Calibration board, calibration component, calibration device, calibration system and calibration method

Abstract

The invention provides a calibration board, a calibration component, a calibration device, a calibration system, a calibration method, a calibration system, electronic equipment and a nonvolatile readable storage medium. The calibration plate comprises a calibration carrier plate, a plurality of identification codes and a metal block; the metal block is fixed at the center of the calibration carrier plate, and the plurality of mark codes are fixed on the calibration carrier plate and surround the metal block; the identification codes carry two-dimensional code information which can be identified by the sensor, and identity information corresponding to the two-dimensional code information of all the identification codes is different. Since the two-dimensional code information on the plurality of identification codes corresponds to different identity information, the ID of the metal block can be quickly identified according to the identity information, confusion caused by over-high similarity between different metal blocks is avoided, the problem that the calibration plate is inaccurately identified by using the edge information of the calibration plate in the prior art is avoided, and the calibration precision of the vehicle sensor is improved.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a calibration board, a calibration component, a calibration device, a calibration system, a calibration method, a system, an electronic device and a non-volatile readable storage medium. Background Art

[0002] With the development of vehicle autonomous driving technology, vehicles can obtain information about the surrounding body through an autonomous driving perception system that organically combines multiple sensors such as lidar, cameras, and millimeter-wave radar, so that the system can automatically drive the vehicle to the destination specified by the user. In order to achieve the fusion of multiple different sensors and improve the performance of the perception system, it is often necessary to transform the data obtained by these sensors into a unified three-dimensional space coordinate system. Due to the tolerances when the sensors are manufactured and installed on the vehicle, as well as vibrations during the movement of the vehicle, the installation positions of these sensors deviate from the preset positions, making it difficult to ensure the accuracy of the measurement. The manual calibration method is time-consuming and labor-intensive. As the number of sensors on the vehicle increases, it is difficult to meet the needs of vehicle mass production.

[0003] In order to solve the above problems, the existing technology often uses automatic calibration methods to calibrate multiple different sensors on the vehicle. Multiple sensors recognize multiple position information obtained by the same calibration plate, and adjust the sensors according to the differences in these position information, thereby realizing the calibration function of multiple sensors. However, the existing calibration method requires multiple combined calibration plates, such as chessboards or dot grids as cooperative markers, and extracts the corner points of the chessboard or dot grid in the calibration plate for sensor calibration. The automatic matching effect of key points is poor, and the automatic calibration effect of sensors is poor. Summary of the invention

[0004] The present application provides a calibration plate, a calibration component, a calibration device, a calibration system, a calibration method, a system, an electronic device and a non-volatile readable storage medium. The calibration plate provided by the present application includes a metal block located in the center for sensor calibration and a plurality of marker codes encoding ID information surrounding the metal block. Since the two-dimensional code information on the plurality of marker codes corresponds to different ID information, the vehicle's sensor can realize automatic recognition on images and point cloud data according to different ID information, and the automatic matching effect of key points is good.

[0005] In a first aspect, the present application provides a calibration board for calibrating sensors of a vehicle autonomous driving system, where the sensors of the vehicle autonomous driving system include millimeter wave radars and cameras;

[0006] Including: calibration carrier, multiple marking codes and millimeter wave radar calibration unit;

[0007] The millimeter-wave radar calibration unit is fixed at the center of the calibration carrier, and is used to provide feedback on the calibration results of the millimeter-wave radar according to the calibration data sent by the millimeter-wave radar, so that the vehicle automatic driving system can calibrate the millimeter-wave radar according to the calibration results of the millimeter-wave radar, wherein the millimeter-wave reflectivity of the millimeter-wave radar calibration unit is higher than the millimeter-wave reflectivity of the calibration carrier;

[0008] A plurality of marking codes are fixed on the calibration carrier and surround the millimeter wave radar calibration unit;

[0009] The marker code carries QR code information for sensor recognition, which is used to provide feedback on the camera's calibration results based on the calibration data sent by the camera, so that the vehicle's automatic driving system can calibrate the camera based on the camera's calibration results. The identity information corresponding to the QR code information of all marker codes is different.

[0010] Optionally, in the calibration plate provided by the present application, the marking code includes a first area and a second area, the laser absorbency of the second area of ​​the marking code is greater than the laser absorbency of the first area of ​​the marking code, the color of the calibration carrier is different from the color of the second area of ​​the marking code, and the laser absorbency of the surface of the calibration carrier is different from the light absorbency of the surface of the second area of ​​the marking code.

[0011] Optionally, in the calibration plate provided in the present application, the second area of ​​the marking code is obtained by spraying a coating having a higher laser absorption than that of the calibration carrier plate.

[0012] Optionally, in the calibration plate provided in the present application, the millimeter-wave radar calibration unit is a polygonal structure, the marking code is a polygonal result, the vertices of multiple marking codes close to the millimeter-wave radar calibration unit are connected to the vertices of the metal block, and the number of vertices of the millimeter-wave radar calibration unit is greater than or equal to 4.

[0013] Optionally, in the calibration plate provided in the present application, the number of marking codes is 4, and the polygonal structures of the millimeter wave radar calibration unit and the marking code are both rectangular.

[0014] Optionally, in the calibration plate provided in the present application, the QR code information carried by the logo code is a QR code-like ArUco code.

[0015] In a second aspect, the present application further provides a calibration component, comprising: a plurality of calibration plates and connectors according to any one of the first aspects;

[0016] The connecting piece is fixedly connected between two adjacent calibration plates, and is used for the vehicle automatic driving system to determine the relative positions of the two adjacent calibration plates according to the connecting piece.

[0017] Optionally, in the calibration component provided in the present application, the connecting member is also used to control the angle between any one of the two calibration plates and the vertical plane where the two calibration plates are located.

[0018] Optionally, in the calibration component provided by the present application, the front sides of the two calibration plates are located on the same side of the calibration component.

[0019] Optionally, in the calibration component provided in the present application, the front sides of the two calibration plates are located on both sides of the calibration component.

[0020] In a third aspect, the present application further provides a calibration device, comprising any calibration component and a calibration bracket according to the second aspect;

[0021] The calibration bracket includes a base, a main bracket, and a plurality of bracket beams;

[0022] The main support is fixedly connected to the base, a plurality of support beams are arranged in parallel and connected to the main support, and ends of the plurality of support beams away from the main support are respectively connected to a plurality of calibration plates in the calibration component.

[0023] Optionally, in the calibration device provided in the present application, the calibration plate further includes a calibration plate bracket;

[0024] A plurality of calibration plate brackets can be movably connected to a plurality of bracket beams for adjusting an angle between the calibration plate and a plumb plane.

[0025] Optionally, in the calibration device provided in the present application, the main support includes a retractable structure for controlling the top height of the main support.

[0026] In a fourth aspect, the present application further provides a calibration system, comprising a plurality of calibration devices and a total station in the third aspect located in a calibration space;

[0027] The total station is used to determine the positional relationship between multiple calibration devices and the vehicle;

[0028] Multiple calibration devices are used to calibrate the vehicle according to the position relationship measured by the total station, wherein the multiple calibration devices surround the vehicle and there are two or more calibration devices in the same direction in any direction of the vehicle.

[0029] Optionally, in the calibration system provided by the present application, the calibration device surrounding the vehicle has multiple layers;

[0030] Among the multiple calibration devices on each layer, the distance from the calibration devices located on the left and right sides of the vehicle to the vehicle is shorter than the distance from the calibration devices located on the front and rear sides of the vehicle to the vehicle;

[0031] The size of the calibration plate in any layer of the calibration device is larger than the size of the calibration plate in a layer of the calibration device closer to the vehicle relative to any layer of the calibration device;

[0032] The height of any layer of calibration devices is greater than or equal to the height of a previous layer of calibration devices that is closer to the vehicle relative to any layer of calibration devices, wherein the calibration plates on the calibration devices are all located within the field of view of the vehicle.

[0033] Optionally, in the calibration system provided in the present application, a plurality of calibration plates and positioning balls corresponding to the calibration plates are laid on the ground of the calibration system;

[0034] Multiple calibration plates are located at the left front, right front, left rear and right rear of the vehicle, and are used for the sensor to obtain surround view stitching calibration parameters;

[0035] Positioning balls corresponding to the multiple calibration plates are fixed at the vertices of the calibration plates away from the vehicle, so as to assist the vehicle in positioning the calibration plates.

[0036] In a fifth aspect, the present application also provides a calibration method, comprising:

[0037] In the calibration site, the vehicle's surrounding environment information is obtained through the camera;

[0038] In the calibration site, the laser radar is used to obtain the point cloud information around the vehicle body;

[0039] In the calibration site, obtaining first position information of the millimeter wave radar calibration unit by using the millimeter wave radar;

[0040] Acquire second position information of the millimeter wave radar calibration unit according to the vehicle body surrounding environment information;

[0041] Acquire third position information of the millimeter wave radar calibration unit according to point cloud information around the vehicle body;

[0042] The camera, the laser radar and the millimeter-wave radar are calibrated according to the fourth position information of the preset millimeter-wave radar calibration unit relative to the vehicle and the first position information, the second position information and the third position information.

[0043] In a sixth aspect, the present application also provides a calibration system, comprising:

[0044] The environment acquisition module is used to obtain the vehicle's surrounding environment information through a camera in the calibration site;

[0045] The point cloud acquisition module is used to obtain the point cloud information around the vehicle body through the laser radar in the calibration site;

[0046] A millimeter wave radar calibration unit first position acquisition module, used to acquire first position information of the millimeter wave radar calibration unit through the millimeter wave radar in the calibration site;

[0047] A millimeter-wave radar calibration unit second position acquisition module, used to acquire second position information of the millimeter-wave radar calibration unit according to the vehicle body surrounding environment information;

[0048] A millimeter-wave radar calibration unit third position acquisition module, used to acquire the third position information of the millimeter-wave radar calibration unit according to the point cloud information around the vehicle body;

[0049] The sensor calibration module is used to calibrate the camera, the laser radar and the millimeter wave radar according to the fourth position information of the preset millimeter wave radar calibration unit relative to the vehicle and the first position information, the second position information and the third position information.

[0050] In a seventh aspect, the present application further provides an electronic device, which includes a processor and a memory, wherein the memory stores programs or instructions that can be run on the processor, and when the programs or instructions are executed by the processor, the calibration method as in the fifth aspect is implemented.

[0051] In an eighth aspect, an embodiment of the present application provides a non-volatile readable storage medium, on which a program or instruction is stored, and when the program or instruction is executed by a processor, the calibration method of the fifth aspect is implemented.

[0052] The calibration plate provided in the present application includes a metal block located in the center for sensor calibration and multiple marking codes surrounding the metal block. Since the two-dimensional code information on the multiple marking codes corresponds to different identity information, the identity ID information of the metal block can be quickly identified according to the identity information. The vehicle's sensor can realize automatic recognition on images and point cloud data according to different ID information, and the automatic matching effect of key points is good; moreover, the ID information can assist in the acquisition of the ID information and spatial position information of the metal block located in the middle of the marking code. Different metal blocks will not be confused due to excessive similarity, thereby solving the problem of automatic correspondence between spatial points of laser radar and millimeter-wave radar.

[0053] Specifically, the prior art often requires manual determination of the correspondence between spatial points during the calibration and solution process, so as to unify the data of multiple sensors in the same coordinate system, such as the correspondence between the image acquired by the camera and the calibration plate in the point cloud acquired by the lidar. However, the technical solution provided by the present application can calibrate the internal and external parameters of the camera, the camera and lidar and other sensor data through a unique two-dimensional code among multiple marker codes, and automatically calibrate the lidar and millimeter-wave radar based on the identity of the metal blocks surrounding the marker codes, without the need for manual assistance, thereby improving the calibration accuracy and the calibration work efficiency.

