Multipath interference suppression method based on lane logic of millimeter wave traffic radar

Abstract

The invention discloses a multipath interference suppression method and system based on lane logic of a millimeter wave traffic radar, and the method comprises the steps: obtaining point cloud data collected by the millimeter wave traffic radar; clustering the point cloud data to obtain a point cloud clustering result, and condensing the point cloud clustering result to obtain a condensed trace point; loading a high-definition map file, extracting map data, and creating a lane model based on the map data; associating the condensed trace point with a currently managed track or a historical trace point to form a new track; and based on the new track, updating a lane model or filtering out tracks with unreasonable logic so as to suppress multipath interference.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of traffic of millimeter wave radar, and more particularly, to a method for suppressing multipath interference based on lane logic of millimeter wave traffic radar. BACKGROUND

[0002] Millimeter wave radar is a high-precision measuring instrument in the field of traffic, and is widely used in the fields of vehicle trajectory detection, road section cross-section flow statistics, and event detection in highways. Due to the scattering of electromagnetic waves by the guardrails, signs, soundproof panels, lamp poles, tunnels and other buildings around the road, especially the electromagnetic waves emitted by the radar are scattered by the vehicle to reach these buildings and then refracted to the radar receiving antenna, false targets, called "ghosts", are caused due to multipath effect. Multipath effect is caused by the reflection, refraction and scattering of target scattered signals during propagation, resulting in the radar receiving multiple signals from different paths. In the actual environment, the echo signal of the millimeter wave traffic radar not only includes the direct wave signal of the target, but also includes the multi-path echo signal reflected by different buildings. Multipath signals will cause aliasing and interference of the target's position, velocity and size, etc., thereby affecting the measurement accuracy and target detection capability of the millimeter wave traffic monitoring radar.

[0003] The identification and suppression method for multipath interference (ghost) is currently mainly divided into two categories. The first category is a model-based method; the second category is a data-based method. The model-based method has good robustness in processing multipath ghosts that meet the conditions of specular reflection, but the complexity of the electromagnetic environment in the actual scene causes the multipath ghost to mismatch the model, which seriously affects the effectiveness of the method. Relatively speaking, the data-based method is less affected by the environment and can handle more complex multipath ghosts, but it faces the problems of less labeled data set and lower recognition accuracy. SUMMARY

[0004] According to the present application, a method and system for suppressing multipath interference based on lane logic of millimeter wave traffic radar are provided to solve the technical problems of less labeled data set and lower recognition accuracy.

[0005] According to a first aspect of the present application, a method for suppressing multipath interference based on lane logic of millimeter wave traffic radar is provided, comprising: acquiring point cloud data collected by a millimeter wave traffic radar; clustering the point cloud data to obtain a point cloud clustering result, and condensing the point cloud clustering result to obtain condensed point traces; loading a high-definition map file, extracting map data, and creating a lane model based on the map data; associating the condensed point traces with a currently managed track or historical point traces to form a new track; Based on the new track, update the lane model or filter out the logically unreasonable track to suppress multipath interference.

[0006] Optionally, the method further comprises a preprocessing operation of filtering, denoising and extracting outliers from the point cloud data.

[0007] Optionally, the point cloud data comprises position information of the target in X and Y directions in a radar coordinate system, radial distance, radial velocity and scattering power.

[0008] Optionally, the method further comprises loading a high-definition map file, extracting map data, and creating a lane model based on the map data, comprising: loading the high-definition map file, intercepting the high-definition map file to obtain a point set in the high-definition map file; converting the point set in the high-definition map file based on the WGS84 coordinate system to the north-east sky coordinate system, and converting the point track in the north-east sky coordinate system to the radar coordinate system, the conversion formula being: that is, wherein , , is a local radar coordinate, E, N, and U are north-east sky coordinates, L is a conversion matrix, is a deflection angle and the value is equal to , is a local north deflection angle of the radar; extracting point set data of each lane in the radar field of view according to the lane attribute in the high-definition map file, and reading the start position, end position and lane segmentation line distance by reading a configuration file; drawing a line segmentation line every certain distance from the start position to the end position, combining the lane line in the map, dividing the map in the radar field of view into several regions, labeling, and creating a spatial model of the lane.

