Sensor calibration method, device, electronic device and computer-readable storage medium

Abstract

The present application provides a sensor calibration method, device, electronic device and computer-readable storage medium, which relate to the field of sensors. The method includes: a first target and a second target are arranged in advance in the surrounding environment of a vehicle equipped with a first sensor, and a second sensor is arranged on the second target. The calibration process includes obtaining first data including the area where the second target is located collected by the first sensor and second data including the area where the first target is located collected by the second sensor, determining the first position of the second target in the coordinate system of the first sensor according to the first data, determining the second position of the second target in the coordinate system of the vehicle according to the second data, and obtaining the calibration position of the first sensor in the coordinate system of the vehicle according to the first position and the second position. The present application simplifies the process of calibrating sensors carried on a vehicle.

Description

Technical Field

[0001] The present application relates to the field of sensors, and more specifically, to a sensor calibration method, device, electronic device and computer-readable storage medium in the field of sensors. Background Art

[0002] In areas such as autonomous driving, the characteristics of each sensor on the car are fully utilized to perceive the environment and realize autonomous driving functions. Accurate sensor calibration is an important basis for autonomous driving functions such as multi-sensor perception and positioning.

[0003] Therefore, how to accurately calibrate the sensors on the vehicle has become an urgent problem to be solved. Summary of the invention

[0004] The present application provides a sensor calibration method, device, electronic device and computer-readable storage medium, which can improve the accuracy of sensor calibration.

[0005] In a first aspect, a sensor calibration method is provided, in which a first target and a second target are arranged in the surrounding environment of a vehicle equipped with a first sensor, the first target and the second target are arranged at different positions, and a second sensor is arranged on the second target; the sensor calibration method comprises: acquiring first data collected by the first sensor and second data collected by the second sensor; wherein the first data includes data of the area where the second target is located, and the second data includes data of the area where the first target is located; determining a first pose of the second target in a first sensor coordinate system according to the first data; determining a second pose of the second target in the vehicle coordinate system according to the second data; and obtaining a calibration pose of the first sensor in the vehicle coordinate system according to the first pose and the second pose.

[0006] In combination with the first aspect, in some possible implementations, a third target is arranged on the vehicle, and the second data also includes data of the area where the third target is located; determining the second posture of the second target in the vehicle coordinate system according to the second data includes: determining the third posture of the third target in the coordinate system where the second sensor is located according to the second data; determining the fourth posture of the second sensor in the vehicle coordinate system according to the third posture; determining the second posture according to the fourth posture and a preset posture, wherein the preset posture is the posture of the second target in the coordinate system where the second sensor is located.

[0007] In combination with the first aspect and the above-mentioned implementation methods, in some possible implementation methods, the vehicle includes a vehicle, and the third target is set on the wheel hub of the vehicle; the sensor calibration method also includes: determining the center point of each wheel according to the third target set on the wheel hub of the vehicle; connecting the center points of each wheel in sequence to obtain a target plane; taking the center point of the rear axle of the vehicle as the origin of the vehicle coordinate system; taking the upward normal vector of the target plane as the direction of the Z axis of the vehicle coordinate system; determining the direction of the front of the vehicle as the direction of the X axis of the vehicle coordinate system; taking the cross product of the X axis and the Z axis as the Y axis of the vehicle coordinate system, thereby constructing the vehicle coordinate system.

[0008] In combination with the first aspect, in some possible implementations, obtaining the calibration pose of the first sensor in the vehicle coordinate system according to the first pose and the second pose includes:

[0009] Obtain a relative pose of the second target relative to the vehicle coordinate system based on the first pose and the initial pose of the first sensor; determine whether the relative pose and the second pose are the same; if the relative pose is not the same as the second pose, determine the difference between the first pose and the second pose; adjust the initial pose of the first sensor in the vehicle coordinate system based on the difference; and determine the marking pose based on the adjusted initial pose.

[0010] In combination with the first aspect, in some possible implementations, determining the calibration pose according to the adjusted initial pose includes: verifying the validity of the adjusted initial pose; and if the validity of the adjusted initial pose is verified, determining the adjusted initial pose as the calibration pose;

[0011] In combination with the first aspect, in some possible implementations, the first target includes multiple sub-targets with different layout postures; the step of verifying the validity of the adjusted initial posture includes: selecting a sub-target with a layout posture as a preset posture from the multiple sub-targets to obtain a verification target; determining a fifth posture of the verification target in the vehicle coordinate system; determining a sixth posture of the verification target in the coordinate system where the first sensor is located; converting the sixth posture according to the adjusted initial posture to obtain a converted posture; and determining whether the fifth posture is consistent with the converted posture to verify the validity of the adjusted initial posture.

[0012] In combination with the first aspect, in some possible implementations, the second targets include a plurality of targets, and the second data collected by two adjacent second sensors have an intersection.

[0013] In a second aspect, a sensor calibration device is provided, wherein a first target and a second target are arranged in an environment surrounding a vehicle equipped with a first sensor, the first target and the second target are arranged at different positions, and a second sensor is arranged on the second target;

[0014] The sensor calibration device comprises:

[0015] A data acquisition module, used to acquire first data collected by a first sensor and second data collected by a second sensor; wherein the first data includes data of an area where the second target is located, and the second data includes data of an area where the first target is located;

[0016] A first calculation module, used for determining a first pose of the second target in a first sensor coordinate system according to the first data;

[0017] A second calculation module, used for determining a second posture of the second target in the vehicle coordinate system according to the second data;

[0018] The third calculation module is used to obtain the calibration posture of the first sensor in the vehicle coordinate system according to the first posture and the second posture.

[0019] In conjunction with the second aspect, in some possible implementations, a third target is arranged on the vehicle, the second data further includes data of an area where the third target is located, and the second calculation module includes:

[0020] A first calculation unit, configured to determine a third position and posture of the third target in the coordinate system where the second sensor is located according to the second data;

[0021] A second calculation unit, configured to determine a fourth posture of the second sensor in the vehicle coordinate system according to the third posture;

[0022] The third calculation unit is configured to obtain a calibration pose of the first sensor in the vehicle coordinate system according to the first pose and the second pose.

[0023] In combination with the second aspect and the above implementation manner, in some possible implementation manners, a fourth posture of the second sensor in the vehicle coordinate system is determined according to the third posture, and the sensor calibration device further includes:

[0024] A coordinate system construction unit, used to construct the vehicle coordinate system;

[0025] The coordinate system construction unit comprises:

[0026] A center acquisition subunit, used to determine the center point of each wheel according to the third target set on the wheel hub of the vehicle;

[0027] A plane construction subunit, used for connecting the center points of the wheels in sequence to obtain a target plane;

[0028] A coordinate system generating subunit is used to take the center point of the rear axle of the vehicle as the origin of the vehicle coordinate system; take the upward normal vector of the target plane as the direction of the Z axis of the vehicle coordinate system; determine the orientation of the front of the vehicle as the direction of the X axis of the vehicle coordinate system; take the cross product of the X axis and the Z axis as the Y axis of the vehicle coordinate system, thereby constructing the vehicle coordinate system.

