Calibration methods, devices, equipment and storage media for roadside radar

Abstract

This application relates to the field of intelligent transportation and proposes a calibration method, device, equipment, and storage medium for roadside radar. The method includes: acquiring first positioning information and speed information of a vehicle, and second positioning information of a connected vehicle; clustering the first positioning information to generate a vehicle trajectory; determining the vehicle trajectory matching the second positioning information based on the relative positional relationship of the vehicle trajectories and pre-determined lane information of the connected vehicle; aligning the second positioning information and third positioning information in the vehicle trajectory according to time, and performing coordinate transformation calculations on the aligned positioning information to determine the calibration information of the roadside radar. Because this application generates vehicle trajectories by clustering based on the first positioning information and speed information, it can effectively solve the noise and discontinuity problems of roadside radar, and it eliminates the need to close roads when calibrating roadside radar on public roads.

Description

Technical Field

[0001] This application relates to the field of intelligent transportation, and in particular to a calibration method, apparatus, device, and storage medium for roadside radar. Background Technology

[0002] With the development of intelligent transportation systems and the intelligent connected vehicle industry, roadside perception systems are playing an increasingly important role. By deploying sensors (including cameras, millimeter-wave radar, and lidar) along the roadside, roadside perception systems can perceive traffic information on the road in real time and transmit this information to vehicles traveling on the road, effectively compensating for blind spots in onboard perception and improving traffic safety.

[0003] When using roadside radar, especially millimeter-wave radar, to sense road traffic information, the millimeter-wave radar needs to be calibrated first. Based on the calibrated millimeter-wave radar and the positional relationship between the vehicle and the radar, the vehicle's position can be determined. However, when using the positioning information from vehicle sensors and the vehicle position information detected by the roadside radar to locate the roadside radar, the high noise level of the roadside radar and the potential discontinuity of the vehicle IDs detected by the roadside radar prevent accurate trajectory generation from the millimeter-wave radar detection data, thus hindering the improvement of the roadside millimeter-wave radar calibration accuracy.

[0004] To improve the calibration accuracy of millimeter-wave radar, traditional roadside millimeter-wave radar calibration methods primarily involve placing corner reflectors on the road to obtain the target's coordinates within the millimeter-wave radar, while simultaneously obtaining the target's geographic coordinates using a handheld GPS positioning device. The calibration relationship between the two is then calculated. This method requires road closures for calibration. This is because engineers placing reflectors or holding positioning devices face collision risks when calibrating on public roads. Closing public roads requires approval from traffic management authorities and disrupts normal traffic flow. Since most current roadside sensing system design projects are conducted on public roads, obtaining approval from traffic management authorities to close roads for roadside millimeter-wave radar calibration is difficult. Summary of the Invention

[0005] In view of this, embodiments of this application provide a calibration method, apparatus, device, and storage medium for roadside radar to solve the problem in the prior art that when using the positioning information of vehicle sensors and the vehicle position information detected by millimeter-wave radar to locate millimeter-wave radar, it is necessary to apply for road closure in order to improve the calibration accuracy, which affects normal traffic flow.

[0006] A first aspect of this application provides a calibration method for roadside radar, the method comprising:

[0007] Acquire the first positioning and speed information of the vehicle collected by the roadside radar, as well as the second positioning information and lane information of the connected vehicle collected by the on-board unit;

[0008] Based on the first positioning information and the speed information, the first positioning information is clustered to generate a vehicle trajectory;

[0009] Based on the relative positional relationship of the vehicle trajectories and combined with the lane information of the connected vehicle, the vehicle trajectory matching the second positioning information is determined.

[0010] The second positioning information and the third positioning information in the vehicle trajectory are aligned according to time, and the coordinate transformation of the aligned positioning information is calculated to determine the calibration information of the roadside radar.

[0011] In conjunction with the first aspect, in a first possible implementation of the first aspect, clustering the first positioning information based on the first positioning information and the speed information to generate a vehicle trajectory includes:

[0012] Calculate the distance between the positioning points in the first positioning information based on the first positioning information and the speed information;

[0013] Clustering is performed based on the distance between the location points, and vehicle trajectories are generated from the clustered location points.

