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputer systems, mainframe computer systems, and distributed cloud computing environments including any of the above systems, etc.

[0066] Electronic devices such as terminal devices, computer systems, and servers can be described in the general context of computer system executable instructions (such as program modules) executed by a computer system. Typically, program modules can include routines, programs, object programs, components, logic, data structures, etc., which perform specific tasks or implement specific abstract data types. Computer systems / servers can be implemented in distributed cloud computing environments, where tasks are executed by remote processing devices linked through communication networks. In distributed cloud computing environments, program modules can reside on local or remote computing system storage media, including storage devices.

[0067] Exemplary methods

[0068] Figure 1This is a flowchart illustrating a dynamic multi-dimensional rapid trajectory association method based on millimeter-wave traffic radar, provided by an exemplary embodiment of the present invention. This embodiment can be applied to electronic devices, such as… Figure 1 As shown, the dynamic multidimensional fast track association method 100 based on millimeter-wave traffic radar includes the following steps:

[0069] Step 101: Acquire point cloud data collected by millimeter-wave traffic radar;

[0070] Step 102: Cluster the point cloud data using the DBSCAN clustering algorithm to obtain the point cloud clustering results;

[0071] Step 103: Use the centroid algorithm to agglomerate the points in the point cloud clustering results to obtain the agglomerated points.

[0072] Step 104: The association algorithm based on the optimal association coefficient performs association calculations with the currently managed track or historical track to obtain the matched track information.

[0073] Specifically, to address at least one of the problems described in the background section, this invention provides a dynamic multi-dimensional fast track association method based on millimeter-wave traffic radar. This method involves jointly associating targets by selecting thresholds based on the distance to and from the detected target's location within the area, considering dimensions such as target X and Y distance, velocity V, and distance R. For dense multi-target scenarios, an association algorithm based on the optimal association coefficient is proposed to address the problems of associating multiple target points with tracks within the same threshold, as well as the problem of associating multiple tracks with the same point.

[0074] Operating mode configuration: This includes configuring system operating parameters, radio frequency module parameters, data preprocessing parameters, track correlation calculation parameters, and track output parameters. The workflow is as follows: Figure 2 As shown.

[0075] Point cloud data acquisition module: This module processes and converts the radar echo signals received by the radio frequency module into usable point cloud data. The acquired radar point cloud data mainly includes the target's position information in the X and Y directions, radial distance R, radial velocity V, and scattering power P in the radar coordinate system. The target's position information in the X and Y directions in the radar coordinate system can be calculated from the acquired azimuth angle and radial distance R.

[0076] Point cloud data preprocessing module: performs preliminary processing on the data, including filtering, noise reduction, and removal of outlier data.

[0077] When a radar detects a target, it receives several point cloud data points reflected from the same target. If tracking filtering is applied to each point cloud, a single target will generate numerous false tracks, affecting the target tracking performance. Therefore, it is necessary to merge all point cloud data points of the same target into a single point cloud set; this process is called point cloud clustering. In this embodiment of the invention, the DBSCAN clustering algorithm is used to perform point cloud clustering. The DBSCAN clustering algorithm is a commonly used technique in this field.

[0078] If the aforementioned point cloud dataset is directly input for correlation processing without any processing, it will not only increase the computational load but also potentially result in multiple tracks for a single target. Since these tracks belong to the same target and are close in both distance and velocity dimensions, they will compete for points, leading to track interruptions and preventing stable tracking. Therefore, it is necessary to preprocess the measurement information and utilize point aggregation to consolidate multiple points from the same target into a single target point track, thereby reducing data processing complexity and improving target tracking stability. In this embodiment of the invention, point aggregation is achieved using the centroid algorithm. Assume that at a certain moment, n points of a target are detected, and their parameters are:

[0079]

[0080] in r Represents radial distance. a It is the azimuth angle. v Represents radial velocity. p The scattering power can be represented by the centroid algorithm to obtain the condensed point trace. R, A, V ):

[0081]

[0082] The track association calculation module: performs association calculations between the aggregated points and the currently managed tracks or historical points, completes the matching, updates the tracks, and destroys invalid points.