[0054] In addition, since the calibration plate provided in the present application realizes the calibration of the sensor through a metal block, the metal block can meet the working requirements of sensors such as millimeter-wave radars, thereby realizing coordinate conversion and calibration between millimeter-wave radars and other sensors, such as cameras or lidars.

[0055] The above description is only an overview of the technical solution provided by the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] One or more embodiments are exemplarily described by pictures in the corresponding drawings, and these exemplified descriptions do not constitute limitations on the embodiments. Elements with the same reference numerals in the drawings represent similar elements, and unless otherwise stated, the figures in the drawings do not constitute proportional limitations.

[0057] Figure 1 It is one of the existing calibration plate examples provided in this application;

[0058] Figure 2 This is the second example of an existing calibration plate provided in this application;

[0059] Figure 3 It is a schematic diagram of the calibration plate structure provided in this application;

[0060] Figure 4 It is a schematic diagram of a three-dimensional diagram of a calibration component for forward splicing provided by the present application;

[0061] Figure 5 It is a schematic side view of the calibration component of the forward splicing provided by the present application;

[0062] Figure 6 It is a schematic diagram of a three-dimensional diagram of a reverse-jointed calibration component provided by the present application;

[0063] Figure 7 It is a schematic side view of the reverse spliced ​​calibration component provided by the present application;

[0064] Figure 8 It is a schematic diagram of a three-dimensional diagram of a hybrid spliced ​​calibration component provided by the present application;

[0065] Fig. 9 It is a schematic side view of a hybrid splicing calibration component provided by the present application;

[0066] Fig.10 It is a schematic diagram of the structure of a calibration device provided by this application;

[0067] Fig.11 This is one of the schematic diagrams of the layout of the calibration device in the calibration site provided by this application;

[0068] Fig.12 This is the second schematic diagram of the layout of the calibration device in the calibration site provided by this application;

[0069] Fig.13This is one of the schematic diagrams of the layout of the ground calibration board in the calibration site provided by this application;

[0070] Fig.14 This is the second schematic diagram of the layout of the ground calibration board in the calibration site provided by this application;

[0071] Fig.15 is a schematic diagram of a calibration method provided in an embodiment of the present application;

[0072] Fig.16 It is an example of a partial image of the four corners of the calibration code provided by this application;

[0073] Fig.17 This is an example of establishing a world coordinate system provided by this application;

[0074] Fig.18 It is a top view of the surround stitching calibration layout provided by this application;

[0075] Fig.19 This is a schematic diagram of the projection transformation matrix selection provided by this application;

[0076] Fig. 20 It is a schematic diagram of the relationship between the millimeter wave radar coordinate system and the main laser radar coordinate system provided by this application;

[0077] Fig.21 It is a schematic diagram of the layout of the calibration ball provided by the present application;

[0078] Fig. 22 It is a schematic diagram of the projection of the point cloud provided by this application onto the camera image;

[0079] Fig.23 It is a schematic diagram of point cloud point extraction provided by this application;

[0080] Fig.24 It is a schematic diagram of a point cloud point fitting circle provided by this application;

[0081] Fig.25 It is a schematic diagram of the layout of the vehicle parking area provided by this application;

[0082] Fig.26 It is a top view of the layout of the vehicle parking area provided by this application;

[0083] Fig. 27 It is a side view of the layout of the vehicle parking area provided by this application;

[0084] Fig.28 is a schematic diagram of a calibration system provided in an embodiment of the present application;

[0085] Fig.29 It is a structural schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0086] The exemplary embodiments of the present application will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present application are shown in the accompanying drawings, it should be understood that the present application can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided in order to enable a more thorough understanding of the present application and to fully convey the scope of the present application to those skilled in the art.

[0087] The terms "first", "second", etc. in the specification and claims of the present application are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable under appropriate circumstances, so that the embodiments of the present application can be implemented in an order other than those illustrated or described here, and the objects distinguished by "first", "second", etc. are generally of one type, and the number of objects is not limited. For example, the first object can be one or more. In addition, "and / or" in the specification and claims represents at least one of the connected objects, and the character " / " generally indicates that the objects associated with each other are in an "or" relationship.

[0088] Since the environment around the vehicle body is very complex and is affected by factors such as lighting, weather, and driving scenarios during driving, a single sensor is difficult to meet the vehicle's autonomous driving perception needs for the environment around the vehicle body due to its own advantages and disadvantages. Therefore, it is necessary to organically combine multiple sensors such as lidar, cameras, millimeter-wave radar, etc., and through data redundancy, achieve accurate identification of the environment around the vehicle body in all weather and all scenarios.

[0089] In order to achieve data interaction between multiple sensors of different types and locations and improve the overall perception performance of vehicle sensors, it is necessary to convert multiple sensor data into a unified three-dimensional spatial coordinate system, thereby providing a prerequisite for sensor fusion. Due to the influence of factors such as tolerances in any sensor manufacturing and installation process when the vehicle leaves the factory and vibration during driving on the sensor position, the vehicle's sensors need to be calibrated and calibrated regularly.

[0090] Existing calibration methods include deep learning-based calibration methods, non-cooperative marker calibration methods, and cooperative marker calibration methods. Among them, the cooperative marker calibration method is widely used due to its high calibration accuracy and good controllability of the calibration process. However, the calibration method of cooperative markers is often manual, which cannot meet the production and use needs of vehicles as the number of sensors on the vehicle perception system increases. For visual sensors in vehicle sensors such as visible light cameras or infrared cameras, automated calibration methods usually use calibration plates with different postures to solve the internal and external parameters of the sensors. Among them, the existing calibration plates are usually such as Figure 1 The checkerboard pattern shown or Figure 2However, due to the characteristics of point cloud data in LiDAR, it is difficult to identify each corner point information in each, and often the entire calibration plate can only be used as a cooperative marker to extract the corner points of the chessboard or dot grid in the calibration plate for sensor calibration. Since a single calibration method cannot be adopted, the automatic matching effect of key points is poor, and the automatic calibration effect of sensors is poor.

[0091] The calibration plate provided by the present application includes a metal block located in the center for sensor calibration and multiple marking codes surrounding the metal block. Since the two-dimensional code information on the multiple marking codes corresponds to different identity information, the identity ID information of the metal block can be quickly identified according to the identity information. The vehicle's sensor can realize automatic recognition on images and point cloud data according to different ID information, and the automatic matching effect of key points is good; and the ID information can assist in obtaining the ID information and spatial position information of the metal block located in the middle of the marking code, and confusion will not be caused between different metal blocks due to excessive similarity, thereby solving the problem of automatic correspondence between the spatial points of the laser radar and the millimeter-wave radar.

[0092] Specifically, the prior art often requires manual determination of the correspondence between spatial points during the calibration and solution process, so as to unify the data of multiple sensors in the same coordinate system, such as the correspondence between the image acquired by the camera and the calibration plate in the point cloud acquired by the lidar. However, the technical solution provided by the present application can calibrate the internal and external parameters of the camera, the camera and lidar and other sensor data through a unique two-dimensional code among multiple marker codes, and automatically calibrate the lidar and millimeter-wave radar based on the identity of the metal blocks surrounding the marker codes, without the need for manual assistance, thereby improving the calibration accuracy and the calibration work efficiency.

[0093] In the following, in combination with the accompanying drawings, the calibration plate, calibration component, calibration device, calibration site, calibration method, system, electronic device and non-volatile readable storage medium provided in the present application are described in detail through specific embodiments and their application scenarios.

[0094] The first embodiment of the present application relates to a calibration board for calibrating sensors of a vehicle autonomous driving system, the sensors of the vehicle autonomous driving system including a millimeter wave radar and a camera;

[0095] Including: calibration carrier, multiple marking codes and millimeter wave radar calibration unit;

[0096] The millimeter-wave radar calibration unit is fixed at the center of the calibration carrier, and is used to provide feedback on the calibration results of the millimeter-wave radar according to the calibration data sent by the millimeter-wave radar, so that the vehicle automatic driving system can calibrate the millimeter-wave radar according to the calibration results of the millimeter-wave radar, wherein the millimeter-wave reflectivity of the millimeter-wave radar calibration unit is higher than the millimeter-wave reflectivity of the calibration carrier;

[0097] A plurality of marking codes are fixed on the calibration carrier and surround the millimeter wave radar calibration unit;

[0098] The marker code carries QR code information for sensor recognition, which is used to provide feedback on the camera's calibration results based on the calibration data sent by the camera, so that the vehicle's automatic driving system can calibrate the camera based on the camera's calibration results. The identity information corresponding to the QR code information of all marker codes is different.

[0099] Specifically, the millimeter wave radar calibration unit in the calibration plate provided in the present application can be a metal block made of metal material, such as iron block, aluminum block and other common metals. The calibration plate is a cooperative marker for vehicle sensor calibration, such as Figure 3 As shown, it includes a calibration carrier, a metal block fixed in the center of the calibration carrier, and a mark code fixed around the metal block. The calibration carrier is a plate body used to carry the mark code and the metal block, and the material can be selected from non-metallic materials that are not easily deformed, such as acrylic plates. The metal block located in the center of the calibration carrier is used for calibration of millimeter-wave radars and other sensors installed on autonomous driving vehicles. The mark code is a two-dimensional code that can encode identity information, such as a binary square reference mark (Augmented Reality University of Cordoba, ArUco) for camera posture estimation, which facilitates the laser radar and other sensors installed on the autonomous driving vehicle to identify each mark code on the mark board. Among them, the size and number of the mark code can be adjusted according to user needs based on factors such as camera focal length and laser radar field of view. In order to facilitate the sensor to distinguish different mark codes, all mark codes on the calibration plate cannot be repeated, and the identity information of each mark code is unique.

[0100] For example, the calibration plate provided in the present application can determine the three-dimensional coordinates of the four corner points of the metal block based on the key points corresponding to each marking code, such as the first three-dimensional coordinates of the four vertices of the rectangular marking code and the positional relationship between the metal block and multiple marking codes, and then determine the three-dimensional coordinates of the center of the metal block based on the three-dimensional coordinates of the four corner points of the metal block.

[0101] It should be emphasized that the metal block in the technical solution provided in the present application is used for the millimeter-wave radar and laser radar on the vehicle to obtain spatial homonymous points, thereby achieving the calibration effect of the millimeter-wave radar and the laser radar, and the ID information carried in the mark code and the QR code information on the mark code is used for automatic calibration actions between the camera internal parameters and the camera external parameters, and the ID information carried in the mark code and the QR code information on the mark code is also used for automatic calibration actions between the camera and the laser radar.

