Calibration method, calibration device, calibration system and readable storage medium

Abstract

The application provides a calibration method, a calibration device, a calibration system and a readable storage medium, wherein the calibration method comprises: acquiring a point cloud obtained by a laser radar from a field of view, the point cloud being in a radar coordinate system; acquiring a surveying point set obtained by a surveying device from the field of view, the surveying point set being in a surveying coordinate system; determining first conversion parameters between the radar coordinate system and the surveying coordinate system based on the point cloud and the surveying point set; and determining calibration parameters between the radar coordinate system and a vehicle coordinate system of a vehicle based on the first conversion parameters and pose information of the vehicle in the surveying coordinate system. The above scheme can improve calibration efficiency and calibration accuracy, and is beneficial to batch calibration.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of automatic driving, and in particular to a calibration method, a calibration device, a calibration system and a readable storage medium. BACKGROUND

[0002] In the current field of automatic driving, a vehicle is usually loaded with various data acquisition devices, such as a laser radar, a camera, etc. Different coordinate systems are used by each data acquisition device, resulting in the data acquired by multiple data acquisition devices being unable to be used in cooperation. At this time, it is usually necessary to convert the data acquired by different data acquisition devices to a specified coordinate system, and to process and analyze the data in the same coordinate system.

[0003] In order to realize coordinate system conversion, it is necessary to obtain the relative pose relationship between the coordinate system of each data acquisition device and the specified coordinate system. This process of obtaining the relative pose relationship can be referred to as calibration, and the data used to represent the relative pose relationship between the coordinate system of the data acquisition device and the specified coordinate system can be referred to as conversion parameters.

[0004] However, the existing calibration process of a laser radar needs to spend a lot of time to control the calibration accuracy, thereby reducing the calibration efficiency of the existing laser radar calibration scheme. Moreover, due to the low calibration efficiency, the existing laser radar calibration scheme cannot meet the demand of batch calibration, and even if batch calibration is performed, a large amount of time is still needed. SUMMARY

[0005] Therefore, the present application provides a calibration method, a calibration device, a calibration system and a readable storage medium, which can improve the calibration efficiency and the calibration accuracy, and are beneficial to batch calibration.

[0006] Specifically, the present application provides a calibration method for obtaining the relative pose relationship between a laser radar and a vehicle; the method comprises:

[0007] obtaining a point cloud obtained by the laser radar from a field of view, the point cloud being in a radar coordinate system;

[0008] obtaining a surveying point set obtained by a surveying device from the field of view, the surveying point set being in a surveying coordinate system;

[0009] determining first conversion parameters between the radar coordinate system and the surveying coordinate system based on the point cloud and the surveying point set;

[0010] determining calibration parameters between the radar coordinate system and a vehicle coordinate system of the vehicle based on the first conversion parameters and pose information of the vehicle in the surveying coordinate system.

[0011] The application further provides a calibration device connected with the laser radar and the mapping device respectively, and used for obtaining the relative pose relationship between the laser radar and the vehicle.

[0012] The data acquisition unit is adapted to acquire a point cloud obtained by the laser radar from a field of view and a mapping point set obtained by the mapping device from the field of view, the point cloud being in a radar coordinate system, and the mapping point set being in a mapping coordinate system.

[0013] The data processing unit is adapted to determine first conversion parameters between the radar coordinate system and the mapping coordinate system according to the point cloud and the mapping point set, and determine calibration parameters between the radar coordinate system and a vehicle coordinate system of the vehicle according to the first conversion parameters and pose information of the vehicle in the mapping coordinate system.

[0014] The application further provides a calibration device comprising a memory and a processor, the memory storing computer instructions capable of running on the processor, and the processor executing the steps of the method according to any one of the above when running the computer instructions.

[0015] The application further provides a calibration system comprising a mapping device and a calibration device, the calibration device being connected with the mapping device and the laser radar respectively, and used for obtaining the relative pose relationship between the laser radar and the vehicle.

[0016] The laser radar is adapted to acquire a point cloud corresponding to a field of view, the point cloud being in a radar coordinate system.

[0017] The mapping device is adapted to acquire a mapping point set corresponding to the field of view, the mapping point set being in a mapping coordinate system.

[0018] The calibration device is adapted to acquire the point cloud and the mapping point set, determine first conversion parameters between the radar coordinate system and the mapping coordinate system according to the point cloud and the mapping point set, and determine calibration parameters between the radar coordinate system and a vehicle coordinate system of the vehicle according to the first conversion parameters and pose information of the vehicle in the mapping coordinate system.

[0019] The application further provides a readable storage medium storing computer instructions, the computer instructions running to execute the steps of the method according to any one of the above.

[0020] The calibration method provided by the application can be used to obtain the relative pose relationship between a laser radar and a vehicle. The first conversion parameter between the radar coordinate system and the surveying coordinate system can be determined by the point cloud obtained by the laser radar from the field of view and the surveying point set obtained by the surveying device from the field of view. The calibration parameter between the radar coordinate system and the vehicle coordinate system of the vehicle can be determined based on the first conversion parameter and the pose information of the vehicle in the surveying coordinate system.

[0021] By the above scheme, on the one hand, the first conversion parameter determined by the point cloud and the surveying point set can represent the relative pose relationship between the radar coordinate system and the surveying coordinate system, so that the data can be converted between the radar coordinate system and the surveying coordinate system. The pose information of the vehicle in the surveying coordinate system can reflect the relative pose relationship between the vehicle coordinate system and the surveying coordinate system, that is, the relative pose relationship between the vehicle coordinate system and the surveying coordinate system is relatively fixed. Therefore, the time for obtaining the relative pose relationship between the vehicle coordinate system and the surveying coordinate system can be saved, and the calibration between the radar coordinate system and the vehicle coordinate system can be quickly completed through the intermediate conversion of the surveying coordinate system, thereby improving the calibration efficiency. On the other hand, the surveying device has high-precision measurement performance, can obtain high-precision surveying point set, and can ensure that the pose information of the vehicle in the surveying coordinate system has high precision, thereby improving the calibration accuracy. In summary, the calibration method provided by the application can improve the calibration efficiency and the calibration accuracy, and is beneficial to batch calibration. BRIEF DESCRIPTION OF DRAWINGS

[0022] In order to more clearly illustrate the technical solutions of the application, the following will briefly introduce the drawings needed to be used in the description of the application or the prior art. Obviously, the drawings described below are only some embodiments of the application, and other drawings can be obtained by those skilled in the art without creative effort.

[0023] Figure 1 A flowchart of a calibration method provided by an embodiment of the application.

[0024] Figure 2 A flowchart of a first conversion parameter acquisition method provided by an embodiment of the application.

[0025] Figure 3 A specific flowchart of a first conversion parameter updating method provided by an embodiment of the application.