[0083] Track output module: Outputs track information through an interface.

[0084] In one embodiment of the present invention, an overall workflow and processing method for a dynamic multidimensional fast track association method are proposed. In dense multi-target scenarios, multiple target tracks often overlap or are close to each other in the radar measurement space, making it difficult to accurately determine which target trajectory a particular track should belong to. This leads to track competition, causing errors in the association between tracks and tracks, thus deviating from the intended track. This mainly falls into two categories: first, the association problem of multiple tracks falling within the same threshold with the same track; second, the association problem of multiple tracks with the same track.

[0085] refer to Figure 3 As shown, the specific implementation process is as follows:

[0086] Step 1: Dynamically determine the threshold dimensions to be used and the priority of each dimension based on the distance of the acquired radar spot data within the radar's field of view. The aforementioned dimensions mainly include the detection target's position in the radar coordinate system. X, Y Position information in direction, radial distance R radial velocity V The selection principles for the four dimensions and multidimensional thresholds are as follows:

[0087] When the target is at close range, X The target is highly sensitive to distance; even if the target's azimuth measurement information is not accurate enough, the target is still within range. X The fluctuations will also be relatively small; Y The direction is the target's main direction of travel, and the fluctuation is relatively... X The direction is relatively large. Therefore, use... X, Y, V Three dimensions serve as the correlation threshold, among which X Dimensions have the highest priority. Y Second, and lastly V .

[0088] When the target is at a distance, X It is highly sensitive to the target measurement azimuth; even a small azimuth error can cause significant fluctuations. Therefore, it was changed to use... R A threshold is used for restriction. Therefore, the following method is adopted. Y, R, V Three dimensions serve as the correlation threshold, among which Y Dimensions have the highest priority. R Second, and lastly V .

[0089] In actual operation, targets within 200m are considered close range, while targets beyond 200m, at the furthest point from the radar's detection range, are considered long range.

[0090] Step 2: Reference Figure 4 As shown, the predicted value at the current time is calculated based on the extrapolation of the flight path. Then, the difference between the measured value and the predicted value in each dimension determined in step 1 is calculated and compared with the threshold values ​​respectively. For points where the difference in each dimension is less than each threshold value at the same time, it is said to fall within the threshold.

[0091] Assuming the state errors in multiple dimensions follow a Gaussian distribution, the threshold for each dimension is selected as three times the variance of the state error of the sequence of points contained in the track along that dimension. X Threshold in dimension is ,but Y Threshold in dimension is ,but RThreshold in dimension is ,but V Threshold in dimension is When the dot falls into X Dimensional threshold needs to satisfy When the dot falls into Y Dimensional threshold needs to satisfy When the dot falls into R Dimensional threshold needs to satisfy When the dot falls into V Dimensional threshold needs to satisfy .

[0092] Step 3: For trajectory points falling within the threshold, calculate the correlation coefficient for each dimension. The calculation formula is as follows:

[0093] (1)

[0094] (2)

[0095] (3)

[0096] (4)

[0097] In the formula, P x for X Correlation coefficients of dimensions; P y for Y Correlation coefficients of dimensions; P r for R Correlation coefficients of dimensions; P v for V Correlation coefficients of dimensions; for X The difference between the measured and predicted dimensional values; For all data in the track X Variance in dimensions; for X Dimensional threshold; for X Dimensional resolution; for Y The difference between the measured and predicted dimensional values; For all data in the track Y Variance in dimensions; for Y Dimensional threshold; for Y Dimensional resolution; forR The difference between the measured and predicted dimensional values; For all data in the track R Variance in dimensions; for R Dimensional threshold; for R Dimensional resolution; for V The difference between the measured and predicted dimensional values; For all data in the track V Variance in dimensions; for V Dimensional threshold; for V Dimensional resolution.

