A laser radar calibration method and device

Abstract

An embodiment of the present invention provides a laser radar calibration method and device, relating to the field of data processing technology. The method includes: obtaining a laser point cloud collected by a laser radar installed on a moving object; determining perception data based on the laser point cloud, the perception data including a first coordinate of a first calibration point in the laser radar coordinate system, and a second coordinate of a second calibration point in the laser radar coordinate system, wherein the second calibration point and the first calibration point are located on the same target coordinate axis of the object coordinate system; determining the conversion relationship between the object coordinate system and the laser radar coordinate system based on the perception data and the distance between the target calibration point and the origin of the object coordinate system, and completing the laser radar calibration, wherein the target calibration points are: the first calibration point and / or the second calibration point. The application of the embodiment of the present invention can complete the laser radar calibration process.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a laser radar calibration method and device. Background Art

[0002] LiDARs installed on vehicles, robots, and other moving objects can collect laser point clouds. Each laser point in the laser point cloud corresponds to information about an object in the environment. The collected position information of the laser point is the first position information of the corresponding point in the environment relative to the LiDAR. This first position information can be expressed as coordinates in the LiDAR coordinate system relative to the LiDAR. This first position information allows for environmental perception, including determining the location of objects in the environment, and thus controlling the safe driving of the moving object.

[0003] However, the position of the object obtained based on the first position information is the position of the object relative to the laser radar. When controlling the movement of the moving object, it is necessary to use the second position information of the point in the environment relative to the moving object to accurately obtain the position of the object in the environment relative to the moving object, and then accurately control the movement of the moving object. The second position information can be expressed as coordinates in the object coordinate system relative to the moving object.

[0004] Therefore, when controlling the movement of a moving object, it is necessary to convert the coordinates of the points in the environment collected by the lidar in the lidar coordinate system into the coordinates of the object coordinate system. Before this, it is necessary to determine the conversion relationship between the lidar coordinate system and the object coordinate system, that is, the lidar needs to be calibrated. Summary of the Invention

[0005] The purpose of the embodiments of the present invention is to provide a laser radar calibration method and apparatus to complete the laser radar calibration process. The specific technical solution is as follows:

[0006] In a first aspect, an embodiment of the present invention provides a laser radar calibration method, the method comprising:

[0007] Obtaining a laser point cloud collected by a laser radar installed on a moving object;

[0008] Determining perception data based on the laser point cloud, the perception data comprising a first coordinate of a first calibration point in a laser radar coordinate system, and a second coordinate of a second calibration point in the laser radar coordinate system, wherein the second calibration point and the first calibration point are located on the same target coordinate axis of the object coordinate system;

[0009] Based on the perception data and the distance between the target calibration point and the origin of the object coordinate system, the conversion relationship between the object coordinate system and the lidar coordinate system is determined to complete the lidar calibration, wherein the target calibration point is: the first calibration point and / or the second calibration point.

[0010] In one embodiment of the present invention, the second calibration point and the first calibration point are located on the same target coordinate axis of the object coordinate system, including:

[0011] The first calibration point and the second calibration point are located on a calibration object, the calibration object and the driving object are placed on the same plane, the origin of the object coordinate axis and the target coordinate axis both coincide with the plane, and the first calibration point and the second calibration point intersect with the plane at the target coordinate axis.

[0012] In one embodiment of the present invention, the calibration object includes a first calibration object and a second calibration object, the first calibration point and the second calibration point are located on the first calibration object and the second calibration object respectively, the volume of the first calibration object is smaller than that of the second calibration object, so that the area projected by the second calibration object in the direction of the moving object is larger than the area projected by the first calibration object in the direction of the moving object, and the distance between the first calibration object and the moving object is smaller than the distance between the second calibration object and the moving object.

[0013] In one embodiment of the present invention, the first calibration point coincides with the second calibration point and both are located on a third calibration object;

[0014] The step of obtaining a laser point cloud collected by a laser radar installed on a moving object includes:

[0015] Acquire a first laser point cloud collected by a laser radar installed on the moving object when the moving object is at an initial position, and acquire a second laser point cloud collected by the laser radar after the moving object travels a preset distance along the target coordinate axis toward the third calibration object;

[0016] The determining of the perception data based on the laser point cloud includes:

[0017] Determining a first coordinate of a first calibration point in a laser radar coordinate system based on the first laser point cloud, and determining a second coordinate of a second calibration point in the laser radar coordinate system based on the second laser point cloud, and obtaining perception data including the first coordinate and the second coordinate;

