Self-calibration method, device, equipment and medium for installation error of vehicle-mounted millimeter-wave radar

Abstract

This application provides embodiments of a method, apparatus, device, and medium for self-calibration of installation errors of vehicle-mounted millimeter-wave radar. The method includes real-time acquisition of vehicle motion state information and single-frame point information detected by the millimeter-wave radar; filtering based on the vehicle motion state information and single-frame point information to determine valid frames; filtering the valid frames to determine valid points; calculating the single-frame angle deviation based on the valid points; fitting the single-frame angle deviation to generate a single-frame deviation fitting result; and fitting multi-frame angle deviations based on the single-frame deviation fitting result to generate a self-calibration value for installation errors. In this way, efficient self-calibration can be performed even when there are stationary targets on both sides of the road.

Description

Technical Field

[0001] The embodiments of this application relate to the field of vehicle-mounted millimeter-wave radar, and more particularly to a method, apparatus, device, and medium for self-calibrating installation errors of vehicle-mounted millimeter-wave radar. Background Technology

[0002] With the continuous development of autonomous driving technology, automotive millimeter-wave radar is being used more and more widely in target tracking and detection, vehicle alarms, and scene recognition, thus placing increasingly higher demands on the accuracy of radar target detection. During driving, radar may be subjected to collisions, compression, bumps, etc., over a long period of use, causing the radar installation angle to shift. If the user cannot detect and recalibrate it in time, it will reduce the accuracy of radar target detection, affecting the radar's ability to detect and track targets. For the radar system, this can easily lead to false alarms and missed alarms, posing significant safety hazards during vehicle operation.

[0003] Existing self-calibration methods for vehicle-mounted millimeter-wave radar installation errors involve joint calibration of the millimeter-wave radar with other sensors, effectively fusing information from other sensors with the high-precision distance and velocity data from the millimeter-wave radar. However, this method is heavily reliant on other sensors and is not suitable for vehicle systems using only a single sensor. In addition, there is a self-calibration method based on guardrail recognition. This method determines the radar offset angle by fitting guardrails to the road surface and calculating their deflection angle in the vehicle's coordinate system. This method has high requirements for road guardrails and requires complex matrix calculations. Therefore, there is an urgent need for a technology that can perform efficient self-calibration even when there are stationary targets on both sides of the road. Summary of the Invention

[0004] According to embodiments of this application, a method, apparatus, device, and medium for self-calibration of installation error of vehicle-mounted millimeter-wave radar are provided, which can perform efficient self-calibration when there are stationary targets on both sides of the road.

[0005] In a first aspect of this application, a self-calibration method for installation error of an on-board millimeter-wave radar is provided. The method includes:

[0006] Real-time acquisition of vehicle motion status information and single-frame point information detected by millimeter-wave radar;

[0007] Based on the vehicle motion state information and the single-frame spot information, a filtering process is performed to determine the valid single-frame.

[0008] Perform spot filtering processing on the single valid frame to determine the valid spots;

[0009] The single-frame angle deviation of the single effective frame is calculated based on the effective points.

[0010] Based on the single-frame angle deviation, a single-frame angle deviation fitting is performed to generate a single-frame deviation fitting result.

[0011] Based on the single-frame deviation fitting results, multi-frame angle deviation fitting is performed to generate installation error self-calibration values.

[0012] In one possible implementation, the step of filtering based on the vehicle motion state information and the single-frame point information to determine the valid single frame includes:

[0013] The criteria for determining valid frames include vehicle speed criteria, straight-ahead criteria, and number of points criteria.

[0014] Determine whether the vehicle's motion state and the single-frame tracking information meet the three conditions in the valid frame judgment criteria;

[0015] If the vehicle's motion state and the single-frame tracking information satisfy the three conditions in the valid frame judgment criteria, then the current frame is determined to be a valid single-frame frame.

[0016] If the vehicle's motion state and the single-frame tracking information do not meet any of the three conditions in the valid frame judgment criteria, then the current frame is determined to be an invalid frame.

[0017] In one possible implementation, performing a point filtering process on the single valid frame to determine valid points includes:

[0018] Obtain the absolute velocity, distance, and filtering criteria of the dots in the single valid frame;

[0019] Based on the absolute velocity of the dots, the distance between the dots, and the filtering criteria, the single frame of valid frames is subjected to dot filtering processing to generate dot filtering results.

[0020] Valid dots are determined based on the dots filtering results.

[0021] In one possible implementation, calculating the single-frame angle deviation of the single-frame valid frame based on the valid point trace includes:

[0022] Data extraction is performed on the vehicle motion state information and the single-frame spot information to obtain the vehicle speed and the relative radial velocity of the effective spot.

