GB2620877A - On-board positioning device-based roadside millimeter-wave radar calibration method - Google Patents

On-board positioning device-based roadside millimeter-wave radar calibration method Download PDF

Info

Publication number
GB2620877A
GB2620877A GB2316625.9A GB202316625A GB2620877A GB 2620877 A GB2620877 A GB 2620877A GB 202316625 A GB202316625 A GB 202316625A GB 2620877 A GB2620877 A GB 2620877A
Authority
GB
United Kingdom
Prior art keywords
trajectory data
radar
millimeter
calibration
roadside
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
GB2316625.9A
Other versions
GB202316625D0 (en
Inventor
Du Yuchuan
Zhao Cong
Du Zhouyang
Ji Yuxiong
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Individual
Original Assignee
Individual
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Individual filed Critical Individual
Publication of GB202316625D0 publication Critical patent/GB202316625D0/en
Publication of GB2620877A publication Critical patent/GB2620877A/en
Pending legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S7/00—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00
    • G01S7/02—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00
    • G01S7/40—Means for monitoring or calibrating
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
    • G01S17/88—Lidar systems specially adapted for specific applications
    • G01S17/89—Lidar systems specially adapted for specific applications for mapping or imaging
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
    • G01S17/87—Combinations of systems using electromagnetic waves other than radio waves
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
    • G01S17/88—Lidar systems specially adapted for specific applications
    • G01S17/93—Lidar systems specially adapted for specific applications for anti-collision purposes
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
    • G01S17/88—Lidar systems specially adapted for specific applications
    • G01S17/93—Lidar systems specially adapted for specific applications for anti-collision purposes
    • G01S17/931—Lidar systems specially adapted for specific applications for anti-collision purposes of land vehicles
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S7/00—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00
    • G01S7/003—Transmission of data between radar, sonar or lidar systems and remote stations
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S7/00—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00
    • G01S7/48—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S17/00
    • G01S7/4808—Evaluating distance, position or velocity data
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S7/00—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00
    • G01S7/48—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S17/00
    • G01S7/497—Means for monitoring or calibrating
    • G01S7/4972—Alignment of sensor
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/50—Context or environment of the image
    • G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/01—Detecting movement of traffic to be counted or controlled
    • G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
    • G08G1/0108—Measuring and analyzing of parameters relative to traffic conditions based on the source of data
    • G08G1/0116—Measuring and analyzing of parameters relative to traffic conditions based on the source of data from roadside infrastructure, e.g. beacons
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/01—Detecting movement of traffic to be counted or controlled
    • G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
    • G08G1/0125—Traffic data processing
    • G08G1/0133—Traffic data processing for classifying traffic situation
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/01—Detecting movement of traffic to be counted or controlled
    • G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
    • G08G1/0137—Measuring and analyzing of parameters relative to traffic conditions for specific applications
    • G08G1/0141—Measuring and analyzing of parameters relative to traffic conditions for specific applications for traffic information dissemination
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/01—Detecting movement of traffic to be counted or controlled
    • G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
    • G08G1/0137—Measuring and analyzing of parameters relative to traffic conditions for specific applications
    • G08G1/0145—Measuring and analyzing of parameters relative to traffic conditions for specific applications for active traffic flow control
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/01—Detecting movement of traffic to be counted or controlled
    • G08G1/04—Detecting movement of traffic to be counted or controlled using optical or ultrasonic detectors
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/01—Detecting movement of traffic to be counted or controlled
    • G08G1/048—Detecting movement of traffic to be counted or controlled with provision for compensation of environmental or other condition, e.g. snow, vehicle stopped at detector
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/16—Anti-collision systems
    • G08G1/164—Centralised systems, e.g. external to vehicles
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
    • G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
    • G06F3/048—Interaction techniques based on graphical user interfaces [GUI]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00—Arrangements for program control, e.g. control units
    • G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/44—Arrangements for executing specific programs
    • G06F9/451—Execution arrangements for user interfaces
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/194—Segmentation; Edge detection involving foreground-background segmentation

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • Theoretical Computer Science (AREA)
  • Electromagnetism (AREA)
  • Data Mining & Analysis (AREA)
  • Analytical Chemistry (AREA)
  • Chemical & Material Sciences (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Evolutionary Biology (AREA)
  • Evolutionary Computation (AREA)
  • General Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Traffic Control Systems (AREA)
  • Radar Systems Or Details Thereof (AREA)
  • Optical Radar Systems And Details Thereof (AREA)

Abstract

An on-board positioning device-based roadside millimeter-wave radar calibration method, relating to the technical field of mobile vehicle detection and sensor detection target calibration. In the method, a calibration vehicle having an on-board positioning device is used to travel along a pre-designed route and acquire data, and the data acquired is processed and analyzed by means of a processing unit to achieve the roadside millimeter-wave radar calibration, thereby solving the problem of roadside millimeter-wave radar calibration.

