Vehicle sensor scene calibration method and vehicle calibration scene
By determining reference points and marking position points using a level in the vehicle calibration scenario, the problem of difficult vehicle sensor calibration operations is solved, achieving efficient and low-cost vehicle calibration and improving calibration accuracy and efficiency.
Patent Information
- Application Number
- CN202210479555.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2022-05-05
- Publication Date
- 2025-11-18
- Estimated Expiration
- 2042-05-05
AI Technical Summary
The existing vehicle sensor calibration operation is difficult and cannot meet the calibration requirements of the actual environment. In addition, the difficulty in aligning the vehicle affects the calibration results.
By determining the reference points used in the scene calibration, and using a level and calibration equipment to mark the position points in the reference coordinate system, the calibration points in the vehicle calibration scene are obtained, including the front-end mapping point, the rear-end mapping point, the vehicle sensor installation position or intersection, etc., as reference points for calibration.
It enables convenient, efficient, and low-cost vehicle calibration, solves the problems of operational difficulties and actual calibration needs, and improves calibration accuracy and efficiency.
Smart Images

Figure CN114742903B_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of scene calibration technology, and in particular to a scene calibration method for vehicle sensors and a vehicle calibration scene. Background Technology
[0002] As people place increasing emphasis on traffic safety, more and more advanced technologies are being applied to vehicles. Among them, vehicle sensors can intuitively show the driver the conditions around the vehicle, greatly facilitating driving safety. However, in the application of vehicle sensors, calibration is required so that the position of identified objects relative to the vehicle can be calculated based on the corresponding calibration parameters of the vehicle sensors.
[0003] Existing technologies for vehicle sensor calibration require the establishment of a calibration environment (or scenario). This calibration environment necessitates placing appropriate calibration objects around the vehicle, with their positions in the vehicle's coordinate system known in advance. The calibration environment must be constructed in a real-world space, such as by drawing QR codes on walls, creating square grids on the ground, or using road lane lines for calibration. The vehicle is then driven into the calibration environment and aligned, ensuring it is parallel or perpendicular to the lane lines. However, in practice, it has been found that pre-constructed calibration environments (such as grids or lane lines) are fixed and cannot be used for vehicle calibration anytime, anywhere, thus failing to meet the requirements of calibrating in real-world vehicle environments. Furthermore, driving the vehicle into the calibration environment and aligning it is difficult and cannot guarantee perfect alignment, affecting the calibration results and failing to meet actual calibration needs. Summary of the Invention
[0004] This application provides a method for calibrating vehicle sensors and a vehicle calibration scenario, which solves the technical problems existing in the calibration of vehicle sensors, such as operational difficulties and inability to meet actual calibration requirements.
[0005] On the one hand, this application provides a scene calibration method for vehicle sensors through an embodiment of this application, applied in a vehicle calibration scenario, the method comprising:
[0006] Determine the reference points used for scenario calibration, wherein the reference points are used to indicate the reference points used when performing scenario calibration in the vehicle calibration scenario;
[0007] Based on the reference point, the vehicle sensor is calibrated in a scene to obtain m calibration points in the vehicle calibration scene, where m is a positive integer.
[0008] Optionally, the reference points used for determining the scene calibration include:
[0009] The front and / or rear mapping points of the vehicle are determined as reference points for the scene calibration; wherein, the front mapping point is the position point on the ground mapped from the front center point of the vehicle, and the front center point is the intersection point between the front bumper of the vehicle and the center line of the vehicle; the rear mapping point is the position point on the ground mapped from the rear center point of the vehicle, and the rear center point is the intersection point between the rear bumper of the vehicle and the center line of the vehicle.
[0010] Optionally, the reference points used for determining the scene calibration include:
[0011] The installation location of the vehicle sensor is mapped to a location point on the ground and determined as the reference point used for scene calibration.
[0012] Optionally, the reference points used for determining the scene calibration include:
[0013] The target intersection point is mapped to a location point on the ground and determined as the reference point used for scene calibration; wherein, the target intersection point is the intersection point between the installation position of the vehicle sensor and the designated reference line of the vehicle.
[0014] Optionally, based on the reference point, the vehicle sensor is calibrated to obtain m calibration points in the vehicle calibration scene, including:
[0015] The reference point is calibrated using a first level to obtain the reference coordinate system used in the scene calibration.
[0016] Using a calibration device, mark position points at a preset first distance in the reference coordinate system along any direction of the reference coordinate system to obtain at least two distance points;
[0017] Using a second level as a reference in any direction of the reference coordinate system, the coordinate system is reconstructed based on the first distance point among the at least two distance points to obtain the reconstructed coordinate system.