[0014] In a second possible implementation of the first aspect, in conjunction with the first possible implementation of the first aspect, calculating the distance between the positioning points in the first positioning information based on the first positioning information and the speed information includes:

[0015] According to the formula Calculate the distance between the two positioning points in the first positioning information, where x1 and x2 are the x-coordinates of the two positioning points in the preset millimeter-wave radar coordinate system, in meters; y1 and y2 are the y-coordinates of the two positioning points in the millimeter-wave radar coordinate system, in meters; ts1 and ts2 are the timestamps of the two positioning points, in seconds; and v1 and v2 are the velocities of the two positioning points, in meters per second.

[0016] In conjunction with the first aspect, in a third possible implementation of the first aspect, the second positioning information and the third positioning information in the vehicle trajectory are aligned in time, including:

[0017] Determine the interpolation formula for the third positioning information;

[0018] The positioning information of the vehicle in the roadside radar coordinate system at the alignment time is determined according to the interpolation formula.

[0019] In conjunction with the first aspect, in the fourth possible implementation of the first aspect, the alignment of the positioning information coordinates is transformed and calculated to determine the calibration information of the roadside radar, including:

[0020] In the alignment positioning information, select a predetermined number of alignment data;

[0021] Substitute the alignment data into the preset coordinate system transformation equation to determine the transformation matrix that serves as calibration information.

[0022] In conjunction with the fourth possible implementation of the first aspect, in the fifth possible implementation of the first aspect, the alignment data includes positioning information based on the local ENU coordinate system and positioning information based on the roadside radar coordinate system; substituting the alignment data into a preset coordinate system transformation equation to determine the transformation matrix as calibration information includes: substituting the alignment data of the positioning information based on the local ENU coordinate system and the positioning information based on the roadside radar coordinate system into a preset local ENU coordinate system-roadside radar coordinate system transformation equation, and determining the transformation matrix between the local ENU coordinate system and the roadside radar coordinate system through the least squares method or a nonlinear optimization method;

[0023] Alternatively, the alignment data includes positioning information based on a geographic coordinate system and positioning information based on roadside radar; substituting the alignment data into a preset coordinate system transformation equation to determine the transformation matrix as calibration information includes: substituting the alignment data of the positioning information based on a geographic coordinate system and the positioning information based on a roadside radar coordinate system into a preset geographic coordinate system-roadside radar coordinate system transformation equation, and determining the transformation matrix between the geographic coordinate system and the roadside radar coordinate system using the least squares method.

[0024] In conjunction with the first aspect, in a sixth possible implementation of the first aspect, after determining the calibration information of the roadside radar, the method further includes:

[0025] Vehicle positioning information is obtained by using roadside radar and determining it based on the roadside radar coordinate system;

[0026] The vehicle's positioning information in the transformed coordinate system is generated in real time using the transformation matrix.

[0027] A second aspect of this application provides a calibration device for roadside radar, the device comprising:

[0028] The information acquisition unit is used to acquire the first positioning information and speed information of the vehicle collected by the roadside radar, and the second positioning information of the connected vehicle collected by the on-board unit.

[0029] A clustering unit is used to cluster the first positioning information based on the first positioning information and the speed information to generate a vehicle trajectory.

[0030] The trajectory matching unit is used to determine the vehicle trajectory matched by the second positioning information based on the relative positional relationship of the vehicle trajectory and in combination with the pre-determined lane information of the connected vehicle.

[0031] The calibration information determination unit is used to align the second positioning information and the third positioning information in the vehicle trajectory according to time, perform coordinate transformation calculation on the aligned positioning information, and determine the calibration information of the roadside radar.

[0032] A third aspect of this application provides a calibration device for roadside radar, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the computer program, implements the steps of the method as described in any of the first aspects.

[0033] A fourth aspect of this application provides 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 of the first aspects.

[0034] The beneficial effects of this application embodiment compared with the prior art are as follows: This application embodiment collects first positioning information and speed information from roadside radar, clusters the first positioning information to generate vehicle trajectory, aligns the generated vehicle trajectory with the second positioning information obtained by the vehicle unit in time, and calculates the calibration information of roadside radar based on the aligned positioning information. This can effectively solve the noise and discontinuity problems of roadside radar, which is conducive to improving the calibration accuracy of roadside radar. At the same time, the calibration of roadside radar can be completed without closing public roads, and the calibration process will not affect traffic. Attached Figure Description

[0035] To more clearly illustrate the technical solutions in the embodiments of this application, 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 this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0036] Figure 1 This is a schematic diagram illustrating an implementation scenario of a roadside radar calibration method provided in an embodiment of this application;