[0023] Calculate the ratio of the radial velocity of the dot to the vehicle speed to obtain the velocity ratio;

[0024] The inverse cosine of the speed ratio is used to obtain the angle between the effective point and the vehicle coordinate system.

[0025] Obtain the radar point angle and radar installation angle of the effective point in the radar coordinate system;

[0026] Based on the transformation relationship between the radar coordinate system and the vehicle coordinate system and the radar installation angle, the radar spot angle is converted into the vehicle spot angle.

[0027] The single-frame angle deviation of the effective single-frame is calculated based on the included angle and the vehicle spot angle.

[0028] In one possible implementation, the step of fitting the single-frame angle deviation based on the single-frame angle deviation to generate the single-frame deviation fitting result includes:

[0029] Obtain a point filtering strategy, and filter out close-range points from the valid points based on the point filtering strategy;

[0030] The average deviation difference between the near-distance point trace and the effective point trace is calculated based on the single-frame angle deviation.

[0031] The road slope is determined based on the average deviation difference.

[0032] Based on the road slope, pitch angle deviation compensation is performed on the single-frame angle deviation to generate a compensated single-frame deviation.

[0033] Obtain the deviation range;

[0034] Based on the compensated single-frame deviation and the deviation range, determine the deviation interval with the largest number of deviations;

[0035] Based on the compensated single-frame deviation, the average deviation between the deviation interval and the adjacent interval is calculated to generate a single-frame deviation fitting result.

[0036] In one possible implementation, the step of performing multi-frame angle deviation fitting based on the single-frame deviation fitting result to generate installation error self-calibration values ​​includes:

[0037] Based on preset verification conditions, the target frame corresponding to the single-frame deviation fitting result is verified twice to filter out the target valid frame and the target invalid frame.

[0038] The target frames are grouped according to a preset time window to generate target frame groups;

[0039] Determine whether there are multiple consecutive invalid target frames within the target frame group;

[0040] If there are no consecutive invalid target frames, then the average value of the single-frame deviation fitting results of all valid target frames in the target frame group is calculated as the single-group angle deviation.

[0041] The installation error self-calibration value is generated based on the single set of angle deviations.

[0042] In one possible implementation, generating the installation error self-calibration value based on the single set of angular deviations includes:

[0043] Calculate the difference in angle deviation between the current effective target frame group and the previous effective target frame group;

[0044] Obtain the difference threshold;

[0045] When the difference in angle deviation of a single group is less than the difference threshold, the current valid target frame group is marked as a qualified group;

[0046] When a predetermined number of consecutive qualified groups are obtained, the mean value of the angle deviation of a single group of the predetermined number of qualified groups is calculated, and the mean value is used as the self-calibration value of the installation error.

[0047] In a second aspect of this application, a self-calibration device for mounting error of a vehicle-mounted millimeter-wave radar is provided. The device includes:

[0048] The status point acquisition module is used to acquire real-time vehicle motion status information and single-frame point information detected by millimeter-wave radar;

[0049] The single-frame valid filtering module is used to filter and process the vehicle motion state information and the single-frame spot information to determine the valid single frames;

[0050] The valid point determination module is used to perform point filtering processing on the single valid frame to determine the valid points.

[0051] The single-frame deviation calculation module is used to calculate the single-frame angle deviation of the effective frame based on the effective point trace;

[0052] The single-frame deviation fitting module is used to perform single-frame angle deviation fitting based on the single-frame angle deviation and generate single-frame deviation fitting results.

[0053] The self-calibration value generation module is used to perform multi-frame angle deviation fitting based on the single-frame deviation fitting result to generate installation error self-calibration values.

[0054] In a third aspect of this application, an electronic device is provided. The electronic device includes a memory and a processor, wherein the memory stores a computer program, and the processor executes the program to implement the method described above.

[0055] In a fourth aspect of this application, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, implements the method according to the first aspect of this application.

[0056] The self-calibration method for installation error of vehicle-mounted millimeter-wave radar provided in this application achieves efficient self-calibration of installation error in a single millimeter-wave radar system by relying solely on stationary targets through a multi-level screening and fitting mechanism. By dual screening of vehicle motion state and point trace information, it ensures that the data used for calibration originates from scenarios where the vehicle is stable and has sufficient stationary reference objects, providing reliable input for subsequent calculations. Then, by filtering at the point trace level based on speed and distance, the influence of moving targets and distant interference points on calibration accuracy is eliminated. Next, an angle calculation model is constructed based on the cosine relationship between radial velocity and vehicle speed, and accurate angle deviation values ​​are obtained through coordinate system transformation to avoid complex matrix operations and significantly improve computational efficiency. Furthermore, road slope is identified by comparing the deviations of near-range points and global points, and a pitch angle compensation mechanism is introduced to effectively overcome the interference of uneven road surfaces on calibration results. Interval statistical methods are used to filter deviation concentration intervals, effectively suppressing the interference of abnormal points on single-frame results. Finally, the robustness and reliability of the output results are ensured through temporal fitting and stability judgment of multi-frame data. Therefore, real-time, accurate, and efficient self-calibration of installation errors can be achieved using only stationary road targets, significantly improving the adaptability and reliability of single millimeter-wave radar systems in complex road environments.