[0018] The step of determining a conversion relationship between the object coordinate system and the lidar coordinate system based on the perception data and the distance between the target calibration point and the origin of the object coordinate system to complete lidar calibration includes:

[0019] Determining a conversion relationship between the object coordinate system and the lidar coordinate system based on the perception data and the first distance to complete lidar calibration, wherein the first distance is the distance between the first calibration point and the origin of the object coordinate system when the moving object is at the initial position;

[0020] and / or,

[0021] Based on the perception data and the second distance, the conversion relationship between the object coordinate system and the lidar coordinate system is determined to complete the lidar calibration, wherein the second distance is: the distance between the second calibration point and the origin of the object coordinate system after the moving object travels a preset distance along the target coordinate axis.

[0022] In one embodiment of the present invention, the perception data further includes a plane model of the plane, and determining the perception data based on the laser point cloud includes:

[0023] Extracting surface laser points corresponding to points on target surfaces of the calibration object from the laser point cloud, wherein the target surfaces are connected to each other and do not coincide with the target coordinate axis, and the first calibration point and the second calibration point are located at the connection between the target surface and the plane;

[0024] Fitting a surface model of each target surface based on the surface laser points;

[0025] Extracting a planar laser point corresponding to a point on the plane where the calibration object is located in the laser point cloud;

[0026] Fitting a planar model of the plane based on the planar laser points;

[0027] Determine the coordinates of the intersection of the surface model and the plane model in the laser radar coordinate system, and determine the first coordinates of the first calibration point and the second coordinates of the second calibration point based on the coordinates of the intersection.

[0028] In one embodiment of the present invention, determining the coordinates of the intersection of the surface model and the plane model in the laser radar coordinate system includes:

[0029] determining intersection lines between surface models of respective target surfaces;

[0030] The coordinates of the intersection point of the intersection line and the plane model in the laser radar coordinate system are determined as the coordinates of the intersection point of the surface model and the plane model in the laser radar coordinate system.

[0031] In one embodiment of the present invention, each target surface is perpendicular to the plane where the calibration object is located.

[0032] In a second aspect, an embodiment of the present invention provides a laser radar calibration device, the device comprising:

[0033] A point cloud acquisition module is used to acquire laser point clouds collected by a laser radar installed on a moving object;

[0034] a coordinate determination module, configured to determine perception data based on the laser point cloud, the perception data comprising a first coordinate of a first calibration point in a laser radar coordinate system, and a second coordinate of a second calibration point in the laser radar coordinate system, wherein the second calibration point and the first calibration point are located on the same target coordinate axis of the object coordinate system;

[0035] A radar calibration module is used to determine the conversion relationship between the object coordinate system and the lidar coordinate system based on the perception data and the distance between the target calibration point and the origin of the object coordinate system to complete the lidar calibration, wherein the target calibration point is: the first calibration point and / or the second calibration point.

[0036] In a third aspect, an embodiment of the present invention provides an electronic device, including a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other via the communication bus;

[0037] Memory for storing computer programs;

[0038] The processor is configured to implement any of the method steps described in the first aspect when executing a program stored in the memory.

[0039] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, any method step described in the first aspect is implemented.

[0040] In a fifth aspect, an embodiment of the present invention further provides a computer program product comprising instructions, which, when executed on a computer, enables the computer to execute any one of the method steps described in the first aspect.

[0041] Beneficial effects of the embodiments of the present invention:

[0042] An embodiment of the present invention provides a lidar calibration method. After obtaining a laser point cloud collected by a lidar installed on a moving object, perception data is determined based on the laser point cloud. The perception data includes a first coordinate of a first calibration point in a lidar coordinate system and a second coordinate of a second calibration point in the lidar coordinate system. The first calibration point and the second calibration point are located on the same target coordinate axis of the object coordinate system. Based on the perception data and the distances between the target calibration points among the first calibration point and the second calibration point and the origin of the object coordinate system, a conversion relationship between the object coordinate system and the lidar coordinate system is determined to complete the lidar calibration.

