Radar-based target fusion method, device, terminal and storage medium
By establishing a coordinate system at the holographic intersection, determining the driving direction, and selecting high-precision radar data for fusion, the problem of poor radar target fusion at the holographic intersection was solved, achieving higher monitoring accuracy and reducing target fragmentation.
Patent Information
- Application Number
- CN202310072131.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2023-01-31
- Publication Date
- 2025-12-02
- Estimated Expiration
- 2043-01-31
AI Technical Summary
Holographic intersection radar suffers from poor target fusion when monitoring vehicles at intersections, especially when dealing with turning targets at intersections, resulting in large errors and frequent target splitting, which affects the fusion effect of millimeter-wave radar.
By acquiring radar data from the target intersection, an intersection coordinate system is established to determine the target's driving direction. Based on the driving direction, the optimal radar data is selected for fusion, and a fusion area is set to reduce the amount of computation. High-precision radar data is prioritized for fusion.
It improves the accuracy of target fusion, avoids target fragmentation, and enhances the radar's monitoring effect at intersections.
Smart Images

Figure CN116363870B_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of radar technology, and in particular to a radar-based target fusion method, device, terminal, and storage medium. Background Technology
[0002] The holographic intersection integrates various sensing devices such as intersection radar and electronic police / checkpoint cameras to conduct real-time sensing and monitoring of vehicle and pedestrian flow information at the intersection.
[0003] Currently, holographic intersection monitoring primarily utilizes radar technology. However, the fusion effect of existing holographic intersection radars on the market is poor, with a still relatively large monitoring error range. This is especially true for turning targets at intersections, where the fusion error range is even larger, frequently resulting in target fragmentation, which directly leads to a significant reduction in the fusion effect of millimeter-wave radar. Summary of the Invention
[0004] In view of this, the present invention provides a radar-based target fusion method, device, terminal and storage medium, which can solve the problem of poor target fusion effect at intersections in the prior art.
[0005] In a first aspect, embodiments of the present invention provide a radar-based target fusion method, comprising:
[0006] Acquire radar data from at least one intersection radar corresponding to the target intersection, which monitors the specified target; the radar data includes position coordinates and velocity.
[0007] The travel direction of the specified target at the target intersection is determined based on the position coordinates or velocity of the specified target after fusion in the previous cycle.
[0008] Based on the driving direction of the designated target at the target intersection, a radar data point is selected from the radar data of the designated target obtained from radar monitoring at each intersection in the current period as the fused radar data of the designated target in the current period.
[0009] Secondly, embodiments of the present invention provide a radar-based target fusion device, comprising:
[0010] The radar data acquisition module is used to acquire radar data obtained by at least one intersection radar corresponding to the target intersection from monitoring the specified target; the radar data includes position coordinates and speed.
[0011] The driving direction determination module is used to determine the driving direction of the specified target at the target intersection based on the position coordinates or speed of the specified target after fusion in the previous cycle.
[0012] The data fusion module is used to select one radar data point from the radar data of the specified target obtained from radar monitoring at each intersection in the current period, based on the driving direction of the specified target at the target intersection, as the fused radar data of the specified target in the current period.
[0013] Thirdly, embodiments of the present invention provide a terminal, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the method as described in any possible implementation of the first aspect above.
[0014] Fourthly, embodiments of the present invention provide a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the method as described in any possible implementation of the first aspect above.
[0015] The beneficial effects of the embodiments of the present invention compared with the prior art are as follows:
[0016] This embodiment of the invention first acquires radar data from at least one intersection radar monitoring a designated target at the target intersection; the radar data includes position coordinates and speed; then, based on the position coordinates or speed of the designated target after fusion in the previous cycle, the travel direction of the designated target at the target intersection is determined; finally, according to the travel direction of the designated target at the target intersection, one radar data point is selected from the radar data of the designated target monitored by each intersection radar in the current cycle as the fused radar data of the designated target in the current cycle. Through the above method, this embodiment can avoid the problem of target splitting when fusing multiple radar targets at an intersection, thereby improving the target fusion effect. Attached Figure Description
[0017] To more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0018] Figure 1 This is an application scenario diagram of the radar-based target fusion method provided in the embodiments of the present invention;
[0019] Figure 2 This is a flowchart illustrating the implementation of the radar-based target fusion method provided in this embodiment of the invention.
[0020] Figure 3 This is another application scenario diagram of the radar-based target fusion method provided in the embodiments of the present invention;
[0021] Figure 4 This is another application scenario diagram of the radar-based target fusion method provided in the embodiments of the present invention;
[0022] Figure 5 This is a schematic diagram of the radar-based target fusion device provided in an embodiment of the present invention;
[0023] Figure 6 This is a schematic diagram of the terminal provided in an embodiment of the present invention. Detailed Implementation
[0024] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of the invention. However, those skilled in the art will understand that the invention can be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods are omitted so as not to obscure the description of the invention with unnecessary detail.