[0057] It should be understood that the description in the Summary Section is not intended to limit the key or essential features of the embodiments of this application, nor is it intended to restrict the scope of this application. Other features of this application will become readily apparent from the following description. Attached Figure Description

[0058] The above and other features, advantages, and aspects of the embodiments of this application will become more apparent from the accompanying drawings and the following detailed description. In the drawings, the same or similar reference numerals denote the same or similar elements, wherein:

[0059] Figure 1 A flowchart of a self-calibration method for installation error of vehicle-mounted millimeter-wave radar according to an embodiment of this application;

[0060] Figure 2 A block diagram of a vehicle-mounted millimeter-wave radar installation error self-calibration device according to an embodiment of this application;

[0061] Figure 3 This is a schematic diagram of the structure of a terminal device or server suitable for implementing the embodiments of this application. Detailed Implementation

[0062] To make the objectives, technical solutions, and advantages of the embodiments of this disclosure clearer, the technical solutions of the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this disclosure, and not all embodiments. Based on the embodiments of this disclosure, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this disclosure.

[0063] Furthermore, the term "and / or" in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Additionally, the character " / " in this article generally indicates that the preceding and following related objects have an "or" relationship.

[0064] Figure 1 A flowchart of a self-calibration method for installation error of vehicle-mounted millimeter-wave radar according to an embodiment of the present disclosure is shown.

[0065] like Figure 1 As shown, the main process of this method is described below (steps S101 to S106):

[0066] Step S101: Real-time acquisition of vehicle motion status information and single-frame point information detected by millimeter-wave radar.

[0067] In some embodiments, the vehicle motion state information is information generated by the vehicle itself during the vehicle's operation, including but not limited to the vehicle speed and the rate of change of the vehicle's yaw angle during the operation. The single-frame point information detected by the millimeter-wave radar is the target situation within the radar detection range, including but not limited to the number of targets and the target position.

[0068] Step S102: Based on the vehicle's motion state information and single-frame point information, perform filtering processing to determine the valid single-frame.

[0069] For step S102, the valid frame judgment criteria are obtained, which include vehicle speed judgment criteria, straight-ahead judgment criteria, and number of points judgment criteria. It is determined whether the vehicle motion state and single-frame point information meet the three conditions in the valid frame judgment criteria. If the vehicle motion state and single-frame point information meet the three conditions in the valid frame judgment criteria, the current frame is determined to be a valid single frame. If the vehicle motion state and single-frame point information do not meet any of the three conditions in the valid frame judgment criteria, the current frame is determined to be an invalid frame.

[0070] In some embodiments, the vehicle speed determination criterion is whether the vehicle speed is above a certain speed, such as 20 km / h. The straight-ahead determination criterion is to determine whether the vehicle is in a straight-ahead state based on the rate of change of the vehicle's yaw angle, for example, the rate of change of the vehicle's yaw angle is less than 0.05 rad / s. The dot count determination criterion is the number of stationary targets within the radar detection range, mainly determining whether the number of stationary targets within the radar detection range is sufficient, for example, requiring a total dot count of more than 10 in a single frame. If all the above conditions are met, the current frame is determined to be a valid single frame and further calculation processing is required. If any one condition is not met, the current frame is determined to be a valid single frame and no further calculation processing is performed.

[0071] Step S103: Perform spot filtering processing on the single valid frame to determine the valid spots.

[0072] For step S103, the absolute velocity, distance, and filtering criteria of the dots in a single valid frame are obtained; the dots in the single valid frame are filtered based on the absolute velocity, distance, and filtering criteria to generate the dots filtering results; and the valid dots are determined based on the dots filtering results.

[0073] In some embodiments, the selection of valid dots is based on two criteria: absolute velocity and distance. Each criterion has a corresponding selection method. For example, absolute velocity filtering removes moving dots with a velocity exceeding 1 m / s, while distance filtering removes distant dots, such as those beyond 10 m horizontally or 20 m vertically. After filtering, the final valid dots are obtained. It should be noted that the selection criteria need to be set according to actual needs; the above is merely an illustrative example for ease of understanding, and specific values ​​are not limited here.

