External parameter calibration method and device of millimeter wave radar, electronic equipment and computer program product

Abstract

The invention discloses an external parameter calibration method and device for a millimeter-wave radar, electronic equipment and a computer program product. The external parameter calibration method for the millimeter-wave radar comprises the following steps: acquiring perception data of the millimeter-wave radar on a vehicle; extracting static target data according to the sensing data of the millimeter wave radar and the vehicle driving speed; generating a track point sequence of a plurality of static targets according to the static target data; calibrating a course angle from the millimeter wave radar to the vehicle body according to the track point sequence of the plurality of static targets to obtain a calibrated course angle; and outputting final external parameters from the millimeter wave radar to the vehicle body according to the calibrated course angle. According to the external parameter calibration method of the millimeter wave radar, automatic calibration of the course angle from the millimeter wave radar to the vehicle body can be realized only based on the sensing data of the millimeter wave radar, cooperation of other sensor data is not needed, the calibration efficiency is improved, the calibration cost is reduced, calibration is performed by using the track point data of multiple static targets in the calibration scene, and the calibration accuracy is improved. And the calibration precision is improved.

Description

Technical Field

[0001] The present application relates to the field of autonomous driving technology, and in particular to an external parameter calibration method, device, electronic equipment, and computer program product for a millimeter-wave radar. Background Art

[0002] In the continuous development of autonomous driving technology, millimeter-wave radar has shown strong adaptability in adverse environmental conditions such as fog, smoke, and dust due to its excellent penetration performance. Compared with other vehicle-mounted sensors such as infrared radar, ultrasonic radar, camera, and lidar, millimeter-wave radar has become an indispensable sensor component in the autonomous driving system due to its unique advantages of all-weather and all-day operation, and is the standard choice for building autonomous driving solutions.

[0003] In the field of autonomous driving, the application of millimeter-wave radar has greatly enriched the functional scope of advanced driver assistance systems (ADAS). Specifically, it can support adaptive cruise control (Adaptive Cruise Control), realize intelligent speed adjustment and distance maintenance; forward collision warning (Forward Collision Warning) function, timely warning of potential collision risks; blind spot detection (Blind Spot Detection), improve the safety and comfort of driving; assisted parking (Parking aid) and assisted lane change (Lane change assistant) and other functions, further simplify driving operations, enhance the convenience and intelligence level of driving.

[0004] In order to ensure the accurate realization of various functions of the ADAS system, high-precision external parameter calibration is particularly important. However, the millimeter-wave radar-vehicle external parameter calibration method used in current autonomous driving technology still has many shortcomings. Some methods rely on cumbersome manual calibration processes, which are not only time-consuming and labor-intensive, but also easily affected by human factors, resulting in limited calibration accuracy. Other methods rely on the complex fusion and coordination of multiple sensor data. Although it improves the calibration accuracy to a certain extent, it also brings high costs and complex system architecture, reducing calibration efficiency. These problems seriously restrict the performance and wide application of autonomous driving systems. Summary of the invention

[0005] In view of this, the embodiments of the present application provide a method, device, electronic device, and computer program product for calibrating the external parameters of a millimeter-wave radar to improve the accuracy and efficiency of millimeter-wave radar calibration in autonomous driving scenarios.

[0006] The present application embodiment adopts the following technical solutions:

[0007] In a first aspect, an embodiment of the present application provides an extrinsic parameter calibration method for a millimeter wave radar, wherein the extrinsic parameter calibration method for the millimeter wave radar includes:

[0008] Obtaining the perception data of the millimeter-wave radar on the vehicle;

[0009] Extracting static target data according to the perception data of the millimeter wave radar and the vehicle driving speed;

[0010] Generate a plurality of trajectory point sequences of static targets according to the static target data;

[0011] Calibrate the heading angle from the millimeter wave radar to the vehicle body according to the trajectory point sequence of multiple static targets to obtain a calibrated heading angle;

[0012] The final external parameter of the millimeter wave radar to the vehicle body is output according to the calibrated heading angle.

[0013] Optionally, the perception data of the millimeter wave radar includes all speeds of the target relative to the vehicle perceived by the millimeter wave radar within a calibration time period, and extracting the static target data according to the perception data of the millimeter wave radar and the vehicle speed includes:

[0014] Determine the speed of the vehicle relative to the target based on all speeds of the target relative to the vehicle sensed by the millimeter-wave radar within a calibration period;

[0015] The static target data is extracted according to the perception data of the millimeter wave radar and the driving speed of the vehicle relative to the target.