[0102] Among them, the same-name points are used to unify the data of different sensors in the same three-dimensional space. Only after obtaining multiple different coordinates of the same point corresponding to different sensors can these sensors be calibrated accordingly according to the differences in these coordinates. For example, the center of the same small ball in space has coordinates (u, v) in the image information obtained by the vehicle's camera; in the point cloud obtained by the vehicle's laser radar, the coordinates are (x, y, z); in the point cloud obtained by the vehicle's millimeter-wave radar, the coordinates are (x, y, )。将这些坐标统一在一个三维坐标系中，并根据不同坐标的差异适应性调整对应传感器的参数，从而实现车辆传感器的标定效果。

[0103] 本申请提供的标定板包括位于中心供传感器标定的金属块和环绕在金属块周围的多个标志码，由于多个标志码上二维码信息对应不同的身份信息，根据身份信息能够快速识别金属块的身份ID信息，车辆的传感器能够根据不同的ID信息实现图像、点云数据上自动识别，关键点自动匹配效果好；并且，ID信息能够辅助位于标志码中间的金属块的ID信息和空间位置信息的获取，不同金属块之间不会因为相似度过高而造成混淆，解决激光雷达与毫米波雷达空间点自动对应问题。

[0104] 具体的，现有技术在标定解算过程中往往需要人工辅助确定多个传感器，例如相机获取的图像与激光雷达获取的点云中标定板的对应关系，但本申请提供的技术方案可以通过多个标志码中独一无二的二维码识别环绕在标志码之间的金属块身份，不需要人工辅助确定，提高了标定准确性的同时提高了标定的工作效率。

[0105] 此外，由于本申请提供的标定板通过标定码和金属块实现传感器的标定，金属块能够满足毫米波雷达等传感器的工作需求，从而实现毫米波雷达与其他传感器，诸如相机或激光雷达之间的坐标转换与标定。相机、相机与激光雷达的标定是利用标定码。具体的，毫米波雷达和激光雷达标定，通常是在户外放置多个金属三角锥，三角锥相互之间的空间关系需要人工量取，然后手动分别在激光雷达点云和毫米波点云上选取多对同名三角锥，解算标定参数，由于两道甚至更多环节需要手动参与，导致车辆传感器的标定自动化程度低。本申请提供的标定板，能够解决现有金属块匹配自动化程度低的问题。并且，本申请提供的技术方案还可以通过前期标定场地三维重建的方式，获得毫米级的金属块定位精度，进一步提升标定精度。

[0106] 在上述实施方式的基础上，本申请提供的标定板中，标志码包括第一区域和第二区域，标志码的第二区域的激光吸收性大于标志码的第一区域的激光吸收性，标定载板的颜色与标志码的第二区域颜色不同，标定载板的表面的激光吸收性与标志码的第二区域表面的光线吸收性不同。

[0107] 具体的，本申请提供的标定板中，第一区域和第二区域可以分别为浅色区域与深色区域，例如白色区域和黑色区域。为了便于车辆传感器区分标定载版上的标志码和金属块，可以将深色涂料在标定载板上喷涂得到标志码，例如黑色标志码或与标定载板颜色差异大的标志码。当车辆的传感器进行标定时，例如激光雷达，通过标定板点云平面拟合能够获取标定载板的位置，进一步通过标定载板点云进行滤波、分割从而识别标定板上的每一个标志码的ID信息及关键点三维坐标。此时，为了便于区分，标定载板本身选取的非金属材质表面颜色与标志码涂层的颜色需要有差别。

[0108] 在上述实施方式的基础上，由于本申请提供的标定板中标定载板与标志码的深色区域表面在颜色等方面有较大差异，标定板中不同位置的激光雷达点云形成差异，能够提升激光雷达点云的标志码识别效率。

[0109] 在上述实施方式的基础上，本申请提供的标定板中，标志码的第二区域由激光吸收性高于标定载板的涂料喷涂得到。

[0110] 具体的，本申请提供的标定板中，将对激光束吸收性优于标定载板的深色涂料在标定载板上喷涂得到标志码。当车辆的传感器进行标定时，例如激光雷达，通过标定板能够获取类似标志码的稀疏点阵，从而识别标定板上的每一个标志码。此时，为了便于区分，标定载板本身选取的非金属材质表面颜色与标志码涂层的颜色需要有差别，并且标定载板的表面需具备光线漫反射特性，例如雷达点云增强材料。

[0111] 在上述实施方式的基础上，由于本申请提供的标定板中载板与标志码表面在激光反射特性、颜色等方面均有较大差异，能够提升激光雷达点云的标志码识别效率。

[0112] 在上述实施方式的基础上，毫米波雷达标定单元为多边形结构，标志码为多边形结果，多个标志码靠近毫米波雷达标定单元方向的顶点与金属块的顶点相连，毫米波雷达标定单元的顶点数大于等于4。

[0113] 具体的，本申请提供的标定板中，标定板上的金属块和标志码均为多边形形状，并且金属块的多个顶点分别与环绕在金属块周边的多个标志码的顶角直接连接，此时，车辆传感器只需要获取金属块相邻多个标志码的身份信息和位置信息就能对金属块进行完整的定位，从而建立金属块的身份信息与定位信息的关联，为了确保定位的准确性，标志码的数量至少为4个，金属块至少具有四条边。

[0114] 在上述实施方式的基础上，由于本申请提供的标定板中金属块与标志码的顶点相接，通过识别标志码的位置和身份信息，就能得到金属块的位置和身份信息，从而便于车辆上安装的毫米波雷达与其他传感器之间的标定，提高本申请的泛用性。

[0115] 在上述实施方式的基础上，本申请提供的标定板中，标志码的数量为4，毫米波雷达标定单元和标志码的多边形结构均为矩形。

[0116] 具体的，本申请提供的技术方案中，标定板上标志码和金属块均为矩形，金属块的4个顶点分别与一个标志码靠近金属块的顶点相接或重合。

[0117] 在上述实施方式的基础上，由于本申请提供的标定板能够兼顾相机的内外参标定，同一块标定板上至少4个标志码对应的ArUco码，共有超过16个关键点。进一步利用相机视场范围内多套标定板的关键点及其三维及其三维空间坐标进行相机内外参标定，一方面实现自动化标定，二提高相机内参解算精度。

[0118] 在上述实施方式的基础上，本申请提供的标定板中，标志码携带的二维码信息为类二维码ArUco码。

[0119] 具体的，本申请提供的标定板中标志码携带的二维码信息为便于相机解算的类二维码，例如ArUco码。

[0120] 本申请的第二实施方式涉及一种标定构件，包括多个第一实施方式中任一标定板和连接件；

[0121] 连接件固定连接在相邻两个标定板之间，用于供车辆自动驾驶系统根据连接件确定相邻两个标定板的相对位置。

[0122] 具体的，在第一实施方式的基础上，为了提高车辆多个不同传感器之间标定的准确性，本申请能够对多个标定板进行组合非共面标定构件，如 图4所示，多个标定板，例如标定板1的下边缘与标定板2的上边缘通过连接件相接，得到本申请的标定构件。

[0123] 本申请提供的标定构件，由于包括同一个地点的上下左右多个标定板，能够增多车辆上传感器，例如相机、激光雷达、毫米波雷达水平和 / 或垂直的视角场(Field of View，FOV)在同一个标定位置的标定数量，从而提升标定精度。

[0124] 在上述实施方式的基础上，本申请提供的标定构件中，连接件还用于控制两个标定板中任一个标定板与两个标定板所在的铅垂面之间的夹角。

[0125] 具体的，本申请提供的标定构件中连接件还能够调整多个相连标定板之间的夹角。如 图5所示，标定板1和标定板2与标定构件所在铅垂面的夹角可以根据用户需求调整，例如基于标定板1和标定板2上的标志码易于传感器识别考虑，通过调整连接件，标志板2保持与标志构件所在铅垂面平行，标志板1调整为与铅锤面存在夹角，例如30度。

[0126] 在上述实施方式的基础上，由于本申请提供的标定构件能够根据用户使用需求进行多个相连标定板之间的夹角调整，在便于车辆上多种不同传感器均能有效识别标定板。并且，标定构件上多个标定板存在夹角，增加非共面点，有效提升了标定精度。

[0127] 在上述实施方式的基础上，本申请提供的标定构件中，两个标定板的正面位于标定构件的同一侧。

[0128] 具体的，如 图5所示，本申请提供的标定构件可以将多个标定板进行正向拼接。此时，标定板1和标定板2的正面位于标定构件的同一侧，并根据车辆的传感器标定需求调整标定板1与铅垂面的夹角，如30度。当车辆的传感器需要通过传感器进行标定时，能够获取标定板1和标定板2的同一面的二维码信息，用于车辆上不同传感器之间的标定。

[0129] 在上述实施方式的基础上，由于本申请提供的标定构件增加了标定板识别的非共面点，提高了传感器的标定精度。

[0130] 在上述实施方式的基础上，本申请提供的标定构件中，两个标定板的正面位于标定构件的两侧。

[0131] 具体的，如 图6-7所示，本申请提供的标定构件还可以将多个标定板进行反向拼接， 图6和 图7分别为反向拼接时标定构件的立体图和侧视图。此时，标定板1和标定板2的正面位于标定构件的两侧，并根据车辆的传感器标定需求调整标定板1与铅垂面的夹角，如30度。当车辆的传感器需要通过传感器进行标定时，能够获取标定板1正面的二维码信息和标定板2反面的二维码信息，用于车辆上不同传感器之间的标定。

[0132] 此外，如 图8和 图9所示，本申请提供的标定构件还可以通过多种正向拼接的标定板和反向拼接的标定板组合得到， 图8和 图9分别是多种不同拼接方式组合得到标定构件的立体图和侧视图。具体的，本申请提供的标定构件可以根据相机、激光雷达、毫米波雷达视场等传感器的标定需求，以一定夹角，进行多个标定板的拼接。举例来说，将 图4和 图6中的拼接在一起的两个标定板组合得到 图8所示的标定构件。此时，车辆的传感器在进行标定时需要对正反两个标定板组合或标定单元的夹角、标志码等信息均进行识别，进一步提高了车辆传感器标定的标定精度。

[0133] 需要强调的是，本申请并不限制标定构件中标定板的具体数量，用户可以根据自身使用需求，基于不同车辆上传感器的数量、视场角的差异，增减标定板数量，从而满足不同车辆的传感器标定需求。

[0134] 在上述实施方式的基础上，由于本申请提供的标定构件中多个标定板朝向车辆传感器的正反面不同，进一步增大了传感器标定用参照物的非共面的差异性，提高了车辆传感器标定的标定精度。

[0135] 本申请的第三实施方式涉及一种标定装置，包括第二实施方式任一标定构件和标定支架；

[0136] 标定支架包括底座、主支架、多个支架梁；

[0137] 主支架固定连接在底座上，多个支架梁平行设置并与主支架连接，多个支架梁远离主支架的一端分别连接标定构件中的多个标定板。

[0138] 具体的，如 图10所示，本申请提供的标定装置包括第二实施方式中任意一种标定构件和标定支架。标定构件的多种形式第二实施方式均以提及，本申请方式不再赘述。标定支架包括底座、主支架和多个支架梁。底座通过螺栓固定等固定方式与标定场地进行固定，确保标定装置不会移位或转动。主支架用于支撑多个支架梁，竖立在底座上，并通过底部与底座固定连接，避免主支架的移位和转动。多个支架梁的一端与主支架连接，另一端分别与对应的标定构建中的标定板连接。举例来说，当标定机构为两个标定板和连接件组成时，支架梁1的一端连接主支架，支架梁1的另一端连接标定板1，支架梁2的一端连接主支架，支架梁2的另一端连接标定板2，从而实现对两个标定板的固定支撑作用。

[0139] 其中，多个支架梁与主支架的连接方式可以为可活动地连接，例如可以调整多个支架梁的安装高度满足标定板的位置需求后，锁紧支架梁与主支架连接的一端，避免发生支架梁的移位和转动。

[0140] 在上述实施方式的基础上，本申请提供的标定装置中，标定板还包括标定板支架；

[0141] 多个标定板支架可活动地连接在多个支架梁上，用于调整标定板与铅垂面的夹角。

[0142] 具体的，支架梁的另一端与多个标定板连接方式通过标定板之间实现，为可活动的连接，便于用户根据实际的传感器标定需求调整多个标定板的俯仰角度。

[0143] 在上述实施方式的基础上，本申请提供的标定装置中，主支架包括可伸缩结构，用于控制主支架的顶部高度。

[0144] 具体的，主支架可以为可伸缩支架，在安装好标定板后，用户可以通过调整主支架的高度，例如主支架顶端的可伸缩机构，避免主支架顶端超过标定板，例如 图10中主支架高度超过标定板1的部分出现在激光雷达和毫米波雷达的视场范围内，干扰传感器的标定工作。此外，主支架下端露出部分，例如 图7中主支架高度低于标定板2的部分，可以再套设一个非金属套筒，避免主支架对毫米波雷达的标定造成影响。