[0009] Optionally, the method further comprises associating the condensed point track with a currently managed track or a historical point track to form a new track, comprising: determining whether the condensed point track falls within a tracking gate, the tracking gate being a region centered on the latest state of the currently managed track, with distance and speed as dimensions, i.e. the horizontal and vertical distances between the condensed point track and the center point meet the set threshold, and the interpolation of the speed and the center point meets the set threshold; If the condensed track falls into the tracking gate, the condensed track is associated with a track, and a new track is formed after successful association, otherwise the condensed track is associated with a historical track to form a new track. If the track does not fall into the tracking gate, return, and determine the next track.

[0010] Optionally, based on the new track, update the lane model or filter out logically unreasonable tracks to suppress multipath interference, including: If the new track is successfully associated with the old track, update the track information and the lane model. If the new track fails to associate with the old track, filter out logically unreasonable tracks to suppress multipath interference.

[0011] Optionally, further comprising: Filtering out logically unreasonable tracks, updating the remaining tracks to the existing tracks, updating the track information and lane information in the lane model, and outputting the tracks.

[0012] According to another aspect of the present application, a lane logic multipath interference suppression system based on a millimeter wave traffic radar is also provided, comprising: An acquisition module for acquiring point cloud data collected by a millimeter wave traffic radar; An aggregation module for clustering the point cloud data to obtain a point cloud clustering result, and condensing the point cloud clustering result to obtain a condensed track; A creation module for loading a high-definition map file, extracting map data, and creating a lane model based on the map data; An association module for associating the condensed track with a currently managed track or a historical track to form a new track; A suppression module for updating the lane model or filtering out logically unreasonable tracks based on the new track to suppress multipath interference.

[0013] According to another aspect of the present application, a computer readable storage medium having a computer program stored thereon is also provided, the program being executed by a processor to implement the steps of the method of any one of the preceding aspects.

[0014] According to another aspect of the present application, a computer readable storage medium having a computer program stored thereon is also provided, the program being executed by a processor to implement the steps of the method of any one of the preceding aspects.

[0015] Therefore, the application provides a lane logic multi-path interference suppression method based on a millimeter wave traffic radar, which associates the condensed point traces with the current managed track or historical point traces to form a new track, updates the lane model based on the new track, or filters out the logically unreasonable track to suppress the multi-path interference, has less environmental impact, and has the advantages of high efficiency, strong reliability, and easy implementation. BRIEF DESCRIPTION OF DRAWINGS

[0016] The exemplary embodiments of the application can be more completely understood in reference to the following drawings: Figure 1 A flowchart of a lane logic multi-path interference suppression method based on a millimeter wave traffic radar according to the present embodiment; Figure 2 A structure block diagram of a lane logic multi-path interference suppression system based on a millimeter wave traffic radar according to the present embodiment; Figure 3 A working flowchart of a lane logic multi-path interference suppression system based on a millimeter wave traffic radar according to the present embodiment; Figure 4 A whole working flowchart of a lane logic multi-path interference suppression method based on a millimeter wave traffic radar according to the present embodiment; Figure 5 A north-east coordinate conversion and radar coordinate system diagram according to the present embodiment; Figure 6 A lane model diagram according to the present embodiment; Figure 7 An occlusion coefficient and control range calculation diagram according to the present embodiment; Figure 8 A track current occupied cell calculation diagram according to the present embodiment; Figure 9 A sliding window algorithm principle diagram according to the present embodiment; Figure 10 A track and track association diagram according to the present embodiment; Figure 11 A diagram of forward multi-track competing for a lane according to the present embodiment; Figure 12 A diagram of reverse multi-track competing for a lane according to the present embodiment; Figure 13 A diagram of a lane logic multi-path interference suppression system based on a millimeter wave traffic radar according to the present embodiment. DETAILED DESCRIPTION

[0017] Reference will now be made to the drawings to describe the exemplary embodiments of the present application in greater detail. The present application can be variously embodied and is not limited to the embodiments described herein. These embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the application to those skilled in the art. The terminology used in the description of the exemplary embodiments herein is not intended to be limiting of the present application. Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. It will be further understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the relevant art and the present disclosure, and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.