[0016] Optionally, extracting static target data according to the perception data of the millimeter wave radar and the vehicle driving speed includes:

[0017] The perception data of the millimeter wave radar is grouped according to the target identifier to obtain a plurality of grouped target perception data, wherein the target perception data includes a speed of the target relative to the vehicle;

[0018] Determine the driving speed of the vehicle corresponding to each group relative to the target according to the speed of the target in the plurality of groups relative to the vehicle;

[0019] Comparing the driving speed of the vehicles corresponding to each group relative to the target with the driving speed of the vehicle;

[0020] The static target data is extracted from the perception data of the millimeter-wave radar according to the comparison result.

[0021] Optionally, the static target data includes a static target identifier and trajectory point data of the static target, and generating trajectory point sequences of multiple static targets according to the static target data includes:

[0022] Determining the trajectory point data belonging to the same static target and the trajectory point data belonging to different static targets according to the static target identifier and the trajectory point data of the static target;

[0023] The trajectory point sequences of multiple static targets are generated according to the trajectory point data belonging to the same static target and the trajectory point data belonging to different static targets.

[0024] Optionally, generating trajectory point sequences of multiple static targets according to trajectory point data belonging to the same static target and trajectory point data belonging to different static targets comprises:

[0025] Determine the trajectory point data of the same static target identifier according to the static target identifier;

[0026] Determine the distance between trajectory points of adjacent timestamps according to the timestamps corresponding to the trajectory point data of the same static target identification;

[0027] The trajectory point data belonging to the same static target and the trajectory point data belonging to different static targets are determined according to the distances between the trajectory points of adjacent time stamps, and trajectory point sequences of multiple static targets are generated.

[0028] Optionally, determining the trajectory point data belonging to the same static target and the trajectory point data belonging to different static targets according to the distances between the trajectory points of adjacent timestamps, and generating trajectory point sequences of multiple static targets includes:

[0029] If the distance between the trajectory points of adjacent timestamps is greater than a preset distance threshold, it is determined that the trajectory points of adjacent timestamps belong to trajectory point data of different static targets, and are added to the trajectory point sequences of different static targets respectively;

[0030] Otherwise, it is determined that the trajectory points of adjacent time stamps belong to the trajectory point data of the same static target, and are added to the trajectory point sequence of the same static target.

[0031] Optionally, calibrating the heading angle from the millimeter wave radar to the vehicle body according to the trajectory point sequences of multiple static targets to obtain the calibrated heading angle includes:

[0032] Calculating the heading angles from the millimeter wave radar to the vehicle body respectively according to the trajectory point sequences of multiple static targets to obtain multiple heading angles;

[0033] The calibrated heading angle is calculated according to multiple heading angles.

[0034] In a second aspect, an embodiment of the present application further provides an external parameter calibration device for a millimeter wave radar, wherein the external parameter calibration device for the millimeter wave radar comprises:

[0035] An acquisition unit, used to acquire perception data of a millimeter-wave radar on a vehicle;

[0036] An extraction unit, used to extract static target data according to the perception data of the millimeter wave radar and the vehicle speed;

[0037] A generating unit, configured to generate trajectory point sequences of a plurality of static targets according to the static target data;

[0038] A calibration unit, used for calibrating the heading angle from the millimeter wave radar to the vehicle body according to the trajectory point sequence of multiple static targets to obtain a calibrated heading angle;

[0039] The output unit is used to output the final external parameter of the millimeter wave radar to the vehicle body according to the calibrated heading angle.

[0040] In a third aspect, an embodiment of the present application further provides an electronic device, including:

[0041] A processor; and a memory arranged to store computer executable instructions, wherein when the executable instructions are executed, the processor executes any of the aforementioned methods for calibrating external parameters of the millimeter-wave radar.

[0042] In a fourth aspect, an embodiment of the present application further provides a computer program product, including a computer program or instructions, which, when executed by a processor, implements any of the aforementioned methods for calibrating external parameters of the millimeter-wave radar.

[0043] At least one of the above technical solutions adopted in the embodiments of the present application can achieve the following beneficial effects: the external parameter calibration method of the millimeter wave radar in the embodiment of the present application first obtains the perception data of the millimeter wave radar on the vehicle; then extracts the static target data according to the perception data of the millimeter wave radar and the vehicle speed; then generates a trajectory point sequence of multiple static targets according to the static target data; then calibrates the heading angle of the millimeter wave radar to the vehicle body according to the trajectory point sequence of multiple static targets to obtain a calibrated heading angle; finally, outputs the final external parameter of the millimeter wave radar to the vehicle body according to the calibrated heading angle. The external parameter calibration method of the millimeter wave radar in the embodiment of the present application can realize the automatic calibration of the heading angle of the millimeter wave radar to the vehicle body based only on the perception data of the millimeter wave radar, without the need for the cooperation of other sensor data, thereby improving the calibration efficiency and reducing the calibration cost, and using the trajectory point data of multiple static targets in the calibration scene for calibration, thereby improving the calibration accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0045] Figure 1 It is a flow chart of an external parameter calibration method of a millimeter wave radar in an embodiment of the present application;