[0145] 现有的标定支架基于耐久、成本等因素往往采用金属材质，例如不锈钢等材质。然而车辆的传感器在标定中，尤其是激光雷达，往往会受到金属材质的支架干扰，传感器标定效果差。在上述实施方式的基础上，由于本申请提供的标定装置中主支架为可伸缩机构，避免了主支架高度高于标定板的部分对激光雷达的标定产生影响，确保了车辆多种传感器之间标定的准确性。

[0146] 本申请的第四实施方式涉及一种标定系统，包括多个位于标定空间中的第三方面中的标定装置和全站仪；

[0147] 全站仪用于确定多个标定装置与车辆的位置关系；

[0148] 多个标定装置用于根据全站仪测得的位置关系对车辆进行标定，其中，多个标定装置环绕在车辆的四周且车辆任意一个方向存在两个及以上同方向的标定装置。

[0149] 具体的，现有自动驾驶车辆往往采用多级感知系统进行车身周围环境的感知，常见自动驾驶车辆的多级感知系统中，前向相机相对较多，后向相机、左侧相机和右侧相机主要是为用于环视的广角相机。毫米波雷达通常分布在车辆前向及后向。主激光雷达分布在车顶中前部，辅助激光雷达分布在车头中下部及车辆两侧。由于融合感知涉及的传感器包括前向相机、激光雷达和毫米波雷达，而双目感知主要涉及的传感器包括双目相机或多目相机，因此，车辆传感器的标定任务往往包括鱼眼相机内参、前向相机内参、前向相机与激光雷达外参、毫米波雷达与激光雷达外参、双目相机外参等内容。如 图11所示为本申请提供的一种视角为斜向下的标定场地，多个标定装置环绕在车辆的四周，为了确保传感器标定的准确性，车辆任意一个方向装有两个及以上的标定装置。

[0150] 在上述实施方式的基础上，本申请提供的标定系统中，环绕车辆的标定装置有多层，每层的多个标定装置中位于车辆左右两侧的标定装置到车辆的距离小于位于车辆前后两侧的标定装置到车辆的距离；

[0151] 任一层标定装置中标定板的尺寸大于相对任一层标定装置更靠近车辆的一层标定装置中标定板的尺寸；

[0152] 任一层标定装置的高度大于等于相对任一层标定装置更靠近车辆的前一层标定装置的高度，其中，所述标定装置上的所述标定板均位于所述车辆的视场内。

[0153] 具体的，以车辆的前向相机为例，如 图11所示，本申请提供的标定场地由四个方向、不同距离、不同高度、不同大小。不同角度的多层标定装置组成， 图11中椭圆线条即为距离车辆不同距离的一层标定装置。

[0154] 由于车辆的前向相机往往由多种不同焦距的相机组成，例如2mm、6mm、8mm和25mm焦距的相机，为了确保这些前向相机的标定准确性，本申请提供的标定场地在对应方向的不同距离上设置了多种不同的标定装置。

[0155] 具体的，如 图11所示，本申请提供的标定场地在不同椭圆实线圆环位置布置多个标定装置，最内层或最内圈安装不少于两个标定装置，不同距离的标定装置数目及安装位置选取基于相互不遮挡同方向标定构件为设计。针对相机焦距的不同问题，本申请提供的标定场地中标定装置距离设定可以为3层及以上。

[0156] 此外，如 图12所示，为了增加非共面标定板布局，进一步提升标定精度，针对车辆融合感知系统中前向安装的鱼眼相机、中短焦相机、长焦相机等相机，可以沿着不同距离的同心圆的不同位置切线方向，安装标定装置，实现标定场地的布置，从而满足车辆传感器不同角度的标定需求。

[0157] 此外，考虑到同一尺寸大小的物理因距离相机远近距离不同导致在图像上呈现的细节效果差异大的问题。本申请提供的标定场地中，距离车辆越远的标定装置和标定板上标志码ArUco码尺寸越大，具体尺寸基于车辆同方向对应相机能够准确识别确定，本申请不作限制。

[0158] 此外，为了降低同方向上多个不同标定装置之间相互遮挡的问题，可以调整不同标定装置上标定板的安装高度。多个不同标定装置之间的高度以满足车辆上传感器，例如相机、激光雷达、毫米波雷达的FOV范围为准，确保多个标定板在各个传感器的FOV范围内均可见。举例来说，可以根据不同标定装置之间的层数或圈数，从内层到外层，将标定装置上标定板的高度依次增高，避免不同层标定装置之间的遮挡影响。需要强调的是，不同层之间的标定装置上的标定板可以高度相同，用户在位于车辆传感器视场角的范围内，可以根据不同层之间的标定装置的遮挡情况进行相应设置以避免标定装置上标定板的相互遮挡。

[0159] 在上述实施方式的基础上，本申请提供的标定系统在不同距离、不同角度、不同大小和不同高度安装标定装置，车辆的各个方向上的不同传感器对这些大小、高度、距离、位置各异的标定装置分别进行位置获取，并根据不同传感器获取的位置结果进行统一，实现对车辆上多个不同的传感器之间的标定效果。

[0160] 在上述实施方式的基础上，本申请提供的标定系统中，标定系统的地面上平铺多个标定板和标定板对应的定位球；

[0161] 多个标定板位于车辆的左前方、右前方、左后方和右后方，用于供传感器获取环视拼接标定参数；

[0162] 多个标定板对应的定位球固定在标定板远离车辆的顶点，用于辅助车辆对标定板进行定位。

[0163] 具体的，本申请提供的标定场地，在需要标定传感器的车辆四周布设多个标定装置外，还在车辆所在场地的地面设置多个标定板，用于满足车辆安装的鱼眼相机或短焦相机，例如焦距为2mm左右的相机的标定功能。鱼眼相机或短焦相机是车辆为满足自动驾驶视觉感知中的环视拼接功能而设置的传感器，鱼眼相机或短焦相机获取车辆的车身周围近距离鸟瞰图((Bird eye view，BEV)视角的360度环境视图，便于车辆的感知系统识别车身周围的环境状态。

[0164] 举例来说，用于标定鱼眼相机或短焦相机的标志码的设置方式如 图13-14所示。其中， 图13为用于环视拼接标定布局的侧视视图， 图14为用于环视拼接标定布局的俯视视图，在需要进行鱼眼相机或短焦相机标定的车辆前后左右各平铺一块标定板，为了便于识别，所有标定板平铺在地面上，且尽量保持在同一平面。此外，可以在这些标志码区域分别设置用于辅助定位的定位球，便于通过全站仪或激光笔等工具确定车辆与标志码之间的相对位置关系。

[0165] 在上述实施方式的基础上，本申请提供的标定场地，便于用户通过全站仪获取地面上所有标志码，例如二维码ArUco码四个顶点的三维坐标，在标定解算过程中利用三维坐标信息，降低车辆上传感器的标定误差。并且，在标定验证环节中，还可以将这些标志码中多个顶点的三维坐标进行投影，投影在BEV系统的平面进行验证。

[0166] 此外，本申请提供的标定场地中每一块标定板均配有定位球或标校小球，能够配合现有算法校验标定结果，便于直观地看出相机、激光雷达、毫米波雷达等车辆传感器之间标定参数是否正确，提高传感器标定的准确性。

[0167] 本申请的第五实施方式涉及一种标定方法，如 图15所示，包括：

[0168] 步骤101、在标定场地中，通过相机获取车辆的车身周围环境信息；

[0169] 步骤102、在标定场地中，通过激光雷达获取车辆的车身周围点云信息；

[0170] 步骤103、在标定场地中，通过毫米波雷达获取毫米波雷达标定单元的第一位置信息；

[0171] 步骤104、根据车身周围环境信息获取毫米波雷达标定单元的第二位置信息；

[0172] 步骤105、根据车身周围点云信息获取毫米波雷达标定单元的第三位置信息；

[0173] 步骤106、根据预先设置的毫米波雷达标定单元相对车辆的第四位置信息和第一位置信息、第二位置信息、第三位置信息对相机、激光雷达和毫米波雷达进行标定。

[0174] 具体的，针对自动驾驶感知系统多源传感器标定复杂耗时、难以自动化实施等问题，本申请提供了一种标定板、标定构件、标定装置、标定场地和标定方法。本身其功能可用于鱼眼相机、短焦相机、长焦相机、主激光雷达、辅助激光雷达、毫米波雷达等车辆上安装的传感器的标定工作。为了实现多源传感器自动标定，本申请提供了一中基于可编码身份信息的二维码的标定板。特别地，为了兼顾毫米波雷达与其他传感器联合标定，在标定板中心安装了一块金属块，并将金属板四角与邻角四邻域的二维码邻接角形成对顶角，利用邻角四邻域标定码的身份与坐标信息，可以便捷地定位每一块标定板上的金属块相关信息。为了提升标定精度，本申请提供了一种增加非共面标定码的标定构件的结构装置，即将本申请提供的标定板按照一定夹角链接，通过正反两种方式形成标定构件。为了便于安装本申请提供的标定构件，本申请提供了一种标定装置，装置包括本申请提供的标定构件和标定支架，为了降低标定支架对标定数据的影响，支架顶部采用可伸缩结构，底部可套装非金属套筒。为了进一步提升标定精度，同时保证所有二维码均可以自动识别，本申请提供一种标定场地，本申请提供的标定场地内以不同距离、不同角度、不同大小和不同高度安装本申请提供的标定装置。此外，为了自动获取环视拼接标定参数，本申请对标定场地地面也进行了标定板布局的改进。

[0175] 本申请的第六实施方式涉及一种标定方法，应用于一种标定系统中，标定系统包括全站仪、多个标定装置，方法包括：

[0176] 在待标定车辆满足第一标定条件时，控制全站仪对标定装置进行扫描，得到第一数据；

[0177] 在满足第二标定条件时，接收待标定车辆上的各个传感器对标定装置进行采集得到的第二数据；

[0178] 根据第一数据得到标定先验信息，并根据标定先验信息及第二数据对待标定车辆上的各个传感器进行标定，以得到各传感器的标定参数；标定先验信息为标定装置的数据信息，标定参数用于表征任意两个传感器之间或传感器与全站仪之间的坐标变换关系。

[0179] 具体的，在进行车辆传感器标定之前，先需要确认待标定车辆是否满足第一标定条件。当满足第一标定条件，系统会控制全站仪对标定装置进行扫描操作，得到第一数据。其中，全站仪用于测量和绘制三维空间的仪器，通过对标定装置进行扫描来获取点云数据。利用全站仪对标定系统进行反复扫描可以获取标定场地稠密点云数据。这些点云数据包含了标定装置的特定信息，可以用来确定标定装置的数据信息，即标定先验信息。标定先验信息是传感器标定的参考数据，可以帮助确定传感器的内外参数。

[0180] 随后，在确认待标定车辆满足第二标定条件后，系统会接收待标定车辆上的各个传感器对标定装置进行采集操作获取到的第二数据。这些数据可以反映出传感器在实际使用场景下的表现情况，用于后续的传感器标定。

[0181] 其中，接收第二数据的具体方式可以包括如下两种，其一，直接控制获取各个所述传感器对所述标定装置进行采集，以得到第二数据；其二，被动接收传感器发送的第二数据。

[0182] 最后，在获得第一批数据后，系统会根据这些数据得到标定的先验信息。同时，结合第二批数据和标定先验信息，对待标定车辆上的各个传感器进行标定操作。标定先验信息是指通过全站仪扫描标定装置获得的数据信息，可以作为传感器标定的参考。通过标定操作，可以校准传感器的测量误差，提高传感器的精度和可靠性。

