Angle determination method and device, vehicle, storage medium and program product
By periodically matching the position information of radar and visual targets and calculating the installation deviation angle, the detection accuracy problem caused by radar installation angle deviation is solved, achieving higher calibration accuracy and detection accuracy.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- XIAOMI EV TECH CO LTD
- Filing Date
- 2024-10-28
- Publication Date
- 2026-04-28
Smart Images
Figure CN121934029A_ABST
Abstract
Description
Technical Field
[0001] This disclosure relates to the field of vehicle technology, and more particularly to a method, apparatus, vehicle, storage medium, and program product for determining an angle. Background Technology
[0002] Vehicles typically carry various types of sensors, such as lidar, millimeter-wave radar, and mono / dual-lens cameras. Radar, by transmitting and receiving electromagnetic waves, can achieve high accuracy in speed and distance measurement, playing a crucial role in advanced intelligent driving systems that demand high speed. Vehicle-mounted radar has specific installation angle design requirements. Due to installation errors, the actual installation angle of the radar will deviate from the design value by a certain angle, and the magnitude of this deviation is one of the important factors directly affecting the radar's detection performance. Summary of the Invention
[0003] To overcome the problems existing in related technologies, this disclosure provides a method, apparatus, vehicle, storage medium, and program product for determining an angle.
[0004] According to a first aspect of the embodiments of the present disclosure, a method for determining an angle is provided, comprising: The first radar target detected by the radar and the first visual target detected by the image acquisition device are periodically determined. For each cycle, when the first radar target and the first visual target are matched, the target angle information is determined based on the first position information of the first radar target and the second position information of the first visual target. The target angle information represents the angle difference between the first radar target and the first visual target. The installation angle of the radar is determined based on the target angle information determined over multiple cycles.
[0005] Optionally, the method further includes: Acquire the first feature information of the first radar target and the second feature information of the first visual target; If the first feature information and the second feature information meet the preset matching conditions, the first radar target and the first visual target are determined to be matched.
[0006] Optionally, the first feature information includes a first motion state and a first type, and the second feature information includes a second motion state and a second type; The preset matching conditions include: The first type is the same as the second type; and / or, The difference between the first motion state and the second motion state is less than a preset threshold.
[0007] Optionally, the method further includes: If the first radar target and the first visual target are not updated, the first information set corresponding to the first radar target and the first visual target is updated according to the target angle information; If the first radar target and the first visual target are updated, a second information set corresponding to the updated first radar target and the updated first visual target is created, and the target angle information is added to the second information set.
[0008] Optionally, updating the first information set corresponding to the first radar target and the first visual target based on the target angle information includes: If the number of angle information items included in the first information set is less than a first preset threshold, the target angle information is added to the first information set; or... If the number of angle information items in the first information set is greater than or equal to the first preset threshold, delete the angle information item that was added earliest in the first information set, and add the target angle information item to the first information set.
[0009] Optionally, the first radar target and the first visual target each include multiple targets, and each set of matched first radar targets and first visual targets corresponds to an information set; determining the installation angle of the radar based on the target angle information determined within multiple periods includes: Determine the angle calibration information of the information set based on the angle information of each information set; Target calibration information is determined from multiple angle calibration information based on the first preset filtering conditions; The installation offset angle is determined based on the target calibration information.
[0010] Optionally, determining the angle calibration information of the information set based on the angle information in each information set includes: The mean of all angle information in the information set is used as the angle calibration information; or... The median of all angle information in the information set is used as the angle calibration information.
[0011] Optionally, the first preset filtering condition includes: the number of angle information in the information set corresponding to the angle calibration information is greater than a second preset quantity threshold.
[0012] Optionally, the periodic determination of the first radar target detected by the radar and the first visual target detected by the image acquisition device includes: The radar target that is closest to the second radar target detected by the radar is taken as the first radar target; The closest visual target among the second visual targets detected by the image acquisition device is taken as the first visual target.
[0013] Optionally, both the first radar target and the first visual target satisfy a second preset screening condition, which includes at least one of the following: The target is located within a preset area around the vehicle; The target's speed is less than a preset speed threshold; The target type is the specified type.
[0014] According to a second aspect of the present disclosure, an angle determining device is provided, comprising: The first determining module is configured to periodically determine the first radar target detected by the radar and the first visual target detected by the image acquisition device. The second determining module is configured to, for each cycle, in the case of a first radar target and a first visual target matching, determine target angle information based on the first position information of the first radar target and the second position information of the first visual target, wherein the target angle information represents the angle difference between the first radar target and the first visual target; The third determining module is configured to determine the installation angle of the radar based on the target angle information determined over multiple periods.
[0015] Optionally, the device further includes: The acquisition module is configured to acquire first feature information of the first radar target and second feature information of the first visual target; The fourth determining module is configured to determine that the first radar target and the first visual target match when the first feature information and the second feature information meet preset matching conditions.
[0016] Optionally, the first feature information includes a first motion state and a first type, and the second feature information includes a second motion state and a second type; The preset matching conditions include: The first type is the same as the second type; and / or, The difference between the first motion state and the second motion state is less than a preset threshold.