[0098] The total correlation coefficient of the points is calculated based on the correlation coefficients of each dimension as follows:

[0099] When the target is at close range, X The dimension with the highest priority and contribution is A. 、Y The second highest contribution level is B. 、 Finally V Contribution C, total correlation coefficient ,in X Dimensional Contribution A Y Dimensional Contribution B V The relationship between the dimensional contribution C is: A+B+C=1, and in this embodiment, the values ​​are A=0.55, B=0.25, and C=0.2.

[0100] When the target is at a distance, Y The highest priority and contribution of dimension D is... 、R The second highest contribution level is E. 、 Finally V The contribution is F, and the total correlation coefficient is... ,in Y Dimensional contribution D R Dimensional contribution E V The relationship between the dimensional contribution F is: D+E+F=1, and in this embodiment, the values ​​are D=0.4, E=0.35, and F=0.25.

[0101] Step 4: Sort the total correlation coefficients between all tracks and all points, and select the track and point with the lowest correlation coefficient as the optimal matching relationship. This method can effectively solve the problem of multiple tracks competing for the same point or multiple points competing for the same track, such as... Figure 5 As shown, tracks T1 and T2 simultaneously compete for point Z1, as... Figure 6 Points Z1 and Z2 shown are simultaneously competing for track T2:

[0102] Step 5: If there are multiple matching relationships with the same total correlation coefficient in Step 4, the correlation coefficients of the calculated single dimensions need to be compared sequentially according to the priority of the dynamically determined correlation dimension determined in Step 1 until the point track and track with the smallest correlation coefficient are selected as the optimal matching relationship.

[0103] For example, when two points are in a close region, the selected dimensions are ordered by priority as follows: X, Y, V, Then, using the calculation method described in step 3, calculate the total correlation coefficient between the two points and a known track. P 1. P 2, and First, compare based on the priority of the selected dimensions. X Correlation coefficients in dimensions Select the matching relationship corresponding to the minimum value. Then compare Y Correlation coefficients in dimensions Select the matching relationship corresponding to the minimum value. Then compare V Correlation coefficients in dimensions Generally, after multiple comparisons, the optimal matching relationship will be selected.

[0104] Step 6: For points that did not fall within the threshold in Step 2, associate them with historical points in the cache to determine if a new track has been formed. If a new track has been formed, update the track. If no new track has been formed, invalidate the historical points in the cache. If invalid, delete these invalid points and update the historical point cache.

[0105] Following the steps described above, the problem of associating points and tracks of multiple targets within the same threshold in dense multi-target scenarios, as well as the problem of associating multiple tracks with the same point, can be effectively solved. This method has advantages such as high efficiency, high reliability, and ease of implementation.

[0106] Therefore, this invention provides a dynamic multi-dimensional rapid trajectory association method and apparatus based on millimeter-wave traffic radar. This method involves dynamically analyzing the distance to and from the target's location within the detected area. X, Y Distance, speed V and distance R Equal-dimensional thresholds are selected for joint association. For dense multi-target scenarios, an association algorithm based on the optimal association coefficient is proposed to solve the problem of associating points and tracks of multiple targets within the same threshold, as well as the problem of associating multiple tracks with the same point. The dynamic multi-dimensional fast track association technology proposed in this invention has advantages such as high efficiency, high reliability, and ease of implementation.

[0107] Exemplary device

[0108] Figure 7 This is a schematic diagram of the structure of a dynamic multi-dimensional rapid trajectory correlation device based on millimeter-wave traffic radar provided in an exemplary embodiment of the present invention. Figure 7 As shown, the device 700 includes:

[0109] The acquisition module 710 is used to acquire point cloud data collected by millimeter-wave traffic radar;

[0110] Clustering module 720 is used to cluster point cloud data using the DBSCAN clustering algorithm to obtain point cloud clustering results;

[0111] The aggregation module 730 is used to aggregate the points in the point cloud clustering results using the centroid algorithm to obtain aggregated points.

[0112] The calculation module 740 is used to perform association calculations between the aggregated points and the currently managed tracks or historical points based on the association algorithm of the optimal association coefficient, and obtain the matched track information.

[0113] Exemplary electronic devices

[0114] Figure 8 This is the structure of an electronic device provided in an exemplary embodiment of the present invention. For example... Figure 8 As shown, the electronic device 80 includes one or more processors 81 and memory 82.