[0037] Figure 2 This is a schematic diagram illustrating the implementation process of a roadside radar calibration method provided in an embodiment of this application;

[0038] Figure 3 This is a schematic diagram of vehicle trajectory matching provided in an embodiment of this application;

[0039] Figure 4 This is a schematic diagram of roadside radar data interpolation provided in an embodiment of this application;

[0040] Figure 5 This is a schematic diagram of a calibration device for a roadside radar provided in an embodiment of this application;

[0041] Figure 6 This is a schematic diagram of the calibration device for roadside radar provided in the embodiments of this application. Detailed Implementation

[0042] 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 this application. However, those skilled in the art will understand that this application may also be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods have been omitted so as not to obscure the description of this application with unnecessary detail.

[0043] To illustrate the technical solution described in this application, specific embodiments are provided below.

[0044] Roadside radar, especially millimeter-wave radar, is a crucial sensor in roadside perception systems. These systems use roadside radar to obtain information such as the relative position, speed, and direction of road users (including vehicles, non-motorized vehicles, and pedestrians). Among these, the positional information of road users is one of the most important pieces of information.

[0045] The location information currently obtained by roadside radar is the relative position of the target with respect to the radar's installation location (i.e., the target's coordinates in the roadside radar coordinate system). In roadside sensing systems, the data used is the target's location information detected by the roadside radar in a geographic coordinate system (including systems such as WGS-84 or GCJ-02). Through roadside radar calibration, the target's coordinates in the roadside coordinate system can be mapped to latitude and longitude in the geographic coordinate system.

[0046] To address the calibration problem of roadside radars on public roads, this application proposes a calibration method for roadside radars based on V2X (Vehicle-to-Everything) communication. The implementation scenarios of this method are as follows: Figure 1As shown, it mainly includes roadside radar (such as millimeter-wave radar), connected vehicles (equipped with onboard units (OBUs)), roadside units (RSUs), edge computing units (ECUs), roadside switches, and other power supply and network auxiliary equipment.

[0047] On public roads, roadside radar can detect information about connected and non-connected vehicles within its sensing area. The information of all vehicles detected by the roadside radar (including the timestamp when the location information was detected, the target ID, the target's x and y coordinates in the roadside radar coordinate system, the target's speed information, etc.) can be transmitted to the roadside edge computing unit (ECU) via the network. The edge computing unit can then obtain the vehicle trajectories of vehicles traveling on the road.

[0048] Simultaneously, the roadside unit (RSU) communicates with connected vehicles traveling on the road via V2X communication (including LTE-V, NR-V2X, DSRC, etc.), thereby obtaining information about the connected vehicles (including timestamps, vehicle IDs, longitude, latitude, speed, heading angle, etc.) through the onboard unit. The RSU then transmits this information to the roadside edge computing unit via the network. By collecting and analyzing data at the roadside edge computing unit, the calibration of the roadside millimeter-wave radar can be achieved.

[0049] Figure 2 A schematic diagram illustrating the implementation process of a roadside radar calibration method provided in this application embodiment is described in detail below:

[0050] In S201, the first positioning information and speed information of the vehicle collected by the roadside radar, and the second positioning information of the connected vehicle collected by the on-board unit are acquired.

[0051] Specifically, when collecting data on public road sections, vehicles passing through the perception area of ​​the roadside radar include both connected and non-connected vehicles. Therefore, the vehicle information detected by the roadside radar includes first positioning information and speed information. This first positioning information includes the first positioning and speed information of connected vehicles, and may also include the first positioning and speed information of non-connected vehicles. The first positioning information, and subsequent second positioning information, includes the positioning coordinates and the timestamp corresponding to those coordinates. The edge computing unit (ECU) can obtain the vehicle's first positioning and speed information from the roadside radar. The first positioning information is the coordinate position based on the roadside radar coordinate system.

[0052] Connected vehicles traveling within the radar sensing area are equipped with onboard units that can collect the vehicle's second positioning information and speed information. The second positioning information is either a geographic coordinate system or a local ENU (east-north-up) coordinate system.

[0053] To improve calibration accuracy, the connected vehicle can be controlled to travel in the leftmost and rightmost lanes of the roadside radar's detection area, thereby obtaining the first positioning and speed information collected by two sets of roadside units. Furthermore, the lane information of the connected vehicle during travel can be determined based on pre-determined driving information or preset information.