[0046] Figure 2 This is a schematic diagram of a calibration scenario in an embodiment of the present application;

[0047] Figure 3 This is a schematic diagram of the effect of generating a trajectory point sequence of a static target in an embodiment of the present application;

[0048] Figure 4 This is a schematic diagram of the effect of generating a static target trajectory in an embodiment of the present application;

[0049] Figure 5 This is a schematic diagram of the structure of an external parameter calibration device for a millimeter-wave radar in an embodiment of the present application;

[0050] Figure 6 This is a schematic diagram of the structure of an electronic device in an embodiment of the present application. DETAILED DESCRIPTION

[0051] In order to make the purpose, technical solution and advantages of the present application clearer, the technical solution of the present application will be clearly and completely described below in combination with the specific embodiments of the present application and the corresponding drawings. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present application.

[0052] The technical solutions provided by various embodiments of the present application are described in detail below in conjunction with the accompanying drawings.

[0053] The present application embodiment provides a method for calibrating the external parameters of a millimeter wave radar, such as Figure 1 As shown, a flow chart of an external parameter calibration method of a millimeter wave radar in an embodiment of the present application is provided, and the external parameter calibration method of the millimeter wave radar at least includes the following steps S110 to S150:

[0054] Step S110, acquiring the perception data of the millimeter-wave radar on the vehicle.

[0055] The external parameter calibration of the millimeter-wave radar needs to be carried out in a certain calibration scenario, and the calibration scenario needs to meet certain conditions, which can include that the vehicle equipped with the millimeter-wave radar needs to be in a road scene with many static targets that can be sensed by the millimeter-wave radar. Static targets can be, for example, static targets such as trees and road signs on both sides of the road. The specific number of static targets can be constrained to be greater than a certain number threshold requirement, and the specific threshold value can be flexibly adjusted according to the actual calibration effect, and is not specifically limited here.

[0056] During calibration, the vehicle is controlled to drive in a straight line in the above road scenario, and the millimeter-wave radar on the vehicle can sense the surrounding targets and output target perception data. Figure 2 As shown, a schematic diagram of a calibration scenario in an embodiment of the present application is provided.

[0057] Step S120: extracting static target data based on the perception data of the millimeter-wave radar and the vehicle's driving speed.

[0058] In order to reduce the requirements for calibration scenes, it is not strictly required to calibrate the millimeter-wave radar in a specific calibration site. As long as the basic requirements of the calibration scene are met, it can be calibrated on the actual road. However, when calibrating in a real road scene, the actual perception data of the millimeter-wave radar may contain data of dynamic targets such as other vehicles and pedestrians, while the perception data used for subsequent calibration needs to be data of static targets. Therefore, it is necessary to remove the data of dynamic targets from the perception data of the millimeter-wave radar and obtain static target data for subsequent calibration calculations.

[0059] The above elimination method can be judged in combination with the vehicle speed. The vehicle speed refers to the speed of the vehicle relative to the target. Since the millimeter wave radar can directly sense the speed of the target relative to the vehicle, in scenarios with many static targets, the dynamic targets can be identified and eliminated in combination with the vehicle speed.

[0060] Step S130, generating trajectory point sequences of multiple static targets according to the static target data.

[0061] Millimeter-wave radar can also sense information such as the distance and position of different targets relative to the vehicle. Therefore, the data of different static targets can be further distinguished based on the above static target data, and then a corresponding trajectory point sequence is generated for each static target. One trajectory point sequence corresponds to one static target, and one trajectory point sequence is composed of all trajectory point data of one static target.

[0062] Step S140, calibrating the heading angle from the millimeter wave radar to the vehicle body according to the trajectory point sequences of multiple static targets to obtain a calibrated heading angle.

[0063] According to the trajectory point sequence of each static target, multiple heading angles can be calculated by combining the straight line fitting algorithm and the heading angle yaw calculation method. Finally, a final heading angle is calculated by combining multiple heading angles as the calibrated heading angle. The heading angle calibration accuracy is improved by integrating the trajectory point data of multiple static targets.

[0064] Step S150: outputting the final external parameter of the millimeter wave radar to the vehicle body according to the calibrated heading angle.

[0065] In addition to the heading angle yaw, the external parameters of the millimeter wave radar to the vehicle body also include the translation parameters x, y, z and the roll angle roll and pitch angle pitch in the rotation parameters. Among them, the translation parameters x, y, z can be directly obtained through the design parameters, and the roll angle roll and pitch angle pitch can be directly set to 0°. Finally, the complete external parameters of the millimeter wave radar to the vehicle body {x, y, z, roll, pitch, yaw} are output.