[0017] Optionally, the device further includes: The update module is configured to update the first information set corresponding to the first radar target and the first visual target based on the target angle information when the first radar target and the first visual target have not been updated; or, The creation module is configured to, when the first radar target and the first visual target are updated, create a second information set corresponding to the updated first radar target and the updated first visual target, and add the target angle information to the second information set.
[0018] Optionally, the update module is configured as follows: If the number of angle information items included in the first information set is less than a first preset threshold, the target angle information is added to the first information set; or... If the number of angle information items in the first information set is greater than or equal to the first preset threshold, delete the angle information item that was added earliest in the first information set, and add the target angle information item to the first information set.
[0019] Optionally, the first radar target and the first visual target each include multiple targets, and each set of matched first radar targets and first visual targets corresponds to an information set; the third determining module is configured to: Determine the angle calibration information of the information set based on the angle information of each information set; Target calibration information is determined from multiple angle calibration information based on the first preset filtering conditions; The installation offset angle is determined based on the target calibration information.
[0020] Optionally, the third determining module is configured as follows: The mean of all angle information in the information set is used as the angle calibration information; or... The median of all angle information in the information set is used as the angle calibration information.
[0021] Optionally, the first preset filtering condition includes: the number of angle information in the information set corresponding to the angle calibration information is greater than a second preset quantity threshold.
[0022] Optionally, the first determining module is configured to: The radar target that is closest to the second radar target detected by the radar is taken as the first radar target; The closest visual target among the second visual targets detected by the image acquisition device is taken as the first visual target.
[0023] Optionally, both the first radar target and the first visual target satisfy a second preset screening condition, which includes at least one of the following: The target is located within a preset area around the vehicle; The target's speed is less than a preset speed threshold; The target type is the specified type.
[0024] According to a third aspect of the present disclosure, a vehicle is provided, comprising: processor; Memory used to store processor-executable instructions; The processor is configured to execute the computer program in the memory to implement the steps of the method described in the first aspect of the present disclosure.
[0025] According to a fourth aspect of the present disclosure, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, implements the steps of the method described in the first aspect of the present disclosure.
[0026] According to a fifth aspect of the present disclosure, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps of the method described in the first aspect of the present disclosure.
[0027] The technical solutions provided by the embodiments of this disclosure can include the following beneficial effects: This disclosure periodically determines a first radar target detected by the radar and a first visual target detected by the image acquisition device. For each period, when the first radar target and the first visual target match, target angle information is determined based on the first position information of the first radar target and the second position information of the first visual target. The target angle information represents the angle difference between the first radar target and the first visual target. Then, based on the target angle information determined within multiple periods, the installation angle of the radar is determined. This disclosure continuously acquires the first radar target and the first visual target for multiple periods. Based on the target angle information corresponding to multiple periods, the installation angle can be determined more accurately, avoiding the problem of inaccurate installation angle determination due to large errors in a single detection data. Furthermore, for each period, the target angle information is further determined only when the first radar target and the first visual target match, avoiding the problem of angle mismeasurement due to mismatch between the first radar target and the first visual target, ensuring the accuracy of each target angle information, thereby further improving the accuracy of the installation angle.
[0028] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description
[0029] The accompanying drawings, which are incorporated in and form a part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure.
[0030] Figure 1This is a flowchart illustrating a method for determining an angle according to an exemplary embodiment.
[0031] Figure 2 It is based on Figure 1 A schematic diagram of a deflection angle is shown in the embodiment.
[0032] Figure 3 This is a flowchart illustrating another method for determining an angle according to an exemplary embodiment.
[0033] Figure 4 This is a flowchart illustrating another method for determining an angle according to an exemplary embodiment.
[0034] Figure 5 This is a flowchart illustrating another method for determining an angle according to an exemplary embodiment.
[0035] Figure 6 This is a block diagram illustrating an angle determining device according to an exemplary embodiment.
[0036] Figure 7 This is a block diagram illustrating another angle determining device according to an exemplary embodiment.
[0037] Figure 8 This is a block diagram illustrating another angle determining device according to an exemplary embodiment.
[0038] Figure 9 This is a block diagram illustrating a vehicle according to an exemplary embodiment. Detailed Implementation
[0039] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numerals in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this disclosure. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this disclosure as detailed in the appended claims.
[0040] Before introducing the method, apparatus, vehicle, storage medium, and program product for determining an angle shown in the embodiments of this disclosure, the application scenarios of the embodiments of this disclosure will be introduced first.
[0041] In the field of vehicle technology, the compensation for the installation angle of radar is called calibration. Common radar calibration methods include pre-departure calibration, after-sales calibration performed at dealerships, and online calibration during vehicle operation. Different radar detection performance and calibration methods result in varying levels of calibration accuracy. This disclosure primarily applies to the field of online calibration during vehicle operation.