[0183] 本申请的第七实施方式涉及一种具体的待标定相机的内参进行标定的方法，针对传统的相机内参标定，需要采集多张标定板，如 图1-2所示的棋盘格图像。标定过程需要将标定板放置在不同位置、不同平面或非共面。而本实施方式中，仅需采集一帧图像，提高对待标定相机的内参进行标定的效率。通过使用标定板的身份信息和图像坐标，以及传感器采集的局部点云数据和参考三维坐标之间的对应关系，计算出各个传感器的标定参数。通过这些标定参数，可以对传感器进行准确的标定，提高其测量精度和定位能力。

[0184] 具体的，首先获取待标定相机发送的第一标定图像，并通过该第一标定图像确定第一标定图像中包括的标定板的身份信息和关键点的图像坐标。然后，利用第二局部点云数据中各个点云的第一参考三维坐标确定和第一标定图像中关键点对应的第二三维坐标。最后，通过关键点的第二图像坐标和第二三维坐标，确定待标定相机的内参。

[0185] 其中，第二ID信息为第一标定图像中包括的标定码的ID信息，第一标定图像中包括的标定码的集合为标定系统中使用标定码的集合的子集，那么第二ID信息为所有标定码的第一ID信息中的一部分。那么在标定码的第二ID信息已知、各关键点在标定板上的第二图像坐标已知、第一参考三维坐标已知的基础上，可以确定各个关键点对应的第二三维坐标。也即，第二三维坐标为所有关键点的第一三维坐标中的一部分。

[0186] 例如，相机的内参包括焦距f x、f y、主点坐标u0、v0和镜头畸变k1、k2等。以车辆前向相机为例，假设相机的视场范围内拍摄到多个标定构件上的个标定板，记为C i，i∈n，每块标定板图像里有个标定码关键点，记为M j，j∈m。需要强调的是，本申请主要考虑镜像畸变

[0187] 对于不同的标定板，同一台相机的内参是一致的。基于此，内参标定初始值获取步骤如下：

[0188] 第一，对于待标定相机，采集一帧标定图像，如第一标定图像；

[0189] 第二通过二维码识别方法，获取每个标定码的ID和局部图像。对于每个标志码局部图像，利用Hough变换提取标志码外接矩形四条边，通过两条边交点确定关键点的第二图像坐标 其中k＝0,1,2,3，分别代表左上角、右上角、右下角、左下角。在图像上分别以 为中心，取11×11局部图像，如 图16所示。对每个局部图像，进行平台核拟合，进一步获取所有标志码关键点亚像素坐标：(x ij，y ij) i∈n,j∈m，其中，此处进行亚像素提取，目的是进一步增加解算精度)。

[0190] 识别图像中所有标定码的关键点的第二图像坐标(x ij，y ij) i∈n,j∈m和ID信息I ij(i∈n,j∈m)(该标定码是第i块标定板中第j个标定码)。其中，可以根据标定板ID先验信息(同一块标定板上所有标定码的ID信息，在先验信息获取过程已知归属关系，即每块标定板包含哪些标志码)，进一步获取关键点对应的第二三维坐标(X ij，Y ij，Z ij) i∈n,j∈m。

[0191] 对于每块相机视场内可见的标定板，建立世界坐标系O wX wY wZ w，例如将全站仪的坐标系作为世界坐标系，即将该标定板左上角标定码的左上角关键点，作为世界坐标系原点O w；该标定板横轴为X w轴，竖轴为Y w轴，按右手系原则建立Zw轴，如 图17所示。对于每块相机视场内可见的标定板，利用该标定板的关键点第二图像坐标(x ij，y ij) i∈n,j∈m与第二三维坐标(X ij，Y ij，Z ij) i∈n,j∈m，根据张正友标定法，求解相机内参f x、f y、主点坐标u0、v0和镜头畸变k1、k2。

[0192] 需要说明的是，张正友标定法需要采集多张不同视角、不同距离的标定图像，例如非共面图像，获取相机内参。因为对于不同图像，相机内参都是一致的。该方法只能解算相对每一张标定板图像的外参，而无法获得真正的相机外参。

[0193] 本申请的第八实施方式涉及一种具体的待标定相机的外参进行标定的方法，根据第二图像坐标、第二三维坐标及待标定相机的内参确定待标定相机的外参；待标定相机的外参至少包括待标定相机坐标系与全站仪坐标系之间的第一坐标变换关系。

[0194] 其中，在确定待标定相机的内参之后，还包括确定待标定相机的外参。所谓相机内参，即上述实施例中描述的相机的内部参数，包括焦距、主点坐标和畸变参数等，用于描述相机内部的几何特征。而相机外参则描述相机坐标系与全站仪坐标系之间的几何关系，即相机在全站仪坐标系下的位置姿态。

[0195] 在本实施例中，根据第一标定图像中各个关键点对应的第二图像坐标和第二三维坐标确定了待标定相机的内参，接下来的步骤是确定待标定相机的外参。具体地说，利用第二图像坐标、第二三维坐标以及待标定相机的内参来确定待标定相机的外参。

[0196] 在确定待标定相机的外参之前，首先需要了解相机的坐标系和全站仪的坐标系之间的关系。全站仪具有自己独立的坐标系，而待标定相机也有自己的坐标系。待标定相机坐标系与全站仪坐标系之间存在一定的坐标变换关系，这个关系包括平移、旋转和尺度参数等。根据待标定相机的内参和第一标定图像中各个关键点对应的第二图像坐标和第二三维坐标，可以利用相机与全站仪坐标系之间的坐标变换关系来确定待标定相机的外参。具体地说，可以通过解算出待标定相机坐标系与全站仪坐标系之间的平移、旋转和尺度参数等，从而确定待标定相机的外参。

[0197] 通过确定待标定相机的外参，可以准确地描述待标定相机在全站仪坐标系下的位置和姿态，从而在本申请的车辆传感器标定方法中用于对待标定相机进行标定。

[0198] 具体的，对待标定相机的外参进行标定的步骤为：

[0199] 对于相机视场范围内所有标定码关键点的三维空间点 或第二三维坐标，其中k∈n×m，n为标定板数目，m为标定板上标志码数目，其在图片上对应的二维像素或第二图像坐标为(x ij，y ij) i∈n,j∈m。理论上，三维空间点经过相机内参、镜头畸变k1、k2以及外参R，T变换后得到的二维像素为(x′ ij，y′ ij) i∈n,j∈。其中，相机内参M如下所，示：

[0200]

[0201] 因此，可以构造一个函数，其参数为内参、外参。第二三维坐标经过该函数，输出一个二维投影图像坐标或第二图像坐标(x ij，y ij) i∈n,j∈m。

[0202] 也即， R为第一坐标变换关系中的旋转矩阵，T为第一坐标变换关系中平移向量。

[0203] 实际中，识别的(x ij，y ij) i∈,j∈m与理论上的(x′ ij，y′ ij) i∈n,j∈m存在一定的偏差。因此，可以构建待优化函数如式1所示：

[0204]

[0205] 用Levenberg-Marquardt(LM)算法进行迭代求解。这里，我们将第一步获得焦距f x、f y、主点坐标u0、v0和镜头畸变k1、k2作为初始值，进行迭代计算。通过给定较好的初始值，后续迭代收敛更快。

[0206] 本申请的第九实施方式涉及一种环视相机的标定方法，包括：控制待标定环视相机对标定装置进行采集，得到第二标定图像；利用环视拼接单应矩阵对第二标定图像进行投影，得到投影图像；根据相邻两个待标定环视相机对应的投影图像中相同的关键点计算相邻两个待标定环视相机的坐标系之间的第二坐标变换关系。

[0207] 在传感器包括待标定环视相机时，首先，获取各个待标定环视相机发送的第二标定图像：这一步骤涉及到收集待标定车辆上各个环视相机所拍摄的标定图像。利用环视拼接单应矩阵对第二标定图像进行投影，得到投影图像：在这一步骤中，采用一种环视拼接单应矩阵的技术，将第二标定图像进行投影变换，生成对应的投影图像。根据相邻两个待标定环视相机对应的投影图像中相同的关键点计算相邻两个待标定环视相机的坐标系之间的第二坐标变换关系：通过比较相邻两个待标定环视相机的投影图像中相同的关键点，可以计算出相邻两个待标定环视相机之间的坐标系变换关系。

[0208] 本实施方式中通过收集待标定环视相机的图像数据，并利用环视拼接单应矩阵技术进行投影转换，最终计算得到相邻两个待标定环视相机之间的坐标系变换关系。这个结果可以作为计算传感器标定参数的一部分，用于对待标定车辆上的各个传感器进行标定。

[0209] 当获取各个待标定环视相机发送的第二标定图像之后，根据待标定相机的内参对第二标定图像进行畸变校准，以得到校准后的第二标定图像。并且，控制待标定环视相机对标定装置进行采集，得到第二标定图像之后，提取第二标定图像中各个标志码的ID信息以及各个关键点的第三图像坐标；根据第二标定图像中各个标志码的ID信息以及各个关键点的第三图像坐标筛选第二标定图像中位于地面上的关键点，并获取位于地面上的各个关键点的第三三维坐标；根据位于地面上的各个关键点的第三三维坐标确定环视拼接图像；利用标定先验信息中与环视拼接图像中关键点对应的第一参考三维坐标对环视拼接图像中关键点的第四三维坐标进行校准，以得到校准后的环视拼接图像；根据校准后的环视拼接图像得到环视拼接单应矩阵。

[0210] 其中，第三三维坐标为第二标定图像对应的视场范围内且位于地面上的所有关键点的三维坐标，第二标定图像对应的视场范围内的且位于地面上的所有关键点的集合为标定系统中所有关键点的集合的子集，那么第三三维坐标为所有第一三维坐标中的一部分。进一步的，第四三维坐标为根据地面上的各个关键点的第三三维坐标确定环视拼接图像中关键点的三维坐标，根据地面上的各个关键点的第三三维坐标确定环视拼接图像中关键点的集合为第二标定图像对应的视场范围内且位于地面上的所有关键点的集合的子集，那么第四三维坐标为所有第三三维坐标的一部分。

[0211] 举例来说，对于每台环视相机c i，采集第二标定图像I i，根据上一步获取的每台相机内参，对第二标定图像I i进行畸变校准，获得校准后的第二标定图像

[0212] 对于校准后第二标定图像 提取其视场范围内的关键点的第三图像坐标和ID信息(第四身份信息)，并根据ID信息，仅保留的地面上的关键点，并获地面上关键点的第三三维坐标信息(如 图18， 图18为本申请提供的环视拼接标定布局俯视图)，相比于手动点取而言，本实施例面向量产，解决自动化问题。

[0213] 对于每台相机，根据ID信息，自动获取视场范围出现的 图18中最大的标志码对应的关键点。选择左右两个最大合作标志关键点，按照如19方式选择虚线矩形ABCD， 图19为本申请提供的投影变换矩阵选取示意图。

[0214] 由于建造标定场地时候，难以保证 图18中的所有标定码水平且共面，现有方法都忽略这点，造成环视拼接精度不够。这里，我们通过 图18标定码关键点的三维坐标(X i，Y i，Z i)，以及第一步过程中获取的相机内外参，对 图19中利用ABCD四点进行校准，即将(X i，Y i，Z i)通过相内外参(这里不用畸变参数)变换到图像中，获得校准后点 (如 图19中黑圆点所在位置)；

[0215] 利用 解算环视拼接单应矩阵E；对于相邻相机的重叠视场内的关键点，根据关键点ID信息及合作标志实际尺寸，解算变换尺度参数。

[0216] 本申请的第十实施方式涉及一种激光雷达的采集与标定方式，包括控制主激光雷达对标定装置进行采集，得到第一测试点云数据；将第一测试点云数据与第一数据进行匹配，以得到主激光雷达坐标系与全站仪坐标系之间的第三坐标变换关系。