[0025] To make the objectives, technical solutions, and advantages of the present invention clearer, specific embodiments will be described below in conjunction with the accompanying drawings.
[0026] Figure 1 This diagram illustrates an application scenario of the radar-based target fusion method provided in this embodiment of the invention. Figure 1 Taking a central intersection as an example, Figure 1 The black dots (R1 to R4) represent intersection radars, and the intersection includes four intersection radars.
[0027] See Figure 2 The diagram illustrates the implementation flowchart of the radar-based target fusion method provided in this embodiment of the invention, which is described in detail below:
[0028] S101: Obtain radar data from at least one intersection radar corresponding to the target intersection, which monitors the specified target; the radar data includes position coordinates and speed.
[0029] The execution subject of this embodiment can be a terminal or a server. The following explanation uses a terminal as an example to illustrate the method provided in this embodiment.
[0030] In one possible implementation, the location coordinates are location coordinates in the intersection coordinate system; prior to S101, the method provided in this embodiment further includes:
[0031] The intersection coordinate system is established by using the line connecting the intersection radar with the largest first metric value and the intersection radar with the smallest first metric value among the multiple intersection radars of the target intersection as the vertical axis and the perpendicular bisector of the line as the horizontal axis. The first metric value is either longitude or latitude.
[0032] Specifically, such as Figure 1 As shown, latitude is used as the first metric. Connecting the radar R1 with the highest latitude and the radar R3 with the lowest latitude, we obtain the vertical axis of the coordinate system. The perpendicular bisector of the line segment between R1 and R3 is used as the horizontal axis to establish the intersection coordinate system xoy.
[0033] After establishing the intersection coordinate system, the radar data of the targets detected by the radar at each intersection are converted from the radar coordinate system to the intersection coordinate system.
[0034] In one possible implementation, prior to S101, the method provided in this embodiment further includes:
[0035] Based on the positions of all intersection radars at the target intersection, create the minimum bounding rectangle of all intersection radars;
[0036] The minimum bounding rectangle is reduced inward by a first length, and the area within the reduced minimum bounding rectangle is used as the fusion area of the target intersection.
[0037] Specifically, since a designated target is only detected by multiple intersection radars when it is close to an intersection, when the designated target is far from the intersection, it is usually only detected by the intersection radar of the road opposite the designated target. Therefore, this embodiment can set a fusion region. When the designated target is within the fusion region, the radar data of the designated target is fused. When the designated target is not within the fusion region, the radar data obtained from the oncoming radar of the designated target is directly used as the fused radar data, thereby reducing the amount of computation and improving the target fusion efficiency.
[0038] Specifically, the location of the intersection radar is defined as its position coordinates. The terminal acquires the position coordinates of all intersection radars at the target intersection in the intersection coordinate system, and then creates the minimum bounding rectangle of all intersection radars at the target intersection, such as... Figure 1 As shown, Figure 1 In the diagram, W represents the minimum bounding rectangle of the intersection radars R1, R2, R3, and R4 at the target intersection. Reducing the minimum bounding rectangle inward by a first length yields the following result: Figure 1 The blending area is shown in the shaded region. The first length can be any value between 5 meters and 15 meters, preferably 10 meters.
[0039] S102: Determine the driving direction of the specified target at the target intersection based on the position coordinates or speed of the specified target after fusion in the previous cycle.
[0040] In one possible implementation, the speed includes lateral speed and longitudinal speed; the specific implementation process for determining the travel direction of the specified target at the target intersection based on the speed of the specified target after fusion in the previous cycle includes:
[0041] If the designated target is located within the fusion area, the driving direction of the designated target at the target intersection is determined based on the lateral and longitudinal velocities of the designated target after fusion in the previous cycle.
[0042] If the designated target is not located within the fusion area, then the travel direction of the designated target at the target intersection is determined to be straight.
[0043] Specifically, within the fusion area, when a designated target is traveling longitudinally, if its lateral speed is greater than a certain value, it indicates that the designated target is turning. The direction of travel can be determined by the sign of the lateral speed, whether it is a left turn or a right turn. Otherwise, the direction of travel of the designated target is straight or a U-turn. When a vehicle is traveling laterally, if its longitudinal speed is greater than a certain value, it indicates that the designated target is turning. The direction of travel can be determined by the sign of the longitudinal speed, whether it is a left turn or a right turn. Otherwise, the direction of travel of the designated target is straight or a U-turn.