[0029] In combination with the second aspect and the foregoing implementation manner, in some possible implementation manners, the third calculation module includes:

[0030] A judging unit, configured to obtain a relative posture of the second target relative to the vehicle coordinate system according to the first posture and the initial posture of the first sensor; and to judge whether the relative posture is the same as the second posture;

[0031] a fourth calculation unit, configured to determine a difference between the relative posture and the second posture when the relative posture is different from the second posture;

[0032] an adjusting unit, configured to adjust an initial position and posture of the first sensor in the vehicle coordinate system according to the difference;

[0033] A determination unit is used to determine the calibration pose according to the adjusted initial pose.

[0034] In combination with the second aspect and the foregoing implementation manner, in some possible implementation manners, the determining unit includes:

[0035] A verification subunit, used to verify the validity of the adjusted initial posture;

[0036] The determination subunit is used to determine the adjusted initial posture as the calibration posture when the validity verification of the adjusted initial posture is passed.

[0037] In combination with the second aspect and the above implementation manner, in some possible implementation manners, the first target includes a plurality of sub-targets with different arrangement postures, and the verification subunit includes:

[0038] A selection sub-unit is used to select a sub-target whose arrangement posture is a preset posture from the plurality of sub-targets to obtain a verification target;

[0039] A first computing subunit, configured to determine a fifth pose of the verification target in the vehicle coordinate system;

[0040] A second computing subunit is used to determine a sixth posture of the verification target in the coordinate system where the first sensor is located;

[0041] A conversion subunit, used for converting the sixth posture according to the adjusted initial posture to obtain a converted posture;

[0042] The judging subunit is used to judge whether the fifth posture is consistent with the converted posture, so as to verify the validity of the adjusted initial posture.

[0043] In combination with the second aspect and the above implementations, in some possible implementations, the second targets include a plurality of targets, and the second data collected by two adjacent second sensors have an intersection.

[0044] In a third aspect, an electronic device is provided, comprising a memory and a processor. The memory is used to store executable program code, and the processor is used to call and run the executable program code from the memory, so that the electronic device executes the sensor calibration method in the first aspect or any possible implementation of the first aspect.

[0045] In a fourth aspect, a computer program product is provided, comprising: a computer program code, which, when executed on a computer, enables the computer to execute the sensor calibration method in the first aspect or any possible implementation of the first aspect.

[0046] In a fifth aspect, a computer-readable storage medium is provided, which stores a computer program code. When the computer program code runs on a computer, the computer executes the sensor calibration method in the above-mentioned first aspect or any possible implementation of the first aspect.

[0047] The sensor calibration method, device, electronic device, and computer-readable storage medium provided in the embodiments of the present application have the following technical effects:

[0048] The technical solution proposed in the embodiment of the present application is that a first target and a second target are arranged in advance in the surrounding environment of a vehicle equipped with a first sensor. The arrangement positions of the first target and the second target are different. A second sensor is arranged on the second target. The calibration process includes: obtaining the first data collected by the first sensor (including the data of the area where the second target is located) and the second data collected by the second sensor (including the data of the area where the first target is located), and then determining the first position of the second target in the coordinate system of the first sensor according to the first data, and determining the second position of the second target in the coordinate system of the vehicle according to the second data. After obtaining the first position and the second position, the calibration position of the first sensor in the coordinate system of the vehicle is determined according to the first position and the second position, thereby realizing the calibration of the sensor carried on the vehicle. For the calibration of the sensor carried on the vehicle, the calibration scheme is simple, the site selection of the calibration site is simple, the target is easy to deploy, and the calibration work can be carried out anytime and anywhere without the help of professional equipment, which is conducive to reducing the calibration cost. After the calibration work is completed, the target can be taken away immediately without occupying the site. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 shows a schematic diagram of target deployment for sensor calibration;

[0050] Figure 2 A schematic flow chart of a sensor calibration method provided in an embodiment of the present application is shown;

[0051] Figure 3 A schematic diagram of a target is shown;

[0052] Figure 4 A schematic diagram including a vehicle coordinate system is shown;

[0053] Figure 5 A schematic diagram showing a first target within a detection area of ​​a first sensor is shown;

[0054] Figure 6 Another schematic flow chart of a sensor calibration method provided in an embodiment of the present application is shown;

[0055] Figure 7 A schematic diagram of the structure of a sensor calibration device provided in an embodiment of the present application is shown;

[0056] Figure 8 A schematic structural diagram of an electronic device provided in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0057] The technical solution in the present application will be described clearly and in detail below in conjunction with the accompanying drawings. In the description of the embodiments of the present application, unless otherwise specified, " / " means or, for example, A / B can mean A or B: "and / or" in the text is only a description of the association relationship of associated objects, indicating that there can be three relationships, for example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, in the description of the embodiments of the present application, "multiple" means two or more than two.

[0058] In the following, the terms "first" and "second" are used for descriptive purposes only and are not to be understood as suggesting or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features.

[0059] In areas such as autonomous driving, the characteristics of each sensor on the car are fully utilized for environmental perception and autonomous driving. Accurate sensor calibration is an important basis for autonomous driving functions such as multi-sensor perception and positioning. In areas such as autonomous driving, the calibration of sensors (such as vehicle-mounted radar) in existing related technologies has the following problems:

[0060] 1. End of Line (EOL) calibration at the vehicle factory. This calibration method establishes the conversion relationship between the two coordinate systems through the known target pose in the vehicle coordinate system and the target pose detected by the vehicle-mounted radar. It requires a dedicated fixed calibration site and target, and professional equipment to locate the vehicle coordinate system and the target pose.

[0061] 2. Online calibration: This calibration method establishes the transformation relationship between two coordinate systems by extracting features in a specific scene under a specific driving condition. It requires setting specific driving conditions and specific scenes to complete the calibration. The calibration accuracy is generally poor and it takes a lot of time.

[0062] 3. Service calibration is mainly limited by the venue of the car sales location (such as 4S stores), and it is impossible to provide a fixed calibration site. At present, there is no effective, stable and easy-to-use vehicle calibration solution that can solve the pain points of most 4S stores. That is, after the user purchases a vehicle with autonomous driving function, the staff of the 4S store is generally required to help the customer perform service calibration of the sensor at a specific calibration site with targets. Due to the limited venue of the 4S store, it is difficult to provide a specific calibration site, resulting in the inability to perform service calibration of the sensor anytime and anywhere.