[0026] Figure 4 A surface diagram of a reference object provided by an embodiment of the application.

[0027] Figure 5 A flowchart of a matching point acquisition method provided for an embodiment of the present application.

[0028] Figure 6 A structure block diagram of a calibration device provided for an embodiment of the present application.

[0029] Figure 7 A structure block diagram of another calibration device provided for an embodiment of the present application.

[0030] Figure 8 A structure block diagram of a calibration system provided for an embodiment of the present application.

[0031] Figure 9 An application scenario diagram of a calibration system provided for an embodiment of the present application. DETAILED DESCRIPTION

[0032] As can be known from the background art content, the calibration process of the existing laser radar needs to spend a lot of time to control the calibration accuracy, which reduces the calibration efficiency of the existing laser radar calibration scheme. Moreover, due to the low calibration efficiency, the existing laser radar calibration scheme cannot meet the demand of batch calibration, and even if batch calibration is performed, a large amount of time is also needed.

[0033] In order to solve the problems existing in the existing calibration scheme, the present application provides a calibration method for acquiring the relative pose relationship between the laser radar and the vehicle. Through the point cloud obtained by the laser radar from the field of view and the surveying point set obtained by the surveying device from the field of view, the first conversion parameter between the radar coordinate system and the surveying coordinate system can be determined. Based on the first conversion parameter and the pose information of the vehicle in the surveying coordinate system, the calibration parameter between the radar coordinate system and the vehicle coordinate system of the vehicle can be determined. Thus, the calibration efficiency and the calibration accuracy can be improved, which is beneficial to batch calibration.

[0034] In order to make those skilled in the art more clearly understand and implement the concept, implementation scheme and advantages of the present application, the following will be described in detail with reference to the accompanying drawings.

[0035] Reference Figure 1 A flowchart of a calibration method provided for an embodiment of the present application can be used to acquire the relative pose relationship between the laser radar and the vehicle. In the specific implementation, the calibration method can include:

[0036] S11, acquiring the point cloud obtained by the laser radar from the field of view, the point cloud being in a radar coordinate system.

[0037] The radar coordinate system can be a coordinate system established with a specified position in the laser radar as the origin.

[0038] In specific implementations, the laser radar can emit light signals within its field of view, the light signals are reflected by reference objects in the field of view and received by the laser radar, based on the emitted light signals and the light signals reflected by the reference objects in the field of view, a plurality of data points can be generated in the field of view of the laser radar, thereby forming a point cloud. Each data point can include coordinate values in the radar coordinate system.

[0039] S12, obtaining a surveying point set obtained by a surveying device from the field of view, the surveying point set being in a surveying coordinate system.

[0040] The surveying coordinate system can be a coordinate system established with a specified position in the surveying device as an origin. The surveying device can be any device with high-precision measurement capability, such as a total station.

[0041] In specific implementations, the surveying device is located at a position capable of surveying the reference objects in the field of view of the laser radar. For example, the surveying device can be located above or aside the vehicle. For another example, the surveying device can be located above, below or aside the laser radar.

[0042] It can be understood that the specific arrangement position of the surveying device can be set according to actual application scenarios, and the embodiments of the present application do not limit this.

[0043] S13, determining first conversion parameters between the radar coordinate system and the surveying coordinate system based on the point cloud and the surveying point set.

[0044] The first conversion parameters can include first relative displacement information and first relative angle information. The first relative displacement information can represent the relative translation distance between the radar coordinate system and the surveying coordinate system, and the first relative angle information can represent the relative rotation angle between the radar coordinate system and the surveying coordinate system.

[0045] Further, the first relative angle information can include at least one of pitch angle information, roll angle information and yaw angle information between the radar coordinate system and the surveying coordinate system.

[0046] S14, determining calibration parameters between the radar coordinate system and a vehicle coordinate system of the vehicle based on the first conversion parameters and pose information of the vehicle in the surveying coordinate system.

[0047] In specific implementations, the pose information of the vehicle in the surveying coordinate system can include coordinate information and orientation information of the vehicle in the surveying coordinate system. Further, the orientation information of the vehicle in the surveying coordinate system can include at least one of pitch angle information, roll angle information and yaw angle information of the vehicle in the surveying coordinate system.

[0048] The vehicle coordinate system can be a coordinate system established with a specified position in the vehicle as an origin. The specified position in the vehicle can be any one of a contact point of a tire with the ground in the vehicle, a wheel shaft center point of a tire in the vehicle, a wheel center of a tire in the vehicle, and an end point of a head region of the vehicle.

[0049] The calibration parameters can include second relative displacement information and second relative angle information. The second relative displacement information can represent a relative translation distance between the radar coordinate system and the mapping coordinate system, and the second relative angle information can represent a relative rotation angle between the radar coordinate system and the mapping coordinate system.

[0050] Further, the second relative angle information can include at least one of pitch angle information, roll angle information, and yaw angle information between the radar coordinate system and the mapping coordinate system.

[0051] With the above scheme, on the one hand, the first conversion parameters determined by the point cloud and the mapping point set can represent the relative pose relationship between the radar coordinate system and the mapping coordinate system, so that data can be converted between the radar coordinate system and the mapping coordinate system, and the pose information of the vehicle in the mapping coordinate system can reflect the relative pose relationship between the vehicle coordinate system and the mapping coordinate system, that is, the relative pose relationship between the vehicle coordinate system and the mapping coordinate system is relatively fixed, thereby the time for obtaining the relative pose relationship between the vehicle coordinate system and the mapping coordinate system can be saved, and the calibration between the radar coordinate system and the vehicle coordinate system can be quickly completed through the intermediate conversion of the mapping coordinate system, thereby improving the calibration efficiency. On the other hand, the mapping device has high-precision measurement performance, can obtain high-precision mapping point sets, and can ensure that the pose information of the vehicle in the mapping coordinate system has high precision, thereby improving the calibration accuracy.

[0052] In summary, the calibration method provided by the present application can improve the calibration efficiency and the calibration accuracy, and is beneficial to batch calibration.

[0053] It should be noted that the steps S11 and S12 in the above embodiments do not have a certain execution order, and steps S11 and S12 can be executed in parallel or in a specified order according to specific circumstances, and the embodiments of the present application do not make specific limitations.

[0054] In specific implementation, the pose information of the vehicle in the mapping coordinate system can be converted by the second conversion parameters between the mapping coordinate system and the vehicle coordinate system, or can be obtained by pre-setting.

[0055] Specifically, before the calibration of the radar coordinate system and the vehicle coordinate system, the second conversion parameter can be obtained by calibrating the vehicle coordinate system and the mapping coordinate system. Thus, the corresponding second conversion parameter can be obtained according to the position of the vehicle in the environment.