[0042] In related technologies, online radar calibration schemes typically involve constructing a geometric or physical model in three-dimensional space when the radar is installed at an angle. Formulas are then derived to calculate the radar's installation angle and its relationship to ranging, velocity, and angle measurements of stationary point clouds in three-dimensional space. Finally, the calibration angle result is obtained by statistically analyzing the calibration angle results from a large number of stationary point cloud datasets. However, this method is limited by the radar's inherently low angle measurement accuracy and interference from numerous radar scattering points, resulting in low calibration accuracy.
[0043] Figure 1 This is a flowchart illustrating a method for determining an angle according to an exemplary embodiment, such as... Figure 1 As shown, the method may include the following steps.
[0044] In step S101, the first radar target detected by the radar and the first visual target detected by the image acquisition device are periodically determined.
[0045] For example, the radar in this embodiment of the present disclosure can be any type of radar installed on a vehicle, such as millimeter-wave radar or ultrasonic radar, and the image acquisition device can be a camera, such as a binocular camera or a monocular camera. The sampling time of one or more image frames can be used as a period to acquire the third radar target detected by the radar and the third visual target detected by the image acquisition device. Here, the third radar target can be understood as all targets detected by the radar, and the third visual target can be understood as all targets detected by the image acquisition device. The third radar target may include at least one, and the third visual target may include at least one.
[0046] In some embodiments, the target closest to the vehicle among the third radar targets can be used as the first radar target, and the target closest to the vehicle among the third visual targets can be used as the first visual target.
[0047] In other embodiments, a fourth radar target located within a drivable area can be determined from a third radar target, and a fourth visual target located within a drivable area can be determined from a third visual target. Here, a drivable area can be understood as an area free of obstacles, ensuring normal movement of the target. Then, the target closest to the vehicle among the fourth radar targets can be designated as the first radar target, and the target closest to the vehicle among the fourth visual targets can be designated as the first visual target.
[0048] In other embodiments, a second radar target that meets preset screening criteria can be determined from a third radar target based on the target's position, speed, and type. Similarly, a second visual target whose position, speed, and type meet the preset screening criteria can be determined from a third visual target. Then, the target closest to the vehicle among the second radar targets is designated as the first radar target, and the target closest to the vehicle among the second visual targets is also designated as the first visual target.
[0049] In step S102, for each cycle, when the first radar target and the first visual target are matched, the target angle information is determined based on the first position information of the first radar target and the second position information of the first visual target.
[0050] For example, for the first radar target and the second radar target acquired in each cycle, it can first be determined whether the first radar target and the first visual target match.
[0051] In some embodiments, a first motion state of a first radar target and a second motion state of a first visual target can be acquired. The motion state may include distance to the vehicle, speed, yaw angle, etc. If the first and second motion states satisfy preset matching conditions, the first radar target and the first visual target are determined to be matched. The preset matching conditions may include: the distance difference between a first distance and a second distance is less than a preset distance threshold; the speed difference between a first speed and a second speed is less than a preset speed threshold; and the angle difference between a first yaw angle and a second yaw angle is less than a preset angle threshold.
[0052] In other embodiments, a first type of the first radar target and a second type of the first visual target can be acquired, wherein the type may include, for example, a car type, a truck type, a bus type, etc. If the first type and the second type satisfy a preset matching condition, the first radar target and the first visual target are determined to be matched. The preset matching condition may include: the first type and the second type are the same.
[0053] In other embodiments, a first motion state and a first type of a first radar target, and a second motion state and a second type of a first visual target can be acquired. If the first motion state, the second motion state, the first type, and the second type satisfy preset matching conditions, a match is determined between the first radar target and the first visual target. These preset matching conditions may include: the distance difference between a first distance and a second distance is less than a preset distance threshold; the speed difference between a first speed and a second speed is less than a preset speed threshold; the angle difference between a first yaw angle and a second yaw angle is less than a preset angle threshold; and the first type and the second type are the same.
[0054] For example, if it is determined that the first radar target and the first visual target match, then the target angle information can be determined based on the first position information of the first radar target and the second position information of the first visual target. The target angle information represents the angular difference between the first radar target and the first visual target. Thus, for each cycle, the target angle information is further determined only when the first radar target and the first visual target match, avoiding the problem of mismeasured angles due to mismatch between the first radar target and the first visual target, and ensuring the accuracy of the target angle information for each period.
[0055] Reference Figure 2 , Figure 2 The radar target detected in the image can be the first radar target. Figure 2 The camera in the image can detect targets that are first-person views. Assume that the radar's clockwise deflection angle is [value missing] from the BEV (Bird's Eye View) perspective. α The coordinates of the first radar target are ( The coordinates of the first radar target are ( The first radar target and the first visual target have a rotational transformation relationship, and the calibration compensation angle can be calculated based on this relationship. In general, the deflection angle is relatively small. To reduce the computational load, the tangent of the deflection angle is used to approximate the sine value:
[0056] For example, it can be As target perspective information, it can also be based on Calculated α and will α As target perspective information.
[0057] In step S103, the installation angle of the radar is determined based on the target angle information determined within multiple cycles.
[0058] For example, if the first radar target and the first visual target match in each cycle, a target angle information can be determined. In this way, multiple target angle information can be determined in multiple cycles, and the installation deflection angle of the radar can be obtained more accurately based on multiple target angle information.