[0063] Based on the problems existing in the existing related technologies for sensor calibration, the embodiments of the present application provide a sensor calibration method, device, electronic device and computer-readable storage medium, which simplify the process of calibrating sensors mounted on vehicles and can solve the pain point of no specific calibration site at the car sales location. The calibration scheme is simple, easy to deploy and operate, and the calibration site selection is simple. The calibration work can be carried out anytime and anywhere without the aid of professional equipment, which is conducive to reducing calibration costs.

[0064] The following is an embodiment of a sensor calibration method provided in an embodiment of the present application.

[0065] The application scenarios of the sensor calibration method provided in the embodiment of the present application include: calibrating the sensors on the vehicle when the vehicle leaves the factory; calibrating the sensors on the vehicle when the vehicle is maintained, repaired or replaced. Figure 1 As shown, Figure 1 A schematic diagram of target deployment for sensor calibration is shown, which exemplarily shows the first target and the second target arranged in the surrounding environment of the vehicle, which is a target deployment method, namely, the first target and the second target are arranged on the ground in front of the vehicle, on the ground behind the vehicle, on the ground on the left side, and on the ground on the right side. Figure 1 In the figure, Vehicle represents a vehicle, C1 represents a first sensor, C2 represents a second sensor, the target B1 in the dotted square box is the first target, also called a ground target (landmarker), and the target B2 in the dotted elliptical box is the second target, also called a calibration target (calibrator).

[0066] The sensor carried on the vehicle is called the first sensor. Before calibrating the first sensor, it is necessary to arrange the first target and the second target in the surrounding environment of the vehicle carrying the first sensor. The arrangement positions of the first target and the second target are different, that is, the arrangement position of the first target and the arrangement position of the second target are independent of each other, and the two do not overlap. The second target is provided with a second sensor. Among them, a large number of first targets are arranged within the detection range of the first sensor. After the arrangement is completed, the relative position and posture of the first target are fixed. Among them, multiple first targets are arranged in front of the first sensor, and the postures of the multiple first targets are different. Multiple first targets with different postures can establish better spatial constraints, which can improve the accuracy of the angle information of the second target collected by the first sensor.

[0067] Figure 2 A schematic flow chart of a sensor calibration method provided in an embodiment of the present application is shown. Figure 2As shown, the sensor calibration method provided in the embodiment of the present application is applied to an electronic device, which may be a terminal device mounted on a vehicle or an external device, such as a computer. The sensor calibration method includes the following schemes:

[0068] S110: Acquire first data collected by the first sensor and second data collected by the second sensor.

[0069] In an exemplary embodiment, first data collected by a first sensor is obtained, and second data collected by a second sensor is obtained. The first data includes data collected by the first sensor in the area where the second target is located, and the first data can be used to obtain relevant information about the second target and the things around the second target in the real environment, such as position, shape or other semantic information, etc. The second data includes data collected by the second sensor, and the second data can be used to describe the relevant information about the first target and the vehicle and the second sensor in the real environment, such as position, shape or other semantic information, etc. In which, a large number of first targets are arranged in advance within the detection range of the first sensor, and the arrangement postures of all the first targets are different, so that constraints can be added, and the position of any one of the first targets can be accurately described by other first targets. Due to the different arrangement postures of all the first targets, the accuracy of the second data describing the relevant information about the first target and the things around the first target in the real environment can be improved. It can be understood that the accuracy of the first data describing the relevant information about the second target and the things around the second target in the real environment and the first sensor can also be improved.

[0070] Among them, as an optional implementation, the second target includes multiple targets, and after the second targets are arranged, the detection range formed by the multiple second targets is greater than or equal to the area where the vehicle and the first target are located. And the second data collected by two adjacent second sensors have an intersection, that is, the second data collected by the two adjacent second sensors have the same part, so that it can be ensured that the data of the area where all the first targets around the vehicle are located are collected to avoid data leakage.

[0071] As another optional implementation, the second target may be a movable target, and by moving the second target, the detection range of the second target may include the area where the vehicle and the first target are located. During the movement of the second target, any two acquisitions of detection data have an intersection, that is, the two acquisitions of data by the second target have the same part, so that it can be ensured that all data of the area where the first target is located around the vehicle are acquired.

[0072] S120: Determine the first pose of the second target in the first sensor coordinate system according to the first data.

[0073] It can be understood that the first data is the detection data collected by the first sensor including the second target. The first position of the second target is determined based on the first data, mainly by obtaining the position information and angle information of the second target relative to the first sensor through the detection data collected by the first sensor. The first position is expressed as

[0074] S130: Determine a second position and posture of the second target in the vehicle coordinate system according to the second data.

[0075] It can be understood that the second data is the detection data collected by the second sensor including the first target and the vehicle. The second pose of the second target in the vehicle coordinate system is determined according to the second data. The position information and angle information of the second target relative to the vehicle are obtained mainly through the detection data collected by the second sensor. The second pose is expressed as

[0076] S140: Obtaining a calibration pose of the first sensor in the vehicle coordinate system according to the first pose and the second pose.

[0077] Before calibrating the first sensor, the position and posture of the first sensor in the vehicle coordinate system is known, which is called the initial position and posture of the first sensor in the vehicle coordinate system. Calibration of the first sensor can also be understood as correcting the initial position and posture of the first sensor in the vehicle coordinate system, and its purpose is to improve the detection accuracy of the first sensor during use. After the vehicle leaves the factory or after maintenance, repair, or replacement, the initial position and posture of the first sensor mounted on the vehicle may shift, which may cause the acquired data to have a large deviation from the original positioning origin. Therefore, the first sensor needs to be calibrated after leaving the factory and after the vehicle carrying the sensor has been running for a period of time.

[0078] After calculating the calibration pose of the first sensor, determine whether there is a difference between the calibration pose and the initial pose. If there is no difference between the two, use the initial pose as the calibration pose of the first sensor in the vehicle coordinate system. If there is a difference between the two, adjust the initial pose according to the difference information between the calibration pose and the initial pose to obtain the pose of the first sensor in the vehicle coordinate system. That is, the calibration of the first sensor is completed. During the subsequent use of the vehicle, the first sensor obtains accurate data based on the calibration pose.

[0079] The technical solution proposed in the embodiment of the present application is that a first target and a second target are arranged in advance in the surrounding environment of a vehicle equipped with a first sensor. The arrangement positions of the first target and the second target are different. A second sensor is arranged on the second target. The calibration process includes: obtaining the first data collected by the first sensor (including the data of the area where the second target is located) and the second data collected by the second sensor (including the data of the area where the first target is located), and then determining the first position of the second target in the coordinate system of the first sensor according to the first data, and determining the second position of the second target in the coordinate system of the vehicle according to the second data. After obtaining the first position and the second position, the calibration position of the first sensor in the coordinate system of the vehicle is determined according to the first position and the second position, thereby realizing the calibration of the sensor carried on the vehicle. For the calibration of the sensor carried on the vehicle, the calibration scheme is simple, the site selection of the calibration site is simple, the target is easy to deploy, and the calibration work can be carried out anytime and anywhere without the help of professional equipment, which is conducive to reducing the calibration cost. After the calibration work is completed, the target can be taken away immediately without occupying the site.