[0018] Using a calibration device, position points are marked along a first direction in the reconstructed coordinate system at a preset second distance to obtain b calibration points, where b is a positive integer;
[0019] Move the second level to the second distance point among the at least two distance points, and repeat the step of using the second level with any direction in the reference coordinate system as a reference to obtain b calibration points according to each distance point.
[0020] Optionally, the step of performing scene calibration on the vehicle sensor based on the reference point to obtain m calibration points in the vehicle calibration scene includes:
[0021] Based on the reference point and the installation orientation of the vehicle sensor, the vehicle sensor is calibrated in a scene to obtain m calibration points in the vehicle calibration scene.
[0022] Optionally, based on the reference point and the installation orientation of the vehicle sensor, scene calibration is performed on the vehicle sensor to obtain m calibration points in the vehicle calibration scene, including:
[0023] The reference point is calibrated using a first level to obtain the reference coordinate system used in the scene calibration.
[0024] Using a calibration device, position points are marked along a first direction in the reference coordinate system at a preset first distance to obtain distance points; wherein, the first direction is the orientation direction corresponding to the installation position of the vehicle sensor;
[0025] Using a second level as a reference in the first direction of the reference coordinate system, the coordinate system is reconstructed based on the distance point to obtain the reconstructed coordinate system.
[0026] Using a calibration device, position points are marked along a second direction in the reconstructed coordinate system at a preset second distance to obtain m calibration points, wherein the second direction is the same as the first direction.
[0027] Optionally, the step of using a first level to calibrate the reference point to obtain the reference coordinate system used in the scene calibration includes:
[0028] If there are two reference points, the first level is used to calibrate the coordinate system of the two parameter points to obtain the reference coordinate system.
[0029] Optionally, the step of using a first level to calibrate the reference point to obtain the reference coordinate system used in the scene calibration includes:
[0030] If there is only one reference point, then the reference point and the designated reference line in the vehicle are calibrated using a first level to obtain the reference coordinate system; wherein the designated reference line is the centerline of the vehicle or the designated edge line in the vehicle.
[0031] On the other hand, this application provides a vehicle calibration scenario through one embodiment of the application, wherein the vehicle calibration scenario is a scenario calibrated using the scenario calibration method of the vehicle sensor as described above.
[0032] One or more technical solutions provided in this application have at least the following technical effects or advantages: This application determines reference points used for scene calibration, wherein the reference points are used to indicate the reference points used when performing scene calibration in the vehicle calibration scene; the vehicle sensor is calibrated according to the reference points to obtain m calibration points in the vehicle calibration scene, where m is a positive integer. In the above solution, this application uses reference points to perform scene calibration on the vehicle sensor, thereby conveniently and efficiently completing the calibration of m calibration points in the vehicle calibration scene. This enables efficient, fast, and low-cost completion of the calibration of the entire vehicle calibration scene, while also solving the technical problems of operational difficulties and inability to meet actual calibration requirements in existing vehicle sensor calibration. Attached Figure Description
[0033] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0034] Figure 1 This is a schematic flowchart of a scene calibration method for vehicle sensors provided in an embodiment of this application.
[0035] Figure 2 This is a schematic diagram of a vehicle calibration scenario provided in an embodiment of this application. Detailed Implementation
[0036] This application provides a method for calibrating vehicle sensors and a vehicle calibration scenario, which solves the technical problems existing in the calibration of vehicle sensors, such as operational difficulties and inability to meet actual calibration requirements.
[0037] The technical solution of this application embodiment is to solve the above-mentioned technical problems. The overall idea is as follows: determine the reference point used for scene calibration, the reference point is used to indicate the reference point used when performing scene calibration in the vehicle calibration scene; perform scene calibration on the vehicle sensor according to the reference point to obtain m calibration points in the vehicle calibration scene, where m is a positive integer.
[0038] To better understand the above technical solutions, the following will provide a detailed explanation of the technical solutions in conjunction with the accompanying drawings and specific implementation methods.
[0039] First, it should be clarified that 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.
[0040] Please see Figure 1 This is a flowchart illustrating a scene calibration method for vehicle sensors provided in an embodiment of this application. Figure 1 The method shown is applied in vehicle calibration scenarios, and the method includes the following implementation steps:
[0041] S101. Determine the reference point used for scenario calibration, wherein the reference point is used to indicate the reference point used when performing scenario calibration in the vehicle calibration scenario.