Description

ON-BOARD POSITIONING DEVICE-BASED ROADSIDE MILLIMETER-WAVE RADAR CALIBRATION METHOD
Technical Field
The invention belongs to the technical field of sensor calibration in the Cooperative Vehicle Infrastructure Systems (CV1Ss), and relates to a method of calibrating the roadside millimeter-wave radar using the vehicle-mounted positioning device.
Technological background
With the rapid development of CVTSs, roadside perception systems play an essential role in modern transportation systems because they can provide a panoramic view of the road traffic and address inadequate vehicle detection. Roadside sensors, such as millimeter-wave (MMW) radars, cameras, and lidars, can perceive real-time traffic infoimation and support cooperative vehicle-infrastructure applications. Compared with cameras and lidars, millimeter-wave radars have advantages such as good environmental adaptability, long detection ranges, and accurate velocity; measurement, making them the most widely used roadside sensors in roadside perception systems. They can realize multi-target detection, trajectory tracking, abnormal events detection in traffic operation, etc. Meanwhile, the roadside millimeter-wave radar can also realize spatial and temporal fusion with other sensors such as lidars and video cameras, so as to obtain the high-precision perception results in CVISs.
An important prerequisite for perception data fusion in CV1Ss is sensor calibration. Sensor calibration refers to estimating the transformation between the world coordinate system and the radar coordinate system of the sensor itself, so as to ensure that the perception data from different vehicle-mounted or roadside sensors have a unified coordinate system and can be converted to each other. Millimeter-wave radars usually map targets' coordinates from the world coordinate system to their own radar coordinate systcm during the measurement, but the corresponding transformation relationship varies due to the different installation positions, attitudes and angles of the radar sensors. At the same time, due to external environment impact such as the wind vibration, the millimeter-wave radar's external parameter will be changed, which needs to be recalibrated in time to meet the requirement for precise positioning and multi-sensor fusion.
Existing calibration methods mainly focus on the calibration of vehicle-mounted millimeter-wave radar before leaving the factory and after coming off the production line, as well as other roadside sensors such as lidars and cameras, and fewer schemes are proposed to calibrate the installed roadside millimeter-wave radar.
One of the traditional calibration methods for roadside millimeter-wave radar equipment is to use the artificial calibrators. For example, in order to calibrate the roadside millimeter-wave radar, the roadside camera installed at the same location should be first calibrated. The calibration checkerboard is put on the road within the common field of view of the camera and the millimeter-wave radar, and the internal and external parameters of the cameras can be calibrated, which can establish the transformation relationship between the video image pixel coordinate system and the world coordinate system. Then the transformation between the image pixel coordinate system and radar coordinate system can be estimated through the calibration targets within their common field of view, and the calibration of the millimeter-wave radar is accomplished. This method has been widely used but the disadvantages are also obvious: it requires road closure and laborious manipulation during calibration, which limits its usage in a large range. And this method requires other installed sensors to complete the indirect calibration for millimeter-wave radar.
Another traditional roadside millimeter-wave radar calibration method is to select calibration objects or features present in the traffic scene. The transformation parameters can be solved according to the corresponding feature point pairs of the selected calibration object under the world coordinate system and the millimeter-wave radar coordinate system. This method has strict requirements on the shape, features and position of the calibration targets to realize accurate calibration. It can avoid the laborious manipulation and achieve sensors' recalibration in real time compared with previous methods. However, this method also has limited application scope due to the need for static features or calibrators with obvious characteristics on the roadside. Consequently, there is an urgent need for a convenient and rapid method to solve the problem of roadside millimeter-wave radar calibration.
With the continuous development of vehicle-infrastructure cooperative technology, the penetration rate of vehicles equipped with high-precision positioning devices is increasing. Due to the needs of autonomous driving, the vehicle-mounted positioning device can achieve centimeter-level positioning accuracy and upload its own position information in real time. Therefore, using vehicles' position information as a calibration data source for millimeter-wave radars can greatly reduce the cost and difficulty of the sensor calibration, and effectively solve the problem of online calibration of multi-source perception sensors.
Summary of the invention
To clarify the content of the invention more clearly, the technical terms involved are explained as follows: Calibration vehicle: Vehicles equipped with the vehicle-mounted positioning device, which is used for roadside millimeter-wave radar calibration. They can be divided into two categories: one category refers to the autonomous vehicles, which is embedded with the high-precision positioning device and can output real-time vehicle positioning data; and the other category refers to normal vehicles equipped with the positioning device for calibration specially.
Vehicle-mounted positioning device: Positioning devices (typically RTK differential positioning devices) installed inside or on the roof of the calibration vehicle, which can obtain the positioning coordinates of the calibration vehicle with the precision of centimeter level.
Roadside millimeter-wave radar: Millimeter-wave radar that has been installed on the roadside, and has the ability to detect the moving target and output their positioning data. They can be divided into three categories according to their installation locations, that is, installed on the left side of the road, installed on the right side of the road, as well as installed above the road.
Processing unit: Computer with data collection, data processing and data analysis functions. In the present invention, the cloud-based processing unit may be selected, which is connected to the roadside millimeter-wave radar and the calibration vehicle, the base station processing unit may be selected, which is installed indoors or on the roadside: and the embedded processing unit may also be selected which is embedded in the roadside millimeter-wave radar or in the calibration vehicle.
Radar calibration: Calculate the radar calibration parameter matrix, which can be used to transform the radar coordinate system into the world coordinate system accurately.
World coordinate system: World coordinate system refers to the reference coordinate system set in the environment. The coordinates collected by the vehicle-mounted positioning device are in the world coordinate system.
Radar coordinate system: Radar coordinate system refers to the reference coordinate system with radar's installation position as the origin. The coordinates collected by the roadside millimeter-wave radar are in the radar coordinate system.
Pre-designed normal route: A pre-designed normal route refers to the straight diagonal lines, curved paths, circular routes in the road, which are mainly used for regular calibration.
Pre-designed complex route: A pre-designed complex route refers to the straight diagonal lines, curved paths, circular routes and any combinations of above routes at the center or edge of the road, which are mainly used for verification, Resampling: Data preprocessing method to ensure that two trajectories have the same number of sampling points and synchronized sampling times. When the sampling frequency and sampling time of the vehicle-mounted positioning device and roadside millimeter-wave radar are the same, resampling is unnecessary; Otherwise, at least one trajectory requires resampling.
First trajectory data D, : Trajectory data collected by the vehicle-mounted positioning device, which uses the world coordinate system Resampled first trajectory data 1): * First trajectory data D, after data resarnpling, which uses the world coordinate system Second trajectory data 1)2: Trajectory data collected by the roadside millimeter-wave radar, which uses the radar coordinate system Third trajectory data 1)3: Second trajectory data that has been transformed from radar coordinate system into the world coordinate system based on the radar calibration parameter matrix,which uses the world coordinate system.
Resampled third trajectory data Third trajectory data D, after data resampling, which uses Fourth trajectory data D4: Trajectory data collected by the roadside millimeter-wave radar in verification procedure, which uses the radar coordinate system Fifth trajectory data D,: Trajectory data collected by the vehicle-mounted positioning device in verification procedure, which uses the world coordinate system.
Resampled fifth trajectory data Di' : Fifth trajectory data D5 after data resampling, which uses world coordinate system.
Sixth trajectory data D": Fourth trajectory data that has been transformed from radar coordinate system into the world coordinate system based on the calibration parameter matrixwhich uses the world coordinate system.
Resampled sixth trajectory data D; : Sixth trajectory data D6 after data resampling, which uses Feature point pairs: Points with spatiotemporal correspondence in two trajectory data, which can form a feature point pairs collection to achieve the coordinate transformation.
Radar calibration parameter matrix H: The radar calibration parameter matrix refers to the matrix that transforms the radar coordinate system into the world coordinate system.
Radar recalibration parameter matrix H: The radar calibration parameter matrix calculated in the recalibration step. The radar recalibration parameter matrix needs to be calculated when the radar calibration parameter matrix H can't meet the requirements of the spatio-temporal similarity threshold.
Spatio-temporal similarity: The weighted average of temporal and spatial similarity between two trajectories, which is used to judge the accuracy of the radar calibration parameter matrix (or radar recalibration parameter matrix).
Spatio-temporal similarity threshold: Threshold that can determine the accuracy of the radar calibration parameter matrix based on the calculated spatio-temporal similarity, which can be set according to expert advice or big data analysis.
The purpose of the invention is to calibrate the roadside millimeter-wave radar using vehicle-mounted positioning devices. In order to achieve the above purpose, the implementation steps of the present invention include: 1) Set vehicle-mounted positioning device on the calibration vehicle with a sampling frequency which is not less than that of the roadside millimeter-wave radar. And synchronize the system clocks of the vehicle-mounted positioning device, the roadside millimeter-wave radar, and the processing unit; 2) The calibration vehicle travels along the pre-designed normal route within the coverage area of the roadside millimeter-wave radar, and outputs the first trajectory data and the second trajectory data; 3) The processing unit collects the first trajectory data and the second trajectory data from the calibration vehicle and the roadside millimeter-wave radar, and the coordinates of the second trajectory data are converted to obtain the third trajectory data through the radar calibration parameter matrix. Process and analyze the first trajectory data and the third trajectory data, and calculate the spatiotemporal similarity between the first trajectory data and the third trajectory data; 4) Based on the spatio-temporal similarity and the spatio-temporal similarity threshold, the processing unit judges whether the roadside millimeter-wave radar needs to be recalibrated. If the calibration parameter matrix of the roadside millimeter-wave radar is judged not to require recalibration, then the calibration procedure is completed and radar calibration parameter matrix H can be used as the calibration result of millimeter-wave radar; If the radar calibration parameter matrix of the roadside millimeter-wave radar is judged to require recalibration, recalibrate the radar calibration parameter matrix of the roadside millimeter-wave radar; 5) Recalibration and verification: The calibration vehicle with the vehicle-mounted positioning device travels along the pre-designed complex route or another normal route within the coverage area of the roadside millimeter-wave radar, and outputs the fourth trajectory data and the fifth trajectory data; For the fourth trajectory data and the fifth trajectory data, perform step 3) to calculate their spatiotemporal similarity, and then peiforrn step 4) according to the spatio-ternporal similarity.