[0115] The processor 81 may be a central processing unit (CPU) or other form of processing unit with data processing capabilities and / or instruction execution capabilities, and may control other components in the electronic device to perform desired functions.

[0116] The memory 82 may include one or more computer program products, which may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may include, for example, random access memory (RAM) and / or cache memory. The non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage medium, and the processor 81 may execute the program instructions to implement the methods of the software programs of the various embodiments of the present invention described above, and / or other desired functions. In one example, the electronic device may also include an input device 83 and an output device 84, these components being interconnected via a bus system and / or other forms of connection mechanisms (not shown).

[0117] In addition, the input device 83 may also include, for example, a keyboard, a mouse, etc.

[0118] The output device 84 can output various information to the outside. The output device 84 may include, for example, a display, a speaker, a printer, and a communication network and its connected remote output devices, etc.

[0119] Of course, for the sake of simplicity, Figure 8 Only some of the components of this electronic device relevant to the present invention are shown, omitting components such as buses, input / output interfaces, etc. In addition, the electronic device may include any other suitable components depending on the specific application.

[0120] Exemplary computer program products and computer-readable storage media

[0121] In addition to the methods and apparatus described above, embodiments of the present invention may also be computer program products, which include computer program instructions that, when executed by a processor, cause the processor to perform the steps in the methods according to various embodiments of the present invention described in the "Exemplary Methods" section above.

[0122] The computer program product can be written in any combination of one or more programming languages ​​to perform the operations of the embodiments of the present invention. The programming languages ​​include object-oriented programming languages ​​such as Java and C++, as well as conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on the user's computing device, partially on the user's computing device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0123] Furthermore, embodiments of the present invention may also be computer-readable storage media storing computer program instructions thereon, which, when executed by a processor, cause the processor to perform the steps of the methods according to various embodiments of the present invention described in the "Exemplary Methods" section above.

[0124] The computer-readable storage medium may be any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, system, or device, or any combination thereof. More specific examples of readable storage media (a non-exhaustive list) include: an electrical connection having one or more wires, a portable disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0125] The basic principles of the present invention have been described above with reference to specific embodiments. However, it should be noted that the advantages, benefits, and effects mentioned in the present invention are merely examples and not limitations, and should not be considered as essential features of each embodiment of the present invention. Furthermore, the specific details disclosed above are for illustrative and facilitative purposes only, and are not limitations. These details do not limit the present invention to the necessity of employing the aforementioned specific details.

[0126] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For system embodiments, since they largely correspond to method embodiments, the description is relatively simple; relevant parts can be referred to the descriptions in the method embodiments.

[0127] The block diagrams of devices, systems, devices, and systems involved in this invention are merely illustrative examples and are not intended to require or imply that they must be connected, arranged, or configured in the manner shown in the block diagrams. As those skilled in the art will recognize, these devices, systems, devices, and systems can be connected, arranged, and configured in any manner. Words such as “comprising,” “including,” “having,” etc., are open-ended terms meaning “including but not limited to,” and are used interchangeably with them. The terms “or” and “and” as used herein refer to the terms “and / or,” and are used interchangeably with them unless the context clearly indicates otherwise. The term “such as” as used herein refers to the phrase “such as but not limited to,” and is used interchangeably with it.

[0128] The methods and systems of the present invention may be implemented in many ways. For example, they may be implemented by software, hardware, firmware, or any combination of software, hardware, and firmware. The above-described order of steps for the methods is for illustrative purposes only, and the steps of the methods of the present invention are not limited to the order specifically described above unless otherwise specifically stated. Furthermore, in some embodiments, the present invention may also be implemented as a program recorded on a recording medium, the program comprising machine-readable instructions for implementing the methods according to the present invention. Thus, the present invention also covers recording media storing programs for performing the methods according to the present invention.