[0043] As can be seen from the above, the embodiment of the present invention can determine the perception data including the first coordinate and the second coordinate by extracting the laser point cloud collected by the laser radar. Moreover, since the first calibration point and the second calibration point are both located on a target coordinate axis of the object coordinate system, the values ​​of the two coordinate items of the first calibration point and the second calibration point in the object coordinate system are all 0 except for the coordinate item corresponding to the target coordinate axis. By measuring the distance between the target calibration point and the origin of the object coordinate system, the complete coordinates of the target calibration point in the object coordinate system can be determined. By comparing the coordinates of the target calibration point in the object coordinate system and the perception data, the conversion relationship between the object coordinate system and the laser radar coordinate system can be determined to complete the laser radar calibration.

[0044] Furthermore, obtaining the accurate coordinates of the calibration points in the object's coordinate system is a prerequisite for ensuring LiDAR calibration accuracy. In existing technologies, to determine the accurate coordinates of the calibration points, it is necessary to measure the values ​​of each coordinate item of multiple calibration points separately. Any inaccurate result from any measurement will affect the accuracy of the LiDAR calibration results. However, this solution only requires measuring the distance between the target calibration point and the origin of the object's coordinate system—that is, measuring the value of a single coordinate item of the target calibration point—to complete the LiDAR calibration process. Therefore, the LiDAR calibration results obtained through this solution are more accurate. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0046] Figure 1 A schematic diagram of a flow chart of a first laser radar calibration method provided in an embodiment of the present invention;

[0047] Figure 2 A schematic diagram of an object coordinate system provided by an embodiment of the present invention;

[0048] Figure 3 A schematic diagram of the relationship between a calibration object and a driving object provided in an embodiment of the present invention;

[0049] Figure 4 A schematic diagram of a flow chart of a second lidar calibration method provided in an embodiment of the present invention;

[0050] Figure 5 A schematic diagram of a flow chart of a third laser radar calibration method provided in an embodiment of the present invention;

[0051] Figure 6 A schematic structural diagram of a first laser radar calibration device provided in an embodiment of the present invention;

[0052] Figure 7 A schematic structural diagram of a second laser radar calibration device provided in an embodiment of the present invention;

[0053] Figure 8 A schematic structural diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0054] The following will be combined with the accompanying drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field based on this application are within the scope of protection of the present invention.

[0055] In order to determine the positional relationship between objects in the environment and the moving object based on the laser point cloud collected by a laser radar installed on the moving object, it is necessary to determine the conversion relationship between the laser radar coordinate system and the object coordinate system. In other words, the laser radar needs to be calibrated. To this end, embodiments of the present invention provide a laser radar calibration method and apparatus.

[0056] An embodiment of the present invention provides a laser radar calibration method, the method comprising:

[0057] Obtaining a laser point cloud collected by a laser radar installed on a moving object;

[0058] Determining perception data based on the laser point cloud, the perception data including a first coordinate of a first calibration point in a laser radar coordinate system, and a second coordinate of a second calibration point in the laser radar coordinate system, wherein the second calibration point and the first calibration point are located on the same target coordinate axis of the object coordinate system;

[0059] Based on the perception data and the distance between the target calibration point and the origin of the object coordinate system, the conversion relationship between the object coordinate system and the lidar coordinate system is determined to complete the lidar calibration, where the target calibration point is: the first calibration point and / or the second calibration point.

[0060] As can be seen from the above, the embodiment of the present invention can determine the perception data including the first coordinate and the second coordinate by extracting the laser point cloud collected by the laser radar. Moreover, since the first calibration point and the second calibration point are both located on a target coordinate axis of the object coordinate system, the values ​​of the two coordinate items of the first calibration point and the second calibration point in the object coordinate system are all 0 except for the coordinate item corresponding to the target coordinate axis. By measuring the distance between the target calibration point and the origin of the object coordinate system, the complete coordinates of the target calibration point in the object coordinate system can be determined. By comparing the coordinates of the target calibration point in the object coordinate system and the perception data, the conversion relationship between the object coordinate system and the laser radar coordinate system can be determined to complete the laser radar calibration.

[0061] Furthermore, obtaining the accurate coordinates of the calibration points in the object's coordinate system is a prerequisite for ensuring LiDAR calibration accuracy. In existing technologies, to determine the accurate coordinates of the calibration points, it is necessary to measure the values ​​of each coordinate item of multiple calibration points separately. Any inaccurate result from any measurement will affect the accuracy of the LiDAR calibration results. However, this solution only requires measuring the distance between the target calibration point and the origin of the object's coordinate system—that is, measuring the value of a single coordinate item of the target calibration point—to complete the LiDAR calibration process. Therefore, the LiDAR calibration results obtained through this solution are more accurate.