If the spatio-temporal similarity is less than or equal to the spatio-temporal similarity threshold, the radar recalibration parameter matrix H' of the roadside millimeter-wave radar meets the requirements, and radar recalibration parameter matrix H' can be used as the calibration result of millimeter-wave radar; If the spatio-temporal similarity is greater than the spatio-temporal similarity threshold, the following three alternatives can be processed: Do not recalibrate the radar calibration parameter matrix of the millimeter-wave radar i e use radar calibration parameter matrix H as the calibration result of millimeter-wave radar; (?..) Recalibrate the radar calibration parameter matrix of the millimeter-wave radar, i.e use the radar recalibration parameter matrix H' as the calibration result of millimeter-wave radar; 0.) Repeat steps I) to 4), and if the spatio-temporal similarity obtained in step 4) is less than the spatio-temporal similarity threshold, the calibration is completed; if the spatio-temporal similarity obtained in step 4) is greater than or equal to the spatio-temporal similarity threshold, the radar is considered as a faulty radar to be reported to the processing unit.
The specific technical solution in the above steps of the present invention is as follows: (1) The installation angle of the roadside millimeter-wave radar can vary in specific scenarios. Calibration vehicle is equipped with high-precision positioning device (typically RTK differential positioning devices). This device can be installed inside or on the roof of the calibration vehicle. The installation position of the roadside millimeter-wave radar and vehicle-mounted positioning device is illustrated in Figure 2.
The sampling frequency of the vehicle-mounted positioning device on the calibration vehicle should be set to be at least equal to or higher than that of the roadside millimeter-wave radar. Maintaining a higher sampling frequency can improve accuracy of the roadside millimeter-wave radar calibration. When the sampling frequency and sampling time of the vehicle-mounted positioning device and roadside millimeter-wave radar are the same, resampling is unnecessary; Otherwise, at least one trajectory requires resampling. After resampling, the trajectories from roadside millimeter-wave radar and vehicle-mounted positioning device will have the same number of sampling points and synchronized sampling times.
The processing unit should adjust the system clock of vehicle-mounted positioning device on the calibration vehicle, the roadside millimeter-wave radar and the processing unit to be strictly synchronized.
(2) The calibration vehicle with the vehicle-mounted positioning device travels along the pre-designed normal route within the coverage area of the roadside millimeter-wave radar, and outputs a first trajectory data and a second trajectory data. Specifically, the calibration vehicle with the vehicle-mounted positioning device continuously collects the vehicle's own positioning data as the first trajectory data. Simultaneously, the roadside millimeter-wave radar continuously collects the positioning data of the calibration vehicle as the second trajectory data.
The data points of the first trajectory data D, collected by said calibration vehicle with vehicle-mounted positioning device can be represented by the following vectors: =[x. y.
where x represents X coordinate from the vehicle-mounted positioning device in the world coordinate system; y, represents Y coordinate from the vehicle-mounted positioning device in the world coordinate system; .7, represents Z coordinate from the vehicle-mounted positioning device in the world coordinate system.
The data points of the second trajectory data 0, collected by said roadside millimeter-wave radar may be represented by the following vectors: where xr. represents A' coordinate from the roadside millimeter-wave radar in the radar coordinate system; yr. represents 1' coordinate from the roadside millimeter-wave radar in the radar coordinate system; 7,, represents Z coordinate from the roadside millimeter-wave radar in the radar coordinate system As shown in Figure 3, a pre-designed normal route refers to the straight diagonal lines, curved paths, circular routes in the road. These routes are utilized for the standard calibration of the roadside millimeter-wave radar in the present invention.
1) The calibration vehicle travels along the pre-designed normal route within the coverage area of the roadside millimeter-wave radar, and the first trajectory data D, is acquired.
The vehicle-mounted positioning device continuously collects the calibration vehicle's real-time positioning data at different moments. This data can be represented as follows: S 1 -
-
where tr" denotes that the n-th trajectories at different moments collected by the vehicle-mounted positioning device.
{(tin,rin, yin), (t2", x2n 2 tin,, /01 where 12 denotes the sampling time of the j-th trajectory point in the n-th trajectory collected by the vehicle-mounted positioning device; X."; denotes the horizontal coordinate of the j-th trajectory point in the n-th trajectory collected by the vehicle-mounted positioning device; yn. denotes the vertical coordinate of the j-th trajectory point in the n-th trajectory collected by the vehicle-mounted positioning device.
2) The second trajectory data D, is the positioning data of the calibration vehicle collected by the roadside millimeter-wave radar. This datti can be represented as follows: = tr,,...tc,,} where it;,, denotes that the nr-th trajectories at different moments collected by the roadside millimeter-wave radar.
= {(tr yin), 02, x., (inr-xn,,y;)1
S
where 17 denotes the sampling time of the j-th trajectory point in the n-th target trajectory collected by roadside millimeter-wave radar: x7 denotes the horizontal coordinate of the j-th trajectory point in the m-th target trajectory collected by roadside millimeter-wave radar: 47 denotes the vertical coordinate of the j-th trajectory point in the m-th target trajectory collected by roadside millimeter-wave radar.
(3) The processing unit acquires D" II, collected by the calibration vehicle and the roadside millimeter-wave radar. The coordinates of the second trajectory data D" are converted to obtain the third trajectory data D., through the radar calibration parameter matrix. Analyze D, and TT, to judge whether the roadside millimeter-wave radar calibration is necessary. The specific process is illustrated in Figure 5, 1) Coordinate transformation. Since D, uses the world coordinate system and D, uses the radar coordinate system, it's necessary to convert their coordinates into the unified coordinate system. Coordinate transformation can be achieved by selecting the corresponding feature points in two trajectory datasets to fonn a feature point pairs collection with four or more pairs. Using the coordinate transformation formula, the radar calibration parameter matrix is calculated, which can be used to transform the radar coordinate system to the world coordinate system. Then D, in the radar coordinate system can be converted to D., in the world coordinate system through the radar calibration parameter matrix. The specific process is as follows: (,-2 Select the feature points from D, and D2 to form a feature point pairs collection with four or more pairs. The selection principle is to select feature point pairs with temporal and spatial correspondence in two sets of trajectory data. The selected feature point pairs collection is shown below: 2T"x.",./0,(x.2..,14, vD, * * .(x,1 4 For each of these feature point pairs in feature point pairs collection, one feature point is derived from D collected by the vehicle-mounted positioning device while the other feature point is derived from D, collected by the roadside millimeter-wave radar.
(1?") Based on the selected feature point pairs, solve the radar calibration parameter matrix for coordinate transfonnat on.
In this invention, world coordinate system refers to the reference coordinate system set in the environment to describe the position of the calibration vehicle, and the coordinates collected by the vehicle-mounted positioning device use the world coordinate system. Radar coordinate system refers to the reference coordinate systcm with radar's installation position as the origin, and the coordinates collected by the roadside millimeter-wave radar use the radar coordinate system. Radar calibration parameter matrix refers to the matrix that transforms the radar coordinate system into the world coordinate system, as shown in the following equation: 41 412 43 h" h27 h23 /131 h3, h33_ h11 hi2 h" 1122 h" where (x,., yr, zr.) denotes the three-dimensional coordinates of a point in D2, denotes the three-dimensional coordinates of a point in D, . By solving the linear equation based the selected corresponding feature point pairs in step 1), the value of the radar calibration parameter matrix H can be determined.
il-31) Using the obtained radar calibration parameter matrix. D2 in the radar coordinate system can be transfomied into D, in the world coordinate system as follows: = x, + +/113 h, x, + hr, + h" h,x, + + h33 +/1373/ +/i33 hmx + 17,y, + h" h"x + + h" where (x,., y" z 7) denotes the three-dimensional coordinates of a point in B. , , zr) denotes the converted coordinates from the radar coordinate system to the world coordinate system, i.e. the points in the third trajectory data D, fi = y, z1, 2) Analyze trajectory data D, and It is usually impossible to directly establish the one-to-one correspondence between D, and D, due to the difference between their sampling time and frequency. Therefore, trajectory data D, and D, are needed to be resampled to ensure that they have the same number of sampling points and synchronized sampling times. When the sampling frequency and sampling time of the vehicle-mounted positioning device and roadside millimeter-wave radar are the same, resampling is unnecessary; Otherwise, at least one trajectory requires rcsampling. The specific rcsampling steps are as follows: The concatenation 2/:," of sampling time points 1 in D, and sampling time points 7; in D, is solved, as shown below: LJT3=7-", Next, the points in the trajectories D, and D, are traversed in turn, taking every four points as a group. For each group of points, the cubic functions G, and Cry are fitted using the horizontal and vertical coordinates in the first trajectory data and the third trajectory data respectively. The expression of the cubic functions is as follows: =ax3 + hx2 +ex+ d =ex' +t2 + gx + h Finally, utilizing the fitted cubic functions G and G, calculate the corresponding resampled coordinates of D, and D, at each time point in Tall The resampled first trajectory data T.): and resampled third trajectory data D; maintain the same number of sampling points and synchronized sampling times, as illustrated in Figure 7.
(4.-) Spatio-temporal similarity calculation: To judge the accuracy of the radar calibration parameter matrix, it is necessary to calculate the spatio-temporal similarity between D and D3', as follows: Firstly, create the feature point pairs collection (:., for 4' and D,' as follows: v v-4 where (x" , , ) denotes the data point of the u-th roadside millimeter-wave radar trajectory in the dataset D3'including horizontal coordinate xL, vertical coordinate y1":-and timestamp) denotes the data point of the u-th vehicle trajectory in the dataset including horizontal coordinate zi7-vertical coordinate and timestamp y, which matches with (4-:, ) of in time Next, based on the feature point pairs collection, evaluate the similarity of feature point pairs in both spatial and temporal dimensions as follows: L yinico, L -a)L.
I[06577"' (I -,6).frukd) (I -tx,o.fre o -m.fr"-d) where sim(p,q) denotes the similarity between feature point pairs p and q, sim(p,q) denotes the sum of the matching similarities of U feature point pairs in the set, measuring the similarity between D: and D; . A higher similarity value indicates that the radar calibration parameter matrix is more accurate denotes the weight of spatial similarity, and (1-0 denotes the weight of temporal similarity.
By adjusting the weight 3 to balance the impact of spatial similarity and temporal similarity,it's possible to achieve accurate evaluation even in the presence of clock asynchronization issues.
fs denotes the spatial similarity of feature point pairs in the set C-2, directly reflecting the accuracy of the radar calibration parameter matrix in the spatial dimension, as shown below: /7-denotes the temporal similarity of feature point pairs in the set C,, indirectly reflecting the accuracy of the radar calibration parameter matrix in the temporal dimension, as shown below: fT p denotes the weight of non-resampled point similarity, while (1-/3) denotes the weight of resampled point similarity. ft.."' denotes the similarity between non-resampled point pairs which is more reliable and directly reflects the similarity between Di' and A.' . red denotes the similarity between resampled point pairs, which is less reliable and indirectly reflects the similarity between D: and By adjusting the weight,6 to balance the impact of non-resampled point pairs and resampled point pairs,it's possible to achieve accurate evaluation even reliability is reduced after resampling.