[0059] In some embodiments, the average value of the angle differences represented by multiple target angle information can be used as the installation angle of the radar, or the median value of the angle differences represented by multiple target angle information can be used as the installation angle of the radar.
[0060] In other embodiments, each set of matched first radar targets and first visual targets may correspond to multiple periods, meaning that the first radar targets and first visual targets remain unchanged within multiple periods. For each set of matched first radar targets and first visual targets, an angle calibration information can be determined based on multiple target angle information corresponding to that set of first radar targets and first visual targets. Then, the average or median of the angle calibration information corresponding to multiple sets of first radar targets and first visual targets can be used as the installation deflection angle of the radar.
[0061] In this way, by combining the angle detected by the image acquisition device with the angle detected by the radar to determine the installation angle of the radar, the advantage of high accuracy of visual lateral position detection can be taken into account, while the inherent disadvantages of low radar angle measurement accuracy and scattering point interference can be made up for. This improves the accuracy of online calibration of radar installation angle, thereby improving the lateral accuracy of radar target detection and providing better detection input for fusion.
[0062] In summary, this disclosure continuously acquires the first radar target and the first visual target for multiple cycles. Based on the target angle information corresponding to multiple cycles, the installation offset angle can be determined more accurately, avoiding the problem of inaccurate installation offset angle determination due to large errors in a single detection data. Furthermore, for each cycle, the target angle information is further determined only when the first radar target and the first visual target match, avoiding the problem of angle mismeasurement caused by mismatch between the first radar target and the first visual target. This ensures the accuracy of the target angle information for each cycle, thereby further improving the accuracy of the installation angle.
[0063] Figure 3 This is a flowchart illustrating another method for determining an angle according to an exemplary embodiment, such as... Figure 3 As shown, the method may further include: In step S104, the first feature information of the first radar target and the second feature information of the first visual target are acquired.
[0064] For example, the first feature information may include a first motion state and a first type, and the second feature information may include a second motion state and a second type. The first motion state may include, for example, the distance between the first radar target and the vehicle, the speed of the first radar target, and the heading angle, etc. The second motion state may include, for example, the distance between the first visual target and the vehicle, the speed of the first visual target, and the heading angle, etc. The first type may characterize the type of the first radar target, and the second type may characterize the type of the first visual target. The first type or the second type may, for example, include car type, truck type, bus type, etc.
[0065] In step S105, if the first feature information and the second feature information meet the preset matching conditions, the first radar target and the first visual target are determined to be matched.
[0066] For example, preset matching conditions may include: the first type is the same as the second type, and / or the difference between the first motion state and the second motion state is less than a preset threshold.
[0067] In some embodiments, the first motion state may include a first distance between the first radar target and the vehicle, a first speed of the first radar target, a first heading angle, etc.; the second motion state may include a second distance between the first visual target and the vehicle, a second speed of the first visual target, a second heading angle; and the preset threshold may include a preset distance threshold, a preset speed threshold, and a preset angle threshold. Correspondingly, the preset matching conditions may include: the distance difference between the first distance and the second distance is less than a preset distance threshold; the speed difference between the first speed and the second speed is less than a preset speed threshold; the angle difference between the first yaw angle and the second yaw angle is less than a preset angle threshold; and the first type and the second type are the same.
[0068] Figure 4 This is a flowchart illustrating another method for determining an angle according to an exemplary embodiment, such as... Figure 4 As shown, the method may further include: In step S106, if the first radar target and the first visual target have not been updated, the first information set corresponding to the first radar target and the first visual target is updated according to the target angle information.
[0069] For example, for the first radar target and the first visual target determined in each cycle, we can first determine whether the first radar target and the first visual target have been updated based on their identifiers. If both the identifiers of the first radar target and the first visual target are the same as in the previous cycle, it means that the first radar target and the first visual target have not been updated. If at least one of the identifiers of the first radar target and the first visual target is different from that in the previous cycle, it means that the first radar target and the first visual target have been updated. There can be multiple first radar targets and first visual targets. For each set of matched first radar targets and first visual targets, there can be an information set, which can be in the form of an array.
[0070] If the first radar target and the first visual target have not been updated, the first information set corresponding to the first radar target and the first visual target can be updated based on the target angle information. For example, the size of the first information set can be a first preset threshold. If the number of angle information items included in the first information set is less than the first preset threshold, the target angle information can be added to the first information set. If the number of angle information items included in the first information set is greater than or equal to the first preset threshold, the angle information with the earliest addition time in the first information set can be deleted first, and then the target angle information can be added to the first information set. This ensures that the angle information in the first information set is the latest angle information, allowing for more accurate determination of the installation deflection angle later.
[0071] Taking the information set as an array as an example, the array can be updated using a scrolling overlay method, and the array dimension does not exceed the set dimension. If the array dimension is less than the set dimension, the target angle information can be added to the end of the array. If the array dimension is greater than or equal to the set dimension, the first element of the array can be deleted first, and then the target angle information can be added to the end of the array.
[0072] In step S107, if the first radar target and the first visual target are updated, a second information set corresponding to the updated first radar target and the updated first visual target is created, and the target angle information is added to the second information set.