[0080] The following Figure 2 The specific implementation methods of each step in the embodiment shown are described as follows:

[0081] In a possible implementation, a third target is arranged on the vehicle, the second data also includes data of the area where the third target is located, and determining the second position and posture of the second target in the vehicle coordinate system according to the second data includes the following scheme:

[0082] Determine a third position and posture of the third target in the coordinate system where the second sensor is located according to the second data;

[0083] Determine a fourth posture of the second sensor in the vehicle coordinate system according to the third posture;

[0084] The second posture is determined according to the fourth posture and a preset posture; wherein the preset posture is the posture of the second target in the coordinate system where the second sensor is located.

[0085] like Figure 1 As shown, a third target is also arranged on the vehicle, B3 represents the third target, there are multiple third targets, which are arranged at different positions on the vehicle, and the second data collected by the second sensor includes not only the data of the area where the first target is located, but also the data of the area where the third target is located.

[0086] like Figure 3 As shown, Figure 3 A schematic diagram of the target is shown, Figure 3 All squares except the pure color squares are called marking patterns, and the styles of all marking patterns are different. The patterns on the first target, the second target, and the third target are the same as Figure 3 The patterns on the targets shown are similar, also including solid color squares and marking patterns, and the pattern of all marking patterns on each target is also different.

[0087] After obtaining the second data, the pose of the target pattern in the coordinate system of the second sensor is calculated based on the second data, that is, the third pose of the first target and the third target in the coordinate system of the second sensor is obtained, and the target pattern includes the marking pattern on the first target and the marking pattern on the third target. Since the target pattern includes the marking pattern on the first target and the marking pattern on the third target, the calculated third pose includes multiple, and then, the multiple third poses are optimized together to obtain the pose of the second sensor in the vehicle coordinate system at different times, and the pose of the first target and the third target in the vehicle coordinate system at different times and / or different positions, which are expressed as Among them, the postures of the second sensor in the vehicle coordinate system at different times, that is, the obtained postures of the second sensor in the vehicle coordinate system have multiple postures, and the multiple postures of the second sensor in the vehicle coordinate system are verified with each other to obtain a fourth posture, which is expressed as

[0088] After obtaining the fourth pose, the second pose is calculated based on the fourth pose and the preset pose. The preset pose is expressed as It is the pose of the second target in the coordinate system of the second sensor. The pose of the second target in the coordinate system of the second sensor is calibrated in advance. The second pose is calculated according to the fourth pose and the preset pose, that is:

[0089]

[0090] In a possible implementation, the vehicle includes a vehicle, that is, when the vehicle is a vehicle, such as Figure 1 As shown, Vehicle represents a vehicle, the third target B3 is set on the wheel hub of the vehicle, the third target B3 includes at least 4, and at least one third target B3 is set on each wheel hub. The sensor calibration method also includes the following schemes:

[0091] Constructing the vehicle coordinate system. Constructing the vehicle coordinate system includes the following schemes:

[0092] Determining the center point of each wheel according to the third target set on the wheel hub of the vehicle;

[0093] Connect the center points of the wheels in sequence to obtain a target plane;

[0094] Taking the center point of the rear axle of the vehicle as the origin of the vehicle coordinate system;

[0095] Taking the upward normal vector of the target plane as the direction of the Z axis of the vehicle coordinate system;

[0096] Determine the direction of the vehicle head as the direction of the X-axis of the vehicle coordinate system;

[0097] The cross product of the X-axis and the Z-axis is used as the Y-axis of the vehicle coordinate system, thereby constructing the vehicle coordinate system.

[0098] like Figure 4 As shown, Figure 4 A schematic diagram of a vehicle coordinate system is shown. Figure 4 In the figure, Q1 and Q2 represent the front wheels, H1 and H2 represent the rear wheels, and the third target B3 is set on the wheel hubs of Q1, Q2, H1 and H2. According to the third target B3 set on the wheel hubs of Q1, Q2, H1 and H2, the center points of Q1, Q2, H1 and H2 can be located, that is, 4 center points, and then the 4 center points are connected in sequence to obtain the target plane, which is represented by S, that is, Figure 4 After obtaining the target plane, take the center point of the rear axle of the vehicle as the origin O of the vehicle coordinate system, and then set the normal vector of the target plane upward As the positive direction of the Z axis of the vehicle coordinate system, the direction of the vehicle head is determined as the direction of the X axis of the vehicle coordinate system, that is, the positive direction of the X axis, that is, Figure 4 The positive direction of the middle X-axis is toward the front of the vehicle, and the cross product of the X-axis and the Z-axis is used as the Y-axis of the vehicle coordinate system, that is, the positive direction of the Y-axis is the direction from the center point of the rear axle to the left rear wheel. Figure 4 The origin O of the vehicle coordinate system is the center point of the connecting axis between H1 and H2 (the rear axle of the vehicle).

[0099] It can be understood that the origin O of the coordinate system can also be the center point of the front axle of the vehicle, and this application does not make the sole limitation to this.

[0100] In a possible implementation, obtaining the calibration pose of the first sensor in the vehicle coordinate system according to the first pose and the second pose includes the following scheme:

[0101] Obtaining a relative posture of the second target relative to a vehicle coordinate system according to the first posture and an initial posture of the first sensor;

[0102] Determining whether the relative posture and the second posture are the same;

[0103] If the relative posture is different from the second posture, determining a difference between the relative posture and the second posture;

[0104] adjusting an initial position of the first sensor in the vehicle coordinate system according to the difference;

[0105] The calibration pose is determined according to the adjusted initial pose.

[0106] The first pose of the second target in the first sensor coordinate system is obtained through the first data collected by the first sensor, and the second pose is obtained through the second data and the second pose collected by the second sensor. By judging whether the relative pose of the second target obtained according to the first pose with respect to the vehicle coordinate system is the same as the second pose, it is possible to determine whether the initial pose of the first sensor in the vehicle coordinate system needs to be adjusted.

[0107] If the relative posture is the same as the second posture, it means that the initial posture of the first sensor in the vehicle coordinate system does not need to be adjusted; if the relative posture is different from the second posture, it means that the initial posture of the first sensor in the vehicle coordinate system needs to be adjusted, then the difference between the relative posture and the second posture is calculated, that is, the difference information between the relative posture and the second posture is obtained, and the initial posture of the first sensor in the vehicle coordinate system is adjusted according to the difference to obtain the adjusted initial posture, and then the calibration posture of the first sensor in the vehicle coordinate system is obtained according to the adjusted initial posture, and the calibration of the first sensor is completed. In a possible implementation method, determining the calibration posture according to the adjusted initial posture includes the following scheme:

[0108] Verifying the validity of the adjusted initial pose;

[0109] When the validity verification of the adjusted initial posture is passed, determining the adjusted initial posture as the calibration posture;

[0110] It can be understood that the method further includes: if the validity verification of the adjusted initial posture fails, reacquiring the initial posture.