[0056] In a specific implementation, since the position information of the vehicle in the mapping coordinate system can be obtained in advance, in order to ensure that the position of the vehicle matches the position information of the vehicle in the mapping coordinate system obtained in advance, the vehicle and the mapping device can be positioned by a third-party device.

[0057] The third-party device can be any device with alignment function. The relative position relationship between the third-party device and the mapping device can be obtained in advance, and data representing the relative position relationship between the third-party device and the mapping device can be stored in any device with storage function, such as the third-party device itself, a calibration device used to execute the calibration method provided in the embodiments of the present application, and the like. The specific type of the third-party device and the data storage object are not limited in the embodiments of the present application.

[0058] In addition, the alignment order among the vehicle, the mapping device, and the third-party device can be set according to specific situations and requirements, which is not limited in the embodiments of the present application.

[0059] In an optional example, the vehicle and the mapping device can be positioned by a positioner. Specifically, the mapping device can be first aligned with a reference point on the positioner; then, the vehicle is moved to the positioner, and the vehicle stops moving when a specified part (such as the center of a wheel or the front of the vehicle) of the vehicle is aligned with the reference point of the positioner. Thus, the positioning between the vehicle and the mapping device is completed. Alternatively, the vehicle can be first moved to the positioner, and the vehicle stops moving after a specified part of the vehicle is aligned with the reference point of the positioner; then, the mapping device is aligned with the reference point on the positioner. Thus, the positioning between the vehicle and the mapping device is completed.

[0060] The data representing the relative position relationship between the mapping device and the positioner can be stored in the calibration device.

[0061] Thus, the position of the vehicle and the mapping device in the environment is determined by the positioner, which can avoid repeatedly calibrating the vehicle coordinate system and the mapping coordinate system, and reduce the data operation amount and operation time.

[0062] In a specific implementation, the first conversion parameter can be determined by matching the point cloud and the set of mapping points. Specifically, the steps of matching the point cloud and the set of mapping points can include:

[0063] A1) set a plurality of cells in the surveying coordinate system, and obtain normal distribution parameters of each cell based on distribution of each surveying point in each cell in the surveying point set;

[0064] A2) determine, based on the preset conversion matrix, a surveying point closest to each data point in the surveying point set, to obtain a neighboring surveying point;

[0065] A3) calculate a distribution error based on the preset distribution error function, each data point, and the neighboring surveying point;

[0066] A4) based on the distribution error value, adjust the value of the conversion matrix, and continue to calculate the distribution error by referring to steps A2) and A3) above, until the calculated error meets the preset error allowable range, or the adjustment times reaches the preset number threshold, stop adjusting, and take the adjusted conversion matrix as the first conversion parameter.

[0067] In specific implementation, in order to improve the accuracy of the first conversion parameter, the first conversion parameter can be updated and evaluated. Specifically, as shown in Figure 2 FIG. 1 is a flowchart of a method for obtaining a first conversion parameter according to an embodiment of the present application. In the process of determining the first conversion parameter between the radar coordinate system and the surveying coordinate system based on the point cloud and the surveying point set, the following steps can be included:

[0068] S21, update the first conversion parameter based on the current first conversion parameter, the surveying point set, and the matching points in the point cloud, and obtain corresponding parameter evaluation information.

[0069] The matching points can be data points selected from the point cloud, and the selection method can be set according to specific application scenarios and requirements; the parameter evaluation information can represent the update state and / or update effect of the first conversion parameter.

[0070] For example, the parameter evaluation information can include the number of updates of the first conversion parameter to represent the update state of the first conversion parameter, and / or the matching error between the matching points and the neighboring surveying points in the surveying point set after the matching points are converted to the surveying coordinate system based on the updated first conversion parameter, to represent the update effect of the first conversion parameter.

[0071] Therefore, by updating the first conversion parameter, the accuracy of the first conversion parameter can be improved, and the parameter evaluation information can provide evaluation information related to the first conversion parameter for subsequent use. For example, the related evaluation information can be used and referred to when determining to iteratively update the first conversion parameter, and specific descriptions can be referred to in the following related parts, which are not described here.

[0072] In a specific implementation, the matching points can be converted to the mapping coordinate system based on the current first conversion parameter, and then combined with the mapping point set to update the first conversion parameter and obtain the parameter evaluation information.

[0073] Specifically, as shown in the flowchart of a first conversion parameter updating method provided by an embodiment of the present application. In the process of updating the first conversion parameter based on the current first conversion parameter, the mapping point set, and the matching points in the point cloud, and obtaining the corresponding parameter evaluation information, the following steps can be included: Figure 3

[0074] S31, obtaining the pose information of the matching points in the mapping coordinate system based on the current first conversion parameter and the pose information of the matching points in the radar coordinate system.

[0075] The pose information of the matching points in the radar coordinate system can include coordinate information and orientation information of the matching points in the radar coordinate system, and the pose information of the matching points in the mapping coordinate system can include coordinate information and orientation information of the matching points in the mapping coordinate system. Further, the orientation information can include at least one of pitch angle information, roll angle information, and yaw angle information.

[0076] Optionally, the relationship between the pose information of the matching points in the radar coordinate system, the first conversion parameter, and the pose information of the matching points in the mapping coordinate system can be expressed by the following equation:

[0077]

[0078] wherein, P i L represents the pose information of the i-th matching point in the mapping coordinate system; represents the first conversion parameter that is not updated; P i L represents the pose information of the i-th matching point in the radar coordinate system.

[0079] S32, updating the first conversion parameter based on the pose information of the matching points in the mapping coordinate system and the mapping point set, and obtaining the parameter evaluation information.

[0080] In a specific implementation, the updated first conversion parameter and the parameter evaluation information can be obtained by matching the pose information of the matching points in the mapping coordinate system and the mapping point set. The specific steps of the matching process can include:

[0081] ​B1) determining a closest mapping point to the matching point based on the pose information of the matching point in the mapping coordinate system and the pose information of each mapping point in the set of mapping points, to obtain a neighboring mapping point;

[0082] B2) performing singular value decomposition (SVD) based on the matching point and the neighboring mapping point, to obtain a new first conversion parameter;

[0083] B3) calculating a matching error between the matching point and the neighboring mapping point based on the matching point, the neighboring mapping point, and a preset matching error function, and determining the number of updates of the first conversion parameter, to obtain the parameter evaluation information.

[0084] The matching error function can be used to calculate the sum of distances between all matching points converted from the radar coordinate system to the mapping coordinate system according to the updated first conversion parameter and the neighboring mapping points. The expression of the matching error function is as follows:

[0085]

[0086] wherein P i L represents the pose information of the i-th matching point in the n matching points; represents the first conversion parameter after the j-th update; P i C represents the pose information of the neighboring mapping point of the i-th matching point in the n matching points.