[0066] The external parameter calibration method of the millimeter-wave radar in the embodiment of the present application can realize the automatic calibration of the heading angle of the millimeter-wave radar to the vehicle body based only on the perception data of the millimeter-wave radar, without the need for the cooperation of other sensor data, thereby improving the calibration efficiency and reducing the calibration cost. In addition, the trajectory point data of multiple static targets in the calibration scenario are used for calibration, thereby improving the calibration accuracy.

[0067] In some embodiments of the present application, the perception data of the millimeter-wave radar includes all speeds of the target relative to the vehicle perceived by the millimeter-wave radar within a calibration time period, and extracting static target data based on the perception data of the millimeter-wave radar and the vehicle's driving speed includes: determining the vehicle's driving speed relative to the target based on all speeds of the target relative to the vehicle perceived by the millimeter-wave radar within a calibration time period; extracting the static target data based on the perception data of the millimeter-wave radar and the vehicle's driving speed relative to the target.

[0068] The perception data of the millimeter-wave radar in the embodiment of the present application includes all target perception data from the beginning to the end of the collection within the calibration time period. The target perception data includes all speed data of the target relative to the vehicle perceived by the millimeter-wave radar. Conversely, when the speed of the target relative to the vehicle can be obtained, the speed of the vehicle relative to the target must be calculated. The essence of this is the change of the reference system. In theory, the opposite of the speed can be directly taken.

[0069] All speeds of the vehicle relative to the target can be calculated in the above manner. Since the calibration scene is a scene with enough static targets, the above speed information is also more of the speed information of the static target. The average of all speed data of the vehicle relative to the target within the calibration time period can be calculated to obtain a comprehensive speed, that is, the above vehicle driving speed v0, which is used as the basis for distinguishing between dynamic and static targets.

[0070] In some embodiments of the present application, extracting static target data based on the perception data of the millimeter-wave radar and the vehicle's driving speed includes: grouping the perception data of the millimeter-wave radar according to the target identifier to obtain target perception data of multiple groups, the target perception data including the speed of the target relative to the vehicle; determining the driving speed of the vehicle corresponding to each group relative to the target based on the speed of the target in the multiple groups relative to the vehicle; comparing the driving speed of the vehicle corresponding to each group relative to the target with the driving speed of the vehicle; and extracting the static target data from the perception data of the millimeter-wave radar based on the comparison result.

[0071] Since the target data sensed by the millimeter-wave radar are target point data, including the target identification, the distance of the target relative to the vehicle, the speed, acceleration and other data, a large amount of target point data will be collected during the calibration period, and it is necessary to filter out a small number of dynamic target data points from these large amounts of target point data.

[0072] In order to improve the efficiency of static target data extraction, the embodiment of the present application can first use the target ID to group the perception data of the millimeter wave radar. One ID is used to mark a target instance within the upper limit of the number of targets perceived by the millimeter wave radar. For example, assuming that the millimeter wave radar is limited to sensing and marking a maximum of 10 targets at a time, these 10 targets can be identified by 01 to 10. Therefore, based on the difference in ID, data with the same ID can be grouped into one group, and data with different IDs can be grouped into different groups.

[0073] After the grouping process based on the above steps, if the data points of a dynamic target are uniformly divided into a group i, then the data is centrally processed in the group dimension. Specifically, the speed of the vehicle corresponding to each group relative to the target can be calculated based on the speed of the target relative to the vehicle contained in multiple groups. The calculation method is the same as the above embodiment. The speed of all vehicles in the group relative to the target can be averaged as the speed v of the vehicle corresponding to the group relative to the target. i , and then the driving speed v of each group is i The speeds are compared with the vehicle speed v0, and moving and static targets are distinguished based on the comparison results.

[0074] Specifically, since the vehicle speed v0 is calculated based on the speed information of more static targets, its speed characteristics are more consistent with the characteristics of static targets. Therefore, by dividing the speed v0 of each group into i Compared with the above vehicle speed v0, if the speed v of a group iThe difference between the above-mentioned vehicle speed v0 is large, indicating that the target speed information in this group does not conform to the speed characteristics of a static target. Therefore, it can be considered that the target data in this group belongs to the data of a dynamic target and can be directly eliminated.

[0075] Through the above-mentioned grouping and speed comparison method, the data of dynamic targets can be quickly eliminated. There is no need to compare the target point data with the vehicle speed one by one, which improves the efficiency of static target extraction and further improves the calibration efficiency.

[0076] In some embodiments of the present application, the static target data includes a static target identifier and trajectory point data of the static target, and generating trajectory point sequences of multiple static targets based on the static target data includes: determining trajectory point data belonging to the same static target and trajectory point data belonging to different static targets based on the static target identifier and the trajectory point data of the static target; generating trajectory point sequences of multiple static targets based on the trajectory point data belonging to the same static target and the trajectory point data belonging to different static targets.