[0042] The reference points described in this application are reference points used during scene calibration in a vehicle calibration scenario. The specific location and number of these reference points are not limited and can be determined according to the actual needs of the system calibration. Optionally, the reference points can be used to determine the reference coordinate system used during scene calibration.
[0043] In one specific embodiment, this application may determine the front-end mapping point and / or rear-end mapping point of the vehicle as reference points used for scene calibration. The front-end mapping point is the position point on the ground mapped from the front center point of the vehicle, and the front center point is the intersection of the front bumper and the vehicle's centerline. The rear-end mapping point is the position point on the ground mapped from the rear center point of the vehicle, and the rear center point is the intersection of the rear bumper and the vehicle's centerline.
[0044] For example, please see Figure 2 This is a schematic diagram of a vehicle calibration scenario provided in an embodiment of this application. Figure 2 In this application, the front and rear center points of the vehicle can be first determined using the vehicle logo as a reference or by measuring with a tape measure. Then, using a plumb bob, the front and rear center points (A and B) are mapped onto the ground. These can also be referred to as plumb bob points A and B. The user can mark the front and rear center points A and B on the ground using chalk, as follows: Figure 2 Points A and B are shown.
[0045] Optionally, after determining point A, this application can select point A', which is a certain distance away from point A, along the vehicle's central axis (AB line) as a reference point for scene calibration. Specifically, since point A is too close to the vehicle body and inconvenient to operate during actual operation, this application can use a first (laser) level to appropriately move point A to a certain position, leaving operating space, to obtain point A', which is then used as the reference point for scene calibration.
[0046] In another specific embodiment, when the vehicle sensor is installed in an external vehicle space such as a vehicle rearview mirror, this application can directly map the installation position of the vehicle sensor to a position point on the ground and determine it as the reference point used for the scene calibration.
[0047] In another specific embodiment, regardless of whether the vehicle sensor is installed in the interior or exterior space of the vehicle, this application can determine the intersection of the installation position of the vehicle sensor and a designated edge line of the vehicle as the target intersection point. Then, the target intersection point is mapped to a location point on the ground and determined as the reference point used for scene calibration. The designated reference line is a reference line specified based on the installation position of the vehicle sensor. For example, when the vehicle sensor is installed in the interior space of the vehicle, the designated reference line may be, for example, the centerline of the vehicle. Conversely, when the vehicle sensor is installed in the exterior space of the vehicle, the designated reference line may be, for example, any designated edge line corresponding to the installation direction of the vehicle sensor that forms the perimeter of the vehicle.
[0048] It should be noted that the vehicle sensors involved in this application include, but are not limited to, vision sensors, lidar, millimeter-wave radar, or other sensors used for environmental calibration, and this application does not limit them.
[0049] S102. Based on the reference point, perform scene calibration on the vehicle sensor to obtain m calibration points in the vehicle calibration scene, where m is a positive integer.
[0050] In one specific embodiment, this application can use a first level to calibrate the coordinate system of the reference points, thereby obtaining the reference coordinate system required for scene calibration. The first level is a device used for calibrating the coordinate system, and can specifically be a laser level, etc. This application does not limit the specific implementation method for calibrating the reference coordinate system. Specifically, for example, when there are two reference points, this application can use a first level to calibrate the coordinate system of these two reference points. Specifically, a straight line passing through the two reference points is used as a direction axis, and another direction axis perpendicular to this direction axis is determined, thereby calibrating the reference coordinate system. As another example, when there is only one reference point, this application can use a first level to calibrate the coordinate system of the reference point and a designated reference line in the vehicle. Specifically, a straight line passing through the reference point and parallel to the designated reference line is used as a direction axis, and another direction axis perpendicular to this direction axis is determined, thereby calibrating the reference coordinate system.
[0051] For example, please see Figure 2 In the example described, this application first uses a first level to draw a crosshair on the ground. The first level is then adjusted so that the center of the crosshair coincides with the front mapping point A. A laser line passes through the rear mapping point B. The straight line passing through AB can be the X-axis of the reference coordinate system, and the line perpendicular to it can be the Y-axis. The front mapping point A is the origin of the reference coordinate system. Optionally, when point A is difficult to manipulate, this application can also use point A' as the origin of the reference coordinate system.
[0052] It should be noted that the reference coordinate system can be arbitrarily adjusted according to actual needs, such as coordinate rotation or translation, so that the origin (point A or point A') and the direction of the coordinate axes can be adjusted arbitrarily. This application does not limit this.