[0087] Thus, the matching points can be converted from the radar coordinate system to the mapping coordinate system by the first conversion parameter, and the matching points and the set of mapping points in the same coordinate system are comparable, thereby ensuring accurate updating of the first conversion parameter and obtaining reliable parameter evaluation information.

[0088] In specific implementations, in order to improve the operation efficiency, the set of mapping points can be screened before determining the closest mapping point to the matching point in the set of mapping points, so as to filter out noise points and reduce the amount of data. The screening method of the set of mapping points can be set according to the position of the matching point in the field of view of the laser radar. For example, if the matching point corresponds to the position of point A in the field of view, the mapping points related to the position of point A can be screened from the set of mapping points.

[0089] In a specific implementation, in order to further improve the accuracy of the first conversion parameter, the parameter evaluation information can also be used as a basis for judging whether the first conversion parameter meets the expected accuracy requirement, and an iteration condition is set, so that whether the first conversion parameter meets the expected accuracy requirement is judged according to at least one of the number of iterations and the matching error, and when the expected accuracy requirement is not met, the first conversion parameter and the parameter evaluation information are continuously updated, so that the current first conversion parameter is iteratively updated and evaluated multiple times.

[0090] Specifically, as shown in Figure 2 In the process of determining the first conversion parameter between the radar coordinate system and the surveying coordinate system based on the point cloud and the surveying point set, the following steps can also be included:

[0091] S22, judging whether the parameter evaluation information meets the iteration condition, when it is determined that the parameter evaluation information meets the iteration condition, returning to the above step S21 to continue updating the first conversion parameter and the parameter evaluation information; until it is determined that the iteration condition is not met to stop.

[0092] When the number of iterations of the first conversion parameter reaches a first threshold value, and / or when the matching error between adjacent surveying points in the surveying point set is not greater than a second threshold value after the matching points are converted to the surveying coordinate system based on the updated first conversion parameter, it can be determined that the parameter evaluation information meets the iteration condition.

[0093] Therefore, by iteratively updating the first conversion parameter, the accuracy of the first conversion parameter can be further improved.

[0094] In a specific implementation, in order to improve the screening speed, a target region can be set, so that the point cloud is screened based on the target region to determine the matching points. The number and size of the target region can be set according to the surface features of the reference object in the field of view of the laser radar, which is not limited in the present application.

[0095] In an optional example, as shown in Figure 4 It is a surface diagram of a reference object. In Figure 4 The surface of the reference object OB1 includes a first region f1 and a second region f2, and the reflectivity of the first region f1 is different from that of the second region f2, so the surface features of the reference object OB1 can include the overall outer contour of the reference object OB1, the geometric center of the surface of the reference object OB1, the contour of the first region f1, the contour of the second region f2, the geometric center of the first region f1, the geometric center of the second region f2, etc.

[0096] Accordingly, based on the surface features of the reference object OB1, one or more target regions can be set. Among them, according to the specific application scene and requirements, the target region containing, matching or excluding the surface features of the reference object can be set. For example, a target region containing the overall outer contour of the reference object OB1 can be set; a target region excluding the first region f1 can also be set; and a target region matching the geometric center of the second region f2 can also be set.

[0097] It can be understood that, Figure 4 The reference object shown is only for illustrative purposes. In actual applications, there can be more reference objects in the field of view, and the shape and surface reflectivity region distribution of the reference object can also be more complex, and the present application does not make specific limitations thereto.

[0098] In specific implementations, in order to improve the screening accuracy, the point cloud can be screened successively according to the target regions containing different information, and the screening range is gradually reduced from different dimensions to obtain more accurate matching points.

[0099] In an optional example, as Figure 5 shown, it is a flowchart of a matching point acquisition method, which can be applied to a reference object with different reflectivity regions. The method can specifically include the following steps:

[0100] S41, based on the first target region, screening the point cloud to obtain a reference plane.

[0101] In specific implementations, the first target region can contain pose information. The pose information of the first target region is matched with the pose information of each data point in the point cloud to extract data points matched with the first target region, so as to determine the reference plane.

[0102] Among them, by clustering the data points matched with the first target region, the corresponding plane equation can be calculated to determine the reference plane.

[0103] In specific implementations, in order to facilitate the setting of the pose information of the first target region, the first target region can correspond to the plane where the bottom surface of the reference object is located. For example, if the reference object is placed on the ground, the first target region can correspond to the ground, and the reference plane is the plane equation of the calculated ground.

[0104] Therefore, only the vertical distance between the bottom surface of the reference object and the laser radar needs to be set as the height coordinate information of the first target region. That is, the height coordinate information of the first target region can be used to screen the data points matched with the plane where the bottom surface of the reference object is located from the point cloud.

[0105] S42, continue to screen the point cloud based on the reference plane, to obtain a screened point cloud.

[0106] In specific implementations, a distance value of each data point in the point cloud to the reference plane can be determined, and the point cloud can be screened based on the distance value to obtain a screened point cloud.

[0107] Specifically, since the reference plane can be represented by a plane equation, a normal vector obtained according to the plane equation and coordinate information of each data point can be used to calculate a distance value of each data point to the reference plane. Then, according to the shape of the reference object, a corresponding distance range can be set, so as to obtain data points with distance values conforming to the distance range as the screened point cloud.

[0108] Herein, the shape of the reference object can be set as a regular shape to facilitate setting of the distance range. For example, the reference plane is a plane equation of a calculated ground, and the reference object is a rectangular panel, so that the distance range can be set according to a distance from a top end of a panel opposite to the laser radar to the ground and a distance from a bottom end of the panel to the ground.

[0109] In this way, data points related to the reference object can be roughly extracted.

[0110] In specific implementations, in order to delete useless data points (such as noise points and discrete data points) and reduce the amount of data, a clustering screening process and / or a regional screening process can be performed on the point cloud in the process of screening the point cloud based on the distance range.

[0111] Specifically, the clustering screening process can include: extracting data points with distance values conforming to the distance range from the point cloud and clustering; when it is determined that a clustering result satisfies a loop condition, screening the clustering result and continuing to cluster, until it is determined that the clustering result does not satisfy the loop condition, to stop, to obtain the screened point cloud. The loop condition can be related to a number of categories indicated by the clustering result, for example, the loop condition can be set as: the number of categories indicated by the clustering result is greater than N, N is a natural number.

[0112] The regional screening process can include: extracting data points with distance values conforming to the distance range from the point cloud, and dividing the data points into a plurality of point cloud regions according to a first direction; determining spatial information of the plurality of point cloud regions in a second direction, and screening the plurality of point cloud regions based on the spatial information to obtain the screened point cloud.

[0113] The first direction can intersect the second direction. The spatial information can include a distance variance calculated based on distances of data points in the point cloud region to a specified plane in the second direction. The specified plane can be any plane parallel to the first direction.