[0018] Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. It will be further understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the relevant art and the present disclosure, and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.

[0019] According to a first aspect of the present application, there is provided a method 100 for mitigating multipath interference based on lane logic of millimeter-wave traffic radar, referring to Figure 1 The method 100 comprises: S101: obtaining point cloud data collected by a millimeter-wave traffic radar; S102: clustering the point cloud data to obtain a point cloud clustering result, and condensing the point cloud clustering result to obtain condensed point tracks; S103: loading a high-definition map file, extracting map data, and creating a lane model based on the map data; S104: associating the condensed point tracks with currently managed tracks or historical point tracks to form new tracks; S105: updating the lane model or filtering out logically unreasonable tracks based on the new tracks to mitigate multipath interference.

[0020] Specifically, to solve at least one problem described in the background, the present application provides a method for mitigating multipath interference based on lane logic of millimeter-wave traffic radar. By associating the condensed point tracks with currently managed tracks or historical point tracks to form new tracks, and updating the lane model or filtering out logically unreasonable tracks based on the new tracks to mitigate multipath interference.

[0021] Working mode configuration: including configuring system working parameters, configuring radio frequency module parameters, configuring data preprocessing parameters, configuring point track clustering and condensing parameters, configuring track management module parameters, and configuring track output parameters, etc. The working flow is shown in Figure 2 and Figure 3 .

[0022] Point cloud data acquisition module: the radar echo signal received by the radio frequency module is calculated and converted into available point cloud data. The collected radar point cloud data mainly includes the position information of the target in the X and Y directions of the radar coordinate system, the radial distance R, the radial velocity V and the scattering power P.

[0023] Point cloud data preprocessing module: filtering, noise reduction and preliminary processing of abnormal data.

[0024] Point cloud data clustering and condensation: when detecting targets, the radar will receive several point cloud data reflected by the same target. If each point cloud is tracked and filtered, a large number of false tracks will be generated for a target, affecting the tracking effect of the target. Therefore, all point cloud data of the same target need to be merged into a point cloud set, and this process is point cloud clustering. In the embodiment of the application, the DBSCAN clustering algorithm is used to complete the clustering of the point cloud. The DBSCAN clustering algorithm is a conventional technical means in the art.

[0025] If the above point cloud set data is not processed and directly input for association processing, not only the calculation amount will be increased, but also a target may form multiple tracks. Since these tracks are from the same target and are close in distance and speed, these tracks will compete with each other, resulting in track interruption and unstable tracking. Therefore, the measurement information needs to be preprocessed, and the point tracks from the same target are condensed into a target point track as much as possible to reduce the data processing complexity and improve the stability of target tracking. In the embodiment of the application, the centroid algorithm is used to complete the condensation of the point track.

[0026] Track management module: load high-precision map file, extract map data, create lane model, associate point track with track for the condensed point track, update track after successful association, associate point track with point track for the point track that fails to be associated, and if a new track is formed, evaluate the logical rationality of the track in combination with the lane model, and filter out the tracks with logical irrationality to suppress multipath interference.

[0027] Track output module: output track information through an interface.

[0028] In the actual environment of the application, the echo signal of the millimeter wave traffic radar not only includes the direct wave signal of the target, but also includes the multipath echo signal reflected by different buildings. The multipath signal will cause aliasing and interference of the parameters such as the position, speed and size of the target, thereby affecting the measurement accuracy and target detection ability of the millimeter wave traffic monitoring radar.