[0044] In one possible implementation, the position coordinates include x-coordinates and y-coordinates; the specific implementation process for determining the driving direction of the specified target at the target intersection based on the position coordinates of the specified target after fusion in the previous cycle includes:
[0045] The position coordinates of the specified target within the effective section of the first road are used as reference position coordinates; based on the reference position coordinates and the slope of the first road, a straight-line model of the specified target is calculated; the first road is the road where the specified target is located; the straight-line model is used to represent the relationship between the x-coordinate and y-coordinate of the specified target when it travels in a straight line;
[0046] Predict the y coordinate of the specified target in the previous period based on the linear model.
[0047] The driving direction of the specified target is determined based on the predicted and actual values of the y-coordinate under the x-coordinate of the specified target in the previous period.
[0048] In this embodiment, in order to improve the accuracy of the driving direction calculation and avoid the problem of poor accuracy in the target driving direction calculation when encountering an intersection at an angle, this embodiment can create a straight linear model of the specified target in real time. The straight linear model predicts the y coordinates of the specified target under each x coordinate when it is driving straight at the target intersection. Based on the deviation between the predicted y coordinates and the actual y coordinates, the driving direction of the specified target is determined.
[0049] Specifically, the slope of the first road can be determined by the following steps:
[0050] The slope of the first road is calculated based on the position coordinates of at least one target within the effective section of the first road.
[0051] In one possible implementation, before calculating the slope of the first road based on the position coordinates of at least one target within an effective section of the first road, the method further includes:
[0052] Obtain the distance between the intersection radar of the first road and the origin of the intersection coordinate system;
[0053] The section of the first road that is at a distance (d, d+m) from the origin of the intersection coordinate system is taken as the effective section of the first road; where d represents the distance between the intersection radar of the first road and the origin of the intersection coordinate system, and m represents a first fixed value.
[0054] In this embodiment, as Figure 3 As shown, taking road A as the first road, the distance d between the intersection radar R3 on the first road A and the origin of the intersection coordinate system is determined in the direction of the first road. The boundary line on the first road at a distance d from the origin is used as one boundary line of the effective section, and the boundary line at a distance d+m from the origin is used as another boundary line of the effective section. The effective section 10 of the first road is determined. This effective section 10 is close to the target intersection and must also ensure that the effective section is a straight line segment. Therefore, the length of this effective section should not be too long.
[0055] The value of d can be determined based on the distance between the center of the intersection and the intersection radar in the actual scenario. For example, d can be 50 meters, and m can be any value in the range of 50 meters to 100 meters.
[0056] In this embodiment, the terminal can take at least two position coordinates of the target when it passes through the effective section and fit a linear formula to obtain the slope of the first road. Then, the slopes of the first road corresponding to multiple targets are averaged to obtain the slope of the first road.
[0057] In one possible implementation, calculating the slope of the first road based on the position coordinates of at least one target within the effective section of the first road includes:
[0058] Step 1: Initialize the number of iterations;
[0059] Step 2: Obtain the coordinates of at least two positions of the current target within the effective segment;
[0060] Step 3: Based on the current target's coordinates at least two locations within the effective segment, calculate the slope of a single track for the current iteration number;
[0061] Step 4: Input the current iteration number and the slope of the single track under the current iteration number into the slope calculation formula, calculate the slope of the first road corresponding to the current iteration number, increment the current iteration number by 1, return to step 2 to continue execution, until the current iteration number reaches the maximum iteration number;
[0062] The slope calculation formula is as follows:
[0063]
[0064] Where, k_x i Let k_x' represent the slope of the first road in the i-th iteration. i Let k_x represent the slope of a single track in the i-th iteration. i-1 Let w represent the slope of the first path in the (i-1)th iteration, and w represent the weight coefficient, where 0 < w < w. <w<1。
[0065] Specifically, if the current iteration count is less than the maximum iteration count, the slope of the first road is updated using the above steps each time the driving direction of the target is calculated. The straight linear model of the specified target is then calculated based on the updated slope of the first road, thereby improving the calculation accuracy of the straight linear model. If the current iteration count reaches the maximum iteration count, the accuracy of the slope of the first road is already high. When determining the driving direction of the specified target in subsequent iterations, the slope of the first road corresponding to the maximum iteration count is directly used to calculate the straight linear model of the specified target, thereby reducing the computational load of the algorithm.