[0114] In this way, data points related to the reference and data points unrelated to the reference (such as a support rod of a fixed reference, a noise point, etc.) can be distinguished.

[0115] S43, based on the second target region, screening the screened point cloud to obtain the matching point.

[0116] In specific implementations, the second target region can include reflectivity information. The reflectivity information of the second target region is matched with reflectivity information of each data point in the screened point cloud, so as to determine a plurality of specified position points and a plurality of flatnesses corresponding to the plurality of specified position points according to data points matched with the second target region; and the plurality of specified position points are screened based on the flatnesses to obtain the matching point.

[0117] Specifically, the data points matched with the second target region can be clustered to determine the plurality of specified position points and the plurality of flatnesses corresponding to the plurality of specified position points according to a clustering result. For example, if the data points matched with the second target region are clustered to obtain a plurality of categories, a specified position point can be selected from data points corresponding to each category, or a specified position point can be calculated based on data points corresponding to each category. Moreover, data points corresponding to each category can form a plane, and the corresponding flatness can be calculated.

[0118] In specific implementations, the second target region can be set according to the reflectivity distribution of the surface of the reference, so as to obtain the matching point of the corresponding resolution region.

[0119] For example, if the surface of the reference includes one or more regions with fixed resolution (such as high resolution) and regular shape, the region with regular shape can be set as the second target region, and a geometric center of the region can be set as the matching point.

[0120] In this way, the point cloud is screened successively according to different screening criteria (i.e., the first target region, the reference plane, and the second target region), and the screening range is gradually reduced from different dimensions, so as to improve the screening accuracy and obtain a more accurate matching point.

[0121] It can be understood that the above describes a plurality of embodiment schemes provided by the present application, and each optional mode introduced by each embodiment scheme can be combined, cross-referenced in the case of no conflict, thereby extending a plurality of possible embodiment schemes, which can be considered as the disclosed and published embodiment schemes of the present application.

[0122] The present application also provides a calibration device corresponding to the above-mentioned calibration method, which will be described in detail below with reference to the accompanying drawings through specific embodiments. It should be noted that the calibration device described below can be considered as the functional modules required to be set for the calibration method provided by the present application; the content of the calibration device described below can be mutually corresponding and referred to with the content of the calibration method described above.

[0123] In an optional example, as shown in FIG. 1, a structure block diagram of a calibration device in an embodiment of the present application is shown. In the figure, the calibration device M10 can be connected with a laser radar LS1 and a mapping device CH1 respectively, the laser radar LS1 can be arranged on a vehicle CA1; the calibration device M10 can include: Figure 6 Figure 6 a data acquisition unit M11 adapted to acquire a point cloud obtained by the laser radar LSA from a field of view and a mapping point set obtained by the mapping device CH1 from the field of view, the point cloud being in a radar coordinate system, and the mapping point set being in a mapping coordinate system;

[0124] a data processing unit M12 adapted to determine a first conversion parameter between the radar coordinate system and the mapping coordinate system according to the point cloud and the mapping point set, and determine a calibration parameter between the radar coordinate system and a vehicle coordinate system of the vehicle CA1 according to the first conversion parameter and pose information of the vehicle CA1 in the mapping coordinate system.

[0125] a data processing unit M12 adapted to determine a first conversion parameter between the radar coordinate system and the mapping coordinate system according to the point cloud and the mapping point set, and determine a calibration parameter between the radar coordinate system and a vehicle coordinate system of the vehicle CA1 according to the first conversion parameter and pose information of the vehicle CA1 in the mapping coordinate system.

[0126] ​It can be seen from the above that, by using the calibration device, on the one hand, the first conversion parameter determined by the point cloud and the surveying point set can represent the relative pose relationship between the radar coordinate system and the surveying coordinate system, so that data can be converted between the radar coordinate system and the surveying coordinate system, and the pose information of the vehicle in the surveying coordinate system can reflect the relative pose relationship between the vehicle coordinate system and the surveying coordinate system, that is, the relative pose relationship between the vehicle coordinate system and the surveying coordinate system is relatively fixed, thereby, the time for obtaining the relative pose relationship between the vehicle coordinate system and the surveying coordinate system can be saved, and the calibration between the radar coordinate system and the vehicle coordinate system can be quickly completed through the intermediate conversion of the surveying coordinate system, so that the calibration efficiency is improved; on the other hand, the surveying device has high-precision measurement performance, can obtain a high-precision surveying point set, and can ensure that the pose information of the vehicle in the surveying coordinate system has high precision, so that the calibration accuracy is improved.

[0127] In summary, the calibration device provided by the present application can improve the calibration efficiency and the calibration accuracy, and is beneficial to batch calibration.

[0128] It can be understood that the specific process of determining the calibration parameter by the data processing unit in the calibration device can refer to the description in the above calibration method part, and will not be described here again.

[0129] In another optional example, as shown in FIG. 20, it is a structure block diagram of another calibration device in the embodiment of the present application, in which the calibration device M20 can include a memory M21 and a processor M22, the memory M21 stores computer instructions capable of running on the processor M22, and the processor M22 can execute the steps of the calibration method of any one of the above embodiments when running the computer instructions, and specific details can refer to the above related content, which will not be described again. Figure 7 Figure 7 In specific implementation, the processor can include a central processing unit (CPU), a graphics processing unit (GPU), a field programmable gate array (FPGA), etc. The memory can include a random access memory (RAM), a read-only memory (ROM), a non-volatile memory (NVM), etc.

[0130] In specific implementation, the processor can include a central processing unit (CPU), a graphics processing unit (GPU), a field programmable gate array (FPGA), etc. The memory can include a random access memory (RAM), a read-only memory (ROM), a non-volatile memory (NVM), etc.

[0131] ​In particular implementations, computer instructions can include any suitable type of code, such as source code, compiled code, interpreted code, executable code, static code, dynamic code, encrypted code, and the like, implemented using any suitable high-level, low-level, object-oriented, visual, compiled and / or interpreted programming language.

[0132] The present application also provides a calibration system comprising the calibration device described above, which will be described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the content of the calibration system described below can be mutually corresponding with the content of the calibration method and calibration device described above.

[0133] In particular implementations, as shown in FIG. 10, a structural block diagram of a calibration system provided by an embodiment of the present application is shown. In Figure 8 the calibration system SYS10 can include a laser radar LS2, a mapping device CH2, and a calibration device M30; the calibration device M30 can be connected with the laser radar LS2 and the mapping device CH2; the laser radar LS2 is arranged on a vehicle CA2; wherein: Figure 8 the laser radar LS2 is adapted to obtain a point cloud corresponding to a field of view, the point cloud being in a radar coordinate system;

[0134] the mapping device CH2 is adapted to obtain a mapping point set corresponding to the field of view, the mapping point set being in a mapping coordinate system;

[0135] the calibration device M30 is adapted to obtain the point cloud and the mapping point set; according to the point cloud and the mapping point set, a first conversion parameter between the radar coordinate system and the mapping coordinate system is determined, and according to the first conversion parameter and pose information of the vehicle CA2 in the mapping coordinate system, a calibration parameter between the radar coordinate system and a vehicle coordinate system of the vehicle CA2 is determined.