[0029] Reference Figure 4 As shown in the figure, the specific implementation process is as follows: Step 1: load the high-definition map file, take the latitude and longitude coordinates of the radar installation position as the origin, and intercept and calculate the high-definition map file with the scanning range of the radar as the radius. The so-called calculation is to first convert the point set in the high-definition map file based on the WGS84 coordinate system to the North-East-Up coordinate system (ENU), which is a common technical means in the art, and then convert the point set in the North-East-Up coordinate system to the radar coordinate system (Cartesian rectangular coordinate system with the radar array normal as the Y axis), as shown in FIG. 1. Figure 5 Convert the North-East-Up coordinate to the radar coordinate system, and the conversion formula is as follows: That is, Among them, , , is the local radar coordinate, E, N, U is the North-East-Up coordinate, L is the conversion matrix, is the deflection angle and the value is equal to , is the local north deflection angle of the radar.

[0030] According to the lane attribute in the map data, the point set data of each lane in the radar field of view is extracted, and the starting position, ending position, lane division line distance and other parameters are read by reading the configuration file. Starting from the starting position, a line division line is drawn every certain distance, and the map in the radar field of view is divided into several regions combined with the lane line in the map, and is labeled to create a spatial model of the lane, as shown in FIG. 2. In this embodiment, the distance of the lane division line is 5m, the starting position is 50m, and the ending position is determined according to the maximum detection distance of the radar. In this embodiment, a 500m millimeter wave traffic radar is used, and the ending position is 450m. Figure 6

[0031] Step 2: obtain the condensed point data, judge whether the point falls into the tracking gate, if not, return, then judge the next point, otherwise associate the point with the existing track, if the association is successful, update the track information, wherein the track information mainly includes track length, track density, track instantaneous speed, track average speed, track direction, track average acceleration, shielding coefficient, control range and track confidence.

[0032] Among them, the tracking gate is a region with distance and speed as dimensions, that is, the horizontal and vertical distances between the condensed point and the center point meet the set threshold, and the interpolation speed of the center point meets the set threshold.

[0033] ​​wherein the length of the track is the difference of the coordinates of the farthest point in the track and the nearest point in the track in the direction of the track, i.e. Y ; the density of the track is the number of points in the track; the instantaneous velocity of the track is the velocity of the newest point in the track; the average velocity of the track is the average of the velocities of all points in the track, i.e. ; the direction of the track is +1 if the target is moving away from the radar and -1 if the target is moving towards the radar; the average acceleration of the track is the difference of the velocity of the newest point in the track and the velocity of the first point in the track divided by the time difference between the two points, i.e. ; ; ; the occlusion coefficient is the ratio of the height of the target and the height of the radar, ; the height of the target is empirically calculated from the length of the target; the control range is wherein y is the coordinate value of the current position in the direction of the track, Y ; the occlusion coefficient is as shown in FIG. 1; Figure 7 the cell occupied by the track in the road model is determined according to the current position of the target and the control range, as shown in FIG. 1, the current cell occupied by the track is 1-1 and 1-2. Figure 8 the confidence of the track is the sum of the initial track confidence,

[0034] the process track confidence, the velocity confidence, i.e. . wherein the initial track confidence is: when the track is positive, the calculation formula is:

[0035] when the track is negative, the calculation formula is: the process track confidence is: wherein the coordinate of the first point in the track in the direction of the track is when Y , when , ​​​​​; is the preset start position of the track in step 1, is the preset end position of the track in step 1; is the length of the track, when , ; is the direction of the track; is the track density, is the track stability threshold, when , .

[0036] is the velocity confidence is: wherein, is the instantaneous velocity of the track in step 2; is the average velocity of the track in step 2; is the variance of all points in the track in the velocity dimension; when , .

[0037] In the above, is a preset initial confidence parameter, which is 20 in the embodiment; is a preset process confidence parameter, which is 70 in the embodiment; is a velocity confidence parameter, which is 10 in the embodiment; wherein =100.