[0066] In this embodiment, the specific implementation process of steps 2 to 3 above may include:
[0067] Obtain the first position coordinates of the target when it enters the effective segment and the first position coordinates when it leaves the effective segment; based on the first position coordinates of the target when it enters the effective segment and the first position coordinates when it leaves the effective segment, calculate the slope of a single track at the current iteration number to improve the accuracy of the slope of a single track.
[0068] Using the above method to calculate the slope of the first road can improve the accuracy of the slope of the first road.
[0069] In this embodiment, the position coordinates of the specified target on the first road at a first distance from the origin of the intersection coordinate system are taken as reference position coordinates. Based on the reference position coordinates and the slope of the first road, a straight linear model of the fused target is calculated. The first distance can be 0 to d. Preferably, the first distance can be d, that is, the position coordinates of the specified target when it leaves the effective section are taken as the reference position coordinates.
[0070] In one possible implementation, the reference position coordinates include a reference x-coordinate and a reference y-coordinate;
[0071] The linear model is: y_predict=k_x*x_real_time+y'-k_x*x';
[0072] Where y' represents the reference y coordinate, x' represents the reference x coordinate; k_x represents the slope of the first road, x_real_time represents the x coordinate of the specified target in the previous period, and y_predict represents the predicted value of the y coordinate of the specified target under the x coordinate of the previous period.
[0073] In one possible implementation, the radar data also includes Doppler values; the specific implementation process for determining the driving direction of the designated target based on the predicted and actual values of the y-coordinate under the x-coordinate of the previous cycle includes:
[0074] Calculate the absolute value of the difference between the predicted value and the actual value of the y-coordinate of the specified target in the previous period under the x-coordinate.
[0075] If the absolute value of the difference is less than or equal to the first preset value, then the driving direction of the specified target is determined to be straight.
[0076] If the absolute value of the difference is greater than the first preset value, and the actual value of the position coordinate of the specified target in the x-coordinate of the previous cycle is to the right of the predicted value, then the driving direction of the specified target is determined to be a right turn.
[0077] If the absolute value of the difference is greater than the first preset value, and the actual value of the position coordinate of the specified target in the x-coordinate of the previous cycle is to the left of the predicted value, then the driving direction of the specified target is determined to be a left turn.
[0078] If the difference between the Doppler value of the specified target in the x-coordinate of the previous cycle and the Doppler value in the reference position coordinate is less than a second preset value, and the Doppler value of the specified target in the x-coordinate of the previous cycle and the Doppler value in the reference position coordinate have opposite signs, then the driving direction of the specified target is determined to be a U-turn.
[0079] S103: Based on the driving direction of the designated target at the target intersection, select one radar data from the radar data of the designated target obtained from the radar monitoring of each intersection in the current period as the fused radar data of the designated target in the current period.
[0080] In this embodiment, when setting the fusion region, the specific implementation process of S103 above includes:
[0081] Determine whether the specified target is located within the fusion area based on the position coordinates of the specified target after the fusion in the previous cycle;
[0082] If the designated target is located within the fusion area, then according to the driving direction of the designated target at the target intersection, one radar data point is selected from the radar data of the designated target obtained from the radar monitoring of each intersection in the current period as the radar data of the designated target after fusion in the current period;
[0083] If the designated target is not located within the fusion area, then the radar data of the designated target obtained from the oncoming intersection radar monitoring in the current period is selected as the fused radar data of the designated target in the current period.
[0084] In one possible implementation, the specific implementation process of S103 further includes:
[0085] The intersection radar located in front of the designated target is designated as the front intersection radar, the intersection radar located behind the designated target is designated as the rear intersection radar, the intersection radar located to the left of the designated target is designated as the left intersection radar, and the intersection radar located to the right of the designated target is designated as the right intersection radar.
[0086] If the designated target is traveling straight at the target intersection, then the intersection radar that detected the designated target's radar data in the current cycle will be selected as the candidate intersection radar. From the candidate intersection radars, the radar data of the designated target detected by the foremost intersection radar in the current cycle will be selected as the fused radar data of the designated target in the current cycle according to a first selection order. The first selection order is: forward intersection radar, rear intersection radar, left intersection radar, and right intersection radar.
[0087] If the designated target's direction of travel at the target intersection is left turn, then the intersection radar that detects the designated target's radar data in the current cycle will be selected as the candidate intersection radar. From the candidate intersection radars, the radar data of the designated target detected by the foremost intersection radar in the current cycle will be selected as the fused radar data of the designated target in the current cycle according to the second selection order. The second selection order is: right intersection radar, left intersection radar, forward intersection radar, and rear intersection radar.