[0062] See also Figure 1 , which is a flow chart of the first laser radar calibration method provided in an embodiment of the present invention, the method includes the following steps S101-S103.

[0063] The execution entity of the embodiment of the present invention can be any device with data processing capabilities that is communicatively connected to the laser radar installed on the moving object. For example, the execution entity can be a data processing device installed on the moving object. For example, when the moving object is a vehicle, the data processing device can be an on-board computer, etc. The execution entity can also be a server located in the cloud, etc.

[0064] S101: Obtaining a laser point cloud collected by a laser radar installed on a moving object.

[0065] The moving object may be a vehicle, a robot, etc. The laser radar can be installed at any position of the moving object as required. For example, when the moving object is a vehicle, the laser radar can be installed on the top, front, or side of the vehicle.

[0066] After collecting the laser point cloud, the laser radar can send the laser point cloud to the execution subject of the present invention, so that the execution subject of the present invention obtains the laser point cloud.

[0067] Specifically, in order to ensure the accuracy of the laser point cloud collected by the laser radar, it is necessary to ensure that the moving object and the laser radar remain stable when the laser radar collects the laser point cloud. For example, when the moving object is a vehicle, it is necessary to avoid opening and closing the vehicle doors and shaking the vehicle and on-board sensors when the laser radar collects the laser point cloud.

[0068] S102: Determine perception data based on the laser point cloud.

[0069] The perception data includes a first coordinate of a first calibration point in a lidar coordinate system and a second coordinate of a second calibration point in the lidar coordinate system. The second calibration point and the first calibration point are located on the same target coordinate axis of the object coordinate system, and the origin of the lidar coordinate system is located on the lidar.

[0070] Specifically, both the LiDAR coordinate system and the object coordinate system are three-dimensional coordinate systems, and the specific positions of the origins and the coordinate axis directions of the LiDAR coordinate system and the object coordinate system are pre-set. For example, the origin of the object coordinate system can be located on the plane where the moving object is located, with the X-axis pointing directly in front of the moving object along the plane, the Y-axis also located on the plane and perpendicular to the X-axis, and the Z-axis perpendicular to the plane according to the right-hand rule. The origin of the LiDAR coordinate system can be located at any position on the LiDAR, with the X-axis pointing forward along the direction of the LiDAR laser point cloud acquisition, and the Y-axis and Z-axis are respectively perpendicular to the X-axis and their directions follow the right-hand rule.

[0071] See also Figure 2 , is a schematic diagram of an object coordinate system provided by an embodiment of the present invention.

[0072] The moving object is a vehicle, and the origin of the object coordinate system is located on a plane below the vehicle at the midpoint of the vehicle's rear axle. The X-axis points along the plane to the front of the vehicle, the Y-axis also lies on the plane and is perpendicular to the X-axis, pointing to the left side of the vehicle. The Z-axis is perpendicular to the plane and points upward.

[0073] In addition, the first calibration point and the second calibration point may be located on any coordinate axis in the object coordinate system. For example, the first calibration point and the second calibration point may be located on the X axis of the object coordinate system.

[0074] In one embodiment of the present invention, the executing entity of this embodiment can fit a three-dimensional model of the environment in which the driving object is located based on the laser point cloud, and then manually select, or use an algorithm in the prior art to determine the positions of the first calibration point and the second calibration point from the three-dimensional model, thereby obtaining the first coordinates of the first calibration point and the second coordinates of the second calibration point.

[0075] Among them, the three-dimensional model of the environment in which the driving object is located can be fitted based on the laser point cloud using the method in the existing technology, which is not limited in this embodiment.

[0076] S103: Based on the perception data and the distance between the target calibration point and the origin of the object coordinate system, determine the conversion relationship between the object coordinate system and the lidar coordinate system to complete the lidar calibration.

[0077] The target calibration point is: the first calibration point and / or the second calibration point. The distance between the target calibration point and the origin of the object coordinate system can be measured in advance.

[0078] Specifically, since the first calibration point and the second calibration point are both located on a target coordinate axis of the object coordinate system, except for the target coordinate item corresponding to the target coordinate axis, the values ​​of the other two coordinate items in the coordinates of the first calibration point and the second calibration point in the object coordinate system are both 0. After measuring the distance between the target calibration point and the origin of the object coordinate system, the value of the target coordinate item can be determined, thereby obtaining the complete coordinates of the target calibration point in the object coordinate system. If the target calibration point is the first calibration point and the second calibration point, then through this embodiment, the coordinates of the first calibration point and the coordinates of the second calibration point can be obtained, totaling six coordinate items. If the target calibration point is one of the first calibration point or the second calibration point, then through this embodiment, five of the six coordinate items totaling the coordinates of the first calibration point and the coordinates of the second calibration point can be obtained.