[0054] In S202, the first positioning information is clustered based on the first positioning information and the speed information to generate a vehicle trajectory.

[0055] Due to limitations such as high noise levels and discontinuous vehicle IDs detected by roadside radars (e.g., millimeter-wave radars), the vehicle trajectories of connected vehicles in the roadside radar coordinate system cannot be reliably extracted directly from the target IDs detected by roadside radars. Furthermore, traditional K-means clustering methods or Euclidean distance-based clustering methods are not effective in extracting the trajectory data of individual vehicles.

[0056] To improve the accuracy of trajectory data extraction, this embodiment of the application introduces the speed information of positioning points when determining the vehicle trajectory. Based on the speed information of the positioning points and their coordinate positions in the roadside radar coordinate system, the distance between two positioning points is determined. That is, the distance between positioning points is determined based on the positional and speed differences between them. The positioning points are then clustered based on this distance, and the vehicle trajectory is obtained based on the clustered positioning points.

[0057] When calculating the distance between two positioning points based on their speed information and their coordinate positions in the roadside radar coordinate system, the following formula can be used:

[0058]

[0059] Where x1 and x2 are the x-coordinates of the two positioning points in the preset millimeter-wave radar coordinate system, in meters; y1 and y2 are the y-coordinates of the two positioning points in the millimeter-wave radar coordinate system, in meters; ts1 and ts2 are the timestamps of the two positioning points, in seconds; and v1 and v2 are the velocities of the two positioning points, in meters per second.

[0060] When calculating the distance between two positioning points, in addition to the coordinates of the positioning points, their velocities are also included. By comprehensively determining the distance between the two positioning points through positional differences and distance differences, the vehicle trajectory obtained by clustering based on positional differences and velocity differences in this embodiment of the application effectively improves the accuracy of the vehicle trajectory compared to clustering based on positional differences.

[0061] In S203, based on the relative positional relationship of the vehicle trajectories and combined with the pre-determined lane information of the connected vehicle, the vehicle trajectory matching the second positioning information is determined.

[0062] The lane information of the connected vehicle can be determined based on pre-determined control or setting information for the connected vehicle's movement. For example, lane information may include the connected vehicle's leftmost lane, leftmost second lane, and rightmost lane on the road. By clustering the first positioning points, the vehicle trajectories corresponding to the vehicles at those points can be obtained. Based on the relative positional relationships between the vehicle trajectories and the vehicle's lane position on the road, the correspondence between the connected vehicle and its trajectories is determined.

[0063] For example, in Figure 3 In the vehicle trajectory matching diagram shown, the connected vehicle is traveling in the rightmost lane of the roadside radar's sensing area. Since all vehicles are traveling away from the roadside radar, Figure 3 In the diagram, the positive Y-axis represents the left side of the roadside radar's sensing area, and the negative Y-axis represents the right side. Therefore, vehicle trajectory 6 corresponds to this connected vehicle (the connected vehicle traveling in the rightmost lane).

[0064] In S204, the second positioning information and the third positioning information in the vehicle trajectory are aligned according to time, and the coordinate transformation of the aligned positioning information is calculated to determine the calibration information of the roadside radar.

[0065] After obtaining the correspondence between connected vehicles and vehicle trajectories, since the period of target detection by roadside radar may be inconsistent with the period of data received by RSU from OBU, we need to synchronize and align the third positioning information of connected vehicles under the vehicle trajectory in the roadside radar coordinate system with the second positioning information of connected vehicles collected through V2X communication.

[0066] In this embodiment of the application, when the third positioning information of the roadside radar coordinate system of a connected vehicle is synchronized with the second positioning information in time using an interpolation method, the interpolation formula corresponding to the third positioning information can be determined first, and interpolation calculation can be performed based on the interpolation formula to obtain the positioning information of the vehicle in the roadside radar coordinate system at the alignment time.

[0067] like Figure 4 As shown, the data sampling period for V2X is 100ms, while that for roadside radar is 72ms; the sampling periods for the two types of data are different. At time m, the x-coordinate of the roadside radar is x... m It can be calculated using the following interpolation formula:

[0068]

[0069] Similarly, the y-coordinate of a connected vehicle in the roadside radar coordinate system at time m can be calculated using the following interpolation formula:

[0070]

[0071] Where, x m ,x k+1 ,x k This represents the x-coordinate of the connected vehicle in the millimeter-wave radar coordinate system at times m, k+1, and k, in meters; t in the formula m ,t k+1 ,t k This represents the timestamps corresponding to times m, k+1, and k, in milliseconds (ms).