[0088] If the designated target's direction of travel at the target intersection is to turn right, then the intersection radar that detects the designated target's radar data in the current cycle will be selected as the candidate intersection radar. From the candidate intersection radars, the radar data of the designated target detected by the foremost intersection radar in the current cycle will be selected as the fused radar data of the designated target in the current cycle according to a third selection order. The third selection order is: left intersection radar, right intersection radar, forward intersection radar, and rear intersection radar.
[0089] If the designated target is making a U-turn at the target intersection, the intersection radar that detects the radar data of the designated target in the current cycle will be used as the candidate intersection radar. The radar data of the designated target in the current cycle detected by the foremost intersection radar from the candidate intersection radars will be selected as the fused radar data of the designated target in the current cycle according to the fourth selection order. The fourth selection order is: forward intersection radar, rear intersection radar, right intersection radar, and left intersection radar.
[0090] Specifically, when the vehicle is a designated target, the direction of the vehicle's front is considered the front of the designated target, and the direction of the vehicle's rear is considered the rear of the designated target. This reference is used to determine the front, rear, left, and right sides of the designated target. Based on the position coordinates of the designated target and the position coordinates of the radars at each intersection, the direction of each intersection radar relative to the designated target is determined. For example... Figure 4 As shown, if the designated target is Card1, then the radar at the intersection in front of it is R1, the radar at the intersection behind it is R3, the radar at the intersection to its left is R4, and the radar at the intersection to its right is R3.
[0091] Specifically, radar has higher detection accuracy for targets traveling in the radial direction than for targets traveling in other directions. Based on this characteristic, this embodiment sorts the intersection radars according to their detection accuracy for the specified target from highest to lowest. Preferably, the radar data monitored by the intersection radar with the highest detection accuracy for the specified target is selected as the fused radar data for the specified target. For example, if the specified target is traveling straight at the intersection, the intersection radars in the radial direction of the specified target are the forward intersection radar and the rear intersection radar. In this case, if the forward intersection radar can detect the specified target, the radar data monitored by the forward intersection radar is selected as the fused radar data for the specified target. If the forward intersection radar cannot detect the specified target, the radar data monitored by the rear intersection radar is selected as the fused radar data for the specified target, and so on, until radar data monitored by a single intersection radar is obtained as the fused radar data for the specified target. This not only improves the accuracy of the fused target data but also avoids target fragmentation, thus improving the target fusion effect.
[0092] In this embodiment, after obtaining the fused radar data of the specified target in the current period using the above method, the position, velocity, and acceleration of the specified target are updated using the fused radar data.
[0093] As can be seen from the above embodiments, this embodiment selects radar data collected by intersection radar with high accuracy in monitoring the specified target within the fusion area as the radar data of the specified target, which can avoid target splitting while ensuring the accuracy of radar detection and improve the target fusion effect.
[0094] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.
[0095] The following are device embodiments of the present invention. For details not described in detail, please refer to the corresponding method embodiments described above.
[0096] Figure 5 A schematic diagram of a radar-based target fusion device provided in an embodiment of the present invention is shown. For ease of explanation, only the parts related to the embodiment of the present invention are shown, and are described in detail below:
[0097] like Figure 5 As shown, the radar-based target fusion device 100 includes:
[0098] The radar data acquisition module 110 is used to acquire radar data obtained by at least one intersection radar corresponding to the target intersection from monitoring the specified target; the radar data includes position coordinates and speed.
[0099] The driving direction determination module 120 is used to determine the driving direction of the specified target at the target intersection based on the position coordinates or speed of the specified target after fusion in the previous cycle.
[0100] The data fusion module 130 is used to select one radar data from the radar data of the specified target obtained from the radar monitoring of each intersection in the current period according to the driving direction of the specified target at the target intersection, as the fused radar data of the specified target in the current period.
[0101] In one possible implementation, the radar-based target fusion device 100 further includes: a fusion region determination module, used for:
[0102] Based on the positions of all intersection radars at the target intersection, create the minimum bounding rectangle of all intersection radars;
[0103] The minimum bounding rectangle is reduced inward by a first length, and the area within the reduced minimum bounding rectangle is used as the fusion area of the target intersection.
[0104] Accordingly, the data fusion module 130 includes:
[0105] Determine whether the specified target is located within the fusion area based on the position coordinates of the specified target after the fusion in the previous cycle;
[0106] If the designated target is located within the fusion area, then according to the driving direction of the designated target at the target intersection, one radar data point is selected from the radar data of the designated target obtained from the radar monitoring of each intersection in the current period as the radar data of the designated target after fusion in the current period.
[0107] In one possible implementation, the speed includes lateral speed and longitudinal speed; the driving direction determination module 120 includes:
[0108] If the designated target is located within the fusion area, the driving direction of the designated target at the target intersection is determined based on the lateral and longitudinal velocities of the designated target after fusion in the previous cycle.