(4) Judge whether spatio-temporal similarity between D: and Dc,' meets the requirements. if it is less than or equal to the spatio-temporal similarity threshold 8, the radar calibration parameter matrix H can be considered to meet the requirements and the roadside millimeter-wave radar doesn't require recalibration. If it exceeds the spatio-temporal similarity threshold 8, the roadside millimeter-wave radar requires recalibration as step (5).
(5) Recalibration and verification: When the radar calibration parameter matrix H is considered not to meet the requirements in step (4), the radar calibration parameter matrix needs to be recalibrated. After recalibration, to ensure the accuracy of the results, further verification of the recalibration results should be performed. The specific process is illustrated in Figure I 0 Recalibration: Select different feature point pairs collection from D, and D, to calculate the radar recalibration parameter matrix H' as follows: k2 hi J121' 112; hc h,,' h2' J73 (2'.) Results verification: The calibration vehicle with the vehicle-mounted positioning device travels along the pre-designed complex route or another pre-designed normal route within the coverage area of the roadside millimeter-wave radar. The data from the roadside millimeter-wave radar is collected as the fourth trajectory data D, and data from the calibration vehicle is collected as the fifth trajectory data D. The calibration vehicle can select a pre-designed complex route as shown in Figure 4. A complex route refers to the straight diagonal lines, curved paths, circular routes at the center or edge of the road, and any combinations of above routes. Alternatively, the calibration vehicle can select another pre-designed normal route as shown in Figure 3. A normal route refers to the straight diagonal lines, curved paths, circular routes in the road. The route can be selected based on the difference between the calculated spatio-temporal similarity and the spatio-temporal similarity threshold. When there is a significant difference, the selected route can be linearly similar to the initial route: Similarly, when the difference is minor, the selected route should be more different in terms of linear characteristics from the initial route.
The radar recalculation parameter matrix can transform the fourth trajectory data D, in radar = coordinate system into the world coordinate system as the sixth trajectory data /.), in, as shown in the following equation: where (x yr, zr) denotes the three-dimensional coordinates of a point in fourth trajectory data 134, (x,' ) denotes the converted coordinates from the radar coordinate system to the world coordinate system, i.e. the points in the sixth trajectory data D6.
Then upload D" D, to the processing unit and then resampled the trajectory to obtain D; and 1)4'. Calculate the spatio-temporal similarity between D; and and judge whether the spatio-temporal similarity meets the spatio-temporal similarity threshold requirements If the spatio-temporal similarity is less than or equal to the spatio-temporal similarity threshold, the radar recalibration parameter matrix H' of the roadside millimeter-wave radar meets the requirements, and radar recalibration parameter matrix H' can be used as the calibration result of millimeter-wave radar; If the spatio-temporal similarity is greater than the spatio-temporal similarity threshold, the following three alternatives can be processed: 1) Do not recalibrate the radar calibration parameter matrix of the millimeter-wave radar, .e use radar calibration parameter matrix H as the calibration result of millimeter-wave radar 2) recalibrate the radar calibration parameter matrix of the millimeter-wave radar i e use the radar recalibration parameter matrix H' as the calibration result of millimeter-wave radar; 3) Repeat steps (1) to (4), and if the spatio-temporal similarity obtained in step 4) is less than the spatio-temporal similarity threshold, the calibration is completed; if the spatio-temporal similarity obtained in step (4) is greater than or equal to the spatio-temporal similarity threshold, the radar is considered as a faulty radar to be reported to the processing unit.
The key technical points and advantages of present invention includes: 1) Using data collected by the vehicle-mounted positioning device on the calibration vehicle as ground truth data to calibrate the roadside millimeter-wave radar. This approach provides an automated and highly accurate data source, effectively enhancing the calibration accuracy of the roadside millimeter-wave radar.
2) Resampling the acquired calibration data for data matching, thereby addressing the challenge of comparing multi-source trajectory data with different sampling frequencies.
3) Employing a metric method based on spatio-temporal similarity to determine whether calibration of the roadside millimeter-wave radar is necessary, which is straightforward and practical. 4) Designing normal and complex driving routes for calibration vehicle to conduct comprehensive verification for the radar calibration result from multiple perspectives.
Drawings: The specific content and advantages of the present invention will become apparent and readily understood in conjunction with the following drawings: Figure 1 shows the workflow diagram of the present invention; Figure 2 shows the installation position of the roadside millimeter-wave radar and vehicle-mounted positioning device; Figure 3 shows the pre-designed normal routes for calibration vehicles during data collection; Figure 4 shows the pre-designed complex driving routes for calibration vehicles during data collection; Figure 5 shows the workflow for data processing and analysis by the processing unit; Figure 6 shows the selection of feature point pairs in trajectory; Figure 7 shows the trajectories that achieve the spatio-temporal matching after data resampling; Figure 8 shows trajectories with different sampling frequencies from the roadside millimeter-wave radar and vehicle-mounted positioning device.
Figure 9 shows the schematic diagram of data resampling, Figure 10 shows the workflow for recalibration and result verification; Specific implementation The present invention relates to a method of calibrating the installed roadside millimeter-wave radar using the vehicle-mounted positioning device. As shown in Figure 1, the specific implementation of the present invention can be divided into five main steps: Step 1: Vehicle-mounted positioning device deployment and clock synchronization setting The vehicle-mounted positioning device on the calibration vehicle can output real-time positioning trajectory points of the calibration vehicle, which can achieve centimeter-level positioning accuracy for autonomous vehicles and normal vehicles. The present invention takes these trajectory data as the reference to calibrate and update the radar calibration parameter matrix of the roadside millimeter-wave radar. The vehicle-mounted positioning device on the calibration vehicle should set the sampling frequency which is not less than that of the roadside millimeter-wave radar.
Roadside millimeter-wave radar has been installed on the roadside, and the installation location should be open-sided without tall buildings or trees blocking the detection field of view, as shown in Figure 2. The roadside millimeter-wave radar can cover the complete range of road and output the position, speed of the moving targets within the range of at least 300m.
The processing unit can be located in the virtual cloud platform or at the base station, or directly embedded in the roadside millimeter-wave radar or the calibration vehicle. It should be connected with the roadside millimeter-wave radar and vehicle-mounted positioning device in real time, and their system docks should be synchronized using the base station connection or network timing.
Step 2: The calibration vehicle travels along the pre-designed normal route and upload the acquired data; Within the coverage area of the roadside millimeter-wave radar, the calibration vehicle with the vehicle-mounted positioning device travels along the pre-designed normal route or pre-designed complex route. The pre-designed normal route is shown as Figure 3, the pre-designed complex route is shown as Figure 4. During the driving, the calibration vehicle with the vehicle-mounted positioning device continuously collects the vehicle's OW11 positioning data as the first trajectory data and uploads the data to the processing unit. The first trajectory data is in the world coordinate system. Simultaneously, the roadside millimeter-wave radar continuously collects the positioning data of the calibration vehicle as the second trajectory data and uploads the data to the processing unit. The second trajectory data is in the radar coordinate system.
Step 3: Process and analyze trajectory data in processing unit; Processing unit processes and analyzes the first trajectory data and the second trajectory data, as shown in Figure 5. The procedure includes coordinate transformation, resampling and spatio-temporal similarity calculation.
Firstly, since the first trajectory data uses the world coordinate system and the second trajectory data uses the radar coordinate system, it's necessary to convert their coordinates into the unified coordinate system. Selecting the corresponding feature points in two trajectory data to form a feature point pairs collection with four or more pairs, as shown in Figure 6. Using the coordinate transformation formula, the radar calibration parameter matrix is calculated, which can be used to transform the radar coordinate system to the world coordinate system. Then the second trajectory data in the radar coordinate system can be converted to the third trajectory data in the world coordinate system through the radar calibration parameter matrix.
Next, there is usually sampling time and frequency difference between the first trajectory data and the third trajectory data, as shown in Figure R. Therefore, the first trajectory data and the third trajectory data are needed to resampled to ensure that they have the same number of sampling points and synchronized sampling times, as shown in Figure 9. Trajectray resampling can be achieved using the fitted cubic functions.
Finally, it is necessary to calculate the spatio-temporal similarity between the resampled first trajectory data and the resampled third trajectory data, in order to judge the accuracy of the radar calibration parameter matrix.
Step 4: Judge the accuracy of the radar calibration parameter matrix Judge whether spatio-temporal similarity between the resampled first trajectory data and the resampled third trajectory data meets the requirements. If it is less than or equal to the spatio-temporal similarity threshold, the radar calibration parameter matrix can be considered to meet the requirements and the roadside millimeter-wave radar doesn't require recalibration. If it exceeds the spatio-temporal similarity threshold, the roadside millimeter-wave radar requires recalibration as step 5.
Step 5: Recalibration and verification; When the radar calibration parameter matrix is considered not to meet the requirements in step 4, the radar calibration parameter matrix needs to be recalibrated and verified following the procedure in step 5. The specific process is illustrated in Figure 10.
Firstly, recalibrate the radar calibration parameter matrix. Select new feature point pairs collection from the first trajectory data and the second trajectory data, and then calculate the radar recalibration parameter matrix.
Next, conduct the verification experiment using the calibration vehicle. Within the coverage area of the roadside millimeter-wave radar, the calibration vehicle with the vehicle-mounted positioning device travels along the pre-designed complex route, as shown in Figure 4.
The roadside millimeter-wave radar collects vehicle's trajectory as the fourth trajectory data and uploads the data to the processing unit. The fourth trajectory data is in the radar coordinate system. Simultaneously, the calibration vehicle collects the positioning data of the calibration vehicle as the fifth trajectory data uploads the data to the processing unit. The fifth trajectory data is in the world coordinate system. Using the radar recalculation parameter matrix, the fourth trajectory data in radar coordinate system can be transformed into the world coordinate system, as the sixth trajectory data.
Finally, processing unit verifies the radar recalibration parameter matrix through the following three steps: 1) The fifth trajectory data and the sixth trajectory data need to be resampled considering their sampling time and frequency difference. Use the fitted cubic functions to obtain the resampled first trajectory data and resampled third trajectory data, which maintain the same number of sampling points and synchronized sampling times.