[0074] Step S104: Calculate the single-frame angle deviation of the single-frame valid frame based on the valid point traces.

[0075] For step S104, data extraction is performed on the vehicle motion state information and single-frame point information to obtain the vehicle speed and relative radial velocity of the valid point; the ratio of the relative radial velocity of the point to the vehicle speed is calculated to obtain the speed ratio; the inverse cosine of the speed ratio is calculated to obtain the angle between the valid point and the vehicle coordinate system; the radar point angle and radar installation angle of the valid point in the radar coordinate system are obtained; based on the transformation relationship between the radar coordinate system and the vehicle coordinate system and the radar installation angle, the radar point angle is converted into the vehicle point angle; the single-frame angle deviation of the single-frame valid frame is calculated based on the angle and the vehicle point angle.

[0076] In some embodiments, after filtering the valid points, the filtered valid points are traversed to calculate the single-frame angle deviation. The single-frame angle deviation is calculated by calculating the relative radial velocity of the points measured by radar. And the actual speed of the vehicle There exists a cosine relationship between them: ,in, This refers to the angle between the valid point and the vehicle coordinate system. The specific calculation steps for the single-frame angle deviation are as follows:

[0077] First, calculate the ratio of the relative radial velocity of the dot to the vehicle's speed to obtain the velocity ratio. , ;

[0078] Next, the inverse cosine of the speed ratio is calculated to determine the angle between the target point and the vehicle coordinate system. , ;

[0079] Then, the radar point angle and radar installation angle in the radar coordinate system are obtained for the valid points, and the angle values ​​of the radar points are transformed from the radar coordinate system to the vehicle coordinate system. ,in, For the vehicle's tracking angle. For radar spot angle, The installation angle for the radar;

[0080] Finally, the single-frame angle deviation of the effective frame is calculated based on the included angle and the vehicle spot angle. , .

[0081] Step S105: Perform single-frame angle deviation fitting based on single-frame angle deviation to generate single-frame deviation fitting results.

[0082] For step S105, the point selection strategy is obtained, and close-range points are selected from the valid points based on the point selection strategy; the average deviation difference between close-range points and valid points is calculated based on the single-frame angle deviation; the road slope is determined based on the average deviation difference; the pitch angle deviation of the single-frame is compensated based on the road slope to generate a compensated single-frame deviation; the deviation interval range is obtained; the deviation interval with the most deviations is determined based on the compensated single-frame deviation and the deviation interval range; the average deviation between the deviation interval and the adjacent interval is calculated based on the compensated single-frame deviation to generate a single-frame deviation fitting result.

[0083] In some embodiments, after calculating the single-frame angle deviation of each valid point, single-frame angle deviation fitting is performed. Single-frame angle deviation fitting includes four main parts: road slope judgment, pitch angle deviation compensation, point error range screening, and result calculation.

[0084] Road gradient assessment refers to determining whether the vehicle is currently on an uphill or downhill section of road. Since roads traveled by vehicles are not always flat, slopes can affect the radar's elevation angle. The radar is no longer parallel to the ground, thus affecting the radar's angle measurement results and leading to inaccurate angle calculations. The specific method for assessing road conditions is as follows:

[0085] Close-range markers are those that are relatively close to the radar. The marker selection strategy is to set up a target example; markers within the target example are considered close-range markers. For example, markers with a distance of less than 10 meters are considered close-range markers, and the number of close-range markers is recorded. and deviation value ; Calculate the average deviation of nearby dots Calculate the average deviation of all valid dots. If the number of valid dots is... ,but ; Calculate the difference between the nearest point and the average deviation of all valid points. , If the average deviation difference is positive, it indicates that the road section is downhill; otherwise, it is uphill.

[0086] Pitch angle deviation compensation refers to the process of compensating for the angle deviation in a single frame after the road slope condition assessment is completed. Changes in pitch angle caused by uphill or downhill sections will affect the angle deviation in a single frame, and this effect needs to be compensated for. If the road section is judged to be uphill, the single-frame angle deviation compensation value is... ,in, The distance to the farthest point among all valid points. The distance to the farthest point among all nearby points. The compensation coefficient can be determined based on the specific radar installation height and angle, for example... After calculating the single-frame angle deviation compensation value, the pitch angle deviation is compensated for the single-frame angle deviation using the single-frame angle deviation compensation value to obtain the compensated single-frame deviation.

[0087] The point error range filtering selects the interval with the highest single-point error value. The deviation interval is divided into [-5, -3], [-3, -1], [-1, 1], [1, 3], and [3, 5]. After dividing the intervals, the number of valid point errors falling within each interval is recorded. and deviation angle .