[0109] If the designated target is not located within the fusion area, then the travel direction of the designated target at the target intersection is determined to be straight.
[0110] In one possible implementation, the position coordinates include x-coordinates and y-coordinates; the driving direction determination module 120 includes:
[0111] The position coordinates of the specified target within the effective section of the first road are used as reference position coordinates; based on the reference position coordinates and the slope of the first road, a straight-line model of the specified target is calculated; the first road is the road where the specified target is located; the straight-line model is used to represent the relationship between the x-coordinate and y-coordinate of the specified target when it travels in a straight line;
[0112] Predict the y coordinate of the specified target in the previous period based on the linear model.
[0113] The driving direction of the specified target is determined based on the predicted and actual values of the y-coordinate under the x-coordinate of the specified target in the previous period.
[0114] In one possible implementation, the data fusion module 130 includes:
[0115] The intersection radar located in front of the designated target is designated as the front intersection radar, the intersection radar located behind the designated target is designated as the rear intersection radar, the intersection radar located to the left of the designated target is designated as the left intersection radar, and the intersection radar located to the right of the designated target is designated as the right intersection radar.
[0116] If the designated target is traveling straight at the target intersection, then the intersection radar that detected the designated target's radar data in the current cycle will be selected as the candidate intersection radar. From the candidate intersection radars, the radar data of the designated target detected by the foremost intersection radar in the current cycle will be selected as the fused radar data of the designated target in the current cycle according to a first selection order. The first selection order is: forward intersection radar, rear intersection radar, left intersection radar, and right intersection radar.
[0117] If the designated target's direction of travel at the target intersection is left turn, then the intersection radar that detects the designated target's radar data in the current cycle will be selected as the candidate intersection radar. From the candidate intersection radars, the radar data of the designated target detected by the foremost intersection radar in the current cycle will be selected as the fused radar data of the designated target in the current cycle according to the second selection order. The second selection order is: right intersection radar, left intersection radar, forward intersection radar, and rear intersection radar.
[0118] If the designated target's direction of travel at the target intersection is to turn right, then the intersection radar that detects the designated target's radar data in the current cycle will be selected as the candidate intersection radar. From the candidate intersection radars, the radar data of the designated target detected by the foremost intersection radar in the current cycle will be selected as the fused radar data of the designated target in the current cycle according to a third selection order. The third selection order is: left intersection radar, right intersection radar, forward intersection radar, and rear intersection radar.
[0119] If the designated target is making a U-turn at the target intersection, the intersection radar that detects the radar data of the designated target in the current cycle will be used as the candidate intersection radar. The radar data of the designated target in the current cycle detected by the foremost intersection radar from the candidate intersection radars will be selected as the fused radar data of the designated target in the current cycle according to the fourth selection order. The fourth selection order is: forward intersection radar, rear intersection radar, right intersection radar, and left intersection radar.
[0120] In one possible implementation, the position coordinates are position coordinates in an intersection coordinate system; the radar-based target fusion device 100 further includes:
[0121] The intersection coordinate system establishment module is used to establish the intersection coordinate system with the line connecting the intersection radar with the largest first metric value and the intersection radar with the smallest first metric value among multiple intersection radars of the target intersection as the vertical axis and the perpendicular bisector of the connecting line as the horizontal axis. The first metric value is either longitude or latitude.
[0122] In one possible implementation, the radar-based target fusion device 100 further includes:
[0123] The second fusion module is used to select the radar data of the specified target obtained by the oncoming intersection radar monitoring of the specified target in the current period as the fused radar data of the specified target in the current period if the specified target is not located in the fusion area.
[0124] The radar-based target fusion device provided in this embodiment can be used to execute the radar-based target fusion method embodiment described above. Its implementation principle and technical effect are similar, and will not be described again here.
[0125] Figure 6 This is a schematic diagram of a terminal provided in an embodiment of the present invention. For example... Figure 6 As shown, the terminal 6 in this embodiment includes: a processor 60, a memory 61, and a computer program 62 stored in the memory 61 and executable on the processor 60. When the processor 60 executes the computer program 62, it implements the steps in the various radar-based target fusion method embodiments described above, for example... Figure 2 Steps 101 to 103 are shown. Alternatively, when the processor 60 executes the computer program 62, it implements the functions of each module / unit in the above-described device embodiments, for example... Figure 5 The functions of modules 110 to 130 are shown.
[0126] For example, the computer program 62 can be divided into one or more modules / units, which are stored in the memory 61 and executed by the processor 60 to complete the present invention. The one or more modules / units can be a series of computer program instruction segments capable of performing a specific function, which describe the execution process of the computer program 62 in the terminal 6.