2) Calculate the spatio-temporal similarity between the resampled fifth trajectory data and the resampled sixth trajectory data, to judge the accuracy of the radar recalibration parameter matrix.
3) Judge whether the spatio-temporal similarity meets the spatio-temporal similarity threshold requirements. If the spatio-temporal similarity is less than or equal to the spatio-temporal similarity threshold, the radar recalibration parameter matrix H' of the roadside millimeter-wave radar meets the requirements, and radar recalibration parameter matrix H' can be used as the calibration result of millimeter-wave radar; If the spatio-temporal similarity is greater than die spatio-temporal similarity threshold, the following three alternatives can be processed: EL1 Do not recalibrate the radar calibration parameter matrix of the millimeter-wave radar i.e., use radar calibration parameter matrix as the calibration result of millimeter-wave radar; (1?") recalibrate the radar calibration parameter matrix of the millimeter-wave radar, i.e., use the radar recalibration parameter matrix as the calibration result of millimeter-wave radar; 011 Repeat steps 1 to 4, and if the spatio-temporal similarity obtained in step 4 is less than the spatio-temporal similarity threshold, the calibration is completed; if the spatio-temporal similarity obtained in step 4 is greater than or equal to the spatio-temporal similarity threshold, the radar is considered as a faulty radar to be reported to the processing unit.
The implementation example 1 is as follows: (1) Deploy vehicle-mounted positioning device and synchronize the system clock, with the cloud server as the processing unit; Set up the experimental scenario in Auto Innovation Park in Jiading, Shanghai. In the experimental scenario, roadside millimeter-wave radars are installed at equal intervals of 250 meters on the roadside, with the height of 5.0 meters and the pitch angle of 10°, The installation location is open-sided without tall buildings or trees blocking the detection field of view, and the roadside millimeter-wave radars can cover the complete range of road. Calibration vehicle is equipped with high-precision RTK differential positioning devices. This device is installed on the roof of the calibration vehicle and maintains a fixed posture with the calibration vehicle. The cloud server is used as the processing unit, and the system clocks of processing unit, calibration vehicle and roadside millimeter-wave radars is synchronized.
(2) The calibration vehicle travels along the pre-designed normal route (curved paths) and outputs the data to the cloud server; In the experimental scenario in Auto innovation Park, the calibration vehicle with the RTK differential positioning devices travels along the pre-designed curved paths on the road. Meanwhile, the RTK differential positioning devices collect the first trajectory data and upload the data to the cloud server; the roadside millimeter-wave radars collect the second trajectory data and upload the data to the cloud server. The sampling frequency of the first trajectory data is 100Hz, arid the sampling frequency of the second trajectory data is 10Hz.
(3) Data processing and analysis in the cloud server; The cloud server processes and analyzes the first trajectory data and the second trajectory data, including the procedures of coordinate transformation, resampling and spatio-temporal similarity calculation 1) Coordinate transformation. Since the first trajectory data and the second trajectory data are in different coordinate system, it's necessary to convert their coordinates into the unified coordinate system.
Selecting the corresponding feature points in two trajectory datasets to form a feature point pairs collection with four or more pairs, and then calculate the radar calibration parameter matrix H: 47.7568 85.8341 -89.6923 9321.58 44.7409 1836.36 H= 0.000219527 -0.000182862 1 Convert the second trajectory data in the radar coordinate system to the third trajectory data in the world coordinate system through the radar calibration parameter matrix H. The second trajectory data and the third trajectory data are in the same coordinate system.
2) Resampling. Resample the first trajectory data and the third trajectory data to ensure that they have the same number of sampling points and synchronized sampling times. Calculate the sampling time points concatenation of the first trajectory data and the third trajectory data, and the result is [1516783680.132207,...151678395-1.932218].
Based on the sampling time points concatenation, the first trajectory data and the third trajectory data can be resampled through the fitted cubic functions. Then the resampled first trajectory data and resampled third trajectory data are in the same coordinate system and maintain the same number of sampling points and synchronized sampling times.
3) Spatio-temporal similarity calculation: To judge the accuracy of the radar calibration parameter matrix, it is necessary to calculate the spatio-temporal similarity between the resampled first trajectory data and resampled third trajectory data. Specifically, set the weight of spatial similarity 5 = 0,7, the weight of temporal similarity (1-0)=0.3, the weight of non-resampled point similarity fi = 0,6, the weight of resampled point similarity (i-113) =0.4. Calculate the spatio-temporal similarity sim(p,q): Esini(p,O= LO,Lies 0.3L =E[0.7(0.6fr + 0.4.f")+ 0.3(0.6.f; + (4) Judge the accuracy of the radar calibration parameter matrix; Compare the spatio-temporal similarity with the spatio-temporal similarity threshold. The similarity is less than the spatio-temporal similarity threshold, thus the radar calibration parameter matrix H can be considered to meet the requirements and the roadside millimeter-wave radar doesn't require recalibration.
The implementation example 2 is as follows: (1) Deploy vehicle-mounted positioning device and synchronize the system dock with the cloud server as the processing unit; Set up the experimental scenario in Auto innovation Park in Jiading, Shanghai. in the experimental scenario, roadside millimeter-wave radars are installed at equal intewals of 250 meters on the roadside, with the height of 5.0 meters and the pitch angle of 100. The installation location is open-sided without tall buildings or trees blocking the detection field of view, and the roadside millimeter-wave radars can cover the complete range of road. Calibration vehicle is equipped with high-precision RTK differential positioning devices. This device is installed on the roof of the calibration vehicle and maintains a fixed posture with the calibration vehicle. The cloud server is used as the processing unit, and the systcm clocks of processing unit, calibration vehicle and roadside millimeter-wave radars is synchronized.
(2) The calibration vehicle travels along the pre-designed normal route (circular routes) and outputs the data to the cloud server: In the experimental scenario in Auto Innovation Park. the calibration vehicle with the RTK differential positioning devices travels along the pre-designed circular routes on the road. Meanwhile, the RTK differential positioning devices collect the first trajectory data and upload the data to the cloud server; the roadside millimeter-wave radars collect the second trajectory data and upload the data to the cloud server. The sampling frequency of the first trajectory data is 100Hz, and the sampling frequency of the second trajectory data is 10Hz.
(3) Data processing and analysis in the cloud server; The cloud server processes and analyzes the first trajectory data and the second trajectory data, including the procedures of coordinate transformation, resampling arid spatio-temporal similarity calculation 1) Coordinate transformation. Since the first trajectory data and the second trajectory data are in different coordinate system, it's necessary to convert their coordinates into the unified coordinate system.
Selecting the corresponding feature points in two trajectory datasets to form a feature point pairs collection with four or more pairs, and then calculate the radar calibration parameter matrix ft 47.7568 -89.6923 9321.58 85.8341 44.7409 1836.36 0.000219527 0.000 I 82862 1 Convert the second trajectory data in the radar coordinate system to the third trajectory data in the world coordinate system through the radar calibration parameter matrix H. The second trajectory data and the third trajectory data are in the same coordinate system 2) Resampling. Resample the first trajectory data and the third trajectory data to ensure that they have the same number of sampling points and synchronized sampling times. Calculate the sampling time points concatenation of the first trajectory data and the third trajectory data, and the result is [1516783680. 132207,...15 I 6783954.932218] . Based on the sampling time points concatenation, the first trajectory data and the third trajectory data can be resampled through the fitted cubic functions. Then the resampled first trajectory data and resampled third trajectory data are in the same coordinate system and maintain the same number of sampling points and synchronized sampling times. H=
3) Spatio-temporal similarity calculation: To judge the accuracy of the radar calibration parameter matrix, it is necessary to calculate the spatio-temporal similarity between the resampled first trajectory data and resampled third trajectory data. Specifically, set the weight of spatial similarity 6= 0.6 the weight of temporal similarity (i-0)=0.4, the weight of' non-resampled point similarity /3 = 0.5, the weight of resampled point similarity 013)=0.5. Calculate the spatio-temporal similarity sim(p,q): Isim(p,q)= E0.6f, + =E[0.6(0.5fri +0,5icsamatec,)+0,40.5.geo, +0,5,fuied)] Ii (4) Judge the accuracy of the radar calibration parameter matrix; Compare the spatio-temporal similarity with the spatio-temporal similarity threshold. The similarity exceeds the spatio-tempoml similarity threshold, the roadside millimeter-wave radar requires recalibration and verification.
(5) Recalibration and verification; When the radar calibration parameter matrix H is considered not to meet the requirements. the radar calibration parameter matrix needs to be recalibrated, as shown in Figure 10.
Firstly, recalibmte the radar calibration parameter matrix. Select new feature point pairs collection from the first trajectory data and the second trajectory data, and then calculate the radar recalibration parameter matrix H' : 47.7568-89.6923 9321.58 85.8341 44.7409 1836.36 0.000219527 -0.000182862 1_ Next, conduct the verification experiment using the calibration vehicle. Within the coverage area of the roadside millimeter-wave radar, the calibration vehicle with the vehicle-mounted positioning device travels along the pre-designed complex route (routes combination I in Figure 4).
The roadside millimeter-wave radar collects vehicle's trajectory as the fourth trajectory data and uploads the data to the processing unit. The fourth trajectory data is in the radar coordinate system. Simultaneously, the calibration vehicle collects the positioning data of the calibration vehicle as the fifth trajectory data uploads the data to the processing unit. The fifth trajectory data is in the world coordinate system. Using the radar recalculation parameter matrix, the fourth trajectory data in radar coordinate system can be transformed into the world coordinate system, as the sixth trajectory data.
Finally, processing unit verifies the radar recalibration parameter matrix through the following three steps: 1) The fifth trajectory data and the sixth trajectory data need to be resampled considering their sampling time and frequency difference. Calculate sampling time concatenation of the fifth trajectory data and the sixth trajectory data, and the result is [1516783680.132207,...1516784063.852348]. H'=
Based on the sampling time points concatenation, resample the fifth trajectory data and the sixth trajectory data through the fitted cubic functions. Then the resampled fifth trajectory data and resampled sixth trajectory data are in the same coordinate system and maintain the same number of sampling points and synchronized sampling times.
2) Calculate the spatio-temporal similarity between the resampled fifth trajectory data and resampled sixth trajectory data to judge the accuracy of the radar calibration parameter matrix. Specifically, set the weight of spatial similarity U = 0.6 the weight of temporal similarity (i-5)=0.4, the weight of non-resampled point similarity /3= 0.5, the weight of resampled point similarity 4-,e) =0.5. Calculate the spatio-temporal similarity slin(p,0: sim(p,q)= I 0.6f, + 0.4f, =L[0.6(0.51'572 + 0.511i'd) + 0.4(0.5f7" + 0.5,ft,d 3) Judge the accuracy of the radar recalibration parameter matrix. Compare the spatio-temporal similarity with the spatio-temporal similarity threshold. The similarity is less than the spatio-temporal similarity threshold, thus the radar recalibration parameter matrix H' can be considered to meet the requirements.