[0077] As in the aforementioned embodiment, although the data belonging to the same target can be roughly distinguished based on the target ID, since the millimeter-wave radar is generally set with an upper limit on the number of perceived targets, when the number of targets exceeds the upper limit, the exceeded targets will continue to use the previously assigned target identifiers. For example, assuming that the millimeter-wave radar is limited to sensing and marking a maximum of 10 targets at a time, these 10 targets can be identified by 01 to 10. When the 01st target disappears from the perception field of the millimeter-wave radar and the 11th target enters the perception field of the millimeter-wave radar, the 11th target will continue to use the identifier of the 1st target, that is, the identifier is 01. In this way, there will be a situation where the ID identifiers are the same but they do not actually belong to the same target. Therefore, simply relying on target identifiers for target differentiation does not apply to this use restriction of millimeter-wave radars.

[0078] Based on this, the embodiment of the present application can further combine the trajectory point data of the static target to determine whether they belong to the same target based on the static target identification, and finally generate a trajectory point sequence of the same static target based on the trajectory point data belonging to the same static target, and generate trajectory point sequences of multiple different static targets based on the trajectory point data belonging to different static targets.

[0079] In some embodiments of the present application, the method of generating trajectory point sequences of multiple static targets based on trajectory point data belonging to the same static target and trajectory point data belonging to different static targets includes: determining trajectory point data with the same static target identifier based on the static target identifier; determining the distance between trajectory points of adjacent timestamps based on the timestamps corresponding to the trajectory point data with the same static target identifier; determining trajectory point data belonging to the same static target and trajectory point data belonging to different static targets based on the distance between trajectory points of adjacent timestamps, and generating trajectory point sequences of multiple static targets.

[0080] Based on the above embodiment, when generating trajectory point sequences of multiple static targets, the trajectory point data of the same static target ID can be determined based on the ID identification of the static target. However, the trajectory point data belonging to the same static target ID does not necessarily mean that they belong to the same static target. The distance between adjacent trajectory points can be further combined to distinguish the trajectory point data that do not belong to the same target, and then gradually generate the trajectory point sequence of each static target. This is mainly due to the fact that the position changes over time between the trajectory points of the same target are significantly different from the position changes over time between the trajectory points of different targets.

[0081] Specifically, the identification of target trajectory points and the generation of trajectory point sequences can be performed synchronously. Each target trajectory point data has a corresponding timestamp. For all trajectory point data belonging to the same static target ID, an empty trajectory point sequence can be initialized first, and then, according to the order of the timestamps of the target trajectory points, the relative distance between each target trajectory point to be added to the trajectory point sequence at the current moment and the corresponding target trajectory point at the previous moment is calculated, and the relative distance between the two trajectory point data is compared with a preset distance threshold, and whether they belong to the same target is determined based on the comparison result. Of course, in addition to the above synchronous method, all trajectory point data belonging to the same target can also be distinguished and then added to the target trajectory point sequence.

[0082] The above embodiment is mainly a differentiation strategy set for the situation where two targets have the same identification but actually belong to different targets, in order to improve the accuracy of generating the trajectory point sequence.

[0083] In some embodiments of the present application, the determining of trajectory point data belonging to the same static target and trajectory point data belonging to different static targets based on the distance between trajectory points of adjacent timestamps, and generating trajectory point sequences of multiple static targets includes: if the distance between trajectory points of adjacent timestamps is greater than a preset distance threshold, determining that the trajectory points of adjacent timestamps belong to trajectory point data of different static targets, and adding them to the trajectory point sequences of different static targets respectively; otherwise, determining that the trajectory points of adjacent timestamps belong to the trajectory point data of the same static target, and adding them to the trajectory point sequence of the same static target.

[0084] If the relative distance between two trajectory point data is less than the preset distance threshold, it means that the two trajectory points are close in time and space, which conforms to the characteristics of the trajectory point position change of the same target, and the target trajectory point data at the current moment is added to the trajectory point sequence of the target trajectory point data at the previous moment. If the relative distance between two trajectory point data is equal to or greater than the preset distance threshold, it means that the trajectory point position changes greatly within the adjacent moments, which does not conform to the characteristics of the change of the same target, and can be considered as trajectory point data of different targets, and it is added to a new trajectory point sequence.

[0085] In order to facilitate the understanding of the above embodiments, Figure 3 As shown, a schematic diagram of the effect of generating a trajectory point sequence of a static target in an embodiment of the present application is provided. Figure 3 The trajectory points of different colors represent the trajectory points of different targets.

[0086] It should also be noted that, considering that in the process of grouping and extracting static target data based on target identification in the aforementioned embodiment, data belonging to the same target identification but actually belonging to different targets may be grouped together. If these data grouped together but belonging to different targets contain both static target data and dynamic target data, then the driving speed calculated based on the grouping dimension may be biased, thereby affecting the accuracy of static target extraction. Therefore, in this case, the embodiment of the present application can advance the above-mentioned differentiation strategy set for the situation where two targets have the same identification but actually belong to different targets to the stage of static target data extraction.