[0127] The terminal 6 can be a computing device such as a desktop computer, laptop, handheld computer, or cloud server. The terminal 6 may include, but is not limited to, a processor 60 and a memory 61. Those skilled in the art will understand that... Figure 6 This is merely an example of terminal 6 and does not constitute a limitation on terminal 6. It may include more or fewer components than shown, or combine certain components, or different components. For example, the terminal may also include input / output devices, network access devices, buses, etc.
[0128] The processor 60 may be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor.
[0129] The memory 61 can be an internal storage unit of the terminal 6, such as a hard disk or memory of the terminal 6. The memory 61 can also be an external storage device of the terminal 6, such as a plug-in hard disk, Smart Media Card (SMC), Secure Digital (SD) card, or Flash Card equipped on the terminal 6. Furthermore, the memory 61 can include both internal storage units and external storage devices of the terminal 6. The memory 61 is used to store the computer program and other programs and data required by the terminal. The memory 61 can also be used to temporarily store data that has been output or will be output.
[0130] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is merely an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. Furthermore, the specific names of the functional units and modules are only for easy differentiation and are not intended to limit the scope of protection of this application. The specific working process of the units and modules in the above system can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.
[0131] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.
[0132] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.
[0133] In the embodiments provided by this invention, it should be understood that the disclosed devices / terminals and methods can be implemented in other ways. For example, the device / terminal embodiments described above are merely illustrative. For instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.
[0134] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.
[0135] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.
[0136] If the integrated module / unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the above embodiments of the present invention can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various radar-based target fusion method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc. It should be noted that the content included in the computer-readable medium can be appropriately added or removed according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, the computer-readable medium does not include electrical carrier signals and telecommunication signals.
[0137] The above-described embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included within the protection scope of the present invention.
Claims
1. A radar-based target fusion method, characterized in that, include: Acquire radar data from at least one intersection radar corresponding to the target intersection, which monitors the specified target. The radar data includes position coordinates and velocity; The travel direction of the specified target at the target intersection is determined based on the position coordinates or velocity of the specified target after fusion in the previous cycle. Based on the driving direction of the designated target at the target intersection, a radar data point is selected from the radar data of the designated target obtained from the radar monitoring of each intersection in the current period as the fused radar data of the designated target in the current period; Before acquiring radar data obtained from at least one intersection radar corresponding to the target intersection monitoring the designated target, the method further includes: Based on the positions of all intersection radars at the target intersection, create the minimum bounding rectangle of all intersection radars; The minimum bounding rectangle is reduced inward by a first length, and the area within the reduced minimum bounding rectangle is used as the fusion area of the target intersection. Accordingly, the step of selecting a radar data point from the radar data of the designated target obtained from radar monitoring at each intersection according to the designated target's travel direction at the target intersection as the fused radar data of the designated target in the current period includes: Determine whether the specified target is located within the fusion area based on the position coordinates of the specified target after the fusion in the previous cycle; If the designated target is located within the fusion area, then according to the driving direction of the designated target at the target intersection, one radar data point is selected from the radar data of the designated target obtained from the radar monitoring of each intersection in the current period as the radar data of the designated target after fusion in the current period.
2. The radar-based target fusion method according to claim 1, characterized in that, The speed includes lateral speed and longitudinal speed; Determining the travel direction of the specified target at the target intersection based on the position coordinates or velocity of the specified target after fusion in the previous cycle includes: If the designated target is located within the fusion area, the driving direction of the designated target at the target intersection is determined based on the lateral and longitudinal velocities of the designated target after fusion in the previous cycle. If the designated target is not located within the fusion area, then the travel direction of the designated target at the target intersection is determined to be straight.
3. The radar-based target fusion method according to claim 1, characterized in that, The position coordinates include x-coordinates and y-coordinates; Determining the travel direction of the specified target at the target intersection based on the position coordinates or velocity of the specified target after fusion in the previous cycle includes: The position coordinates of the specified target within the effective section of the first road are used as reference position coordinates; based on the reference position coordinates and the slope of the first road, a straight-line model of the specified target is calculated; the first road is the road where the specified target is located; the straight-line model is used to represent the relationship between the x-coordinate and y-coordinate of the specified target when it travels in a straight line; Predict the y coordinate of the specified target in the previous period based on the linear model. The driving direction of the specified target is determined based on the predicted and actual values of the y-coordinate under the x-coordinate of the specified target in the previous period.