[0129] It should also be noted that in the systems, apparatus, and methods of the present invention, the components or steps can be disassembled and / or recombined. These disassemblies and / or recombinations should be considered equivalents of the present invention. The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use the invention. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein can be applied to other aspects without departing from the scope of the invention. Therefore, the invention is not intended to be limited to the aspects shown herein, but rather to be carried out within the widest scope consistent with the principles and novel features disclosed herein.

[0130] The above description has been given for purposes of illustration and description. Furthermore, this description is not intended to limit the embodiments of the invention to the forms disclosed herein. Although numerous exemplary aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, alterations, additions, and sub-combinations thereof.

Claims

1. A dynamic multi-dimensional fast track association method based on millimeter wave traffic radar, characterized in that, The method comprises the following steps: acquiring point cloud data collected by a millimeter wave traffic radar; performing clustering on the point cloud data through a DBSCAN clustering algorithm to obtain a point cloud clustering result; performing condensation of the point tracks in the point cloud clustering result by using a centroid algorithm to obtain condensed point tracks; performing correlation calculation on the condensed point tracks and currently managed tracks or historical point tracks based on an optimal correlation coefficient correlation algorithm to obtain matched track information; performing correlation calculation on the condensed point tracks and currently managed tracks or historical point tracks based on an optimal correlation coefficient correlation algorithm to obtain matched track information, which comprises the following steps: According to the position of the condensed point traces, different dimensions of thresholds are selected, and the priority of each dimension threshold is selected, wherein the dimensions include four dimensions of position information, radial distance X, Y in the direction of the target in the radar coordinate system R and radial velocity V ​ calculating a predicted value of the track at the current time according to track extrapolation; calculating a difference between the point track and the predicted value in each dimension; determining whether the difference falls within a preset threshold; if the difference falls within the threshold, calculating a total correlation coefficient of the point track; sorting the total correlation coefficients of all tracks and all point tracks, and selecting a point track and a track with the smallest total correlation coefficient as an optimal matching relationship to obtain matched track information; if the difference does not fall within the threshold, correlating the point track with historical point tracks in a cache to form new track information; the threshold selection principles of different dimensions and the priorities of the thresholds of different dimensions are as follows: When the target is within a preset distance range, using X, Y, V three dimensions as the correlation threshold, wherein X the priority of the dimensions is highest, Y second, and last V ; Target is outside the preset distance range, use Y, R, V Three dimensions as the correlation threshold, wherein Y The priority of the dimension is highest, R Second, last is V ; if the difference falls within the threshold, calculating a total correlation coefficient of the point track, which comprises the following steps: respectively calculating the correlation coefficients and correlation weights of the point track in each dimension that falls within the threshold; calculating the total correlation coefficient of the point track according to the correlation coefficients and correlation weights in each dimension; the calculation expression of the correlation coefficient in each dimension is as follows: wherein is X a difference between the measured value and the predicted value for the dimension; is a variance of all data in the track over X dimension; is X a threshold value for the dimension; is X a resolution for the dimension; is Y a difference between the measured value and the predicted value for the dimension; is a variance of all data in the track over Y dimension; is Y a threshold value for the dimension; is Y a resolution for the dimension; is R a difference between the measured value and the predicted value for the dimension; is a variance of all data in the track over R dimension; is R a threshold value for the dimension; is R a resolution for the dimension; is V a difference between the measured value and the predicted value for the dimension; is a variance of all data in the track over V dimension; is V a threshold value for the dimension; is V a resolution for the dimension; The total correlation coefficient when the target is within the preset distance range Wherein A is the target within the preset distance range X The dimension contribution degree; B is the target within the preset distance range Y The dimension contribution degree; C is the target within the preset distance range V The dimension contribution degree; The total correlation coefficient when the target is outside the preset distance range wherein D when the target is outside the preset distance range Y dimensional contribution degree E when the target is outside the preset distance range R dimensional contribution degree F when the target is outside the preset distance range V dimensional contribution degree 2. The method of claim 1, wherein, The method further comprises the following steps: performing filtering, noise reduction and pre-processing operations of extracting abnormal numbers on the point cloud data.

3. The method of claim 1, wherein, The point cloud data includes position information, radial distance, radial velocity and scattering power of the target in the radar coordinate system X 、 Y direction.