[0053] After obtaining the reference coordinate system, this application can use a calibration device to mark position points at a preset first distance along a first direction in the reference coordinate system, thereby obtaining at least two distance points. The calibration device is a device used for position calibration, such as a measuring tape, ruler, or scale. The first direction is a custom-selected direction in the reference coordinate system, such as the X-axis or Y-axis.
[0054] For example, please refer to the example above. After obtaining the reference coordinate system XAY, this application straightens the measuring tape along the Y-axis and marks the predetermined first distance with chalk to obtain the corresponding distance points y1 and y2, as detailed below. Figure 2 Points y1 and y2 are shown. The preset first distance is a system-defined setting, for example, customized according to user or system needs. Optionally, the user can retract the measuring tape after marking.
[0055] After obtaining the distance points, this application can use a second level to reconstruct the coordinate system based on any direction in the reference coordinate system and the first distance point among the at least two distance points, thereby obtaining a reconstructed coordinate system. The first distance point is any one of the at least two distance points. For a description of the second level, please refer to the description of the first level; it will not be repeated here.
[0056] For example, referring to the example above, this application uses a second level to mark a cross on the ground and adjusts the second level so that one line of the cross coincides with the Y-axis (or the X-axis, but the illustration only shows the Y-axis as an example). The straight line passing through point y1 and perpendicular to the Y-axis is denoted as CD, thus obtaining the reconstructed coordinate system Dy1Y.
[0057] Furthermore, this application uses a calibration device to mark position points at a preset second distance along a first direction in the reconstructed coordinate system, thereby obtaining b calibration points, where b is a positive integer. The first direction is perpendicular to any direction in the reference coordinate system.
[0058] For example, referring to the example above, this application can use a measuring tape stretched straight along the CD line (X-axis) of the second level, and mark it with chalk at the designed preset second distance to obtain at least one calibration point, specifically for example... Figure 2 The marking points are x1, x2, x3, and x4. Optionally, the measuring tape can be retracted after marking is completed. The preset second distance can be a distance value that the system can customize according to the actual calibration needs, and this application does not limit it.
[0059] Furthermore, this application can move the second level to the second distance point among the at least two distance points, and repeat the above steps of using the second level to create a reconstructed coordinate system for the second distance point with any direction in the reference coordinate system as a reference, and calibrating b calibration points in the reconstructed coordinate system, until the calibration of b calibration points under each distance point is completed.
[0060] For example, referring to the example above, this application's movable second level instrument can be repeated with the steps of reconstructing the coordinate system and calibrating multiple calibration points under the reconstructed coordinates. This allows all the calibration points required by the system to be calibrated as needed. Specifically, for example… Figure 2 Taking the two rows of calibration points parallel to the X-axis as an example, the coordinates of each calibration point can be as follows: (x1, y1), (x2, y1), (x3, y1), (x4, y1), (x1, y2), (x2, y2), (x3, y2) and (x4, y2).
[0061] In another specific embodiment, this application can perform scene calibration on the vehicle sensor based on the reference location and the installation orientation of the vehicle sensor to obtain m calibration points in the vehicle calibration scene. Specifically, this application can use a first level to calibrate the coordinate system of the reference point to obtain the reference coordinate system used in the scene calibration. Further, this application can determine a first direction in the reference coordinate system based on the installation orientation of the vehicle sensor, where the first direction is the orientation direction corresponding to the installation orientation of the vehicle sensor in the reference coordinate system, to mark calibration points within the visible range of the vehicle sensor. Then, a calibration device is used to mark position points at a preset first distance along the first direction in the reference coordinate system to obtain at least one distance point. Then, a second level is used with the first direction in the reference coordinate system as a reference to reconstruct the coordinate system based on the first distance point among the at least one distance point, to obtain a reconstructed coordinate system. Then, a calibration device is used to mark position points at a preset second distance along the second direction in the reconstructed coordinate system to obtain b calibration points, where the second direction is the same as the first direction. Move the second level to the second distance point among the at least one distance point, and repeat the steps described above: using the second level as a reference to the first direction in the reference coordinate system, reconstructing the coordinate system of the second distance point, and marking calibration points in the reconstructed coordinate system, until all distance points have been marked, thereby obtaining m calibration points. For any content not described or introduced in this embodiment, please refer to the relevant description in the previous embodiment; it will not be repeated here.