[0111] It can be understood that if the validity of the initial posture has not been passed, the method needs to keep reacquiring the initial posture until the validity of the initial position is verified, and then determine the adjusted initial posture as the calibration posture.

[0112] By judging the validity of the adjusted initial posture, it is helpful to improve the accuracy of the first sensor calibration.

[0113] In a possible implementation, the first target includes a plurality of sub-targets with different arrangement postures. Figure 5 As shown, Figure 5 shows a schematic diagram of a first target within a detection area of ​​a first sensor, Figure 5The first target is shown in , including 2 sub-targets B11, 2 sub-targets B12 and 4 sub-targets B13, among which sub-targets B11 and sub-targets B12 are arranged in a posture of standing on the ground, which is equivalent to standing upright on the ground, but the specific arrangement postures of sub-targets B11 and sub-targets B12 are different, for example, the arrangement posture of sub-target B11 is facing the vehicle, the arrangement posture of sub-target B12 is facing the vehicle sideways, and sub-target B13 is arranged in a posture of being flat on the ground, which is equivalent to being attached to the ground, that is, the arrangement postures of sub-targets B11, sub-targets B12 and sub-targets B13 are all different. The validity of the initial posture after verification after adjustment includes the following schemes:

[0114] Selecting a sub-target with a layout posture of a preset posture from the plurality of sub-targets to obtain a verification target;

[0115] Determine a fifth pose of the verification target in the vehicle coordinate system; wherein the fifth pose is a pose of the verification target relative to the vehicle coordinate system obtained according to the point cloud data acquired by the second sensor. wherein the second sensor is a sensor fixed on the second target.

[0116] Determining a sixth pose of the verification target in the coordinate system of the first sensor;

[0117] Converting the sixth posture according to the adjusted initial posture to obtain a converted posture, wherein the converted posture is a posture of the verification target relative to the vehicle coordinate system;

[0118] It is determined whether the fifth posture is consistent with the converted posture to verify the validity of the adjusted initial posture.

[0119] When verifying the validity of the adjusted initial position, a sub-target with a preset posture is selected from multiple sub-targets to obtain a verification target. For example, if the preset posture is a posture of standing up and facing the vehicle, the layout posture of sub-target B11 is consistent with the preset posture, and sub-target B11 is used as the verification target.

[0120] After obtaining the verification target, the fifth pose of the verification target in the vehicle coordinate system is calculated, and the sixth pose of the verification target in the coordinate system where the first sensor is located is calculated; wherein, the calculation method of the fifth pose is the same as the calculation method of the second pose, and the calculation method of the sixth pose is the same as the calculation method of the pose of the second target in the coordinate system where the first sensor is located. For details, please refer to the aforementioned implementation method, which will not be repeated here.

[0121] After obtaining the converted posture, compare the converted posture with the fifth posture to determine whether the two are consistent. If the difference between the converted posture and the fifth posture is within the preset range, it is considered that the validity verification of the adjusted initial posture has passed; if the difference between the converted posture and the fifth posture is not within the preset range, it is considered that the validity verification of the adjusted initial posture has failed.

[0122] In addition, since the adjusted initial pose can be calculated through the pose and second pose of the second target in the coordinate system where the first sensor is located, when the adjusted initial pose is used as the calibration pose of the first sensor in the vehicle coordinate system, that is, the calibration pose is calculated through the pose and second pose of the second target in the coordinate system where the first sensor is located, then, when calibrating the first sensor, the difference between the calibration pose and the initial pose of the first sensor in the vehicle coordinate system is calculated, and then the difference is used to adjust the initial pose, so that the initial pose is adjusted to the calibration pose, that is, the calibration of the first sensor is completed.

[0123] The following is another embodiment of a sensor calibration method provided in an embodiment of the present application.

[0124] Taking the vehicle as an example, the application scenarios of a sensor calibration method provided in an embodiment of the present application include: calibrating the sensors installed on the vehicle when the vehicle leaves the factory; calibrating the sensors installed on the vehicle when the vehicle is maintained, repaired or replaced.

[0125] like Figure 1 As shown, Figure 1 In the figure, Vehicle represents a vehicle, C1 represents a first sensor, specifically a vehicle-mounted radar, such as a lidar, C2 represents a second sensor, specifically a camera, the target B1 in the dotted square box is the first target, also called a ground target, and the target B2 in the dotted elliptical box is the second target, also called a calibration target.

[0126] The coordinate system where the first sensor is located is the coordinate system where the vehicle-mounted radar is located, also known as the radar coordinate system; the coordinate system where the second sensor is located is the coordinate system where the camera is located, also known as the camera coordinate system; the vehicle coordinate system is called the vehicle body coordinate system. Before calibrating the vehicle-mounted radar, the first target and the second target are arranged on the ground in front of the vehicle, the ground behind the vehicle, the ground on the left side, and the ground on the right side, and the third target is set on the wheel hub of the vehicle. The arrangement positions of the first target and the second target are different, that is, the arrangement position of the first target and the arrangement position of the second target are independent of each other, the two do not overlap, and the first target includes a plurality of sub-targets with different arrangement postures, and a camera is arranged on the second target. Among them, a large number of first targets are arranged within the detection range of the vehicle-mounted radar. After the arrangement is completed, the relative position and posture between the first target and the second target are fixed.

[0127] Figure 6 Another schematic flow chart of a sensor calibration method provided in an embodiment of the present application is shown. Figure 6 As shown, the sensor calibration method provided in the embodiment of the present application is applied to an electronic device, which may be a terminal device mounted on a vehicle or an external device, such as a computer. The sensor calibration method includes the following schemes:

[0128] S210: Construct a vehicle body coordinate system where the vehicle is located.

[0129] S220: Acquire point cloud data of a second target acquired by the vehicle-mounted radar and a target image acquired by the camera.

[0130] In an exemplary embodiment, point cloud data of the second target collected by the vehicle-mounted radar at different times is obtained, that is, the point cloud data includes multiple points, and a target image collected by the camera is obtained, and the target image includes images of the areas where the first target and the third target are located.

[0131] As an optional embodiment, the second target includes multiple targets. After the second targets are arranged, the detection range formed by the multiple second targets is greater than or equal to the area where the vehicle and the first target are located. And the target images captured by two adjacent cameras have an intersection, that is, the target images captured by the two adjacent cameras have the same part, so that it can be ensured that all the data of the area where the first target is located around the vehicle is collected, avoiding data leakage. As another optional embodiment, the second target can be a movable target, and by moving the second target, the detection range of the second target can include the area where the vehicle and the first target are located. In the process of moving the second target, there is an intersection between any two acquired target images, that is, there are the same parts in the two data collected by the second target, so that it can be ensured that all the data of the area where the first target is located around the vehicle is collected.