[0217] 具体地，首先获取主激光雷达发送的第一测试点云数据。接下来，将第一测试点云数据与第一数据进行匹配，以得到主激光雷达坐标系与全站仪坐标系之间的第三坐标变换关系。

[0218] 在这个实施方式中，传感器采集的第二数据是指各个传感器对标定装置进行的数据采集。其中，主激光雷达发送的第一测试点云数据是其中的一种。这些传感器和标定装置可以通过无线或有线连接进行数据传输。

[0219] 通过将第一测试点云数据与第一数据匹配，可以确定主激光雷达坐标系与全站仪坐标系之间的第三坐标变换关系。这个变换关系可以用于后续的传感器标定过程。通过获得主激光雷达坐标系与全站仪坐标系之间的第三坐标变换关系，可以计算出主激光雷达的标定参数。这些参数可以包括旋转矩阵和 / 或平移向量等。

[0220] 随后，将第一测试点云数据与第一数据进行匹配，得到主激光雷达的视场范围内的标志码的ID信息及关键点的第五三维坐标；

[0221] 根据第一标定图像中各个标志码的ID信息、各个关键点对应的第二三维坐标、主激光雷达的视场范围内的标志码的ID信息及关键点的第五三维坐标确定第一标定图像中与主激光雷达的视场范围内的相同关键点，并确定相同关键点的三维坐标；

[0222] 根据相同关键点的三维坐标计算待标定相机坐标系和主激光雷达坐标系之间的第四坐标变换关系。其中，第五三维坐标为主激光雷达的视场范围的关键点对应的三维坐标，其主激光雷达的视场范围的关键点的集合为标定系统中所有关键点的集合的子集，那么第五三维坐标为所有第一三维坐标中的一部分。

[0223] 具体地，假设相机坐标系中关键点坐标为 (为上述描述的第二三维坐标)，主激光雷达坐标系中关键点坐标(也即上述第五三维坐标)为 理论上，两个坐标系中同名点变换关系如下式：

[0224]

[0225] 考虑各种误差，则

[0226]

[0227] 待优化函数如式2所示:

[0228]

[0229] 标定步骤为:

[0230] 第一，提取相机c1视场内的关键点的图像坐标与ID，并根据ID信息获取对应的空间三维坐标(也即上述第二三维坐标)；

[0231] 第二，提取主激光雷达l1视场内的关键点的三维坐标(也即上述第五三维坐标)与ID；

[0232] 第三，根据ID信息，利用同名点关系，利用Levenberg-Marquardt(LM)算法求解外参(第四坐标变换关系)。

[0233] 本申请的第十一实施方式涉及一种毫米波雷达的采集与标定方式，标定板上设有金属块，标定系统还包括两条轨道、设于轨道上的传送带装置，两条轨道之间平行且两条轨道之间的距离与待标定车辆左右轮之间的间距相同，在进行传感器标定时待标定车辆位于传送带装置上；控制待标定车辆上的各个传感器对标定装置进行采集，得到第二数据之前，还包括：通过对传送带装置进行控制以使待标定车辆以预设速度移动；控制待标定车辆上的各个传感器对标定装置进行采集，得到第二数据，包括：在待标定车辆移动过程中，触发毫米波雷达对视场范围内的金属块的坐标进行采集，得到采集数据，采集数据中至少包括金属块坐标；根据数据时间戳确定第一测试点云数据和采集数据的对齐数据；将对齐数据中的第一测试点云数据中的金属块的第六三维坐标投影至水平面上，得到水平面投影数据；根据水平面投影数据、对齐数据中的采集数据中的金属块坐标及各金属块在标定系统中的位置计算毫米波雷达坐标系与主激光雷达坐标系之间的第五坐标变换关系。其中，第六三维坐标为毫米波雷达的视场范围的金属块对应的水平面二维坐标和偏航角，其毫米波雷达的视场范围的金属块的集合为标定系统中所有金属块的集合的子集，那么第六三维坐标为上述所有金属块的三维坐标在水平面上的投影坐标。

[0234] 具体的，毫米波雷达可以得到目标的x、y坐标信息，没有目标的z坐标信息，因此，可以将毫米波坐标系O wX wY w到主激光雷达坐标系O lX lY l的转换看做二维X-Y坐标系的转换(如 图20所示， 图20为本申请提供的毫米波雷达坐标系和主激光雷达坐标系的关系示意图)，待标定参数包括平移向量T和旋转角度θ。

[0235] 毫米波坐标到主激光雷达坐标系的转换关系为：

[0236]

[0237] 可以构造一个函数F，其参数为T x、T y、θ。三维世界坐标经过该函数F，输出一个二维投影图像坐标(x i′ j，y i′ j)；

[0238] (x l，y l)＝F(T x，T y，θ，x w，y w)；

[0239] 考虑误差因素，则

[0240] 待优化函数为：

[0241]

[0242] 标定步骤如下：

[0243] 第一，由于车辆在轨道上前后固定，通过轨道上的传送带，可以方便的控制车辆在前后方向短距离直线运动(在标定过程中，仅仅需要移动非常短距离(如1米)即可)；

[0244] 第二，保存车辆运动过程中主激光雷达数据(第一测试点云数据)和毫米波雷达数据(毫米波雷达发送的对金属块的采集数据)；

[0245] 第三，根据数据时间戳，找到主激光雷达和毫米波雷达时间对齐数据帧。对于主激光雷达l1视场内的每块标定板中心金属块的三维坐标(金属块的第六三维坐标)，并投影到水平面上，得到水平面投影数据；对于毫米雷达，识别其视场范围内的所有金属块坐标；

[0246] 第四，根据水平面投影数据，并已知金属块的空间拓扑关系，获取最优匹配关系。根据最优匹配关系，利用Levenberg-Marquardt(LM)算法，对上述优化函数进行迭代计算，求解第五坐标变换关系。

[0247] 本申请的第十二实施方式涉及一种辅助激光雷达的采集与标定方式：控制辅助激光雷达对标定装置进行采集，得到第二测试点云数据；将第二测试点云数据与第一测试点云数据进行匹配，以得到辅助激光雷达坐标系与主激光雷达坐标系之间的第六坐标变换关系。

[0248] 具体的，辅助激光雷达与主激光雷达之间的标定参数(第六坐标变换关系)是旋转矩阵R和平移向量T。

[0249] 假设主激光雷达点云数据分别为Q＝{q1,q2,..,q m}(第一测试点云数据)，辅助激光雷达点云数据为P＝{p1,p2,..,p m}(第二测试点云数据)。利用标定场地标定构件的空间拓扑结构，根据点云空间匹配性，两个点云数据中空间同名点坐标变换关系为：

[0250] 构建优化函数： 通过高斯牛顿或者LM算法，可以求得第六坐标变换关系对应的R和T。

[0251] 主 / 辅助激光雷达标定步骤如下：

[0252] 第一，分布获取主激光雷达和辅助激光雷达点云数据和；

[0253] 第二，分别针对点云数据 和 利用"获取标定场地先验信息”预处理中方法，获得剔除天花板、地面、四周墙壁后的点云数据和；剔除这些干扰，可以极大地提升标定精度；

[0254] 第三，分别对点云数据和，利用"获取标定场地先验信息”中标定板平面拟合方法，获取各自点云中的标定板平面、标校小球球面等信息，包括其ID信息。其中标定板的ID可由其内部标定码ID组合而成。例如其上有6个标定码，ID分别为ID i(i≤6)那么该标定板ID为标定码ID从小到大串联，如ID1ID2ID3ID4ID5ID6；

[0255] 第四，根据标定板ID信息以及标校小球ID，解算第六坐标变换关系对应的标定参数RT的初始值；进一步根据标定板拟合平面、标校小球球面，基于标定参数RT的初始值，通过NDT或ICP进一步求精，获取最终的标定参数RT。

[0256] 传统的方法，直接用点数数据进行匹配，如NDT、各种ICP改进方法时，由于主 / 辅助激光雷达硬件参数差异可能较大，点云分辨率、投射角度等造成真正的空间同名点可能非常少。两帧激光点云数据中的点不可能表示的是空间中相同的位置。所以用点到点的距离作为误差方程势必会引入随机误差。本申请中通过拟合出各个标定板平面，可以有效降低上述影响，即提高标定精度。

[0257] 如 图21所示，本申请的第十三实施方式涉及一种利用多个校验构建进行标定的标定方法：根据第一标定数据确定标定先验信息，包括：

[0258] 根据各个校验构件在标定系统中的位置对第一标定数据进行空间聚类分割，得到每个校验构件对应的第三局部点云数据；

[0259] 根据第三局部点云数据确定各个校验构件对应的第五身份信息和第五坐标信息。

[0260] 首先需要根据各个校验构件在标定系统中的位置对第一标定数据进行空间聚类分割，以得到每个校验构件对应的第三局部点云数据。所谓空间聚类分割，即将第一标定数据中相邻或接近的点云集合在一起，形成一个个点云簇。这样做的目的是为了将第一标定数据中即将被标定的各个校验构件所对应的点云分开，便于后续处理。聚类分割可以根据空间距离、密度等因素进行。聚类分割后，每个点云簇可以看作是一个校验构件的局部点云数据。通过对每个点云簇进行处理，可以得到该校验构件的第三局部点云数据。这些局部点云数据可以用于后续的校验参数计算、误差分析等。接下来，根据第三局部点云数据，可以确定各个校验构件对应的第五身份信息和第五坐标信息。第五身份信息通常是指校验构件的唯一标识，用于区分不同的校验构件。在校验系统中，可以通过对校验构件的形状、大小、纹理等特征进行提取和匹配，来确定校验构件的身份信息。第五坐标信息通常是指校验构件在标定系统中的位置和姿态信息。通过对点云数据进行配准和匹配，可以确定校验构件相对于标定系统的位置和姿态。这样，就可以得到校验构件对应的第五坐标信息。

[0261] 综上所述，通过对第一标定数据进行空间聚类分割，可以得到每个校验构件对应的第三局部点云数据。然后，通过对第三局部点云数据进行处理和分析，可以确定各个校验构件对应的第五身份信息和第五坐标信息。这样，就可以用来校准传感器的参数，并进行自动驾驶系统的相关工作。

[0262] 在一种实施例中，根据所述第三局部点云数据确定各个所述校验构件对应的第五身份信息和第五坐标信息，包括：

[0263] 对所述第三局部点云数据进行拟合，得到各个所述校验构件的结构信息和三维坐标。

[0264] 本实施例提到了根据第三局部点云数据确定各个校验构件对应的第五身份信息和第五坐标信息。为了获取校验构件的身份信息和坐标信息，需要对第三局部点云数据进行处理。首先，需要对第三局部点云数据进行拟合，即利用数学模型对点云数据进行适当的拟合，可以得到校验构件的结构信息。拟合可以通过使用曲面拟合算法，例如最小二乘法等，来拟合球体的形状。通过拟合得到的结构信息，可以了解校验构件的形状、大小等特征。其次，通过拟合后的结果，可以获取校验构件的三维坐标。由于拟合主要是基于点云数据，因此可以得到校验构件的中心点坐标，即第五坐标信息。通过获取校验构件的中心点坐标，可以确定校验构件的位置。最后，根据校验构件的结构信息和三维坐标，可以得到校验构件的身份信息，即第五身份信息。校验构件的身份信息可以包括校验构件的类型、编号等，可以用于唯一标识每个校验构件。

[0265] 综上所述，通过对第三局部点云数据进行拟合，可以得到校验构件的结构信息和三维坐标，进而确定校验构件的身份信息和坐标信息。这样可以对自动驾驶传感器自动标定系统中的校验构件进行精确定位和识别，提高标定参数的准确性和稳定性。