[0073] For example, if the first radar target and the first visual target are updated, a second information set can be created for the updated first radar target and the updated first visual target, and the target angle information can be added to the second information set. The second information set is different from the first information set; it stores the angle information corresponding to the updated first radar target and the updated first visual target.
[0074] Accordingly, step S103 can be achieved through the following steps: In step S1031, the angle calibration information of the information set is determined based on the angle information of each information set.
[0075] For example, there may be multiple first radar targets and first visual targets. Each set of matched first radar targets and first visual targets corresponds to an information set, and each information set may include at least one angle information. For each information set, the mean of all angle information in the information set can be used as the angle calibration information, or the median of all angle information in the information set can be used as the angle calibration information.
[0076] In step S1032, target calibration information is determined from multiple angle calibration information according to the first preset screening conditions.
[0077] For example, the first preset filtering condition may include: the number of angle information in the information set corresponding to the angle calibration information is greater than the second preset number threshold.
[0078] Taking a second preset quantity threshold of 5 as an example, the information set includes information set A, information set B and information set C. Information set A includes 8 angle information, information set B includes 10 angle information and information set C includes 3 angle information. Then the angle calibration information corresponding to information set A and information set B can be used as target calibration information.
[0079] In step S1033, the installation offset angle is determined based on the target calibration information.
[0080] For example, if the target calibration information includes angle values and there is only one target calibration information, the angle values included in the target calibration information can be used as the installation deflection angle. If the target calibration information includes angle values and there are multiple target calibration information, the average value of the target calibration information can be used as the installation deflection angle, or the median value of the target calibration information can be used as the installation deflection angle.
[0081] When the target calibration information includes the sine value of the angle and there is only one target calibration information, the angle value corresponding to the target calibration information can be used as the installation deflection angle. When the target calibration information includes the sine value of the angle and there are multiple target calibration information, the average value of the angle values corresponding to the target calibration information can be used as the installation deflection angle, or the median value of the angle values corresponding to the target calibration information can be used as the installation deflection angle.
[0082] Figure 5 This is a flowchart illustrating another method for determining an angle according to an exemplary embodiment, such as... Figure 5 As shown, step S101 can be achieved through the following steps: In step S1011, the radar target closest to the second radar target detected by the radar is taken as the first radar target.
[0083] In step S1012, the closest visual target among the second visual targets detected by the image acquisition device is taken as the first visual target.
[0084] For example, it can acquire the third radar target detected by the radar and the third visual target detected by the image acquisition device in the vehicle coordinate system, as well as the position information, speed information, and identification information of the third radar target converted to the vehicle coordinate system through camera calibration extrinsic parameters, and the position information, speed information, and identification information of the third visual target converted to the vehicle coordinate system through camera calibration extrinsic parameters.
[0085] In some embodiments, since the detection accuracy of radar and image acquisition devices varies depending on the target's location, state, type, and other characteristics, to improve the accuracy of determining the installation angle, a second radar target can be first determined from the third radar targets based on a second preset screening condition, and then a second visual target can be determined from the third visual targets. The second preset screening condition includes at least one of the following: 1) the target is located within a preset range around the vehicle; 2) the target's speed is less than a preset speed threshold; 3) the target type is a specified type. The preset range may, for example, include a longitudinal range of 10-100m and a lateral range of ±1.5m, where the longitudinal range can be the vehicle's forward direction, and the lateral range can be a direction perpendicular to the vehicle's forward direction. The preset speed threshold may, for example, be 10m / s, and the specified type may, for example, be a sedan.
[0086] In other embodiments, the closest radar target among the second radar targets can be used as the first radar target, and the closest visual target among the second visual targets can be used as the first visual target. In this way, by filtering the targets detected by the radar and image acquisition devices before further determining the first radar target and the first visual target, the accuracy of the target angle information determined based on the first and second radar targets can be ensured, thereby improving the accuracy of the installation angle.
[0087] In summary, this disclosure continuously acquires the first radar target and the first visual target for multiple cycles. Based on the target angle information corresponding to multiple cycles, the installation offset angle can be determined more accurately, avoiding the problem of inaccurate installation offset angle determination due to large errors in a single detection data. Furthermore, for each cycle, the target angle information is further determined only when the first radar target and the first visual target match, avoiding the problem of angle mismeasurement caused by mismatch between the first radar target and the first visual target. This ensures the accuracy of the target angle information for each cycle, thereby further improving the accuracy of the installation angle.
[0088] Figure 6 This is a block diagram illustrating an angle determining device according to an exemplary embodiment, such as... Figure 6 As shown, the device 200 may include: The first determining module 201 is configured to periodically determine a first radar target detected by the radar and a first visual target detected by the image acquisition device.
[0089] The second determining module 202 is configured to, for each cycle, in the case of a first radar target and a first visual target being matched, determine target angle information based on the first position information of the first radar target and the second position information of the first visual target, wherein the target angle information represents the angle difference between the first radar target and the first visual target.
[0090] The third determining module 203 is configured to determine the radar's installation angle based on target angle information determined over multiple cycles.