[0088] The result is calculated by selecting the deviation interval with the most deviations, and recording the compensated single-frame deviation and the total number of valid points falling within this deviation interval and the intervals to its left and right. The average deviation of the dots within this deviation range. As the final result of the calculation for this frame, namely the single-frame deviation fitting result, it should be noted that if it is an uphill or downhill road section, an angle deviation compensation value needs to be added. If it is a normal road, the single-frame angle deviation will be directly used for calculation. That is, when the road is a normal road, all the compensation single-frame deviations in the above processing steps will be replaced with single-frame angle deviations.

[0089] Step S106: Perform multi-frame angle deviation fitting based on the single-frame deviation fitting result to generate installation error self-calibration value.

[0090] For step S106, a secondary verification is performed on the target frame corresponding to the single-frame deviation fitting result based on preset verification conditions to filter out the target valid frames and target invalid frames; the target frames are grouped according to a preset time window to generate a target frame group; it is determined whether there are multiple consecutive target invalid frames in the target frame group; if there are no multiple consecutive target invalid frames, the average value of the single-frame deviation fitting result of all target valid frames in the target frame group is calculated as the single-group angle deviation; and an installation error self-calibration value is generated based on the single-group angle deviation.

[0091] In some embodiments, after calculating the single-frame deviation fitting result, multi-frame angle deviation fitting is performed. Multi-frame angle deviation fitting includes valid frame judgment, single-group angle deviation calculation, single-group validity judgment, and result calculation.

[0092] The valid frame determination involves assessing the reliability of the single-frame deviation fitting result calculated for each frame. Preset verification conditions include: whether the number of valid points in the town meets a preset value (e.g., does it exceed 5); and whether the vehicle's movement in the target frame is stable, without sudden acceleration or deceleration. Specifically, this is achieved by calculating the vehicle speed difference between the current target frame and the previous target frame. If the difference is greater than a preset difference, the target frame is considered invalid; otherwise, it is considered valid. It should be noted that the specific values ​​of the preset value and the preset difference need to be set according to actual needs and are not specifically limited here.

[0093] The target frames are grouped according to a preset time window. For example, using three seconds as a standard, all target frames within three seconds are divided into a group, generating a target frame group containing multiple frames of data. The validity of the data within a single target frame group is determined. If a single target frame group contains multiple consecutive invalid target frames, the data for that target frame group is invalid; otherwise, it is considered valid. If a single target frame group is valid, the average deviation of all valid target frames within that group is calculated. The calculation result is used as the single-group angle deviation of the target frame group. Then, an installation error self-calibration value is generated based on the single-group angle deviation.

[0094] Furthermore, generating installation error self-calibration values ​​based on single-group angle deviations includes: calculating the difference between the single-group angle deviations of the current valid target frame group and the previous valid target frame group; obtaining a difference threshold; when the single-group angle deviation difference is less than the difference threshold, marking the current valid target frame group as a qualified group; when a consecutive preset number of qualified groups are obtained, calculating the average of the single-group angle deviations of the consecutive preset number of qualified groups, and using the average as the installation error self-calibration value.

[0095] When calculating the installation error self-calibration, the difference in single-group angle deviation between the current valid target frame group and the previous valid target frame group is first calculated. If the difference in single-group angle deviation is greater than the difference threshold, the current valid target frame group is classified as an invalid group, and the self-calibration fails, requiring a re-performance. Conversely, if the difference in single-group angle deviation is less than or equal to the difference threshold, the current valid target frame group is classified as a qualified group. If a preset number of consecutive current valid target frame groups are classified as qualified groups, the average of the single-group angle deviations of these preset number of qualified groups is calculated, and the calculated average is output as the final installation angle deviation result. It should be noted that the actual data for the preset number and the difference threshold need to be set according to requirements, and no specific limitations are made here.

[0096] According to the embodiments of this disclosure, the following technical effects are achieved: Through a multi-level screening and fitting mechanism, efficient self-calibration of installation errors can be completed using only stationary targets in a single millimeter-wave radar system. Dual screening of vehicle motion state and point trace information ensures that the data used for calibration originates from scenarios where the vehicle is stable and has sufficient stationary reference objects, providing reliable input for subsequent calculations. Then, point trace-level speed and distance screening eliminates the influence of moving targets and distant interference points on calibration accuracy. Next, an angle calculation model is constructed based on the cosine relationship between radial velocity and vehicle speed, and accurate angle deviation values ​​are obtained through coordinate system transformation to avoid complex matrix operations and significantly improve computational efficiency. Furthermore, road slope is identified by comparing the deviations of near-range and global points, and a pitch angle compensation mechanism is introduced to effectively overcome the interference of uneven road surfaces on calibration results. Interval statistical methods are used to screen for concentrated deviation intervals, effectively suppressing the interference of abnormal points on single-frame results. Finally, time-series fitting and stability judgment of multi-frame data ensure the robustness and reliability of the output results. Therefore, real-time, accurate, and efficient self-calibration of installation errors can be achieved using only stationary road targets, significantly improving the adaptability and reliability of single millimeter-wave radar systems in complex road environments.