4. The radar-based target fusion method according to claim 1, characterized in that, The step of selecting a radar data point from the radar data of the designated target obtained from radar monitoring at each intersection according to the designated target's travel direction at the target intersection as the fused radar data of the designated target in the current period includes: The intersection radar located in front of the designated target is designated as the front intersection radar, the intersection radar located behind the designated target is designated as the rear intersection radar, the intersection radar located to the left of the designated target is designated as the left intersection radar, and the intersection radar located to the right of the designated target is designated as the right intersection radar. If the designated target is traveling straight at the target intersection, then the intersection radar that detected the designated target's radar data in the current cycle will be selected as the candidate intersection radar. From the candidate intersection radars, the radar data of the designated target detected by the foremost intersection radar in the current cycle will be selected as the fused radar data of the designated target in the current cycle according to a first selection order. The first selection order is: forward intersection radar, rear intersection radar, left intersection radar, and right intersection radar. If the designated target's direction of travel at the target intersection is left turn, then the intersection radar that detects the designated target's radar data in the current cycle will be selected as the candidate intersection radar. From the candidate intersection radars, the radar data of the designated target detected by the foremost intersection radar in the current cycle will be selected as the fused radar data of the designated target in the current cycle according to the second selection order. The second selection order is: right intersection radar, left intersection radar, forward intersection radar, and rear intersection radar. If the designated target's direction of travel at the target intersection is to turn right, then the intersection radar that detects the designated target's radar data in the current cycle will be selected as the candidate intersection radar. From the candidate intersection radars, the radar data of the designated target detected by the foremost intersection radar in the current cycle will be selected as the fused radar data of the designated target in the current cycle according to a third selection order. The third selection order is: left intersection radar, right intersection radar, forward intersection radar, and rear intersection radar. If the designated target is making a U-turn at the target intersection, the intersection radar that detects the radar data of the designated target in the current cycle will be used as the candidate intersection radar. The radar data of the designated target in the current cycle detected by the foremost intersection radar from the candidate intersection radars will be selected as the fused radar data of the designated target in the current cycle according to the fourth selection order. The fourth selection order is: forward intersection radar, rear intersection radar, right intersection radar, and left intersection radar.
5. The radar-based target fusion method according to any one of claims 1 to 4, characterized in that, The location coordinates are location coordinates in the intersection coordinate system; before acquiring the radar data obtained by the radars at each intersection corresponding to the target intersection from the monitoring of the specified target, the method further includes: The intersection coordinate system is established by using the line connecting the intersection radar with the largest first metric value and the intersection radar with the smallest first metric value among the multiple intersection radars of the target intersection as the vertical axis and the perpendicular bisector of the line as the horizontal axis. The first metric value is either longitude or latitude.
6. The radar-based target fusion method according to claim 1, characterized in that, The method further includes: If the designated target is not located within the fusion area, then the radar data of the designated target obtained from the oncoming intersection radar monitoring in the current period is selected as the fused radar data of the designated target in the current period.
7. A radar-based target fusion device, characterized in that, include: The fusion region determination module is used to determine the fusion region of the target intersection based on the location of at least one intersection radar corresponding to the target intersection; The radar data acquisition module is used to acquire radar data obtained by at least one intersection radar corresponding to the target intersection from monitoring the specified target; the radar data includes position coordinates and speed. The driving direction determination module is used to determine the driving direction of the specified target at the target intersection based on the position coordinates or speed of the specified target after fusion in the previous cycle. The data fusion module is used to select one radar data point from the radar data of the specified target obtained from the radar monitoring of each intersection in the current period according to the driving direction of the specified target at the target intersection, and use it as the fused radar data of the specified target in the current period. The radar-based target fusion device also includes a fusion region determination module, used for: Based on the positions of all intersection radars at the target intersection, create the minimum bounding rectangle of all intersection radars; The minimum bounding rectangle is reduced inward by a first length, and the area within the reduced minimum bounding rectangle is used as the fusion area of the target intersection. Accordingly, the data fusion module includes: Determine whether the specified target is located within the fusion area based on the position coordinates of the specified target after the fusion in the previous cycle; If the designated target is located within the fusion area, then according to the driving direction of the designated target at the target intersection, one radar data point is selected from the radar data of the designated target obtained from the radar monitoring of each intersection in the current period as the radar data of the designated target after fusion in the current period.
8. A terminal, characterized in that, It includes a processor and a memory, the memory being used to store a computer program, and the processor being used to call and run the computer program stored in the memory to perform the method as described in any one of claims 1 to 6.
9. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method as described in any one of claims 1 to 6 above.
Citation Information
Patent Citations
Sensor fusion based on intersection scene to determine vehicle collision potential
CN113257037A
Roadway sensing systems
WO2014160027A1