Claims (11)

  1. CLAIMSI An on-board positioning device-based roadside millimeter-wave radar calibration method, involving roadside millimeter-wave radars, a calibration vehicle and a processing unit, comprising the following steps: 1) Set a vehicle-mounted positioning device on said calibration vehicle with a sampling frequency which is not less than that of said roadside millimeter-wave radar; synchronize the system clocks of said vehicle-mounted positioning device, said roadside millimeter-wave radars, and said processing unit; 2) Said calibration vehicle travels along a pre-designed normal route within the coverage area of said roadside millimeter-wave radar, and outputs the first trajectory data and the second trajectory data 3) Said processing unit collects the first trajectory data and the second trajectory data from said calibration vehicle and said roadside millimeter-wave radar, and the coordinates of the second trajectory data are converted to obtain the third trajectory data through a radar calibration parameter matrix; Process and analyze the first trajectory data and the third trajectory data, and calculate a spatio-temporal similarity between the first trajectory data and the third trajectory data; 4) Based on said spatio-temporal similarity and a spatio-temporal similarity threshold, said processing unit judges whether said roadside millimeter-wave radar needs to be recalibrated; Recalibrate said radar calibration parameter matrix, if recalibration is needed; 5) Recalibration and verification: 5.1) Said calibration vehicle with said vehicle-mounted positioning device travels along a pre-designed complex route or another normal route within the coverage area of said roadside millimeter-wave radar, and outputs the fourth trajectory data and the fifth trajectory data; 5.2) For the fourth trajectory data and the fifth trajectory data, perform step 3) to calculate their spatio-temporal similarity, and then perform step 4) according to their spatio-temporal similarity.If their spatio-temporal similarity is less than or equal to said spatio-temporal similarity threshold, then said radar recalibration parameter matrix of said roadside millimeter-wave radar meets requirements; If their spatio-temporal similarity is greater than said spatio-temporal similarity threshold, the following three alternatives maybe processed: 5.2.1) Do not recalibrate said radar calibration parameter matrix of said millimeter-wave radar; 5.2.
  2. 2) Recalibrate said radar calibration parameter matrix of said millimeter-wave radar, 5.2.
  3. 3) Repeat steps 1) to 4), and if said spatio-temporal similarity obtained in step 4) is less than said spatio-temporal similarity threshold, the calibration is completed: if said spatio-temporal similarity obtained in step 4) is greater than or equal to said spatio-temporal similarity threshold, the radar is considered as a faulty radar to be reported to said processing unit.
    2 A method according to claim 1, wherein said roadside millimeter-wave radars have an ability to detect moving targets and output their positioning data: said roadside millimeter-wave radars are installed on the left side of the road, the right side of the road, or above the road.
    3 A method according to claim 1, wherein said calibration vehicle is equipped with said vehicle-mounted positioning device: said calibration vehicle includes two categories: one category refers to autonomous vehicles embedded with a high-precision positioning device and can output real-time vehicle positioning data; and the other category refers to nonnal vehicles equipped with a positioning device for calibration specially; the sampling frequency of said vehicle-mounted positioning device should be equal to or higher than that of said roadside millimeter-wave radar.
  4. 4 A method according to claim I. wherein said radar calibration refers to calculating said radar calibration parameter matrix, which can be used to transform radar coordinate system into a world coordinate system accurately.
  5. A method according to claim 1, wherein said processing unit has the functions of data collection, data processing and data analysis; the system clocks of said processing unit is synchronized with said vehicle-mounted positioning device and said roadside millimeter-wave radar.
  6. 6 A method according to claim 1, wherein said first trajectory data and said second trajectory data can be obtained as following: When driving along said pre-designed normal route, said calibration vehicle with said vehicle-mounted positioning device continuously collects its own positioning data as said first trajectory data and uploads to said processing unit; said first trajectory data is in the world coordinate system: Simultaneously, said roadside millimeter-wave radar continuously collects the positioning data of said calibration vehicle as said second trajectory data, uploads to said processing unit; said second trajectory data is in the radar coordinate system.
  7. 7 A method according to claim 1, wherein said processing unit processes and analyzes trajectory data through a procedure of coordinate transformation, a procedure of resampling and spatio-temporal similarity calculation;
  8. S. A method according to claim 7, wherein said procedure of coordinate transformation contains the following steps: I) Select the corresponding feature points in first trajectory data and the second trajectory data to form a feature point pairs collection with four or more pairs; 2) Based on said feature point pairs collection. calculate a radar calibration parameter matrix H: 1211 1117 /113 xi /221 17" =II Yr Zr _1131 k2 123 _z, where (-vr, y, z,.) denotes the coordinates in the second trajectory data, (xv, y",z") denotes the three-dimensional coordinates of a point in the first trajectory data; 3) Use H to tra.nsforin the second trajectory data in the radar coordinate system into the third trajectory data in the world coordinate system: =kg,. +12,3-1731x" + h"y" +1233, h""er + h,y,+17" Y, 1 73x1 + h"y, +1133 h x-+ h v +1233 31 r 32, r 33Z/73211,, -V /733 where (xt., y,.,z,.) denotes the coordinates in the second trajectory data (t:, -;) denotes the converted coordinates from the radar coordinate system to the world coordinate system, i.e. the coordinates in the third trajectory data.
  9. 9 A method according to claim 7, wherein said procedure of resampling contains the following steps: I) Calculate a sampling time points concatenation 77," of the first trajectory data and the third trajectory data: Tic) 7-1=Tall 2) Fix the cubic functions G and GY using the horizontal and vertical coordinates in the first trajectory data and the third trajectory data respectively: qt. = ax2 + bx2 +cx + d G = ex2 +A-2 gx + h 3) Utilize the fitted cubic functions G" and G to calculate the corresponding resampled coordinates of the first trajectory data and the third trajectory data at each time point in Tall; then the resampled first trajectory data iti9 and resampled third trajectory data 1)3' maintain the same number of sampling points and synchronized sampling times.ID.
  10. A method according to claim 7, wherein said spatio-temporal similarity can be calculated in both spatial and temporal dimensions as: Esitn(p,q)= E of; (1-e)t, =L[acturt =0 -iofsesb-d)±(1-0)ceril ±(1-PMest where (1) denotes the weight of spatial similarity, and by adjusting the weight 0 to balance the impact of spatial similarity and temporal similarity, accurate evaluation can be achieved even in the presence of clock asynchronization issues; 6 denotes the weight of non-resampled point similarity, and by adjusting the weight ft to balance the impact of non-resampled point pairs and resampled point pairs, accurate evaluation can be achieved even reliability is reduced after resampling, denotes the spatial similarity of feature point pairs, b denotes the temporal similarity of feature point pairs, ,f:s.nai denotes the similarity between non-resampled point pairs, jr"""d denotes the similarity between resampled point pairs;
  11. 11. A method according to claim 10 wherein if said spatio-temporal similarity Isim(p,q) is less than or equal to said spatio-temporal similarity threshold, the radar calibration parameter matrix H can be considered to meet the requirements; If said spatio-temporal similarity sim(p,q) exceeds said spatio-temporal similarity threshold, the roadside millimeter-wave radar requires recalibration.
GB2316625.9A 2021-01-01 2021-04-01 On-board positioning device-based roadside millimeter-wave radar calibration method Pending GB2620877A (en)