[0132] S230: Determine the first position of the second target in the vehicle-mounted laser radar coordinate system according to the point cloud data.

[0133] The first position of the second target is determined according to the point cloud data. The position information and angle information of the second target relative to the vehicle-mounted radar are obtained through the point cloud data collected by the vehicle-mounted radar. The first position is expressed as

[0134] S240: Determine a second position and posture of the second target in the vehicle body coordinate system according to the target image.

[0135] The second position and posture of the second target is determined according to the target image. The position and angle information of the second target relative to the vehicle coordinate system are obtained mainly through the target image captured by the camera. The second position and posture is expressed as

[0136] Among them, the scheme for determining the second pose of the second target in the vehicle coordinate system according to the target image is as follows:

[0137] like Figure 1 As shown, a third target is also arranged on the vehicle, B3 represents the third target, there are multiple third targets, which are arranged at different positions on the vehicle, and the target image collected by the camera includes not only the data of the area where the first target is located, but also the data of the area where the third target is located. As an optional implementation, B3 is set on the wheel hub of the vehicle.

[0138] like Figure 3 As shown, Figure 3 A schematic diagram of the target is shown, Figure 3 All squares except the pure color squares are called marking patterns, and the styles of all marking patterns are different. The patterns on the first target, the second target, and the third target are the same as Figure 3 The patterns on the targets shown are similar, also including solid color squares and marking patterns, and the pattern of all marking patterns on each target is also different.

[0139] After obtaining the target image, the pose of the target pattern in the coordinate system of the camera is calculated based on the target image, that is, the third pose of the first target and the third target in the coordinate system of the camera is obtained, and the target pattern includes the marking pattern on the first target and the marking pattern on the third target. Since the target pattern includes the marking pattern on the first target and the marking pattern on the third target, the calculated third pose includes multiple ones, and then the multiple third poses are optimized together to obtain the pose of the camera in the vehicle coordinate system at different times, and the pose of the first target and the third target in the vehicle coordinate system at different times, which are expressed as Among them, the camera's position and posture in the vehicle coordinate system at different times, that is, the obtained camera's position and posture in the vehicle coordinate system has multiple positions and postures. According to the mutual verification and optimization between the multiple position and postures, the fourth position and posture are obtained, which is expressed as

[0140] After obtaining the fourth pose, the second pose is calculated based on the fourth pose and the preset pose. The preset pose is expressed as It is the position and posture of the second target in the coordinate system of the camera. The position and posture of the second target in the coordinate system of the camera is calibrated in advance, that is:

[0141]

[0142] S250: Obtaining a calibration pose of the vehicle-mounted radar in the vehicle body coordinate system according to the first pose and the second pose.

[0143] Before calibrating the vehicle-mounted radar, the position and posture of the vehicle-mounted radar in the vehicle body coordinate system is known, which is called the initial position and posture of the vehicle-mounted radar in the vehicle body coordinate system. Calibration of the vehicle-mounted radar can also be understood as correcting the initial position and posture of the vehicle-mounted radar in the vehicle body coordinate system. Its purpose is to improve the detection accuracy of the vehicle-mounted radar. When the vehicle leaves the factory or after maintenance, repair, or replacement, the initial position and posture of the vehicle-mounted radar mounted on the vehicle may be inaccurate, which may cause a large deviation in the acquired data. Therefore, the vehicle-mounted radar needs to be calibrated.

[0144] The relative pose of the second target relative to the vehicle coordinate system is obtained according to the first pose and the initial position of the vehicle-mounted laser radar; whether there is a difference between the relative pose and the second pose, if there is no difference between the two, the initial pose is used as the calibration pose of the vehicle-mounted radar in the vehicle body coordinate system; if there is a difference between the two, the initial pose is adjusted according to the difference information between the relative pose and the second pose to obtain the calibration pose of the vehicle-mounted radar in the vehicle body coordinate system, that is, the calibration of the vehicle-mounted radar is completed, and the vehicle-mounted radar obtains accurate data based on the calibration pose during the subsequent use of the vehicle.

[0145] Determining the calibration pose of the vehicle-mounted radar in the vehicle coordinate system according to the adjusted initial pose includes the following schemes:

[0146] Considering that the calculated adjusted initial pose of the vehicle-mounted radar in the vehicle coordinate system may be inaccurate, if the calibration pose is determined based on the adjusted initial pose, the obtained calibration pose will also be inaccurate. Therefore, it is necessary to judge the accuracy of the adjusted initial pose.

[0147] The accuracy of the adjusted initial pose is determined by verifying the validity of the adjusted initial pose, that is, the validity of the adjusted initial pose is verified. If the validity of the adjusted initial pose is verified, it means that the calculated adjusted initial pose is accurate, and it can be used as the calibration pose of the vehicle-mounted radar. The adjusted initial pose is determined as the calibration pose of the vehicle-mounted radar. By judging the validity of the adjusted initial pose, it is beneficial to improve the accuracy of the vehicle-mounted radar calibration.

[0148] like Figure 5 As shown, when verifying the validity of the adjusted initial posture, a sub-target with a preset posture is selected from multiple sub-targets to obtain a verification target. For example, the preset posture is a posture of standing up and facing the vehicle, and the layout posture of sub-target B11 is consistent with the preset posture, so sub-target B11 is used as the verification target.

[0149] After obtaining the verification target, the fifth pose of the verification target in the vehicle body coordinate system is calculated, and the sixth pose of the verification target in the coordinate system where the vehicle-mounted radar is located is calculated; wherein, the calculation method of the fifth pose is the same as the calculation method of the second pose, and the calculation method of the sixth pose is the same as the calculation method of the pose of the second target in the coordinate system where the vehicle-mounted radar is located.

[0150] The adjusted initial pose is expressed as According to the point cloud data, the position and posture of the second target in the coordinate system of the vehicle-mounted radar can also be determined, which is expressed as The adjusted initial position and posture can also be based on the position and posture of the second target in the coordinate system of the vehicle-mounted radar and the second position and posture Calculated, that is: Therefore, to verify the validity of the adjusted initial pose, after obtaining the fifth pose and the sixth pose, based on the calculation formula of the adjusted initial pose, the sixth pose is transformed using the adjusted initial pose to obtain the transformed pose, that is, the transformed pose is to transform the sixth pose of the verification target in the coordinate system of the vehicle-mounted radar to the pose in the vehicle coordinate system.