[0087] Specifically, the grouping result obtained only based on the target identification can be corrected based on the distance between the trajectory points at adjacent moments. If the distance between the trajectory points at adjacent moments is equal to or greater than the distance threshold, even if their ID identifications are the same, they need to be grouped into different groups because they are essentially different targets. This is equivalent to grouping all different targets into different groups in the grouping stage, avoiding the data of dynamic and static targets from being mixed into one group, and then filtering out the groups of dynamic targets from these groups based on the comparison of speed, thereby improving the accuracy of static target extraction.

[0088] All the groups finally obtained by the above method correspond to the groups of all different static targets, and the trajectory point data contained in each group represents the trajectory point sequence of a static target, so that the trajectory points can be directly fitted in the dimensions of each group.

[0089] In some embodiments of the present application, calibrating the heading angle from the millimeter wave radar to the vehicle body according to the trajectory point sequences of multiple static targets to obtain the calibrated heading angle includes: calculating the heading angles from the millimeter wave radar to the vehicle body according to the trajectory point sequences of multiple static targets respectively to obtain multiple heading angles; and calculating the calibrated heading angle according to the multiple heading angles.

[0090] After obtaining the trajectory point sequences of all static targets, a straight line fitting of a single trajectory point sequence can be performed first. Specifically, the vehicle body coordinate system O xyz As the benchmark, all trajectory points in the trajectory point sequence of all static targets are projected onto x O y Plane, get all 2D points, and use Hough transform and other methods to solve the straight line equation y=kx+b for all 2D points.

[0091] After obtaining the straight line equations corresponding to all trajectory point sequences, it is equivalent to obtaining the trajectories of all static targets. Then the inverse tangent function can be used to solve the yaw value of each trajectory, and finally the average yaw value of all trajectories is calculated as the final calibrated yaw.

[0092] like Figure 4 As shown, a schematic diagram of the effect of generating a static target trajectory in an embodiment of the present application is provided. Figure 4 The trajectories of different colors represent the trajectories of different targets.

[0093] The present application also provides an external parameter calibration device 500 for a millimeter wave radar. Figure 5 As shown, a schematic diagram of the structure of an external parameter calibration device for a millimeter wave radar in an embodiment of the present application is provided. The external parameter calibration device 500 for the millimeter wave radar includes: an acquisition unit 510, an extraction unit 520, a generation unit 530, a calibration unit 540 and an output unit 550, wherein:

[0094] An acquisition unit 510 is used to acquire perception data of a millimeter-wave radar on a vehicle;

[0095] An extraction unit 520, configured to extract static target data according to the sensing data of the millimeter wave radar and the vehicle speed;

[0096] A generating unit 530, configured to generate trajectory point sequences of multiple static targets according to the static target data;

[0097] A calibration unit 540 is used to calibrate the heading angle from the millimeter wave radar to the vehicle body according to the trajectory point sequence of multiple static targets to obtain a calibrated heading angle;

[0098] The output unit 550 is used to output the final external parameter of the millimeter wave radar to the vehicle body according to the calibrated heading angle.

[0099] In some embodiments of the present application, the perception data of the millimeter-wave radar includes all speeds of the target relative to the vehicle perceived by the millimeter-wave radar within a calibration time period, and the extraction unit 520 is specifically used to: determine the vehicle's relative speed to the target based on all speeds of the target relative to the vehicle perceived by the millimeter-wave radar within a calibration time period; and extract the static target data based on the perception data of the millimeter-wave radar and the vehicle's relative speed to the target.

[0100] In some embodiments of the present application, the extraction unit 520 is specifically used to: group the perception data of the millimeter-wave radar according to the target identifier to obtain multiple groups of target perception data, the target perception data including the speed of the target relative to the vehicle; determine the driving speed of the vehicle corresponding to each group relative to the target based on the speed of the target relative to the vehicle in the multiple groups; compare the driving speed of the vehicle corresponding to each group relative to the target with the driving speed of the vehicle; and extract the static target data from the perception data of the millimeter-wave radar based on the comparison result.

[0101] In some embodiments of the present application, the static target data includes a static target identifier and trajectory point data of the static target, and the generation unit 530 is specifically used to: determine the trajectory point data belonging to the same static target and the trajectory point data belonging to different static targets based on the static target identifier and the trajectory point data of the static target; generate trajectory point sequences of multiple static targets based on the trajectory point data belonging to the same static target and the trajectory point data belonging to different static targets.