4. The method of claim 3, wherein, The condensed dots ( R, A, V The expression for ) is: wherein is the radial distance of a certain target, n is the azimuth angle of a certain target, r is the radial distance of a certain target, a is the azimuth angle of a certain target, v is the radial velocity of a certain target, p is the scattering power of a certain target, R , A , V are the radial distance, the azimuth angle and the radial velocity of the condensed point trace, respectively.

5. The method of claim 1, wherein, selecting a point track and a track with the smallest total correlation coefficient as an optimal matching relationship to obtain matched track information, which further comprises the following steps: if there are multiple matching relationships with the smallest total correlation coefficient, comparing the calculated single-dimensional correlation coefficients according to the priorities of the dimensions until a point track and a track with the smallest correlation coefficient are selected as an optimal matching relationship to obtain matched track information.

6. A dynamic multi-dimensional fast track association device based on millimeter wave traffic radar, characterized in that, The method comprises the following steps: an acquisition module, configured to acquire point cloud data collected by a millimeter wave traffic radar; a clustering module, configured to perform clustering on the point cloud data through a DBSCAN clustering algorithm to obtain a point cloud clustering result; a condensation module, configured to perform condensation of the point tracks in the point cloud clustering result by using a centroid algorithm to obtain condensed point tracks; a calculation module, configured to perform correlation calculation on the condensed point tracks and currently managed tracks or historical point tracks based on an optimal correlation coefficient correlation algorithm to obtain matched track information; the calculation module comprises the following steps: According to the position of the condensed point traces, different dimensions of thresholds are selected, and the priority of each dimension threshold is selected, wherein the dimensions include four dimensions of position information, radial distance, radial velocity and direction of the detected target in a radar coordinate system X, Y R V ​​​ calculating a predicted value of the track at the current time according to track extrapolation; calculating a difference between the point track and the predicted value in each dimension; determining whether the difference falls within a preset threshold; if the difference falls within the threshold, calculating a total correlation coefficient of the point track; sorting the total correlation coefficients of all tracks and all point tracks, and selecting a point track and a track with the smallest total correlation coefficient as an optimal matching relationship to obtain matched track information; If not falling in the threshold, the point is associated with the history points in the cache to form new track information; The threshold selection principles of different dimensions and the priority of each dimension threshold are: When the target is within a preset distance range, using X, Y, V three dimensions as the correlation threshold, wherein X the priority of the dimensions is highest, Y second, and last V ; The target is outside the preset distance range, using Y, R, V Three dimensions as the correlation threshold, wherein Y The priority of the dimensions is highest, R Second, and last is V ; If falling in the threshold, the total association coefficient of the point is calculated, including: The association coefficients and association weights of the point falling in the threshold are calculated respectively; According to the association coefficients and association weights of each dimension, the total association coefficient of the point is calculated; The calculation expression of the association coefficient of each dimension is: wherein is X a difference between the measured value and the predicted value for the dimension; is a variance of all data in the track in the X dimension; is X a threshold value for the dimension; is X a resolution for the dimension; is Y a difference between the measured value and the predicted value for the dimension; is a variance of all data in the track in the Y dimension; is Y a threshold value for the dimension; is Y a resolution for the dimension; is R a difference between the measured value and the predicted value for the dimension; is a variance of all data in the track in the R dimension; is R a threshold value for the dimension; is R a resolution for the dimension; is V a difference between the measured value and the predicted value for the dimension; is a variance of all data in the track in the V dimension; is V a threshold value for the dimension; is V a resolution for the dimension; The total correlation coefficient when the target is within the preset distance range Wherein A is the target within the preset distance range X The dimension contribution degree; B is the target within the preset distance range Y The dimension contribution degree; C is the target within the preset distance range V The dimension contribution degree; The total correlation coefficient when the target is outside the preset distance range wherein D when the target is outside the preset distance range Y dimensional contribution degree E when the target is outside the preset distance range R dimensional contribution degree F when the target is outside the preset distance range V dimensional contribution degree

Images