[0151] In addition, since the adjusted initial pose can be calculated through the pose and the second pose of the second target in the coordinate system where the vehicle-mounted radar is located, when the adjusted initial pose is used as the calibration pose of the vehicle-mounted radar in the vehicle body coordinate system, that is, the calibration pose is calculated through the pose and the second pose of the second target in the coordinate system where the vehicle-mounted radar is located, then, when calibrating the vehicle-mounted radar, the difference between the calibration pose and the initial pose of the vehicle-mounted radar in the vehicle body coordinate system is calculated, and then the difference is used to adjust the initial pose, so that the initial pose is adjusted to the calibration pose, that is, the calibration of the vehicle-mounted radar is completed.

[0152] The technical solution proposed in the embodiment of the present application is to arrange the first target and the second target in the surrounding environment of the vehicle equipped with the vehicle-mounted radar in advance. The arrangement positions of the first target and the second target are different. A camera is arranged on the second target. The calibration process includes: constructing a body coordinate system where the vehicle is located, obtaining the point cloud data of the second target collected by the vehicle-mounted radar, and the target image collected by the camera including the image of the area where the first target and the third target are located, and then determining the first position of the second target in the body coordinate system according to the point cloud data, and determining the second position of the second target in the body coordinate system according to the target image. After obtaining the first position and the second position, the calibration position of the vehicle-mounted radar in the body coordinate system is determined according to the first position and the second position, thereby realizing the calibration of the vehicle-mounted radar carried on the vehicle. For the calibration of the vehicle-mounted radar carried on the vehicle, the calibration scheme is simple, the calibration site selection is simple, the target is easy to deploy, and the calibration work can be carried out anytime and anywhere without the help of professional equipment, which is conducive to reducing the calibration cost. After the calibration work is completed, the target can be taken away immediately without occupying the site.

[0153] The following is an embodiment of the device of the present application, which can be used to execute the embodiment of the method of the present application. For details not disclosed in the embodiment of the device of the present application, please refer to the embodiment of the method of the present application.

[0154] Figure 7 FIG. 1 shows a schematic diagram of the structure of a sensor calibration device provided in an embodiment of the present application. Figure 7 As shown, a first target and a second target are arranged in the surrounding environment of a vehicle equipped with a first sensor, the first target and the second target are arranged at different positions, and a second sensor is arranged on the second target. The sensor calibration device 700 includes:

[0155] The data acquisition module 710 is used to acquire first data collected by a first sensor and second data collected by a second sensor; wherein the first data includes data of an area where the second target is located, and the second data includes data of an area where the first target is located;

[0156] A first calculation module 720, configured to determine a first pose of the second target in a first sensor coordinate system according to the first data;

[0157] A second calculation module 730, configured to determine a second position and posture of the second target in the vehicle coordinate system according to the second data;

[0158] The third calculation module 740 is used to obtain a calibration pose of the first sensor in the vehicle coordinate system according to the first pose and the second pose.

[0159] In a possible implementation, a third target is arranged on the vehicle, the second data further includes data of an area where the third target is located, and the second calculation module 730 includes:

[0160] A first calculation unit, configured to determine a third position and posture of the third target in the coordinate system where the second sensor is located according to the second data;

[0161] A second calculation unit, configured to determine a fourth posture of the second sensor in the vehicle coordinate system according to the third posture;

[0162] The third calculation unit is configured to obtain a calibration pose of the first sensor in the vehicle coordinate system according to the first pose and the second pose.

[0163] In a possible implementation, the fourth posture of the second sensor in the vehicle coordinate system is determined according to the third posture, and the sensor calibration device 700 further includes:

[0164] A coordinate system construction unit, used to construct the vehicle coordinate system;

[0165] The coordinate system construction unit comprises:

[0166] A center acquisition subunit, used to determine the center point of each wheel according to the third target set on the wheel hub of the vehicle;

[0167] A plane construction subunit, used for connecting the center points of the wheels in sequence to obtain a target plane;

[0168] The coordinate system generating subunit is used to take the center point of the rear axle of the vehicle as the origin of the vehicle coordinate system; take the upward normal vector of the target plane as the direction of the Z axis of the vehicle coordinate system; determine the orientation of the front of the vehicle as the direction of the X axis of the vehicle coordinate system; take the cross product of the X axis and the Z axis as the Y axis of the vehicle coordinate system, thereby constructing a vehicle coordinate system.

[0169] In a possible implementation, the third calculation module 730 includes:

[0170] A judgment unit, configured to obtain a relative posture of the second target relative to the vehicle coordinate system according to the first posture and the initial posture of the first sensor; judge whether the relative posture is the same as the second posture; judge whether the first posture is the same as the second posture;

[0171] a fourth calculation unit, configured to determine a difference between the relative posture and the second posture when the relative posture is different from the second posture;

[0172] an adjusting unit, configured to adjust an initial posture of the first sensor in the vehicle coordinate system according to the difference to obtain the adjusted initial posture;

[0173] A determination unit is used to determine the calibration pose according to the adjusted initial pose.

[0174] In a possible implementation manner, the determining unit includes:

[0175] A verification subunit, used to verify the validity of the adjusted initial posture;

[0176] The determination subunit is used to determine the adjusted initial posture as the calibration posture when the validity verification of the adjusted initial posture is passed.

[0177] In a possible implementation, the first target includes a plurality of sub-targets with different arrangement postures, and the verification sub-unit includes:

[0178] A selection sub-unit is used to select a sub-target whose arrangement posture is a preset posture from the plurality of sub-targets to obtain a verification target;

[0179] A first computing subunit, configured to determine a fifth pose of the verification target in the vehicle coordinate system;

[0180] A second computing subunit is used to determine a sixth posture of the verification target in the coordinate system where the first sensor is located;

[0181] A conversion subunit, used for converting the sixth posture according to the adjusted initial posture to obtain a converted posture;

[0182] The judging subunit is used to judge whether the fifth posture is consistent with the converted posture, so as to verify the validity of the adjusted initial posture.

[0183] In a possible implementation, the second targets include a plurality of second targets, and the second data collected by two adjacent second sensors have an intersection.

[0184] It should be noted that the sensor calibration device provided in the above embodiment only uses the division of the above functional modules as an example when executing the sensor calibration method. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the sensor calibration device provided in the above embodiment belongs to the same concept as the sensor calibration method embodiment. Therefore, for details not disclosed in the device embodiment of the present application, please refer to the above-mentioned sensor calibration method embodiment of the present application, which will not be repeated here.

[0185] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0186] Figure 8 A schematic structural diagram of an electronic device provided in an embodiment of the present application is shown.

[0187] For example, Figure 8 As shown, the electronic device 800 includes: a memory 801 and a processor 802, wherein the memory 801 stores an executable program code 8011, and the processor 802 is used to call and execute the executable program code 8011 to perform a sensor calibration method.