[0038] Then, the basic information of each lane in the lane logic model is updated, mainly including the lane density, the lane occupancy range, the lane average velocity, the lane average acceleration, and the average confidence of the track. The lane density m is the number of all tracks in the lane, the lane occupancy range is the position of the track farthest from the radar in the lane and the position of the track closest to the radar in the lane, i.e. Y , Y , when there is only one track, , wherein is the length of the target; the lane average velocity is the ratio of the sum of the products of the average velocities of all tracks in the lane and the track direction to the lane density, i.e. ; the lane average acceleration is the ratio of the sum of the products of the average accelerations of all tracks in the lane and the track direction to the lane density, i.e. ; and the lane average confidence is the ratio of the sum of the products of the confidences of all tracks in the lane and the track direction to the lane density, i.e. .

[0039] Step 3: Track-to-track association is performed for the points that failed to be associated with the tracks in step 2. The current time point is associated with the historical time points, and a new track is formed if the association is successful. In the track initiation algorithm, the most widely used method is the m / n logic nearest neighbor initiation method of the "sliding window". This method has small calculation amount and is easy to implement in engineering. The "sliding window" method needs to process the point sequence of the current time point and the historical continuous several periods. These points are all failed to be associated with the existing tracks successfully. The basic idea of this algorithm is: taking the current time point as the time end point, in the continuous n periods, the number of successful point-to-point association is greater than or equal to m, then a new track is output. In engineering applications, n and m are often taken as 3 and 2, and the principle is as shown in Figure 9

[0040] Step 4: Multi-period association calculation is performed for the new track formed in step 3 and the existing track. The main purpose is to solve the problem that the same target leads to track interruption due to occlusion and other reasons, and when the target is detected again, the front and back form multiple tracks that cannot be associated. Referring to Figure 10 , the old track is forward extrapolated to the starting time of the new track, and the new track is backward extrapolated to the end time of the old track, and then the data of the two tracks are associated. When the point of the continuous multiple periods falls within the association threshold, it is considered that the new track is successfully associated with the old track. The track information is updated, and then the track information in each lane of the lane model is updated.

[0041] Step 5: For the new track that fails to be associated with the existing track in step 4, the basic information of the lane is obtained from the lane model according to the lane number where the new track is located, and the rationality judgment problem of the new track is converted into the problem of multiple tracks competing for the lane. Mainly includes the following several cases: For example, case 1 in Figure 11 , the new track appears in the cell range occupied by the existing track, which means that multiple tracks compete for the same space. The confidence of the existing track and the new track is compared to filter out the track with low confidence; For example, case 2 in Figure 11 , if there is track information in the lane, the new track appears after the last track or there is no track information in the lane, and if the current position of the track is taken as the upper left point and the radar position is taken as the lower right point to draw a rectangle, if there is no other target in the area of the rectangle, it means that there is no occlusion, and the track is directly filtered out. Otherwise, it means that there may be a side occlusion. If the new track is interrupted before the confidence meets the set threshold, it is considered that the new track is caused by interference and is directly filtered out, otherwise the track is retained; For example, case 3 in Figure 11 ​Case 3 in Fig. 2, whether there is track information in the lane or not, the starting point of the new track is before the starting position set in step 1, without any competition shelter, when the confidence of the new track is greater than the set threshold, the track is reserved; As Figure 11 Case 4 in Fig. 2, there is track information in the lane, the new track appears before the current position of the existing track, when the target height of the first existing track behind the new track is less than the set threshold, it means that the target cannot shelter a target until the sheltered target escapes from the shelter area and is detected by the radar, so the appearance of the new track is not logical, and the track is directly filtered out in this embodiment; otherwise, it means that the new track may be caused by being sheltered, and if the new track is interrupted before the confidence meets the set threshold, it is considered that the new track is caused by interference and is directly filtered out, and if the set threshold is met, it is considered that the track is a real target and is reserved; As Figure 12 Case 5 in Fig. 2, there is track information in the lane, the starting point of the new track is before the termination position set in step 1, and the direction is reverse, because there is no sheltering situation for the reverse moving target at this time, so the track appears unreasonable, and the track is considered to be directly filtered out; As Figure 12 Case 6 in Fig. 2, there is track information in the lane, the starting point of the new track is after the termination position set in step 1, and the direction is reverse, at this time, the feasibility of the reverse moving vehicle is analyzed according to the average speed, average acceleration and lane occupation range of the track in the lane, for example, when the average speed in the lane information in the above step 2 tends to be less than a preset threshold, and there is a decrease in the lane acceleration that exceeds a preset threshold, and the lane occupation length is less than a preset threshold, it is considered that the reverse moving vehicle appears, otherwise, the reverse moving vehicle in the lane is not logical, and can be directly filtered out; As Figure 12 Case 7 in Fig. 2, there is no track information in the lane, the starting point of the new track is after the termination position set in step 1, and the direction is reverse, when the confidence of the new track is greater than the set threshold, the track is reserved, and it is considered that the reverse moving vehicle appears; As Figure 12 Case 8 in Fig. 2, there is no track information in the lane, the starting point of the new track is before the termination position set in step 1, and the direction is reverse, the current position of the track is taken as the upper left point and the radar position is taken as the lower right point to draw a rectangle, if there is no other target in the area of the rectangle, it means that there is no sheltering situation, and the track is directly filtered out. Otherwise, it means that there may be a side sheltering situation, if the new track is interrupted before the confidence meets the set threshold, it is considered that the new track is caused by interference and is directly filtered out, otherwise, the track is reserved.