[0091] Figure 7 This is a block diagram illustrating another angle determining device according to an exemplary embodiment, such as... Figure 7 As shown, the device 200 may further include: The acquisition module 204 is configured to acquire first feature information of the first radar target and second feature information of the first visual target.
[0092] The fourth determining module 205 is configured to determine the match between the first radar target and the first visual target when the first feature information and the second feature information meet the preset matching conditions.
[0093] In some embodiments, the first feature information includes a first motion state and a first type, and the second feature information includes a second motion state and a second type.
[0094] Preset matching conditions include: Type 1 is the same as Type 2. And / or, The difference between the first motion state and the second motion state is less than a preset threshold.
[0095] Figure 8 This is a block diagram illustrating another angle determining device according to an exemplary embodiment, such as... Figure 8 As shown, the device 200 may further include: The update module 206 is configured to update the first information set corresponding to the first radar target and the first visual target based on the target angle information when the first radar target and the first visual target have not been updated. Alternatively, The creation module 207 is configured to create a second information set corresponding to the updated first radar target and the updated first visual target when the first radar target and the first visual target are updated, and to add the target angle information to the second information set.
[0096] In other embodiments, the update module 206 is configured to: If the number of angle information items in the first information set is less than a first preset threshold, the target angle information is added to the first information set. Alternatively, If the number of angle information items in the first information set is greater than or equal to the first preset threshold, delete the angle information item that was added earliest in the first information set and add the target angle information to the first information set.
[0097] In other embodiments, the first radar target and the first visual target include multiple targets, and each set of matched first radar targets and first visual targets corresponds to an information set. The third determining module 203 is configured to: The angle calibration information of each information set is determined based on the angle information in each information set.
[0098] Target calibration information is determined from calibration information from multiple angles based on the first preset screening criteria.
[0099] Determine the installation offset angle based on the target calibration information.
[0100] In other embodiments, the third determining module 203 is configured to: The average of all angle information in the information set is used as the angle calibration information. Alternatively, The median of all angle information in the information set is used as the angle calibration information.
[0101] In other embodiments, the first preset filtering condition includes: the number of angle information in the information set corresponding to the angle calibration information is greater than the second preset number threshold.
[0102] In other embodiments, the first determining module 201 is configured to: The closest radar target among the second radar targets detected by the radar is taken as the first radar target.
[0103] The closest visual target among the second visual targets detected by the image acquisition device is taken as the first visual target.
[0104] In other embodiments, both the first radar target and the first visual target satisfy a second preset screening condition, which includes at least one of the following: The target is located within a preset range around the vehicle.
[0105] The target's speed is less than the preset speed threshold.
[0106] The target type is the specified type.
[0107] Regarding the apparatus in the above embodiments, the specific manner in which each module performs its operation has been described in detail in the embodiments related to the method, and will not be elaborated upon here.
[0108] In summary, this disclosure continuously acquires the first radar target and the first visual target for multiple cycles. Based on the target angle information corresponding to multiple cycles, the installation offset angle can be determined more accurately, avoiding the problem of inaccurate installation offset angle determination due to large errors in a single detection data. Furthermore, for each cycle, the target angle information is further determined only when the first radar target and the first visual target match, avoiding the problem of angle mismeasurement caused by mismatch between the first radar target and the first visual target. This ensures the accuracy of the target angle information for each cycle, thereby further improving the accuracy of the installation angle.
[0109] This disclosure also provides a computer-readable storage medium having stored thereon computer program instructions that, when executed by a processor, implement the steps of the angle determination method provided in this disclosure.
[0110] Figure 9 This is a block diagram illustrating a vehicle according to an exemplary embodiment. For example, vehicle 300 may be a hybrid vehicle, a non-hybrid vehicle, an electric vehicle, a fuel cell vehicle, or other types of vehicle. Vehicle 300 may be an autonomous vehicle, a semi-autonomous vehicle, or a non-autonomous vehicle.
[0111] Reference Figure 9 The vehicle 300 may include various subsystems, such as an infotainment system 310, a perception system 320, a decision control system 330, a drive system 340, and a computing platform 350. The vehicle 300 may also include more or fewer subsystems, and each subsystem may include multiple components. Furthermore, each subsystem and each component of the vehicle 300 can be interconnected via wired or wireless means.
[0112] In some embodiments, the infotainment system 310 may include a communication system, an entertainment system, and a navigation system, etc.
[0113] The perception system 320 may include several sensors for sensing information about the environment surrounding the vehicle 300. For example, the perception system 320 may include a global positioning system (which may be a GPS system, a BeiDou system, or another positioning system), an inertial measurement unit (IMU), a lidar, a millimeter-wave radar, an ultrasonic radar, and a camera device.
[0114] The decision control system 330 may include a computing system, a vehicle controller, a steering system, a throttle, and a braking system.
[0115] The drive system 340 may include components that provide powered motion to the vehicle 300. In one embodiment, the drive system 340 may include an engine, an energy source, a transmission system, and wheels. The engine may be one or a combination of internal combustion engines, electric motors, and compressed air engines. The engine is capable of converting energy provided by the energy source into mechanical energy.