[0072] After aligning the third positioning information in the roadside radar coordinate system with the second positioning information acquired by the RSU in time, the transformation matrix in the coordinate system transformation equation can be calculated based on the corresponding data sets and substituted into a pre-set coordinate system transformation equation. After calculating the transformation matrix of the coordinate system transformation equation, the first positioning information acquired by the roadside radar in the roadside radar coordinate system can be converted in real time into the required coordinate system, i.e., the target coordinate system.

[0073] The target coordinate system in this application embodiment may include a geographic coordinate system (or a geodetic coordinate system) or a local ENU coordinate system. The geographic coordinate system and the local ENU coordinate system can be converted to each other, specifically in two steps: 1. Converting the geographic coordinate system to an ECEF (Earth-Centered, Earth-Fixed) coordinate system; 2. Converting the ECEF coordinate system to the local ENU coordinate system.

[0074] The transformation from geographic coordinate system to ECEF coordinate system is shown in formula (4).

[0075]

[0076]

[0077] Where φ, λ, and h represent latitude, longitude, and altitude in the geographic coordinate system, respectively, in radians, meters, and latitude. a is the equatorial radius, and b is the polar radius. Here, represents the Earth's eccentricity. X, Y, and Z are the coordinate values ​​corresponding to the X, Y, and Z axes in the ECEF coordinate system, respectively, in meters. This application can disregard the influence of altitude, and h can be set to 0.

[0078] The transformation of ECEF coordinates to local ENU coordinates is shown in formula (5).

[0079]

[0080] In the formula, φ r λ r h r , representing the latitude, longitude, and altitude of the selected reference point, respectively; X r Y r Z r These are the reference points in the ECEF coordinate system, converted from the latitude, longitude, and altitude of the reference point using formula (4). enu ,y enu ,z enu These are the coordinate values ​​corresponding to the X, Y, and Z axes in the local ENU coordinate system, in meters.

[0081] When solving for the calibration parameters of roadside radar, different calibration parameters can be determined based on the target coordinate system. For example, the target coordinate system can be a geographic coordinate system or a local ENU coordinate system. A predetermined set of data can be extracted from the time-aligned second and third positioning information, for example, M sets of data (M≥4). Simultaneously, its corresponding M geographic coordinate system data can be obtained based on its timestamp. Based on the extracted data, calculate the transformation matrix between the roadside radar coordinate system and the local ENU coordinate system.

[0082] 1) The mapping between local ENU coordinates and millimeter-wave radar coordinates is set as follows:

[0083] m=H*p (6)

[0084] Where p = [xy 0] T Let m be the coordinates in the radar coordinate system, where m = [x] enu y enu 0] T These are the coordinates in the local ENU coordinate system. The H matrix is ​​shown below:

[0085]

[0086] The parameters of matrix H can be obtained by substituting the M sets of data from previously connected vehicles, totaling 2M data points. and The solution is obtained by the least squares method.

[0087] 2) When the target coordinate system is a geographic coordinate system, the mapping between the geographic coordinate system and the millimeter-wave radar coordinates can be set as follows:

[0088] q=H1*p (7)

[0089]

[0090] Where p = [xy] T These are the coordinates in the radar coordinate system, q = [λ φ]. T These are the latitude and longitude coordinates in the geographic coordinate system. The parameters of the H1 matrix can be obtained by substituting the previous M sets of data from connected vehicles, totaling 2M data pairs. and The solution is obtained by the least squares method.

[0091] 3) The mapping between local ENU coordinates and millimeter-wave radar coordinates is set as follows:

[0092] m=[R|t]p (8)

[0093] Where p = [xy 0 1] T Let m be the coordinates in the radar coordinate system, where m = [x] enu y enu 0] T These are the coordinates in the local ENU coordinate system. The specific representation of the matrix [R|t] is shown below.

[0094] R = R z R y R x (9)

[0095]

[0096]

[0097]

[0098] t = [t x t y t z ] T

[0099] The corresponding parameter matrix w = [θ x θ y θ z t x ty t z ] T We can utilize the M sets of data from previous connected vehicles, totaling 2M data pairs, and substitute them in ( and The solution is obtained through nonlinear optimization methods.