[0062] By implementing the embodiments of this application, one or more technical solutions provided in the embodiments of this application have at least the following technical effects or advantages: This application determines the reference points used for scene calibration, the reference points being used to indicate the reference points used when performing scene calibration in the vehicle calibration scene; the vehicle sensor is calibrated according to the reference points to obtain m calibration points in the vehicle calibration scene, where m is a positive integer. In the above solution, this application uses reference points to perform scene calibration on the vehicle sensor, thereby conveniently and efficiently completing the calibration of m calibration points in the vehicle calibration scene. This allows for efficient, fast, and low-cost completion of the calibration of the entire vehicle calibration scene, while also solving the technical problems of operational difficulties and inability to meet actual calibration requirements in existing vehicle sensor calibration.
[0063] Based on the same inventive concept, this application also provides a vehicle calibration scenario, wherein the vehicle calibration scenario is a calibration scenario obtained by using the scenario calibration method of the vehicle sensor described above.
[0064] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.
[0065] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.
[0066] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.
[0067] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.
[0068] Although preferred embodiments of the invention have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including both the preferred embodiments and all changes and modifications falling within the scope of the invention.
[0069] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.
Claims
1. A method for scene calibration of vehicle sensors, characterized in that, When applied to vehicle calibration scenarios, the method includes: Determine the reference points used for scenario calibration, wherein the reference points are used to indicate the reference points used when performing scenario calibration in the vehicle calibration scenario; The reference points used for determining the scene calibration include: The front-end mapping point and / or rear-end mapping point of the vehicle are determined as the reference points used for the scene calibration. Wherein, the front-end mapping point is the position point on the ground mapped from the front center point of the vehicle, and the front center point is the intersection point between the front bumper of the vehicle and the center line of the vehicle; the rear-end mapping point is the position point on the ground mapped from the rear center point of the vehicle, and the rear center point is the intersection point between the rear bumper of the vehicle and the center line of the vehicle; or The installation locations of the vehicle sensors are mapped to corresponding points on the ground, which are then used as reference points for scene calibration; or The target intersection point is mapped to a location point on the ground and determined as the reference point used for scene calibration; wherein, the target intersection point is the intersection point between the installation position of the vehicle sensor and the designated reference line of the vehicle; Based on the reference point, the vehicle sensor is calibrated to obtain m calibration points in the vehicle calibration scene, where m is a positive integer, including: The reference point is calibrated using a first level to obtain the reference coordinate system used in the scene calibration. Using a calibration device, mark position points at a preset first distance in the reference coordinate system along any direction of the reference coordinate system to obtain at least two distance points; Using a second level as a reference in any direction of the reference coordinate system, the coordinate system is reconstructed based on the first distance point among the at least two distance points to obtain the reconstructed coordinate system. Using a calibration device, position points are marked along a first direction in the reconstructed coordinate system at a preset second distance to obtain b calibration points, where b is a positive integer; Move the second level to the second distance point among the at least two distance points, and repeat the step of using the second level with any direction in the reference coordinate system as a reference to obtain b calibration points according to each of the distance points; or Based on the reference point and the installation orientation of the vehicle sensor, scene calibration is performed on the vehicle sensor to obtain m calibration points in the vehicle calibration scene, including: The reference point is calibrated using a first level to obtain the reference coordinate system used in the scene calibration. Using a calibration device, position points are marked along a first direction in the reference coordinate system at a preset first distance to obtain distance points; wherein, the first direction is the orientation direction corresponding to the installation position of the vehicle sensor; Using a second level as a reference in the first direction of the reference coordinate system, the coordinate system is reconstructed based on the distance point to obtain the reconstructed coordinate system. Using a calibration device, position points are marked along a second direction in the reconstructed coordinate system at a preset second distance to obtain m calibration points, wherein the second direction is the same as the first direction.
2. The method according to claim 1, characterized in that, The process of using a first level to calibrate the reference point and obtain the reference coordinate system used in the scene calibration includes: If there are two reference points, the first level is used to calibrate the coordinate system of the two reference points to obtain the reference coordinate system.
3. The method according to claim 1, characterized in that, The process of using a first level to calibrate the reference point and obtain the reference coordinate system used in the scene calibration includes: If there is only one reference point, then the reference point and the designated reference line in the vehicle are calibrated using a first level to obtain the reference coordinate system; wherein the designated reference line is the centerline of the vehicle or the designated edge line in the vehicle.
4. A vehicle calibration scenario, characterized in that, The vehicle calibration scenario is the scenario calibrated using the scenario calibration method of the vehicle sensor described in any one of claims 1-3 above.
Citation Information
Patent Citations
Image-based distance measurement method and device
CN109752709A
Field-end multi-wire-harness laser radar internal reference calibration method
CN111060898A