[0097] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, as some steps may be performed in other orders or simultaneously according to this application. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily essential to this application.

[0098] The above is an introduction to the method embodiments. The following describes the solution of this application further through device embodiments.

[0099] Figure 2 A block diagram of a vehicle-mounted millimeter-wave radar installation error self-calibration device 200 according to an embodiment of this application is shown, as follows: Figure 2 The following are included:

[0100] The status point acquisition module 201 is used to acquire the vehicle's motion status information and single-frame point information detected by millimeter-wave radar in real time.

[0101] The single-frame valid filtering module 202 is used to perform filtering based on the vehicle's motion state information and single-frame point information to determine the valid single-frame.

[0102] The valid point determination module 203 is used to perform point filtering processing on a single valid frame to determine valid points.

[0103] The single-frame deviation calculation module 204 is used to calculate the single-frame angle deviation of a single effective frame based on the effective point traces.

[0104] The single-frame deviation fitting module 205 is used to perform single-frame angle deviation fitting based on single-frame angle deviation and generate single-frame deviation fitting results.

[0105] The self-calibration value generation module 206 is used to perform multi-frame angle deviation fitting based on the single-frame deviation fitting result to generate installation error self-calibration values.

[0106] As an optional implementation of this embodiment, the single-frame valid filtering module 202 is specifically used to obtain valid frame judgment criteria, wherein the valid frame judgment criteria include vehicle speed judgment criteria, straight-ahead judgment criteria, and number of points judgment criteria; to determine whether the vehicle motion state and single-frame point information meet the three conditions in the valid frame judgment criteria; if the vehicle motion state and single-frame point information meet the three conditions in the valid frame judgment criteria, then the current frame is determined to be a single-frame valid frame; if the vehicle motion state and single-frame point information do not meet any of the three conditions in the valid frame judgment criteria, then the current frame is determined to be an invalid frame.

[0107] As an optional implementation of this embodiment, the effective spot determination module 203 is specifically used to obtain the absolute velocity, spot distance and filtering criteria of the spot in a single effective frame; perform spot filtering processing on the single effective frame based on the absolute velocity, spot distance and filtering criteria to generate spot filtering results; and determine the effective spot based on the spot filtering results.

[0108] As an optional implementation of this embodiment, the single-frame deviation calculation module 204 is specifically used to extract data from the vehicle's motion state information and single-frame point information to obtain the vehicle speed and the relative radial velocity of the valid point; calculate the ratio of the relative radial velocity of the point to the vehicle speed to obtain the speed ratio; perform inverse cosine calculation on the speed ratio to obtain the angle between the valid point and the vehicle coordinate system; obtain the radar point angle and radar installation angle of the valid point in the radar coordinate system; convert the radar point angle to the vehicle point angle based on the transformation relationship between the radar coordinate system and the vehicle coordinate system and the radar installation angle; and calculate the single-frame angle deviation of the single-frame valid frame based on the angle and the vehicle point angle.

[0109] As an optional implementation of this embodiment, the single-frame deviation fitting module 205 is specifically used to obtain a point screening strategy, filter out close-range points among the valid points based on the point screening strategy; calculate the average deviation difference between close-range points and valid points based on the single-frame angle deviation; determine the road slope based on the average deviation difference; perform pitch angle deviation compensation on the single-frame angle deviation based on the road slope to generate a compensated single-frame deviation; obtain the deviation interval range; determine the deviation interval with the most deviations based on the compensated single-frame deviation and the deviation interval range; calculate the average deviation between the deviation interval and adjacent intervals based on the compensated single-frame deviation to generate a single-frame deviation fitting result.

[0110] As an optional implementation of this embodiment, the self-calibration value generation module 206 includes:

[0111] There is an invalid frame filtering module, which is used to perform secondary verification on the target frame corresponding to the single frame deviation fitting result based on preset verification conditions, and filter out the target valid frame and the target invalid frame.