[0100] Understandably, the calibration calculation process for roadside radar described above can be completed offline. After pre-calibration offline, the vehicle's positioning information in the target coordinate system can be obtained online in real time during subsequent vehicle positioning applications.

[0101] The target coordinate system can be a local ENU coordinate system or a geographic coordinate system.

[0102] When the target coordinate system is a local ENU coordinate system, after the roadside radar obtains the target's x,y coordinates in the roadside radar coordinate system, the vehicle's coordinates in the local ENU coordinate system can be obtained through the transformation matrix of the corresponding method. It can be obtained through formula (6), or it can also be obtained through formula (8).

[0103] When the target coordinate system is a geographic coordinate system, the conversion from the local coordinate system to the geographic coordinate system may include the following steps: (a) converting the local ENU coordinates to ECEF coordinates using formula (9), and (b) converting the ECEF coordinates to geographic coordinates using formula (10).

[0104]

[0105] λ = atan2(Y,X)

[0106]

[0107]

[0108] in The above transformation achieves the conversion from the local coordinate system to geographic coordinates. Alternatively, formula 7 can directly convert millimeter-wave radar coordinates to geographic coordinates, thus eliminating the need for this step.

[0109] 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 this application.

[0110] Figure 5 This is a schematic diagram of a calibration device for a roadside radar provided in an embodiment of this application. The device includes:

[0111] The information acquisition unit 501 is used to acquire the first positioning information and speed information of the vehicle collected by the roadside radar, and the second positioning information of the connected vehicle collected by the on-board unit.

[0112] Clustering unit 502 is used to cluster the first positioning information based on the first positioning information and the speed information to generate a vehicle trajectory;

[0113] The trajectory matching unit 503 is used to determine the vehicle trajectory matched by the second positioning information based on the relative positional relationship of the vehicle trajectory and in combination with the lane information of the connected vehicle that is driven in advance.

[0114] The calibration information determination unit 504 is used to align the second positioning information and the third positioning information in the vehicle trajectory according to time, perform coordinate transformation calculation on the aligned positioning information, and determine the calibration information of the roadside radar.

[0115] Figure 5 The calibration device for the roadside radar shown is... Figure 2 The calibration method for the roadside radar shown corresponds to this.

[0116] Figure 6 This is a schematic diagram of a roadside radar calibration device provided in one embodiment of this application. Figure 6 As shown, the roadside radar calibration device 6 of 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, such as a roadside radar calibration program. When the processor 60 executes the computer program 62, it implements the steps in the various roadside radar calibration method embodiments described above. Alternatively, when the processor 60 executes the computer program 62, it implements the functions of each module / unit in the various device embodiments described above.

[0117] For example, the computer program 62 may be divided into one or more modules / units, which are stored in the memory 61 and executed by the processor 60 to complete this application. The one or more modules / units may be a series of computer program instruction segments capable of performing specific functions, which describe the execution process of the computer program 62 in the calibration device 6 of the roadside radar.

[0118] The calibration equipment for the roadside radar may include, but is not limited to, a processor 60 and a memory 61. Those skilled in the art will understand that... Figure 6This is merely an example of the calibration device 6 for roadside radar and does not constitute a limitation on the calibration device 6 for roadside radar. It may include more or fewer components than shown, or combine certain components, or different components. For example, the calibration device for roadside radar may also include input / output devices, network access devices, buses, etc.

[0119] 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.

[0120] The memory 61 can be an internal storage unit of the roadside radar calibration device 6, such as a hard disk or memory of the roadside radar calibration device 6. The memory 61 can also be an external storage device of the roadside radar calibration device 6, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, etc., equipped on the roadside radar calibration device 6. Furthermore, the memory 61 can include both internal and external storage units of the roadside radar calibration device 6. The memory 61 is used to store the computer program and other programs and data required by the roadside radar calibration device. The memory 61 can also be used to temporarily store data that has been output or will be output.

[0121] 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.

[0122] 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.

[0123] 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 implementation should not be considered beyond the scope of this application.

[0124] In the embodiments provided in this application, it should be understood that the disclosed devices / terminal equipment and methods can be implemented in other ways. For example, the device / terminal equipment 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 displayed or discussed mutual coupling or direct coupling or communication connection may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0125] 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.

[0126] Furthermore, the functional units in the various embodiments of this application 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.