[0042] The new appearing track is filtered through the logical relationship in the lane, and the track generated due to the multipath interference can be effectively removed.

[0043] Step 6: The track determined to be filtered in step 5 is destroyed, the track determined to be reserved is updated to the existing track, the track information in the lane model and the lane information are synchronously updated, and finally the track is output.

[0044] Therefore, the application provides a lane logic multipath interference suppression method based on a millimeter wave traffic radar, the condensed point track is associated with the currently managed track or the historical point track to form a new track, the lane model is updated or the track with unreasonable logic is filtered out based on the new track, and thus the multipath interference is suppressed, the influence of the environment is small, the advantages of high efficiency, high reliability and easy implementation are obtained, and the multipath interference can be effectively suppressed, and thus the target detection precision is improved.

[0045] According to another aspect of the application, a lane logic multipath interference suppression system 1300 based on a millimeter wave traffic radar is also provided, as shown in Figure 13 The system 1300 comprises: An acquisition module 1310 is configured to acquire point cloud data collected by the millimeter wave traffic radar. An agglomeration module 1320 is configured to cluster the point cloud data to obtain a point cloud clustering result, and agglomerate the point cloud clustering result to obtain a condensed point track. A creation module 1330 is configured to load a high-definition map file, extract map data, and create a lane model based on the map data. An association module 1340 is configured to associate the condensed point track with a currently managed track or a historical point track to form a new track. A suppression module 1350 is configured to update the lane model or filter out a track with unreasonable logic based on the new track to suppress multipath interference.

[0046] The lane logic multipath interference suppression system 1300 based on the millimeter wave traffic radar of the embodiment of the application corresponds to the lane logic multipath interference suppression method 100 based on the millimeter wave traffic radar of another embodiment of the application, and thus will not be described here.

[0047] Those skilled in the art will appreciate that embodiments of the application can be readily used as software, hardware, or a combination of software and hardware. In one embodiment, the application can be implemented in software and / or firmware. In addition, the software implementation can be implemented by one or more computer programs.

[0048] The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 one or more flowcharts and / or blocks Figure 1 means for functionally implementing the steps listed in the flowchart

[0049] These computer program instructions can also be stored in a computer- readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instructions which implement the function specified in the flowchart block or blocks. Figure 1 one or more flowcharts and / or blocks Figure 1 means for functionally implementing the steps listed in the flowchart

[0050] The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 one or more flowcharts and / or blocks Figure 1 means for functionally implementing the steps listed in the flowchart

[0051] While the preferred embodiments of the application have been described, additional variations and modifications can be employed. Therefore, the terms and expressions

[0052] Obviously, numerous modifications and variations of the present application are possible in light of the above teachings. It is therefore to be understood that within the scope of the appended claims and their equivalents, the application can be practiced otherwise than as specifically described.