[0266] 在一种实施例中，校验构件为校验球，根据第三局部点云数据确定各个校验构件对应的第五身份信息和第五坐标信息，包括：

[0267] 对第三局部点云数据进行球面拟合，得到校验球的半径信息和三维坐标。

[0268] 在这个实施例中，校验构件是校验球。根据第三局部点云数据确定各个校验构件(即校验球)对应的第五身份信息和第五坐标信息的步骤包括以下两部分：对第三局部点云数据进行球面拟合：根据第三局部点云数据可以得到校验球表面的点云数据。通过对这些点云数据进行球面拟合，可以得到拟合后的球面的信息，主要包括校验球的半径信息和球心的三维坐标。球面拟合是通过数学方法对点云数据进行处理，使得拟合结果能够最好地满足球面模型。确定校验球的身份信息和坐标信息：通过对球面拟合后得到的校验球的半径信息和球心的三维坐标，可以确定校验球的身份信息和坐标信息。校验球的身份信息通常用来区分不同的校验球，而坐标信息用来确定校验球在三维空间中的位置。

[0269] 这样，通过对第三局部点云数据进行球面拟合，可以得到每个校验球的半径信息和位置信息，从而确定各个校验构件(即校验球)对应的第五身份信息和第五坐标信息。这些信息在自动驾驶传感器自动标定系统中用于校验各个传感器的标定参数。

[0270] 需要说明的是，第五身份信息为校验构件的身份信息，如在校验构件为校验球时，第五身份信息可以为校验球的半径信息。第五坐标信息表征校验构件在标定系统中的位置，如空间位置。

[0271] 还需要说明的是，使用校验球对各个传感器的标定参数进行校验。这是因为校验球具有较为均匀的球形，无论从哪个角度观察，都呈现出圆面(具有较好的描述一致性)。这种球形特征使得校验球产生的数据相对容易处理和分析。也即，使用校验球进行传感器标定校验可以提供准确且可靠的结果。校验球的均匀球形能够确保传感器在不同角度和方向上获取到一致的数据，从而减少了标定误差的可能性。此外，校验球的球面特性使其在接收到传感器的激光、雷达或摄像机信号时，能够以相同方式反射或散射光线，进而保证了数据的一致性和稳定性。校验球的数据处理相对简单。由于校验球呈现出完美的圆面，其在传感器中形成的图像或点云数据可以轻松地进行处理和分析。通过对校验球数据的处理，可以获得传感器的标定参数，并对其进行优化和调整，从而提高传感器的精度和准确性。

[0272] 除了校验球，校验构件还可以有其他实现方式，例如校验板、方形或十字形的校验构件等。

[0273] 总之，使用校验球对自动驾驶传感器的标定参数进行校验具有重要意义。校验球的均匀球形特性和数据处理优势，能够确保传感器标定的准确性和可靠性，为自动驾驶系统的性能提供有效支持。

[0274] 具体地，令为剔除天花板、地面和四周墙壁点云后的第一标定数据，仅仅包含各个标定构件点云和地面据校验小球点云。

[0275] 对于校验小球，具体步骤如下：

[0276] 第一，由于校验小球安装高度均低于标定构件，因此，可以先根据点云P的高度z坐标，分成仅包含据校验小球点云 和仅包含标定构件点云

[0277] 第二，根据校验小球空间间隔进行聚类，对于点云进行空间聚类分割，得到每个据校验小球的局部点云 (M1为标校小球总数)；对于每个 通过点云球面拟合，可以获得校验小球中心三维空间坐标(x j,y j,z j)和小球半径R j信息。

[0278] 在一种实施例中，根据第一数据得到标定先验信息，并根据标定先验信息及第二数据对待标定车辆上的各个传感器进行标定之后，还包括：

[0279] 根据各个校验球的半径信息和三维坐标对各个传感器的标定参数进行校验。

[0280] 由于多级感知系统所需要传感器数量众多，标定结果的正确性将直接影响感知系统性能。本申请提出了一种标定参数自动校验的方法，具体地，对于双目标定、相机与主激光雷达雷达标定、主 / 辅激光雷达标定、毫米波雷达与主激光雷达标定结果验证，其基本思路为：

[0281] 对于标定系统中已知空间位置和大小的球体，识别其球心在不同坐标系中的三维坐标，并与真值进行比较。具体步骤如下：

[0282] 在一种实施例中，在传感器的标定参数包括主激光雷达坐标系与全站仪坐标系之间的第三坐标变换关系时，根据各个校验球的半径信息和三维坐标对各个传感器的标定参数进行校验，包括：

[0283] 获取主激光雷达视场范围内的各个校验球的第七三维坐标；

[0284] 根据第三坐标变换关系对第七三维坐标进行坐标变换，得到待比较的第七三维坐标；

[0285] 将待比较的第七三维坐标与第七参考三维坐标比较，以确定第三坐标变换关系是否准确；

[0286] 第一参考三维坐标为全站仪获取到的与主激光雷达视场范围内校验构件对应的三维坐标。

[0287] 本实施例旨在验证主激光雷达与全站仪坐标系校准精度。对于激光雷达，通过预先知道的球体ROI区域，根据反射率差异和空间聚类，获得球体中心三维坐标 (也即第七三维坐标)；根据主激光雷达与全站仪之间的外参R / t关系(也即第三坐标变换关系)，对 进行坐标变换，获得 (也即待比较的第七三维坐标)；将 与真值(全站仪获得坐标，也即第七参考三维坐标)进行比较，判断R / T的误差。

[0288] 需要说明的是，第七三维坐标为主激光雷达视场范围内的校验构件的三维坐标，主激光雷达视场范围内的校验构件的集合为所有校验构件的集合的子集，那么相适应的，第七三维坐标为所有第五坐标信息中的一部分。

[0289] 在一种实施例中，在传感器的标定参数包括待标定相机坐标系和主激光雷达坐标系之间的第四坐标变换关系时，根据各个校验球的半径信息和三维坐标对各个传感器的标定参数进行校验，包括：

[0290] 获取主激光雷达视场范围内的校验球的第一校验点云数据；

[0291] 根据第四坐标变换关系将第一校验点云数据反投影至相机图像上；

[0292] 对反投影的相机图像进行预设处理得到相机图像中的圆形边缘，根据圆形边缘确定对应的第一圆形拟合方程；

[0293] 将第一圆形拟合方程与参考圆形拟合方程比较，以确定第四坐标变换关系是否准确。

[0294] 本实施例旨在验证相机与主激光雷达标定参数误差。在实施例中，首先获取主激光雷达视场范围内的校验构件的第一校验点云数据。接下来，根据第四坐标变换关系，将第一校验点云数据反投影至相机图像上。通过反投影操作，将校验点云的三维坐标映射到相机的二维图像上。最后，根据反投影后的相机图像，确定第四坐标变换关系是否准确。通过对比相机图像上的校验点位置和实际校验构件的位置，可以评估第四坐标变换关系的准确性。

[0295] 在校验构件为校验小球时，将主激光雷达视场范围内的校验构件的第一校验点云数据根据第四坐标变换关系对应的外参R c-l、t c-l反投影到每个相机图像上；对每个相机中球体区域点云反投影如 图22所示，其中球体在图像上为灰色原型，虚线代表激光雷达点云反投影。通过灰度及二值化等处理，提取图像中所有圆形边缘，并获取第一圆形拟合方程(,为图像圆形区域个数)；根据空间距离差异性，通过聚类获取球体内部点云数据，并获取每条横线端点，如 图23所示，横线断线拟合圆形(如 图24所示)。计算与的距离，进一步判断相机内参、相机与主激光雷达的外参R c-l、t c-l(第四坐标变换关系)的精度。

[0296] 这种校验方法的目的是确保待标定相机和主激光雷达之间的坐标变换关系准确无误。通过校验，可以验证该标定参数的准确性，提高传感器标定的可靠性和精度。

[0297] 在一种实施例中，校验球为金属球体，在传感器的标定参数包括毫米波雷达坐标系与主激光雷达坐标系之间的第五坐标变换关系时，根据各个校验球的半径信息和三维坐标对各个传感器的标定参数进行校验，包括：

[0298] 获取毫米波雷达的视场范围内的各个校验球的毫米波雷达坐标和角度；

[0299] 获取主激光雷达的视场范围内的第七三维坐标；

[0300] 根据第五坐标变换关系将毫米波雷达坐标和角度投影至主激光雷达坐标系的二维平面；

[0301] 根据投影后的毫米波雷达坐标和角度及第七三维坐标计算欧氏距离，以确定第五坐标变换关系是否准确。

[0302] 本实施例中旨在对于辅助激光雷达l1坐标系和主激光雷达l2坐标系之间的第五坐标变换关系进行校验。该校验过程包括以下步骤：获取毫米波雷达的视场范围内各个校验球的毫米波雷达坐标和角度。获取主激光雷达的视场范围内的第七三维坐标。根据第五坐标变换关系将毫米波雷达坐标和角度投影至主激光雷达坐标系的二维平面。根据投影后的毫米波雷达坐标和角度以及第七三维坐标，计算欧氏距离。根据计算得到的欧氏距离，确定第五坐标变换关系是否准确。

[0303] 具体而言，分别提取毫米波雷达坐标和yaw角、主激光雷达坐标系中球心三维坐标；通过第五坐标变换关系，将毫米波数据中球心坐标投影主激光雷达坐标系XY平面；计算欧式距离，判断标定精度。

[0304] 通过上述的校验过程，可以对毫米波雷达坐标系与主激光雷达坐标系之间的第五坐标变换关系进行准确性的判定。这样可以确保传感器的标定参数的准确性和可靠性，从而提高传感器在车辆中的应用性能和精度。

[0305] 在一种实施例中，在传感器的标定参数包括辅助激光雷达坐标系与主激光雷达坐标系之间的第六坐标变换关系时，根据各个校验球的半径信息和三维坐标对各个传感器的标定参数进行校验，包括：

[0306] 获取主激光雷达视场范围内校验球的第一校验点云数据；

[0307] 获取辅助激光雷达视场范围内校验球的第二校验点云数据；

[0308] 根据第六坐标变换关系将第二校验点云数据变换至主激光雷达坐标系中，得到待校验的第二校验点云数据；

[0309] 根据第一校验点云数据及待校验的第二校验点云数据确定第六坐标变换关系是否准确。

[0310] 本实施例旨在对辅助激光雷达坐标系与主激光雷达坐标系之间的第六坐标变换关系进行校验。具体地，首先，获取主激光雷达视场范围内的校验构件的第一校验点云数据。接下来，获取辅助激光雷达视场范围内的校验构件的第二校验点云数据。然后，根据第六坐标变换关系，将获取的第二校验点云数据进行坐标转换，将其变换到主激光雷达坐标系中。这个变换过程通常涉及到旋转、平移、以及可能的尺度变化。最后，通过对比第一校验点云数据和待校验的第二校验点云数据，可以评估第六坐标变换关系的准确性。如果两组点云数据之间的差异较小，则说明第六坐标变换关系是准确的；如果差异较大，则需要调整或重新计算第六坐标变换关系。

[0311] 具体而言，分别对两台激光雷达点云，根据空间距离和发射率差异性，提取各自视场范围内球体点云；通过 (第五坐标变换关系)，将中球体点云变换到坐标系l1中；计算欧氏距离，判断第五坐标变换关系精度。

[0312] 综上，本实施例用于验证传感器标定参数中的辅助激光雷达与主激光雷达之间的第六坐标变换关系的准确性。这种方法可以帮助确保传感器的标定参数能够准确地反映出实际场景中传感器之间的空间相对位置关系。