[0127] 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 methods of the above embodiments can also be implemented by hardware related to computer program instructions. 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 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, computer-readable media do not include electrical carrier signals and telecommunication signals.

[0128] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application 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 this application, and should all be included within the protection scope of this application.

Claims

1. A calibration method for roadside radar, characterized in that, The method includes: Acquire the first positioning and speed information of the vehicle collected by the roadside radar, and the second positioning information of the connected vehicle collected by the on-board unit; Clustering the first positioning information based on the first positioning information and the speed information to generate a vehicle trajectory includes: calculating the distance between positioning points in the first positioning information based on the first positioning information and the speed information; clustering the positioning points based on the distance between the positioning points; and generating a vehicle trajectory from the clustered positioning points. Based on the relative positional relationship of the vehicle trajectories and combined with the pre-determined lane information of the connected vehicle, the vehicle trajectory matching the second positioning information is determined. The second positioning information and the third positioning information in the vehicle trajectory are aligned according to time, and the coordinate transformation of the aligned positioning information is calculated to determine the calibration information of the roadside radar.

2. The method according to claim 1, characterized in that, Based on the first positioning information and the speed information, the distance between the positioning points in the first positioning information is calculated, including: According to the formula Calculate the distance between two positioning points in the first positioning information, where, These are the x-coordinates of the two positioning points in the preset millimeter-wave radar coordinate system, in meters; These are the y-coordinates of the two positioning points in the millimeter-wave radar coordinate system, in meters; These are the timestamps for the two locations, in seconds. These represent the speeds of the two positioning points, in meters per second.

3. The method according to claim 1, characterized in that, Aligning the second location information and the third location information in the vehicle trajectory according to time includes: Determine the interpolation formula for the third positioning information; The positioning information of the vehicle in the roadside radar coordinate system at the alignment time is determined according to the interpolation formula.

4. The method according to claim 1, characterized in that, The alignment of the positioning information coordinates is transformed and calculated to determine the calibration information of the roadside radar, including: In the alignment positioning information, select a predetermined number of alignment data; Substitute the alignment data into the preset coordinate system transformation equation to determine the transformation matrix that serves as calibration information.

5. The method according to claim 4, characterized in that, The alignment data includes positioning information based on the local ENU coordinate system and positioning information based on the roadside radar coordinate system; Substituting the alignment data into a preset coordinate system transformation equation to determine the transformation matrix as calibration information includes: substituting the alignment data of the positioning information based on the local ENU coordinate system and the positioning information based on the roadside radar coordinate system into a preset local ENU coordinate system-roadside radar coordinate system transformation equation, and determining the transformation matrix between the local ENU coordinate system and the roadside radar coordinate system through the least squares method or a nonlinear optimization method. Alternatively, the alignment data includes positioning information based on a geographic coordinate system and positioning information based on roadside radar; substituting the alignment data into a preset coordinate system transformation equation to determine the transformation matrix as calibration information includes: substituting the alignment data of the positioning information based on a geographic coordinate system and the positioning information based on a roadside radar coordinate system into a preset geographic coordinate system-roadside radar coordinate system transformation equation, and determining the transformation matrix between the geographic coordinate system and the roadside radar coordinate system using the least squares method.

6. The method according to claim 1, characterized in that, After determining the calibration information of the roadside radar, the method further includes: Vehicle positioning information is obtained by using roadside radar and determining it based on the roadside radar coordinate system; The vehicle's positioning information in the transformed coordinate system is generated in real time using the transformation matrix.

7. A calibration device for a roadside radar, characterized in that, The device includes: The information acquisition unit is used to acquire the first positioning information and speed information of the vehicle collected by the roadside radar, and the second positioning information of the connected vehicle collected by the on-board unit. A clustering unit is configured to cluster the first positioning information based on the first positioning information and the speed information to generate a vehicle trajectory, including: calculating the distance between positioning points in the first positioning information based on the first positioning information and the speed information; performing clustering based on the distance between the positioning points; and generating a vehicle trajectory from the clustered positioning points. The trajectory matching unit is used to determine the vehicle trajectory matched by the second positioning information based on the relative positional relationship of the vehicle trajectory and in combination with the pre-determined lane information of the connected vehicle. The calibration information determination unit is used to align the second positioning information and the third positioning information in the vehicle trajectory according to time, perform coordinate transformation calculation on the aligned positioning information, and determine the calibration information of the roadside radar.

8. A calibration device for a roadside radar, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of 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.

Images