Claims

1. A multipath interference suppression method based on lane logic of millimeter-wave traffic radar, characterized in that, include: Acquire point cloud data collected by millimeter-wave traffic radar; Cluster the point cloud data to obtain point cloud clustering results, then aggregate the point cloud clustering results to obtain aggregated point traces; Load a high-resolution map file, extract map data, and create a lane model based on the map data; The aggregated points are associated with the currently managed track or historical points to form a new track; Based on this, new trajectories can be used to update lane models or filter out logically illogical trajectories to suppress multipath interference.

2. The method according to claim 1, characterized in that, Also includes: Preprocessing operations such as filtering, noise reduction, and outlier extraction are performed on point cloud data.

3. The method according to claim 1, characterized in that, The point cloud data includes the target's position information in the X and Y directions, radial distance, radial velocity, and scattering power in the radar coordinate system.

4. The method according to claim 1, characterized in that, Loading a high-resolution map file, extracting map data, and creating a lane model based on the map data includes: Load a high-resolution map file, extract a section from the high-resolution map file, and obtain the point set from the high-resolution map file; The point sets in the high-resolution map file based on the WGS84 coordinate system are converted to the North-Sky-East coordinate system, and the points in the North-Sky-East coordinate system are converted to the radar coordinate system. The conversion formula is as follows: Right now in , , Here, E, N, and U are the local radar coordinates, E, N, and U are the northeast-sky coordinates, and L is the transformation matrix. The deflection angle and its value is equal to , This is the radar's local north-north angle; The point set data of each lane in the radar field of view is extracted based on the lane attributes in the high-definition map file, and the start position, end position and lane dividing line distance are read by reading the configuration file. Starting from the initial position, draw a dividing line at regular intervals until the end position. Combined with the lane lines on the map, divide the map in the radar field of view into several areas, label them, and create a spatial model of the lanes.

5. The method according to claim 1, characterized in that, The aggregated points are associated with currently managed tracks or historical points to form a new track, including: Determine whether the agglomerated point falls within the tracking gate. The tracking gate is the area centered on the latest state of the current managed track, with distance and speed as the dimensions. That is, the horizontal and vertical distances between the agglomerated point and the center point meet the set threshold values, and the interpolation of the speed and the center point meets the set threshold values. If the agglomerated point falls into the tracking gate, the agglomerated point is associated with the track. If the association is successful, a new track is formed. Otherwise, the agglomerated point is associated with the historical point to form a new track. If the trace does not fall within the tracking gate, the process returns to the next trace for evaluation.

6. The method according to claim 1, characterized in that, Based on the aforementioned methods, updating the lane model or filtering out logically illogical tracks to suppress multipath interference includes: If the new track is successfully associated with the old track, then update the track information and the lane model. If the new track fails to associate with the old track, multipath interference is suppressed by filtering out logically illogical tracks.

7. The method according to claim 6, characterized in that, Also includes: Filter out logically illogical tracks, update the existing tracks with the retained tracks, update the track information and lane information in the lane model, and output the track.

8. A multipath interference suppression system based on lane logic of millimeter-wave traffic radar, characterized in that, include: The acquisition module is used to acquire point cloud data collected by millimeter-wave traffic radar; The aggregation module is used to cluster the point cloud data to obtain point cloud clustering results, and aggregate the point cloud clustering results to obtain aggregated point traces. A module is created to load high-definition map files, extract map data, and create lane models based on the map data. The association module is used to associate the aggregated points with currently managed tracks or historical points to form a new track; The suppression module is used to suppress multipath interference by updating the lane model or filtering out logically illogical tracks based on the new track.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the steps of the method as described in any one of claims 1-7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the steps of the method as described in any one of claims 1-7.

Images