Applications Claiming Priority (3)

Application Number Priority Date Filing Date Title
CN202110000327 2021-01-01
CN202110228419 2021-03-01
PCT/CN2021/085149 WO2022141913A1 (en) 2021-01-01 2021-04-01 On-board positioning device-based roadside millimeter-wave radar calibration method

Publications (2)

Publication Number Publication Date
GB202316625D0 GB202316625D0 (en) 2023-12-13
GB2620877A true GB2620877A (en) 2024-01-24

Family

ID=82260124

Family Applications (2)

Application Number Title Priority Date Filing Date
GB2316625.9A Pending GB2620877A (en) 2021-01-01 2021-04-01 On-board positioning device-based roadside millimeter-wave radar calibration method
GB2313215.2A Pending GB2618936A (en) 2021-01-01 2021-04-01 Vehicle-road collaboration-oriented sensing information fusion representation and target detection method

Family Applications After (1)

Application Number Title Priority Date Filing Date
GB2313215.2A Pending GB2618936A (en) 2021-01-01 2021-04-01 Vehicle-road collaboration-oriented sensing information fusion representation and target detection method

Country Status (3)

Country Link
CN (5) CN116685873A (en)
GB (2) GB2620877A (en)
WO (9) WO2022141912A1 (en)

Families Citing this family (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114724362B (en) * 2022-03-23 2022-12-27 中交信息技术国家工程实验室有限公司 Vehicle track data processing method
CN115358530A (en) * 2022-07-26 2022-11-18 上海交通大学 Vehicle-road cooperative sensing roadside test data quality evaluation method
CN115236628B (en) * 2022-07-26 2024-05-31 中国矿业大学 Method for detecting residual cargoes in carriage based on laser radar
CN115113157B (en) * 2022-08-29 2022-11-22 成都瑞达物联科技有限公司 Beam pointing calibration method based on vehicle-road cooperative radar
CN115166721B (en) * 2022-09-05 2023-04-07 湖南众天云科技有限公司 Radar and GNSS information calibration fusion method and device in roadside sensing equipment
CN115480243B (en) * 2022-09-05 2024-02-09 江苏中科西北星信息科技有限公司 Multi-millimeter wave radar end-edge cloud fusion calculation integration and application method thereof
CN115272493B (en) * 2022-09-20 2022-12-27 之江实验室 Abnormal target detection method and device based on continuous time sequence point cloud superposition
CN115235478B (en) * 2022-09-23 2023-04-07 武汉理工大学 Intelligent automobile positioning method and system based on visual label and laser SLAM
CN115830860B (en) * 2022-11-17 2023-12-15 西部科学城智能网联汽车创新中心(重庆)有限公司 Traffic accident prediction method and device
CN115966084B (en) * 2023-03-17 2023-06-09 江西昂然信息技术有限公司 Holographic intersection millimeter wave radar data processing method and device and computer equipment
CN116189116B (en) * 2023-04-24 2024-02-23 江西方兴科技股份有限公司 Traffic state sensing method and system
CN117452392B (en) * 2023-12-26 2024-03-08 哈尔滨工业大学(深圳)(哈尔滨工业大学深圳科技创新研究院) Radar data processing system and method for vehicle-mounted auxiliary driving system
CN117471461B (en) * 2023-12-26 2024-03-08 哈尔滨工业大学(深圳)(哈尔滨工业大学深圳科技创新研究院) Road side radar service device and method for vehicle-mounted auxiliary driving system
CN117961915B (en) * 2024-03-28 2024-06-04 太原理工大学 Intelligent auxiliary decision-making method of coal mine tunneling robot

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE60212556D1 (en) * 2001-12-11 2006-08-03 Fujitsu Ten Ltd Apparatus and method for radar data processing
CN109188379A (en) * 2018-06-11 2019-01-11 深圳市保途者科技有限公司 Drive the automatic calibrating method of backup radar operating angle
CN110850378A (en) * 2019-11-22 2020-02-28 深圳成谷科技有限公司 Automatic calibration method and device for roadside radar equipment
CN111157965A (en) * 2020-02-18 2020-05-15 北京理工大学重庆创新中心 Vehicle-mounted millimeter wave radar installation angle self-calibration method and device and storage medium
CN111537966A (en) * 2020-04-28 2020-08-14 东南大学 Array antenna error correction method suitable for millimeter wave vehicle-mounted radar field