[0136]

[0137] ​It can be seen from the above that, by using the calibration system, on the one hand, the first conversion parameter determined by the point cloud and the survey point set can represent the relative pose relationship between the radar coordinate system and the survey coordinate system, so that data can be converted between the radar coordinate system and the survey coordinate system, and the pose information of the vehicle in the survey coordinate system can reflect the relative pose relationship between the vehicle coordinate system and the survey coordinate system, that is, the relative pose relationship between the vehicle coordinate system and the survey coordinate system is relatively fixed, thereby the time for obtaining the relative pose relationship between the vehicle coordinate system and the survey coordinate system can be saved, and the calibration between the radar coordinate system and the vehicle coordinate system can be quickly completed through the intermediate conversion of the survey coordinate system, so that the calibration efficiency is improved; on the other hand, the survey device has high-precision measurement performance, can obtain a high-precision survey point set, and can ensure that the pose information of the vehicle in the survey coordinate system has high precision, so that the calibration accuracy is improved.

[0138] In summary, the calibration system provided by the present application can improve the calibration efficiency and the calibration accuracy, is beneficial to batch calibration, and can be applied to a scene with the demand of batch calibration of laser radar and vehicles, such as a vehicle production scene.

[0139] It can be understood that the specific process of determining the calibration parameter by the calibration device in the calibration system can refer to the description in the calibration method part above, which will not be repeated here.

[0140] In a specific implementation, the field of view can include a reference object, and a surface of the reference object can include a first area and a second area, and the reflectivity of the first area is different from the reflectivity of the second area.

[0141] It can be understood that the number of reference objects, the number of first areas, and the number of second areas can be set according to specific application scenarios and requirements, and the present application does not limit this.

[0142] It can also be understood that the placement position of the reference object, the distribution of the first area and the second area on the surface of the reference object can be set according to specific application scenarios and requirements, and the present application does not limit this.

[0143] In order for those skilled in the art to more clearly understand and implement the concept, implementation scheme and advantages of the present application, the following will be described in detail through specific application scenarios.

[0144] In an optional example, as shown in Figure 9 , it is a schematic diagram of an application scenario of a calibration system provided by an embodiment of the present application. In Figure 9 , the calibration system can include a centering device BZ, a survey device CHA, and a calibration device M40.

[0145] In addition, in the present example scenario, a plurality of reference objects (such as Figure 9 The reference objects OBA, OBB and OBC have similar structures.

[0146] Taking the reference object OBA as an example, the reference object OBA includes a base A1, a support rod A2 and a panel A3. The panel A3 includes a plurality of first regions (such as Figure 9 The first regions a1, a2, a3 and a4 have high reflectivity, and the second region b1 has low reflectivity. The first regions a1, a2, a3 and a4 can be formed of a material with a reflectivity of 90%-95%, and the second region b1 can be formed of a material with a reflectivity of 5%-10%.

[0147] Further, in order to facilitate data screening, the contour of the first region can be a geometric shape, such as a polygon, a circle, etc. In Figure 9 The first regions a1-a4 are square.

[0148] The structures of the reference objects OBB and OBC can refer to the structure of the reference object OBA, which will not be described here. The reference objects OBA, OBB and OBC are arranged in the environment in a staggered manner, so that the panels of the three are not in the same plane.

[0149] The mapping device CHA is arranged above the reference objects OBA, OBB and OBC and is aligned with the reference point P1 of the aligner BZ. The data representing the relative pose relationship between the mapping device CHA and the aligner BZ is stored in the calibration device M40.

[0150] When the vehicle (such as Figure 9 The vehicle CA with the laser radar LSA arranged on the roof is shown in FIG. 4B. After the front of the vehicle CA with the laser radar moves to the reference point P1, the vehicle CA stops moving, and the positioning between the vehicle CA and the mapping device CHA is completed.

[0151] The laser radar LSA is directed towards the reference objects OBA, OBB and OBC, and the reference objects OBA, OBB and OBC are in the field of view of the laser radar LSA. Using the laser radar LSA, according to the emitted light signal and the light signal reflected by the reference objects OBA, OBB and OBC, a point cloud corresponding to the field of view can be obtained, and the point cloud is in a radar coordinate system ZB1.

[0152] Using the mapping device CHA, the reference objects OBA, OBB and OBC are measured, and a set of mapping points corresponding to the field of view can be obtained, and the set of mapping points is in a mapping coordinate system ZB2.

[0153] The calibration device M40 can be connected with the mapping device CHA and the laser radar LSA respectively. The calibration device M40 can calibrate the radar coordinate system ZB1 and the vehicle coordinate system ZB3 of the vehicle CA to obtain calibration parameters. The calibration device M40 can specifically perform the following steps:

[0154] C1) The first conversion parameter can be obtained by matching the mapping point set in the mapping coordinate system ZB2 with the point cloud in the radar coordinate system ZB1.

[0155] C2) In the point cloud in the radar coordinate system ZB1, the height coordinate information of each data point is used as a screening basis to screen out data points corresponding to the ground (i.e., the first target region in this example), and the data points corresponding to the ground are clustered to calculate the plane equation of the ground (i.e., the reference plane in this example).

[0156] C3) According to the plane equation of the ground, the distance value of each data point in the point cloud to the ground can be calculated.

[0157] C4) The distance range is set according to the distance of the panels of the reference objects OBA, OBB and OBC to the ground, and the point cloud is screened according to the distance value of each data point to the ground, and the point cloud corresponding to the panels of the reference objects OBA, OBB and OBC is screened. Thus, the point cloud related to the reference objects OBA, OBB and OBC can be roughly extracted.

[0158] C5) The point cloud corresponding to the panels of the reference objects OBA, OBB and OBC can be subjected to clustering screening processing and regional screening processing respectively to obtain the screened point cloud corresponding to each reference object panel.

[0159] Taking the reference object OBA as an example, if the category obtained by clustering the point cloud corresponding to the panel A3 of the reference object OBA is 1, it is considered that the point cloud is the point cloud after clustering screening processing corresponding to the panel A3, and the loop condition is not satisfied, and the next step C6 can be performed; if the number of categories obtained by clustering is greater than 1, the loop condition is satisfied, and the category with the most data points is retained, and the data points corresponding to the category are clustered again until the category obtained by clustering is 1, and the point cloud after clustering screening processing corresponding to the panel A3 is obtained.