[0079] The transformation relationship can be expressed in the form of a coordinate transformation matrix, which includes a translation matrix and a rotation matrix. The elements contained in the translation matrix represent the translation distance between the object coordinate system and the lidar coordinate system, respectively, along the X, Y, and Z axes. The elements contained in the rotation matrix represent the rotation angles between the object coordinate system and the lidar coordinate system, respectively, along the X, Y, and Z axes. In total, six parameters need to be solved.

[0080] A feasible implementation method is that the perception data of the laser radar includes fitting plane (ground) data. The fitting plane (ground) can be generated based on manually selected ground points or automatically identified fitting ground points. Specifically, the algorithm in the prior art can be used to calculate the conversion relationship between the object coordinate system plane and the laser radar coordinate system plane, and then obtain the pitch angle (angle of rotation around the X axis), roll angle (angle of rotation around the Y axis) and vertical height (translation distance along the Z axis), which will not be repeated here. Based on the fitting plane (ground), the conversion relationship between the object coordinate system plane and the laser radar coordinate system plane has been obtained, and the following can be regarded as a plane coordinate system conversion.

[0081] Furthermore, based on the five or six coordinate items of the acquired target calibration point in the object coordinate system and the first and second coordinates in the lidar coordinate system, plane coordinate conversion or two-dimensional vector alignment can be performed. Using the three coordinate items in the object coordinate system and the first and second coordinates in the lidar coordinate system, the coordinate system rotation angle, i.e., the heading angle (angle of rotation around the Z axis) and the offset along the X and Y axes can be obtained. That is, assuming that the coordinates of the first and second calibration points in the object coordinate system are (x1, y1, z1) and (x2, y2, z2) respectively, the heading angle (angle of rotation around the Z axis) and the offset along the X and Y axes can be solved by y1, y2, x1 and the first and second coordinates, or by y1, y2, x2 and the first and second coordinates. Specifically, the conversion relationship between the object coordinate system and the lidar coordinate system can be calculated using algorithms in the prior art, which will not be described in detail here.

[0082] As can be seen from the above, the embodiment of the present invention can determine the perception data including the first coordinate and the second coordinate by extracting the laser point cloud collected by the laser radar. Moreover, since the first calibration point and the second calibration point are both located on a target coordinate axis of the object coordinate system, the values ​​of the two coordinate items of the first calibration point and the second calibration point in the object coordinate system are all 0 except for the coordinate item corresponding to the target coordinate axis. By measuring the distance between the target calibration point and the origin of the object coordinate system, the complete coordinates of the target calibration point in the object coordinate system can be determined. By comparing the coordinates of the target calibration point in the object coordinate system and the perception data, the conversion relationship between the object coordinate system and the laser radar coordinate system can be determined to complete the laser radar calibration.

[0083] Furthermore, obtaining the accurate coordinates of the calibration points in the object's coordinate system is a prerequisite for ensuring LiDAR calibration accuracy. In existing technologies, to determine the accurate coordinates of the calibration points, it is necessary to measure the values ​​of each coordinate item of multiple calibration points separately. Any inaccurate result from any measurement will affect the accuracy of the LiDAR calibration results. However, this solution only requires measuring the distance between the target calibration point and the origin of the object's coordinate system—that is, measuring the value of a single coordinate item of the target calibration point—to complete the LiDAR calibration process. Therefore, the LiDAR calibration results obtained through this solution are more accurate.

[0084] In one embodiment of the present invention, the first calibration point and the second calibration point are located on the calibration object, the calibration object and the driving object are placed on the same plane, the origin of the object coordinate axis and the target coordinate axis coincide with the plane, and the first calibration point and the second calibration point intersect the plane at the target coordinate axis, thereby ensuring that the first calibration point and the second calibration point are located on the target coordinate axis.