[0112] The target group generation module is used to group target frames according to a preset time window to generate target frame groups;

[0113] The consecutive invalidity judgment module is used to determine whether there are multiple consecutive invalid target frames within the target frame group;

[0114] The single-frame deviation calculation module is used to calculate the average value of the single-frame deviation fitting results of all effective frames in the target frame group, as the single-frame angle deviation.

[0115] The error calibration generation module is used to generate self-calibration values ​​for installation errors based on a single set of angular deviations.

[0116] In this optional embodiment, the error calibration generation module is specifically used to calculate the difference in single-group angle deviation between the current effective target frame group and the previous effective target frame group; obtain the difference threshold; when the difference in single-group angle deviation is less than the difference threshold, mark the current effective target frame group as a qualified group; when a consecutive preset number of qualified groups are calculated, calculate the average value of the single-group angle deviation of the consecutive preset number of qualified groups, and use the average value as the installation error self-calibration value.

[0117] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working process of the described module can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0118] Figure 3 A schematic diagram of the structure of a terminal device or server suitable for implementing the embodiments of this application is shown.

[0119] like Figure 3 As shown, the terminal device or server includes a central processing unit (CPU) 301, which can perform various appropriate actions and processes according to a program stored in read-only memory (ROM) 302 or a program loaded from storage section 308 into random access memory (RAM) 303. The RAM 303 also stores various programs and data required for the operation of the terminal device or server. The CPU 301, ROM 302, and RAM 303 are interconnected via bus 304. An input / output (I / O) interface 305 is also connected to bus 304.

[0120] The following components are connected to I / O interface 305: an input section 306 including a keyboard, mouse, etc.; an output section 307 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and speakers, etc.; a storage section 308 including a hard disk, etc.; and a communication section 309 including a network interface card such as a LAN card, modem, etc. The communication section 309 performs communication processing via a network such as the Internet. A drive 310 is also connected to I / O interface 305 as needed. A removable medium 311, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on drive 310 as needed so that computer programs read from it can be installed into storage section 308 as needed.

[0121] Specifically, according to embodiments of this application, the above method flow steps can be implemented as a computer software program. For example, embodiments of this application include a computer program product comprising a computer program carried on a machine-readable medium, the computer program containing program code for performing the methods shown in the flowchart. In such embodiments, the computer program can be downloaded and installed from a network via communication section 309, and / or installed from removable medium 311. When the computer program is executed by central processing unit (CPU) 301, it performs the functions defined in the system of this application.

[0122] It should be noted that the computer-readable medium shown in this application can be a computer-readable signal medium or a computer-readable storage medium, or any combination of the two. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this application, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In this application, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media can also be any computer-readable medium other than computer-readable storage media, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wireless, wire, optical fiber, RF, etc., or any suitable combination thereof.

[0123] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0124] The units or modules described in the embodiments of this application can be implemented in software or hardware. The described units or modules can also be located in a processor. The names of these units or modules do not, in certain circumstances, constitute a limitation on the unit or module itself.

[0125] In another aspect, this application also provides a computer-readable storage medium, which may be included in the electronic device described in the above embodiments; or it may exist independently and not assembled into the electronic device. The aforementioned computer-readable storage medium stores one or more programs that, when used by one or more processors, execute the methods described in this application.

[0126] The above description is merely a preferred embodiment of this application and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of this application is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the foregoing application concept. For example, technical solutions formed by substituting the above features with (but not limited to) technical features with similar functions claimed in this application.

Claims

1. A vehicle-mounted millimeter wave radar installation error self-calibration method, characterized in that, The method comprises the following steps: real-time acquisition of vehicle motion state information and single-frame track information detected by a millimeter wave radar; screening processing based on the vehicle motion state information and the single-frame track information to determine a single-frame valid frame; and acquisition of valid frame judgment criteria, wherein the valid frame judgment criteria comprise vehicle speed judgment criteria, straight-line judgment criteria, and track quantity judgment criteria; determination of whether the vehicle motion state and the single-frame track information meet the three conditions in the valid frame judgment criteria; if the vehicle motion state and the single-frame track information meet the three conditions in the valid frame judgment criteria, the current frame is determined to be a single-frame valid frame; if the vehicle motion state and the single-frame track information do not meet any of the three conditions in the valid frame judgment criteria, the current frame is determined to be an invalid frame; track screening processing of the single-frame valid frame to determine valid tracks; calculation of single-frame angle deviation of the single-frame valid frame based on the valid tracks; single-frame angle deviation fitting based on the single-frame angle deviation to generate a single-frame deviation fitting result; multi-frame angle deviation fitting based on the single-frame deviation fitting result to generate an installation error self-calibration value.