[0116] Some or all of the functions of the vehicle 300 are controlled by a computing platform 350. The computing platform 350 may include at least one processor 351 and a memory 352, the processor 351 being able to execute instructions 353 stored in the memory 352.
[0117] Processor 351 can be any conventional processor, such as a commercially available CPU. Processors may also include graphics processing units (GPUs), field-programmable gate arrays (FPGAs), systems-on-chips (SoCs), application-specific integrated circuits (ASICs), or combinations thereof.
[0118] The memory 352 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk or optical disk.
[0119] In addition to instruction 353, memory 352 can also store data, such as road maps, route information, vehicle location information, direction, speed, etc. The data stored in memory 352 can be used by computing platform 350.
[0120] In this embodiment of the disclosure, processor 351 may execute instruction 353 to complete all or part of the steps of the above-described angle determination method.
[0121] In another exemplary embodiment, a computer program product is also provided, the computer program product comprising a computer program executable by a programmable device, the computer program having a code portion for performing the above-described angle determination method when executed by the programmable device.
[0122] Furthermore, the term “exemplary” is used herein to mean serving as an example, instance, or illustration. Any aspect or design described herein as “exemplary” is not necessarily to be construed as advantageous compared to other aspects or designs. Rather, the use of the term “exemplary” is intended to present the concept in a concrete manner. As used herein, the term “or” is intended to mean an inclusive “or” rather than an exclusive “or.” That is, unless otherwise specified or clear from the context, “X applies A or B” is intended to mean any of the natural inclusive arrangements. That is, “X applies A or B” satisfies any of the foregoing instances if X applies A; X applies B; or both X applies A and B. Additionally, unless otherwise specified or clear from the context to refer to the singular form, the articles “a” and “an” as used in this application and the appended claims are generally understood to mean “one or more.”
[0123] Similarly, although this disclosure has been shown and described with respect to one or more implementations, equivalent variations and modifications will occur to those skilled in the art upon reading and understanding this specification and the accompanying drawings. This disclosure includes all such modifications and variations and is limited only by the scope of the claims. In particular, with respect to the various functions performed by the components described above (e.g., elements, resources, etc.), unless otherwise indicated, the terminology used to describe such components is intended to correspond to any component (functionally equivalent) that performs the specific function of the described component, even if structurally not equivalent to the disclosed structure. Furthermore, although specific features of this disclosure may have been disclosed with respect to only one of several implementations, such features may be combined with one or more other features of other implementations, as may be desired and advantageous to any given or particular application. Moreover, with regard to the terms “comprising,” “owning,” “having,” “having,” or variations thereof as used in the detailed description or claims, such terms are intended to be inclusive in a manner similar to the term “including.”
[0124] Other embodiments of this disclosure will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this disclosure are indicated by the appended claims.
[0125] It should be understood that this disclosure is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this disclosure is limited only by the appended claims.
[0126] In the above detailed description, reference has been made to the accompanying drawings, which illustrate specific aspects of how this disclosure can be practiced. In this regard, terms indicating direction or positional relationships, such as “center,” “longitudinal,” “lateral,” “length,” “width,” “thickness,” “up,” “down,” “front,” “back,” “left,” “right,” “vertical,” “horizontal,” “top,” “bottom,” “inner,” “outer,” “clockwise,” “counterclockwise,” “axial,” “radial,” and “circumferential,” can be used with reference to the orientation of the described figures. Since components of the described device can be positioned in multiple different orientations, directional terms are used for illustrative purposes and not for limitation. It should be understood that other aspects can be utilized and structural or logical changes can be made without departing from the concept of this disclosure. Therefore, the following detailed description should not be considered limiting.
[0127] It should be understood that, unless otherwise specifically indicated, features of various embodiments of this disclosure described herein can be combined with each other. As used herein, the term “and / or” includes any one of the relevant listed items and any combination of any two or more; similarly, “at least one of…” includes any one of the relevant listed items and any combination of any two or more.
[0128] It should be understood that, unless otherwise expressly specified and limited, the terms "joining," "attaching," "installing," "connecting," "linking," "fixing," etc., used in the embodiments of this disclosure should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral part; they can refer to a mechanical connection, an electrical connection, or a connection that allows communication between them; they can refer to a direct connection or an indirect connection through an intermediate medium; they can refer to the internal communication of two components or the interaction between two components, unless otherwise expressly limited. Those skilled in the art can understand the specific meaning of the above terms herein based on the specific circumstances.
[0129] Furthermore, the term "above" as used herein with respect to components, elements, or material layers formed or located "above" a surface may be used to indicate that the component, element, or material layer is "indirectly" positioned (e.g., placed, formed, deposited, etc.) on the surface such that one or more additional components, elements, or layers are arranged between the surface and the component, element, or material layer. However, the term "above" as used with respect to components, elements, or material layers formed or located "above" a surface may also optionally have a specific meaning: that the component, element, or material layer is "directly" positioned (e.g., placed, formed, deposited, etc.) on the surface, for example, in direct contact with the surface.