[0160] Based on the point cloud after clustering screening processing corresponding to the panel A3, the geometric center point of the panel A3 of the reference object OBA is calculated, and the horizontal distance value and the vertical distance value of each data point to the geometric center point of the panel A3 in the horizontal direction of the panel A3 and in the vertical direction of the panel A3 are calculated. According to the vertical distance value of each data point, the data points are divided in the horizontal direction to obtain a plurality of point cloud regions.

[0161] For the horizontal distance values of each data point in each point cloud region, the distance variance is calculated as the spatial information of each point cloud region. When the distance variance of the point cloud region is greater than the variance threshold, the data points in the point cloud region are retained to obtain the screened point cloud corresponding to the panel A3.

[0162] In this way, the data points related to the references OBA, OBB and OBC and the data points unrelated to the references OBA, OBB and OBC (such as noise points, discrete data points corresponding to support rods, etc.) can be distinguished, and it is ensured that the screened point cloud can accurately correspond to the panels of the references OBA, OBB and OBC.

[0163] C6) The reflectivity threshold is set according to the reflectivity of the first region (i.e., the second target region in this example). For the screened point cloud corresponding to each reference panel, the point data corresponding to the first region is screened according to the reflectivity threshold, and is used for clustering to obtain the point cloud corresponding to each first region of the corresponding reference. Then, based on the point cloud corresponding to each first region, the geometric center data point (i.e., the specified position point) of the corresponding first region and the corresponding flatness are calculated, and the geometric center data point with a flatness greater than the flatness threshold is taken as a matching point. The matching point is in the radar coordinate system ZB1.

[0164] Taking the reference OBA as an example, for the screened point cloud corresponding to the panel A3, the point data corresponding to the first regions a1-a4 is screened according to the reflectivity threshold, and is clustered to obtain the point cloud corresponding to the first region a1, the point cloud corresponding to the first region a2, the point cloud corresponding to the first region a3 and the point cloud corresponding to the first region a4.

[0165] Then, based on the point cloud corresponding to the first region a1, the geometric center data point of the first region a1 and the corresponding flatness are calculated, and similarly, the geometric center data point of the first region a2 and the corresponding flatness, the geometric center data point of the first region a3 and the corresponding flatness, and the geometric center data point of the first region a4 and the corresponding flatness are calculated. The geometric center data point with a flatness greater than the flatness threshold is taken as a matching point.

[0166] C7) Based on the current first conversion parameter and the pose information of the matching point in the radar coordinate system ZB1, the pose information of the matching point in the mapping coordinate system ZB2 is obtained.

[0167] C8) In the mapping point set, the mapping point corresponding to the geometric center point of the first region of the corresponding reference is obtained, the coordinate information of the mapping point corresponding to the geometric center point is matched with the coordinate information of the matching point in the mapping coordinate system ZB2, and the new first conversion parameter and the parameter evaluation information are obtained.

[0168] C9) judging whether the parameter evaluation information meets an iteration condition, and when it is judged that the parameter evaluation information meets the iteration condition, continuing to update the first conversion parameter and the parameter evaluation information until it is judged that the iteration condition is not met, and stopping, thereby obtaining a final first conversion parameter.

[0169] C10) determining a calibration parameter between the radar coordinate system and a vehicle coordinate system of the vehicle based on the first conversion parameter and the pose information of the vehicle in the mapping coordinate system.

[0170] Therefore, the calibration device M40 completes the calibration between the radar coordinate system ZB1 and the vehicle coordinate system ZB3, the calibration time can be about 1 minute, the calibration error can be within 1 cm, the calibration efficiency is high, and the calibration precision is high.

[0171] The present application also provides a computer readable storage medium having computer instructions stored thereon, wherein the computer instructions can execute the steps of the calibration method according to any one of the above embodiments of the present application when running, and the details can be referred to the above related content, and will not be repeated here

[0172] The computer readable storage medium can include any suitable type of memory unit, memory device, memory article, memory medium, storage device, storage article, storage medium and / or storage unit. For example, a memory, a removable or non-removable medium, an erasable or non-erasable medium, a writable or rewritable medium, a digital or analog medium, a hard disk, a floppy disk, a compact disk read-only memory (CD-ROM), a compact disk recordable (CD-R), a compact disk rewritable (CD-RW), an optical disk, a magnetic medium, a magneto-optical medium, a removable memory card or disk, various types of digital versatile disks (DVDs), a magnetic tape, a cassette magnetic tape, etc.

[0173] In addition, the computer instructions can include any suitable type of code implemented by using any suitable high-level, low-level, object-oriented, visualized, compiled and / or interpreted programming language, such as source code, compiled code, interpreted code, executable code, static code, dynamic code, encrypted code, etc.

[0174] It should be noted that the terms "one embodiment" or "an embodiment" as used herein mean that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one implementation of the application. The appearances of the phrase "in one embodiment" or "in an embodiment" in various places in the specification are not necessarily all referring to the same embodiment, nor are the various embodiments necessarily mutually exclusive, unless more restrictive language is used. As used herein, the term "or" is synonymous with "and / or" unless the context clearly dictates otherwise.

[0175] It should be noted that, in the description of the application, unless otherwise explicitly specified and limited, the terms in the application can be understood according to different application scenarios. For example, the verb "connect" can be understood as wired connection, wireless connection and the like. For those skilled in the art, the specific meaning of the above terms in the application can be understood according to the specific circumstances.

[0176] In addition, in the description of the application, unless otherwise explicitly specified and limited, "on" or "under" of the first feature to the second feature can include that the first and second features are in direct contact, or the first and second features are not in direct contact but are in contact through another feature between them. Moreover, "on" of the first feature to the second feature can include that the first feature is directly above and obliquely above the second feature, or only indicates that the height of the first feature is higher than that of the second feature. "Under" of the first feature to the second feature can include that the first feature is directly below and obliquely below the second feature, or only indicates that the height of the first feature is less than that of the second feature.

[0177] Although the embodiments of the application are disclosed as above, the application is not limited thereto. Any person skilled in the art, without departing from the spirit and scope of the application, can make various changes and modifications, therefore the protection scope of the application should be limited by the scope defined by the claims.