2. The method of claim 1, wherein, The track screening processing of the single-frame valid frame to determine valid tracks comprises the following steps: acquisition of track absolute speed, track distance, and screening criteria of the single-frame valid frame; track screening processing of the single-frame valid frame based on the track absolute speed, the track distance, and the screening criteria to generate a track screening result; determination of valid tracks based on the track screening result.

3. The method of claim 1, wherein, The calculation of single-frame angle deviation of the single-frame valid frame based on the valid tracks comprises the following steps: data extraction of the vehicle motion state information and the single-frame track information to obtain vehicle speed and track relative radial speed of the valid tracks; calculation of a ratio of the track relative radial speed to the vehicle speed to obtain a speed ratio; arc-cosine calculation of the vehicle speed ratio to obtain an included angle between the valid tracks and a vehicle coordinate system; acquisition of a radar track angle and a radar installation angle of the valid tracks in a radar coordinate system; conversion of the radar track angle to a vehicle track angle based on a conversion relationship between the radar coordinate system and the vehicle coordinate system and the radar installation angle; calculation of single-frame angle deviation of the single-frame valid frame based on the included angle and the vehicle track angle.

4. The method of claim 1, wherein, The single-frame angle deviation fitting based on the single-frame angle deviation to generate a single-frame deviation fitting result comprises the following steps: acquisition of a track screening strategy, and screening of close-range tracks in the valid tracks based on the track screening strategy; calculation of an average deviation difference value of the close-range tracks and the valid tracks based on the single-frame angle deviation; determination of a road slope condition based on the average deviation difference value; pitching angle deviation compensation of the single-frame angle deviation based on the road slope condition to generate a compensated single-frame deviation; acquisition of a deviation interval range; determination of a deviation interval with the largest number of deviations based on the compensated single-frame deviation and the deviation interval range; calculation of average values of deviations of the deviation interval and adjacent intervals based on the compensated single-frame deviation to generate a single-frame deviation fitting result.

5. The method of claim 1, wherein, The multi-frame angle deviation fitting based on the single-frame deviation fitting result comprises: performing secondary verification on the target frame corresponding to the single-frame deviation fitting result based on a preset verification condition, screening out a target valid frame and a target invalid frame; grouping processing the target frame according to a preset time window, generating a target frame group; judging whether there are continuous multiple target invalid frames in the target frame group; if there are no continuous multiple target invalid frames, calculating the average value of the single-frame deviation fitting results of all target valid frames in the target frame group as a single-group angle deviation; generating an installation error self-calibration value based on the single-group angle deviation.

6. The method of claim 5, wherein, The generation of the installation error self-calibration value based on the single-group angle deviation comprises: calculating the single-group angle deviation difference value of the current valid target frame group and the last valid target frame group; obtaining a difference threshold value; when the single-group angle deviation difference value is less than the difference threshold value, marking the current valid target frame group as a qualified group; when a continuous preset number of qualified groups are calculated, calculating the average value of the single-group angle deviations of the continuous preset number of qualified groups, and taking the average value as the installation error self-calibration value.

7. A vehicle-mounted millimeter wave radar installation error self-calibration device, characterized by, comprise: a state point trail acquisition module, configured to acquire real-time self-vehicle motion state information and single-frame point trail information detected by a millimeter wave radar; a single-frame valid screening module, configured to perform screening processing based on the self-vehicle motion state information and the single-frame point trail information, determine a single-frame valid frame, and obtain a valid frame judgment standard, wherein the valid frame judgment standard comprises a vehicle speed judgment standard, a straight driving judgment standard, and a point trail number judgment standard; judging whether the self-vehicle motion state and the single-frame point trail information satisfy three conditions in the valid frame judgment standard; if the self-vehicle motion state and the single-frame point trail information satisfy the three conditions in the valid frame judgment standard, determining that the current frame is a single-frame valid frame; if the self-vehicle motion state and the single-frame point trail information do not satisfy any one of the three conditions in the valid frame judgment standard, determining that the current frame is an invalid frame; an effective point trail determination module, configured to perform point trail screening processing on the single-frame valid frame, and determine an effective point trail; a single-frame deviation calculation module, configured to calculate a single-frame angle deviation of the single-frame valid frame based on the effective point trail; a single-frame deviation fitting module, configured to perform single-frame angle deviation fitting based on the single-frame angle deviation, and generate a single-frame deviation fitting result; a self-calibration value generation module, configured to perform multi-frame angle deviation fitting based on the single-frame deviation fitting result, and generate an installation error self-calibration value.

8. An electronic device comprising a memory and a processor, said memory having stored thereon a computer program, characterized in that, The processor executes the computer program to implement the method in any one of claims 1-6.

9. A computer readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to implement the method in any one of claims 1-6.

Images