[0188] In this embodiment, the electronic device can be divided into functional modules according to the above method example. For example, each functional module can be corresponded to, or two or more functions can be integrated into one processing module. The above integrated module can be implemented in the form of hardware. It should be noted that the division of modules in this embodiment is schematic and is only a logical function division. There may be other division methods in actual implementation.

[0189] In the case of dividing each functional module according to each function, the electronic device may include: a data acquisition module, a first calculation module, a second calculation module, a third calculation module, etc. It should be noted that all relevant contents of each step involved in the above method embodiment can be referred to the functional description of the corresponding functional module, which will not be repeated here.

[0190] The electronic device provided in this embodiment is used to execute the above-mentioned sensor calibration method, and thus can achieve the same effect as the above-mentioned implementation method.

[0191] In the case of an integrated unit, the electronic device may include a processing module and a storage module. The processing module may be used to control and manage the actions of the electronic device. The storage module may be used to support the electronic device in executing mutual program codes and data.

[0192] The processing module may be a processor or a controller, which may implement or execute various exemplary logic blocks, modules and circuits disclosed in the present application. The processor may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of digital signal processing (DSP) and a microprocessor, etc. The storage module may be a memory.

[0193] This embodiment also provides a computer-readable storage medium, in which a computer program code is stored. When the computer program code is executed on a computer, the computer executes the above-mentioned related method steps to implement a sensor calibration method in the above-mentioned embodiment.

[0194] This embodiment further provides a computer program product. When the computer program product is run on a computer, the computer is enabled to execute the above-mentioned related steps to implement a sensor calibration method in the above-mentioned embodiment.

[0195] In addition, the electronic device provided in the embodiments of the present application may specifically be a chip, a component or a module, and the electronic device may include a connected processor and a memory; wherein the memory is used to store instructions, and when the electronic device is running, the processor may call and execute instructions so that the chip executes a sensor calibration method in the above-mentioned embodiments.

[0196] Among them, the electronic device, computer-readable storage medium, computer program product or chip provided in this embodiment is used to execute the corresponding sensor calibration method provided above. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects in the corresponding sensor calibration method provided above, and will not be repeated here.

[0197] Through the description of the above implementation methods, technical personnel in the relevant field can understand that for the convenience and simplicity of description, only the division of the above-mentioned functional modules is used as an example. In actual applications, the above-mentioned functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.

[0198] In the embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of modules or units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0199] The above contents are only specific implementation methods of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A sensor calibration method, characterized in that: A first target and a second target are arranged in the surrounding environment of the vehicle equipped with the first sensor, the first target and the second target are arranged at different positions, and the second target is provided with a second sensor; The sensor calibration method comprises: Acquire first data collected by a first sensor and second data collected by a second sensor, wherein the first data includes data of an area where the second target is located, and the second data includes data of an area where the first target is located; Determine a first pose of the second target in a first sensor coordinate system according to the first data; Determine a second pose of the second target in the vehicle coordinate system according to the second data; According to the first posture and the second posture, a calibration posture of the first sensor in the vehicle coordinate system is obtained.

2. The sensor calibration method according to claim 1, characterized in that: A third target is arranged on the carrier, and the second data further includes data of an area where the third target is located; Determining a second position and posture of the second target in the vehicle coordinate system according to the second data includes: Determine a third position and posture of the third target in the coordinate system where the second sensor is located according to the second data; Determine a fourth posture of the second sensor in the vehicle coordinate system according to the third posture; The second posture is determined according to the fourth posture and a preset posture, wherein the preset posture is the posture of the second target in the coordinate system where the second sensor is located.

3. The sensor calibration method according to claim 2, characterized in that: The vehicle includes a vehicle, and the third target is disposed on a wheel hub of the vehicle; The sensor calibration method further comprises: Determining the center point of each wheel according to the third target set on the wheel hub of the vehicle; Connect the center points of the wheels in sequence to obtain a target plane; Taking the center point of the rear axle of the vehicle as the origin of the vehicle coordinate system; Taking the upward normal vector of the target plane as the direction of the Z axis of the vehicle coordinate system; Determine the direction of the vehicle head as the direction of the X-axis of the vehicle coordinate system; The cross product of the X-axis and the Z-axis is used as the Y-axis of the vehicle coordinate system, thereby constructing the vehicle coordinate system.

4. The sensor calibration method according to any one of claims 1 to 3, characterized in that: The obtaining, according to the first posture and the second posture, a calibration posture of the first sensor in the vehicle coordinate system comprises: Obtaining a relative posture of the second target relative to the vehicle coordinate system according to the first posture and the initial posture of the first sensor; Determining whether the relative posture and the second posture are the same; If the relative posture is different from the second posture, determining a difference between the relative posture and the second posture; adjusting an initial position of the first sensor in the vehicle coordinate system according to the difference; The calibration pose is determined according to the adjusted initial pose.

5. The sensor calibration method according to claim 4, characterized in that: Determining the calibration pose according to the adjusted initial pose includes: Verify the validity of the adjusted initial pose; When the validity verification of the adjusted initial posture is passed, determining the adjusted initial posture as the calibration posture; If the validity verification of the adjusted initial posture fails, the initial posture is reacquired.

6. The sensor calibration method according to claim 5, characterized in that: The first target includes a plurality of sub-targets with different arrangement postures; The verifying the validity of the adjusted initial posture comprises: Selecting a sub-target with a layout posture of a preset posture from the plurality of sub-targets to obtain a verification target; Determining a fifth pose of the verification target in the vehicle coordinate system; Determining a sixth pose of the verification target in the coordinate system of the first sensor; Convert the sixth posture according to the adjusted initial posture to obtain a converted posture; It is determined whether the fifth posture is consistent with the converted posture to verify the validity of the adjusted initial posture.

7. The sensor calibration method according to any one of claims 1 to 3, characterized in that: The second targets include a plurality of second targets, and the second data collected by two adjacent second sensors have an intersection.

8. A sensor calibration device, characterized in that: A first target and a second target are arranged in the surrounding environment of the vehicle equipped with the first sensor, the first target and the second target are arranged at different positions, and the second target is provided with a second sensor; The sensor calibration device comprises: A data acquisition module, used to acquire first data collected by a first sensor and second data collected by a second sensor; wherein the first data includes data of an area where the second target is located, and the second data includes data of an area where the first target is located; A first calculation module, used for determining a first pose of the second target in a first sensor coordinate system according to the first data; A second calculation module, used for determining a second position and posture of the second target in the vehicle coordinate system according to the second data; The third calculation module is used to obtain the calibration posture of the first sensor in the vehicle coordinate system according to the first posture and the second posture.

9. An electronic device, characterized in that: The electronic device comprises: A memory for storing executable program codes; A processor, configured to call and run the executable program code from the memory, so that the electronic device executes the sensor calibration method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed, the sensor calibration method according to any one of claims 1 to 7 is implemented.

Images