[0102] In some embodiments of the present application, the generation unit 530 is specifically used to: determine the trajectory point data of the same static target identifier based on the static target identifier; determine the distance between the trajectory points of adjacent timestamps based on the timestamps corresponding to the trajectory point data of the same static target identifier; determine the trajectory point data belonging to the same static target and the trajectory point data belonging to different static targets based on the distance between the trajectory points of adjacent timestamps, and generate trajectory point sequences for multiple static targets.

[0103] In some embodiments of the present application, the generation unit 530 is specifically used to: if the distance between the trajectory points of adjacent timestamps is greater than a preset distance threshold, determine that the trajectory points of adjacent timestamps belong to trajectory point data of different static targets, and add them to the trajectory point sequences of different static targets respectively; otherwise, determine that the trajectory points of adjacent timestamps belong to the trajectory point data of the same static target, and add them to the trajectory point sequence of the same static target.

[0104] In some embodiments of the present application, the calibration unit 540 is specifically used to: calculate the heading angle from the millimeter wave radar to the vehicle body according to the trajectory point sequences of multiple static targets to obtain multiple heading angles; and calculate the calibrated heading angle according to the multiple heading angles.

[0105] It can be understood that the above-mentioned millimeter-wave radar external parameter calibration device can implement each step of the millimeter-wave radar external parameter calibration method provided in the aforementioned embodiment, and the relevant explanations on the millimeter-wave radar external parameter calibration method are applicable to the millimeter-wave radar external parameter calibration device, which will not be repeated here.

[0106] Figure 6 This is a schematic diagram of the structure of an electronic device according to an embodiment of the present application. Figure 6 At the hardware level, the electronic device includes a processor, and optionally also includes an internal bus, a network interface, and a memory. The memory may include a memory, such as a high-speed random access memory (RAM), and may also include a non-volatile memory (non-volatile memory), such as at least one disk storage. Of course, the electronic device may also include hardware required for other services.

[0107] The processor, network interface and memory can be interconnected through an internal bus, which can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 6 Only one bidirectional arrow is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0108] The memory is used to store the program. Specifically, the program may include a program code, and the program code includes a computer operation instruction. The memory may include a memory and a non-volatile memory, and provides instructions and data to the processor.

[0109] The processor reads the corresponding computer program from the non-volatile memory into the memory and then runs it, forming an external parameter calibration device for the millimeter wave radar at the logical level. The processor executes the program stored in the memory and is specifically used to perform the following operations:

[0110] Obtaining the perception data of the millimeter-wave radar on the vehicle;

[0111] Extracting static target data according to the perception data of the millimeter wave radar and the vehicle driving speed;

[0112] Generate a plurality of trajectory point sequences of static targets according to the static target data;

[0113] Calibrate the heading angle from the millimeter wave radar to the vehicle body according to the trajectory point sequence of multiple static targets to obtain a calibrated heading angle;

[0114] The final external parameter of the millimeter wave radar to the vehicle body is output according to the calibrated heading angle.

[0115] The above application Figure 1The method performed by the external parameter calibration device of the millimeter wave radar disclosed in the illustrated embodiment can be applied to a processor or implemented by a processor. The processor may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by an integrated logic circuit of hardware in the processor or an instruction in the form of software. The above processor may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it may also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiments of the present application can be implemented or executed. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. The steps of the method disclosed in conjunction with the embodiments of the present application can be directly embodied as being executed by a hardware decoding processor, or executed by a combination of hardware and software modules in a decoding processor. The software module can be located in a storage medium mature in the art such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory, and the processor reads the information in the memory and completes the steps of the above method in combination with its hardware.

[0116] The present application also provides a computer program product, which stores one or more programs, wherein the one or more programs include instructions, which, when executed by an electronic device including multiple application programs, enable the electronic device to execute Figure 1 The method performed by the external parameter calibration device of the millimeter wave radar in the embodiment shown is specifically used to perform:

[0117] Obtaining the perception data of the millimeter-wave radar on the vehicle;

[0118] Extracting static target data according to the perception data of the millimeter wave radar and the vehicle driving speed;

[0119] Generate a plurality of trajectory point sequences of static targets according to the static target data;

[0120] Calibrate the heading angle from the millimeter wave radar to the vehicle body according to the trajectory point sequence of multiple static targets to obtain a calibrated heading angle;

[0121] The final external parameter of the millimeter wave radar to the vehicle body is output according to the calibrated heading angle.

[0122] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0123] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0124] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0125] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0126] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0127] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0128] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0129] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0130] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0131] The above is only an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims

1. A method for calibrating external parameters of a millimeter wave radar, wherein: The external parameter calibration method of the millimeter wave radar includes: Obtaining the perception data of the millimeter-wave radar on the vehicle; Extracting static target data according to the perception data of the millimeter wave radar and the vehicle driving speed; Generate a plurality of trajectory point sequences of static targets according to the static target data; Calibrate the heading angle from the millimeter wave radar to the vehicle body according to the trajectory point sequence of multiple static targets to obtain a calibrated heading angle; The final external parameter of the millimeter wave radar to the vehicle body is output according to the calibrated heading angle.