[0130] Although terms such as “first,” “second,” and “third” may be used herein to describe various components, parts, regions, layers, or sections, these components, parts, regions, layers, or sections are not limited to these terms. Rather, these terms are used only to distinguish one component, part, region, layer, or section from another. Therefore, without departing from the teachings of the examples described herein, the first component, part, region, layer, or section mentioned in the examples may also be referred to as the second component, part, region, layer, or section. Furthermore, the terms “first” and “second” are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, a feature defined as “first” or “second” may explicitly or implicitly include at least one of that feature. In the description herein, “a plurality” means at least two, such as two, three, etc., unless otherwise explicitly specified.
[0131] It should be understood that spatial relative terms, such as “above,” “upper,” “below,” and “lower,” are used herein to describe the relationship between one element and another shown in the figures. In addition to the orientation depicted in the figures, these spatial relative terms are also intended to encompass different orientations of the device in use or operation. For example, if the device in the figures is flipped, an element described as “above” or “upper” relative to another element would be “below” or “lower” relative to that other element. Thus, depending on the spatial orientation of the device, the term “above” encompasses both above and below orientations. Devices may have other orientations (e.g., rotated 90 degrees or in other orientations), and the spatial relative terms used herein should be interpreted accordingly.
Claims
1. A method for determining an angle, characterized in that, include: The first radar target detected by the radar and the first visual target detected by the image acquisition device are periodically determined. For each cycle, when the first radar target and the first visual target are matched, the target angle information is determined based on the first position information of the first radar target and the second position information of the first visual target. The target angle information represents the angle difference between the first radar target and the first visual target. The installation angle of the radar is determined based on the target angle information determined over multiple cycles.
2. The method according to claim 1, characterized in that, The method further includes: Acquire the first feature information of the first radar target and the second feature information of the first visual target; If the first feature information and the second feature information meet the preset matching conditions, the first radar target and the first visual target are determined to be matched.
3. The method according to claim 2, characterized in that, The first feature information includes a first motion state and a first type, and the second feature information includes a second motion state and a second type; The preset matching conditions include: The first type is the same as the second type; and / or, The difference between the first motion state and the second motion state is less than a preset threshold.
4. The method according to claim 1, characterized in that, The method further includes: If the first radar target and the first visual target have not been updated, the first information set corresponding to the first radar target and the first visual target is updated according to the target angle information; or... If the first radar target and the first visual target are updated, a second information set corresponding to the updated first radar target and the updated first visual target is created, and the target angle information is added to the second information set.
5. The method according to claim 4, characterized in that, The step of updating the first information set corresponding to the first radar target and the first visual target based on the target angle information includes: If the number of angle information items included in the first information set is less than a first preset threshold, the target angle information is added to the first information set; or... If the number of angle information items in the first information set is greater than or equal to the first preset threshold, delete the angle information item that was added earliest in the first information set, and add the target angle information item to the first information set.
6. The method according to claim 1, characterized in that, The first radar target and the first visual target each include multiple ones, and each set of matched first radar targets and first visual targets corresponds to an information set; Determining the installation angle of the radar based on the target angle information determined over multiple periods includes: Determine the angle calibration information of the information set based on the angle information of each information set; Target calibration information is determined from multiple angle calibration information based on the first preset filtering conditions; The installation offset angle is determined based on the target calibration information.
7. The method according to claim 6, characterized in that, Determining the angle calibration information of the information set based on the angle information of each information set includes: The mean of all angle information in the information set is used as the angle calibration information; or... The median of all angle information in the information set is used as the angle calibration information.
8. The method according to claim 6, characterized in that, The first preset filtering condition includes: the number of angle information in the information set corresponding to the angle calibration information is greater than the second preset number threshold.
9. The method according to any one of claims 1-8, characterized in that, The periodic determination of the first radar target detected by the radar and the first visual target detected by the image acquisition device includes: The radar target that is closest to the second radar target detected by the radar is taken as the first radar target; The closest visual target among the second visual targets detected by the image acquisition device is taken as the first visual target.
10. The method according to claim 9, characterized in that, Both the first radar target and the first visual target satisfy the second preset screening conditions, which include at least one of the following: The target is located within a preset area around the vehicle; The target's speed is less than a preset speed threshold; The target type is the specified type.
11. An angle determining device, characterized in that, include: The first determining module is configured to periodically determine the first radar target detected by the radar and the first visual target detected by the image acquisition device. The second determining module is configured to, for each cycle, in the case of a first radar target and a first visual target matching, determine target angle information based on the first position information of the first radar target and the second position information of the first visual target, wherein the target angle information represents the angle difference between the first radar target and the first visual target; The third determining module is configured to determine the installation angle of the radar based on the target angle information determined over multiple periods.
12. A vehicle, characterized in that, include: processor; Memory used to store processor-executable instructions; The processor is configured to execute the computer program in the memory to implement the steps of the method according to any one of claims 1-10.
13. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by a processor, the computer program performs the steps of the method described in any one of claims 1-10.
14. A computer program product, characterized in that, Includes a computer program that, when executed by a processor, implements the steps of the method according to any one of claims 1-10.