Family Cites Families (42)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP2923174A2 (en) * 2012-11-22 2015-09-30 GeoSim Systems Ltd. Point-cloud fusion
KR101655606B1 (en) * 2014-12-11 2016-09-07 현대자동차주식회사 Apparatus for tracking multi object using lidar and method thereof
TWI597513B (en) * 2016-06-02 2017-09-01 財團法人工業技術研究院 Positioning system, onboard positioning device and positioning method thereof
CN105892471B (en) * 2016-07-01 2019-01-29 北京智行者科技有限公司 Automatic driving method and apparatus
WO2018126248A1 (en) * 2017-01-02 2018-07-05 Okeeffe James Micromirror array for feedback-based image resolution enhancement
KR102056147B1 (en) * 2016-12-09 2019-12-17 (주)엠아이테크 Registration method of distance data and 3D scan data for autonomous vehicle and method thereof
CN106846494A (en) * 2017-01-16 2017-06-13 青岛海大新星软件咨询有限公司 Oblique photograph three-dimensional building thing model automatic single-body algorithm
US10281920B2 (en) * 2017-03-07 2019-05-07 nuTonomy Inc. Planning for unknown objects by an autonomous vehicle
CN108629231B (en) * 2017-03-16 2021-01-22 百度在线网络技术（北京）有限公司 Obstacle detection method, apparatus, device and storage medium
CN107133966B (en) * 2017-03-30 2020-04-14 浙江大学 Three-dimensional sonar image background segmentation method based on sampling consistency algorithm
CN108932462B (en) * 2017-05-27 2021-07-16 华为技术有限公司 Driving intention determining method and device
FR3067495B1 (en) * 2017-06-08 2019-07-05 Renault S.A.S METHOD AND SYSTEM FOR IDENTIFYING AT LEAST ONE MOVING OBJECT
CN109509260B (en) * 2017-09-14 2023-05-26 阿波罗智能技术(北京)有限公司 Labeling method, equipment and readable medium of dynamic obstacle point cloud
CN107609522B (en) * 2017-09-19 2021-04-13 东华大学 Information fusion vehicle detection system based on laser radar and machine vision
CN108152831B (en) * 2017-12-06 2020-02-07 中国农业大学 Laser radar obstacle identification method and system
CN108010360A (en) * 2017-12-27 2018-05-08 中电海康集团有限公司 A kind of automatic Pilot context aware systems based on bus or train route collaboration
CN108639059B (en) * 2018-05-08 2019-02-19 清华大学 Driver based on least action principle manipulates behavior quantization method and device
CN112368598A (en) * 2018-07-02 2021-02-12 索尼半导体解决方案公司 Information processing apparatus, information processing method, computer program, and mobile apparatus
US10839530B1 (en) * 2018-09-04 2020-11-17 Apple Inc. Moving point detection
CN109297510B (en) * 2018-09-27 2021-01-01 百度在线网络技术（北京）有限公司 Relative pose calibration method, device, equipment and medium
CN111429739A (en) * 2018-12-20 2020-07-17 阿里巴巴集团控股有限公司 Driving assisting method and system
JP7217577B2 (en) * 2019-03-20 2023-02-03 フォルシアクラリオン・エレクトロニクス株式会社 CALIBRATION DEVICE, CALIBRATION METHOD
CN110296713B (en) * 2019-06-17 2024-06-04 广州卡尔动力科技有限公司 Roadside automatic driving vehicle positioning navigation system and single/multiple vehicle positioning navigation method
CN110220529B (en) * 2019-06-17 2023-05-23 深圳数翔科技有限公司 Positioning method for automatic driving vehicle at road side
CN110532896B (en) * 2019-08-06 2022-04-08 北京航空航天大学 Road vehicle detection method based on fusion of road side millimeter wave radar and machine vision
CN110443978B (en) * 2019-08-08 2021-06-18 南京联舜科技有限公司 Tumble alarm device and method
CN110458112B (en) * 2019-08-14 2020-11-20 上海眼控科技股份有限公司 Vehicle detection method and device, computer equipment and readable storage medium
CN110850431A (en) * 2019-11-25 2020-02-28 盟识(上海)科技有限公司 System and method for measuring trailer deflection angle
CN110906939A (en) * 2019-11-28 2020-03-24 安徽江淮汽车集团股份有限公司 Automatic driving positioning method and device, electronic equipment, storage medium and automobile
CN111121849B (en) * 2020-01-02 2021-08-20 大陆投资(中国)有限公司 Automatic calibration method for orientation parameters of sensor, edge calculation unit and roadside sensing system
CN111999741B (en) * 2020-01-17 2023-03-14 青岛慧拓智能机器有限公司 Method and device for detecting roadside laser radar target
CN111476822B (en) * 2020-04-08 2023-04-18 浙江大学 Laser radar target detection and motion tracking method based on scene flow
CN111554088B (en) * 2020-04-13 2022-03-22 重庆邮电大学 Multifunctional V2X intelligent roadside base station system
CN111192295B (en) * 2020-04-14 2020-07-03 中智行科技有限公司 Target detection and tracking method, apparatus, and computer-readable storage medium
CN111766608A (en) * 2020-06-12 2020-10-13 苏州泛像汽车技术有限公司 Environmental perception system based on laser radar
CN111880191B (en) * 2020-06-16 2023-03-28 北京大学 Map generation method based on multi-agent laser radar and visual information fusion
CN111880174A (en) * 2020-07-03 2020-11-03 芜湖雄狮汽车科技有限公司 Roadside service system for supporting automatic driving control decision and control method thereof
CN111914664A (en) * 2020-07-06 2020-11-10 同济大学 Vehicle multi-target detection and track tracking method based on re-identification
CN111985322B (en) * 2020-07-14 2024-02-06 西安理工大学 Road environment element sensing method based on laser radar
CN111862157B (en) * 2020-07-20 2023-10-10 重庆大学 Multi-vehicle target tracking method integrating machine vision and millimeter wave radar
CN112019997A (en) * 2020-08-05 2020-12-01 锐捷网络股份有限公司 Vehicle positioning method and device
CN112509333A (en) * 2020-10-20 2021-03-16 智慧互通科技股份有限公司 Roadside parking vehicle track identification method and system based on multi-sensor sensing

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE60212556D1 (en) * 2001-12-11 2006-08-03 Fujitsu Ten Ltd Apparatus and method for radar data processing
CN109188379A (en) * 2018-06-11 2019-01-11 深圳市保途者科技有限公司 Drive the automatic calibrating method of backup radar operating angle
CN110850378A (en) * 2019-11-22 2020-02-28 深圳成谷科技有限公司 Automatic calibration method and device for roadside radar equipment
CN111157965A (en) * 2020-02-18 2020-05-15 北京理工大学重庆创新中心 Vehicle-mounted millimeter wave radar installation angle self-calibration method and device and storage medium
CN111537966A (en) * 2020-04-28 2020-08-14 东南大学 Array antenna error correction method suitable for millimeter wave vehicle-mounted radar field

Also Published As

Publication number Publication date
WO2022141912A1 (en) 2022-07-07
CN117836667A (en) 2024-04-05
WO2022141911A1 (en) 2022-07-07
WO2022206974A1 (en) 2022-10-06
GB202313215D0 (en) 2023-10-11
CN117836653A (en) 2024-04-05
CN117441197A (en) 2024-01-23
WO2022206978A1 (en) 2022-10-06
CN117441113A (en) 2024-01-23
WO2022206942A1 (en) 2022-10-06
WO2022141910A1 (en) 2022-07-07
GB2618936A (en) 2023-11-22
CN116685873A (en) 2023-09-01
WO2022141913A1 (en) 2022-07-07
GB202316625D0 (en) 2023-12-13
WO2022141914A1 (en) 2022-07-07
WO2022206977A1 (en) 2022-10-06

Similar Documents

Publication Publication Date Title
GB2620877A (en) On-board positioning device-based roadside millimeter-wave radar calibration method
CN109696663B (en) Vehicle-mounted three-dimensional laser radar calibration method and system
CN111522043B (en) Unmanned vehicle laser radar quick re-matching positioning method
CN110837080B (en) Rapid calibration method of laser radar mobile measurement system
CN110033489B (en) Method, device and equipment for evaluating vehicle positioning accuracy
CN108983248A (en) It is a kind of that vehicle localization method is joined based on the net of 3D laser radar and V2X
CN113124856B (en) Visual inertia tight coupling odometer based on UWB (ultra wide band) online anchor point and metering method
CN110859044A (en) Integrated sensor calibration in natural scenes
CN114444158B (en) Underground roadway deformation early warning method and system based on three-dimensional reconstruction
CN104200086A (en) Wide-baseline visible light camera pose estimation method
CN108775901B (en) Real-time SLAM scene map construction system, navigation system and method
CN107356244B (en) Calibration method and device for road side unit antenna
CN112683260A (en) High-precision map and V2X-based integrated navigation positioning precision improving system and method
CN113566833A (en) Multi-sensor fusion vehicle positioning method and system
CN106370160A (en) Robot indoor positioning system and method
AU2021350657A1 (en) Positioning method and system for fully mechanized mining face
CN114755662A (en) Calibration method and device for laser radar and GPS with road-vehicle fusion perception
CN113850102A (en) Vehicle-mounted vision detection method and system based on millimeter wave radar assistance
KR101764222B1 (en) System and method for high precise positioning
CN105301621A (en) Vehicle positioning device and intelligent driving exam system
CN114485654A (en) Multi-sensor fusion positioning method and device based on high-precision map
CN114674311B (en) Indoor positioning and mapping method and system
CN114923477A (en) Multi-dimensional space-ground collaborative map building system and method based on vision and laser SLAM technology
CN112950980A (en) Intelligent car searching method for parking lot based on car body CAN data and terminal application
CN110426034B (en) Indoor positioning method based on map information auxiliary inertial navigation array

Legal Events

Date Code Title Description
732E Amendments to the register in respect of changes of name or changes affecting rights (sect. 32/1977)

Free format text: REGISTERED BETWEEN 20240516 AND 20240522

732E Amendments to the register in respect of changes of name or changes affecting rights (sect. 32/1977)

Free format text: REGISTERED BETWEEN 20240523 AND 20240529