[0313] 此外，为了提升标定效率及标定精度，需要实现待标定车辆进行快速限位，即快速驶入标定系统中的指定位置。本申请利用车辆四个触地点进行限位。限位包括前后和左右两个方面。方案如 图25-27所示，具体为在标定系统内，安装两条轨道，轨道宽度与车辆轮胎等宽；车辆轮胎与轨道平行驶上轨道；轨道前端有限位器，当轮胎与限位器接触后，即可停车，停车后需要固定后轮限位。固定后轮，一方面是安全考虑。另一方面是为了标定毫米波雷达与激光雷达坐标系。

[0314] 通过该操作，可以保障所有待标定车辆的初始位置比较接近，且主激光雷达坐标系和全站仪坐标系偏差尽可能小。在点云匹配过程中，两个点云坐标系偏差尽可能小，迭代算法收敛更快，且精度更容易保障。

[0315] 另外，为了辅助毫米波雷达与主激光雷达标定，在轨道上安装有传动带装置，可以实现车辆短距离匀速直线运动。

[0316] 本申请的第十四实施方式涉及一种标定系统，如 图28所示，包括：

[0317] 环境获取模块201，用于在标定场地中，通过相机获取车辆的车身周围环境信息；

[0318] 点云获取模块202，用于在标定场地中，通过激光雷达获取车辆的车身周围点云信息；

[0319] 毫米波雷达标定单元第一位置获取模块203，用于在标定场地中，通过毫米波雷达获取毫米波雷达标定单元的第一位置信息；

[0320] 毫米波雷达标定单元第二位置获取模块204，用于根据车身周围环境信息获取毫米波雷达标定单元的第二位置信息；

[0321] 毫米波雷达标定单元第三位置获取模块205，用于根据车身周围点云信息获取毫米波雷达标定单元的第三位置信息；

[0322] 传感器标定模块206，用于根据预先设置的毫米波雷达标定单元相对车辆的第四位置信息和第一位置信息、第二位置信息、第三位置信息对相机、激光雷达和毫米波雷达进行标定。

[0323] 本申请的第八实施方式涉及一种电子设备，如 图29所示，包括：

[0324] 至少一个处理器301；以及，

[0325] 与所述至少一个处理器301通信连接的存储器302；其中，

[0326] 所述存储器302存储有可被所述至少一个处理器执行的指令，所述指令被所述至少一个处理器301执行，以使所述至少一个处理器301能够实现本申请第一实施方式或第五实施方式所述的标定方法。

[0327] 其中，存储器和处理器采用总线方式连接，总线可以包括任意数量的互联的总线和桥，总线将一个或多个处理器和存储器的各种电路连接在一起。总线还可以将诸如外围设备、稳压器和功率管理电路等之类的各种其他电路连接在一起，这些都是本领域所公知的，因此，本文不再对其进行进一步描述。总线接口在总线和收发机之间提供接口。收发机可以是一个元件，也可以是多个元件，比如多个接收器和发送器，提供用于在传输介质上与各种其他装置通信的单元。经处理器处理的数据通过天线在无线介质上进行传输，进一步，天线还接收数据并将数据传送给处理器。

[0328] 处理器负责管理总线和通常的处理，还可以提供各种功能，包括定时，外围接口，电压调节、电源管理以及其他控制功能。而存储器可以被用于存储处理器在执行操作时所使用的数据。

[0329] 本申请第八实施方式涉及一种非易失性计算机可读存储介质，存储有计算机程序。计算机程序被处理器执行时实现本申请第五实施方式所述的标定方法。

[0330] 即，本领域技术人员可以理解，实现上述实施例方法中的全部或部分步骤是可以通过程序来指令相关的硬件来完成，该程序存储在一个存储介质中，包括若干指令用以使得一个设备(可以是单片机，芯片等)或处理器(processor)执行本申请各个实施例所述方法的全部或部分步骤。而前述的存储介质包括：U盘、移动硬盘、只读存储器(ROM，Read-OnlyMemory)、随机存取存储器(RAM，Random Access Memory)、磁碟或者光盘等各种可以存储程序代码的介质。

[0331] 本领域技术人员在考虑说明书及实践这里公开的申请后，将容易想到本申请的其它实施方案。本申请旨在涵盖本申请的任何变型、用途或者适应性变化，这些变型、用途或者适应性变化遵循本申请的一般性原理并包括本公开未公开的本技术领域中的公知常识或惯用技术手段。说明书和实施例仅被视为示例性的，本申请的真正范围和精神由下面的权利要求指出。

[0332] 应当理解的是，本申请并不局限于上面已经描述并在附图中示出的精确结构，并且可以在不脱离其范围进行各种修改和改变。本申请的范围仅由所附的权利要求来限制。

Claims

1. A calibration plate, characterized in that: Used to calibrate sensors of a vehicle's autonomous driving system, wherein the sensors of the vehicle's autonomous driving system include millimeter-wave radars and cameras; Including: calibration carrier, multiple marking codes and millimeter wave radar calibration unit; The millimeter-wave radar calibration unit is fixed at the center of the calibration carrier, and is used to feed back the calibration result of the millimeter-wave radar according to the calibration data sent by the millimeter-wave radar, so that the vehicle automatic driving system can calibrate the millimeter-wave radar according to the calibration result of the millimeter-wave radar, wherein the millimeter-wave reflectivity of the millimeter-wave radar calibration unit is higher than the millimeter-wave reflectivity of the calibration carrier; A plurality of the marking codes are fixed on the calibration carrier and surround the millimeter wave radar calibration unit; The identification code carries two-dimensional code information for identification by the sensor, and is used to provide feedback on the calibration result of the camera based on the calibration data sent by the camera, so that the vehicle's automatic driving system can calibrate the camera based on the calibration result of the camera, wherein the identity information corresponding to the two-dimensional code information of all the identification codes is different.

2. The calibration plate according to claim 1, characterized in that: The marking code includes a first area and a second area, and the laser absorption of the second area of ​​the marking code is greater than the laser absorption of the first area of ​​the marking code; The color of the calibration carrier plate is different from the color of the second area of ​​the marking code, and the laser absorptivity of the surface of the calibration carrier plate is different from the light absorptivity of the surface of the second area of ​​the marking code.

3. The calibration plate according to claim 2, characterized in that: The second area of ​​the marking code is obtained by spraying a coating material having a higher laser absorption than that of the calibration carrier plate.

4. The calibration plate according to claim 1, characterized in that: The millimeter-wave radar calibration unit is a polygonal structure, the marking code is a polygonal result, multiple vertices of the marking code close to the direction of the millimeter-wave radar calibration unit are connected to the vertices of the millimeter-wave radar calibration unit, and the number of vertices of the millimeter-wave radar calibration unit is greater than or equal to 4.

5. The calibration plate according to claim 4, characterized in that: The number of the marking codes is 4, and the polygonal structures of the millimeter wave radar calibration unit and the marking codes are both rectangular.

6. The calibration plate according to claim 1, characterized in that: The two-dimensional code information carried by the flag code is a two-dimensional code-like ArUco code.

7. A calibration component, characterized in that: comprising a plurality of calibration plates and connectors according to any one of claims 1 to 6; The connecting member is fixedly connected between two adjacent calibration plates, and is used for the vehicle automatic driving system to determine the relative positions of the two adjacent calibration plates based on the connecting member.

8. The calibration component according to claim 7, characterized in that: The connecting member is also used to control the angle between any one of the two calibration plates and the vertical plane where the two calibration plates are located.

9. The calibration component according to claim 8, characterized in that: The front sides of the two calibration plates are located on the same side of the calibration component.

10. The calibration component according to claim 8, characterized in that: The front sides of the two calibration plates are located on both sides of the calibration component.

11. A calibration device, characterized in that: It comprises a calibration component and a calibration bracket composed of a calibration plate according to any one of claims 1 to 6; The calibration bracket includes a base, a main bracket, and a plurality of bracket beams; The main support is fixedly connected to the base, a plurality of support beams are arranged in parallel and connected to the main support, and one end of the plurality of support beams away from the main support is respectively connected to a plurality of calibration plates in the calibration component.

12. The calibration device according to claim 11, characterized in that: The calibration plate also includes a calibration plate bracket; The plurality of calibration plate brackets can be movably connected to the plurality of bracket beams to adjust the angle between the calibration plate and the plumb plane.

13. The calibration device according to claim 11, characterized in that: The main support includes a retractable structure for controlling the top height of the main support.

14. A calibration system, characterized in that: A calibration device and a total station comprising a plurality of calibration plates according to any one of claims 1 to 6 located in a calibration space; The total station is used to determine the positional relationship between the plurality of calibration devices and the vehicle; The multiple calibration devices are used to calibrate the vehicle according to the position relationship measured by the total station, wherein the multiple calibration devices surround the vehicle and there are two or more calibration devices in any direction of the vehicle, wherein the angles of the two or more calibration devices are the same.

15. The calibration system according to claim 14, characterized in that: The calibration device surrounding the vehicle has multiple layers; Among the plurality of calibration devices on each layer, the distance from the calibration devices located on the left and right sides of the vehicle to the vehicle is smaller than the distance from the calibration devices located on the front and rear sides of the vehicle to the vehicle; The size of the calibration plate in any layer of the calibration devices is larger than the size of the calibration plate in a layer of the calibration devices that is closer to the vehicle than any layer of the calibration devices; The height of any layer of the calibration devices is greater than or equal to the height of the calibration devices of the previous layer that is closer to the vehicle relative to any layer of the calibration devices, wherein the calibration plates on the calibration devices are all located within the field of view of the vehicle.

16. The calibration system according to claim 14, characterized in that: A plurality of calibration plates as described in any one of claims 1 to 6 and positioning balls corresponding to the calibration plates are laid flat on the ground of the calibration system; The plurality of calibration plates are located at the left front, right front, left rear and right rear of the vehicle, and are used for the sensor to obtain surround view stitching calibration parameters; A plurality of positioning balls corresponding to the calibration plates are fixed at the apex of the calibration plates away from the vehicle, so as to assist the vehicle in positioning the calibration plates.

17. A calibration method, characterized in that: Calibration is performed by using the calibration plate as described in any one of claims 1 to 6, wherein the sensor includes a camera, a laser radar, and a millimeter wave radar, and the method includes: Acquiring the vehicle's surrounding environment information through the camera; Acquiring point cloud information around the vehicle body through the laser radar; Acquiring first position information of the millimeter wave radar calibration unit in the calibration plate through the millimeter wave radar; Acquire second position information of the millimeter-wave radar calibration unit according to the vehicle body surrounding environment information; Acquire third position information of the millimeter-wave radar calibration unit according to the point cloud information around the vehicle body; The camera, the laser radar and the millimeter-wave radar are calibrated according to the fourth position information of the vehicle and the first position information, the second position information and the third position information of the preset millimeter-wave radar calibration unit.

18. A calibration system, characterized in that: include: An environment acquisition module, used to acquire the vehicle's surrounding environment information through a camera in the calibration site; A point cloud acquisition module, used to acquire point cloud information around the vehicle body by using a laser radar in the calibration site; A millimeter wave radar calibration unit first position acquisition module, used to acquire first position information of the millimeter wave radar calibration unit through the millimeter wave radar in the calibration site; A millimeter-wave radar calibration unit second position acquisition module, used to acquire second position information of the millimeter-wave radar calibration unit according to the vehicle body surrounding environment information; A millimeter-wave radar calibration unit third position acquisition module, used to acquire third position information of the millimeter-wave radar calibration unit according to the point cloud information around the vehicle body; A sensor calibration module is used to calibrate the camera, the laser radar and the millimeter wave radar according to the fourth position information of the millimeter wave radar calibration unit relative to the vehicle and the first position information, the second position information and the third position information.

19. An electronic device, characterized in that: It includes a processor and a memory, wherein the memory stores programs or instructions that can be run on the processor, and when the programs or instructions are executed by the processor, the steps of the calibration method as claimed in claim 17 are implemented.

20. A non-volatile readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the calibration method according to claim 17 is implemented.

Images