Claims

1. A calibration method characterized by, A method for obtaining a relative pose relationship between a laser radar and a vehicle; the method comprises: obtaining a point cloud obtained by the laser radar from a field of view, the point cloud being in a radar coordinate system; obtaining a surveying point set obtained by a surveying device from the field of view, the surveying point set being in a surveying coordinate system; determining first conversion parameters between the radar coordinate system and the surveying coordinate system based on the point cloud and the surveying point set; based on a target region, screening the point cloud to determine matching points; wherein the target region includes a first target region and a second target region, and the screening of the point cloud based on the target region to determine the matching points comprises: matching reflectivity information of the second target region with reflectivity information of each data point in the screened point cloud, and clustering data points matching the second target region to determine a plurality of specified position points and corresponding flatness; based on the flatness, screening the plurality of specified position points to obtain the matching points, wherein the screened point cloud is obtained by screening the point cloud based on the first target region; based on the first conversion parameters and pose information of the vehicle in the surveying coordinate system, determining calibration parameters between the radar coordinate system and a vehicle coordinate system of the vehicle, comprising: updating the first conversion parameters based on the current first conversion parameters, the surveying point set, and the matching points in the point cloud, and obtaining corresponding parameter evaluation information.

2. The calibration method of claim 1, wherein The pose information of the vehicle in the surveying coordinate system is obtained by converting the second conversion parameters between the surveying coordinate system and the vehicle coordinate system; or it is obtained by pre-setting.

3. The method of claim 1, wherein The updating of the first conversion parameters based on the current first conversion parameters, the surveying point set, and the matching points in the point cloud, and the obtaining of the corresponding parameter evaluation information, comprises: based on the current first conversion parameters and the pose information of the matching points in the radar coordinate system, obtaining the pose information of the matching points in the surveying coordinate system; based on the pose information of the matching points in the surveying coordinate system and the surveying point set, updating the first conversion parameters and obtaining the parameter evaluation information.

4. The method of claim 1, wherein The determination of the first conversion parameters between the radar coordinate system and the surveying coordinate system based on the point cloud and the surveying point set further comprises: when it is determined that the parameter evaluation information meets the iteration condition, continue to update the first conversion parameters and the parameter evaluation information until it is determined that the parameter evaluation information does not meet the iteration condition.

5. The method of claim 4, wherein When the number of updates of the first conversion parameters reaches a first threshold, and / or when the matching error between adjacent surveying points in the surveying point set based on the updated first conversion parameters converted to the surveying coordinate system is not greater than a second threshold, it is determined that the parameter evaluation information meets the iteration condition.

6. The method of claim 1, wherein The screened point cloud is obtained by screening the point cloud based on the first target region, comprising: based on the first target region, screening the point cloud to obtain a reference plane; based on the reference plane, continue to screen the point cloud to obtain the screened point cloud.

7. The method of claim 6, wherein The screening of the point cloud based on the first target region comprises: Matching the pose information of the first target region with the pose information of each data point in the point cloud to determine the reference plane.

8. The method of claim 6, wherein The screening of the point cloud based on the reference plane comprises: Determining the distance value of each data point in the point cloud to the reference plane; The screening of the point cloud based on the distance value comprises:

9. The method of claim 8, wherein Extracting data points with distance values meeting a distance range from the point cloud and clustering them; When the clustering result meets a loop condition, the clustering result is screened and clustering is continued until the clustering result does not meet the loop condition, and the screened point cloud is obtained. The screening of the point cloud based on the distance value comprises:

10. The method of claim 8, wherein Extracting data points with distance values meeting a distance range from the point cloud and dividing them into multiple point cloud regions according to a first direction; Determining the spatial information of the multiple point cloud regions in a second direction, the first direction intersecting the second direction; Screening the multiple point cloud regions based on the spatial information to obtain the screened point cloud. The calibration device is connected with the laser radar and the surveying and mapping device respectively and is used to obtain the relative pose relationship between the laser radar and the vehicle; the calibration device comprises:

11. A calibration apparatus characterized by comprising: A data acquisition unit is adapted to acquire a point cloud obtained by the laser radar from a field of view and a surveying and mapping point set obtained by the surveying and mapping device from the field of view, the point cloud being in a radar coordinate system, and the surveying and mapping point set being in a surveying and mapping coordinate system; A data processing unit is adapted to determine a first conversion parameter between the radar coordinate system and the surveying and mapping coordinate system according to the point cloud and the surveying and mapping point set, screen the point cloud based on a target region, determine matching points, and determine a calibration parameter between the radar coordinate system and a vehicle coordinate system of the vehicle based on the first conversion parameter and the pose information of the vehicle in the surveying and mapping coordinate system, comprising: updating the first conversion parameter based on the current first conversion parameter, the surveying and mapping point set, and the matching points in the point cloud, and obtaining corresponding parameter evaluation information; wherein the target region comprises a first target region and a second target region, the screening of the point cloud based on the target region to determine the matching points comprises: matching the reflectivity information of the second target region with the reflectivity information of each data point in the screened point cloud, clustering the data points matching the second target region, determining multiple specified position points and corresponding flatness, and screening the multiple specified position points based on the flatness to obtain the matching points, wherein the screened point cloud is obtained by screening the point cloud based on the first target region. ​ 12. A calibration apparatus comprising: A memory and a processor, the memory having computer instructions stored thereon that are executable on the processor, wherein the processor executes the computer instructions to perform the steps of the method of any one of claims 1 to 10.

13. A calibration system characterized by, Comprise: A mapping device and a calibration device; the calibration device is connected with the mapping device and the laser radar respectively, and is used for acquiring the relative pose relationship between the laser radar and the vehicle; wherein: The laser radar is adapted to acquire a point cloud corresponding to a field of view, and the point cloud is in a radar coordinate system; The mapping device is adapted to acquire a mapping point set corresponding to the field of view, and the mapping point set is in a mapping coordinate system; The calibration device is adapted to acquire the point cloud and the mapping point set; according to the point cloud and the mapping point set, determine the first conversion parameter between the radar coordinate system and the mapping coordinate system, and based on a target region, screen the point cloud to determine a matching point, and according to the first conversion parameter and the pose information of the vehicle in the mapping coordinate system, determine the calibration parameter between the radar coordinate system and a vehicle coordinate system of the vehicle, including: based on the current first conversion parameter, the mapping point set, and the matching point in the point cloud, updating the first conversion parameter and obtaining corresponding parameter evaluation information; wherein the target region includes a first target region and a second target region, and the screening of the point cloud based on the target region to determine the matching point includes: matching the reflectivity information of the second target region with the reflectivity information of each data point in the screened point cloud, and clustering the data points matched with the second target region to determine a plurality of specified position points and corresponding flatness; based on the flatness, screening the plurality of specified position points to obtain the matching point, wherein the screened point cloud is screened based on the first target region.

14. The calibration system of claim 13, wherein, The field of view contains a reference object, and the surface of the reference object includes a first region and a second region, and the reflectivity of the first region is different from that of the second region.

15. A readable storage medium, having stored thereon computer instructions, characterized in that, The computer instructions execute the steps of the method of any one of claims 1 to 10. The computer instructions execute the steps of the method of any one of claims 1 to 10.

Images