2. The method for calibrating the external parameters of a millimeter-wave radar as claimed in claim 1, wherein: The perception data of the millimeter wave radar includes all speeds of the target relative to the vehicle perceived by the millimeter wave radar within a calibration time period, and extracting static target data according to the perception data of the millimeter wave radar and the vehicle speed includes: Determine the speed of the vehicle relative to the target based on all speeds of the target relative to the vehicle sensed by the millimeter-wave radar within a calibration period; The static target data is extracted according to the perception data of the millimeter wave radar and the driving speed of the vehicle relative to the target.

3. The method for calibrating the external parameters of a millimeter-wave radar as claimed in claim 1, wherein: The extracting of static target data according to the perception data of the millimeter wave radar and the vehicle speed includes: The perception data of the millimeter wave radar is grouped according to the target identifier to obtain a plurality of grouped target perception data, wherein the target perception data includes a speed of the target relative to the vehicle; Determine the driving speed of the vehicle corresponding to each group relative to the target according to the speed of the target in the plurality of groups relative to the vehicle; Comparing the driving speed of the vehicles corresponding to each group relative to the target with the driving speed of the vehicle; The static target data is extracted from the perception data of the millimeter-wave radar according to the comparison result.

4. The method for calibrating the external parameters of a millimeter-wave radar as claimed in claim 1, wherein: The static target data includes a static target identifier and track point data of the static target, and the step of generating a plurality of track point sequences of static targets according to the static target data includes: Determining the trajectory point data belonging to the same static target and the trajectory point data belonging to different static targets according to the static target identifier and the trajectory point data of the static target; The trajectory point sequences of multiple static targets are generated according to the trajectory point data belonging to the same static target and the trajectory point data belonging to different static targets.

5. The method for calibrating the external parameters of a millimeter-wave radar as claimed in claim 4, wherein: The step of generating trajectory point sequences of multiple static targets according to trajectory point data belonging to the same static target and trajectory point data belonging to different static targets comprises: Determine the trajectory point data of the same static target identifier according to the static target identifier; Determine the distance between trajectory points of adjacent timestamps according to the timestamps corresponding to the trajectory point data of the same static target identification; The trajectory point data belonging to the same static target and the trajectory point data belonging to different static targets are determined according to the distances between the trajectory points of adjacent time stamps, and trajectory point sequences of multiple static targets are generated.

6. The method for calibrating the external parameters of a millimeter-wave radar as claimed in claim 5, wherein: The step of determining the trajectory point data belonging to the same static target and the trajectory point data belonging to different static targets according to the distances between the trajectory points of adjacent timestamps, and generating trajectory point sequences of multiple static targets comprises: If the distance between the trajectory points of adjacent timestamps is greater than a preset distance threshold, it is determined that the trajectory points of adjacent timestamps belong to trajectory point data of different static targets, and are added to the trajectory point sequences of different static targets respectively; Otherwise, it is determined that the trajectory points of adjacent time stamps belong to the trajectory point data of the same static target, and are added to the trajectory point sequence of the same static target.

7. The method for calibrating the external parameters of a millimeter-wave radar as claimed in claim 1, wherein: The step of calibrating the heading angle from the millimeter wave radar to the vehicle body according to the trajectory point sequence of multiple static targets to obtain the calibrated heading angle includes: Calculating the heading angles from the millimeter wave radar to the vehicle body respectively according to the trajectory point sequences of multiple static targets to obtain multiple heading angles; The calibrated heading angle is calculated according to multiple heading angles.

8. An external parameter calibration device for millimeter wave radar, wherein: The external parameter calibration device of the millimeter wave radar comprises: An acquisition unit, used to acquire perception data of a millimeter-wave radar on a vehicle; An extraction unit, used to extract static target data according to the perception data of the millimeter wave radar and the vehicle speed; A generating unit, configured to generate trajectory point sequences of a plurality of static targets according to the static target data; A calibration unit, used for calibrating the heading angle from the millimeter wave radar to the vehicle body according to the trajectory point sequence of multiple static targets to obtain a calibrated heading angle; The output unit is used to output the final external parameter of the millimeter wave radar to the vehicle body according to the calibrated heading angle.

9. An electronic device, comprising: processor; And a memory arranged to store computer executable instructions, which, when executed, cause the processor to execute the external parameter calibration method of the millimeter wave radar according to any one of claims 1 to 7.

10. A computer program product, comprising a computer program or an instruction, wherein when the computer program or the instruction is executed by a processor, the method for calibrating the external parameters of the millimeter-wave radar according to any one of claims 1 to 7 is implemented.

Images