[0085] In addition, the embodiment of the present invention does not limit the shape of the calibration object. However, in order to facilitate the identification of the laser point corresponding to the calibration object, and thereby determine the first coordinate of the first calibration point and the second coordinate of the second calibration point based on the identified laser point in the subsequent process, the shape of the calibration object can be a relatively regular shape, such as a cube, a cuboid, a pyramid, etc., and the first calibration point and the second calibration point can be vertices of the calibration object that are easier to identify.

[0086] Specifically, the laser points located on the calibration object can be identified from the laser point cloud, a three-dimensional model of the calibration object can be fitted based on the identified laser points, and then the positions of the first calibration point and the second calibration point can be identified from the three-dimensional model to obtain the first coordinate and the second coordinate.

[0087] In one embodiment of the present invention, the following Figure 5 Steps S102B-S102F shown determine the first coordinate and the second coordinate, which will not be repeated here.

[0088] In another embodiment of the present invention, the calibration object includes two calibration objects, a first calibration object and a second calibration object, the first calibration point and the second calibration point are located on the first calibration object and the second calibration object respectively, the volume of the first calibration object is smaller than that of the second calibration object, so that the area projected by the second calibration object in the direction of the traveling object is larger than the area projected by the first calibration object in the direction of the traveling object, and the distance between the first calibration object and the traveling object is smaller than the distance between the second calibration object and the traveling object.

[0089] Among them, since the first calibration point and the second calibration point are respectively located on two different calibration objects, the distances between the first calibration point and the second calibration point and the traveling object are different. If only one of the first calibration point and the second calibration point is selected as the target calibration point, the first calibration point that is closer to the origin of the object coordinate system can be selected as the target calibration point. Since the distance between the target calibration point and the traveling object is closer, the distance between the target calibration point and the origin of the object coordinate system is often also closer. Compared with measuring the distance between another calibration point and the origin of the object coordinate system, measuring the distance between the target calibration point with a closer distance and the origin of the object coordinate system is more convenient, and the measurement result is also more accurate.

[0090] Specifically, the second calibration object, which is farther away from the moving object, has a larger volume. For the laser radar installed on the moving object, the projection area of ​​the second calibration object is larger, making it easier for the laser radar to accurately obtain the laser point corresponding to the second calibration object at a farther distance.

[0091] See also Figure 3 , which is a schematic diagram of the relationship between a calibration object and a driving object provided in an embodiment of the present invention.

[0092] With the aforementioned Figure 2 Correspondingly, Figure 3 The application scenario shown contains two calibration objects. Figure 3 The first and second calibration objects shown can each consist of two calibration plates. The edges of the two calibration plates of the first calibration object are connected at a first fixed angle, while the edges of the two calibration plates of the second calibration object are connected at a second fixed angle. The first fixed angle and the second fixed angle can be the same or different. The first calibration point is located at the end where the connected edge of the two calibration plates connects to the plane where the first calibration object is located, and the second calibration point is located at the end where the connected edge of the two calibration plates connects to the plane where the second calibration object is located. The first fixed angle and the second fixed angle can be the same or different. Figure 3 Shown is a top view of a first calibration object and a second calibration object.

[0093] In another embodiment of the present invention, the first calibration point coincides with the second calibration point and both are located on the third calibration object. Figure 4 , is a flow chart of the second laser radar calibration method provided by an embodiment of the present invention, which is similar to the aforementioned Figure 1 Compared with the embodiment shown, step S101 can be implemented by the following step S101A, step S102 can be implemented by the following step S102A, and step S103 can be implemented by the following steps S103A and / or S103B.

[0094] S101A: Obtain a first laser point cloud collected by a laser radar installed on a moving object when the moving object is at an initial position, and obtain a second laser point cloud collected by the laser radar after the moving object travels a preset distance along a target coordinate axis toward a third calibration object.

[0095] Specifically, since the traveling object travels along the target coordinate axis, it can be ensured that the first calibration point and the second calibration point on the third calibration object can always be located on the target coordinate axis.

[0096] S102A: Based on the first laser point cloud, determine the first coordinate of the first calibration point in the laser radar coordinate system, and based on the second laser point cloud, determine the second coordinate of the second calibration point in the laser radar coordinate system, and obtain perception data including the first coordinate and the second coordinate.

[0097] Specifically, the moving object shifts during the process of determining the first and second coordinates, which is equivalent to a change in the relative position between the third calibration object and the moving object. Although the first and second calibration points essentially coincide, based on the origin of the LiDAR coordinate system, the distance between the first calibration point and the origin is greater, while the distance between the second calibration point and the origin is smaller, resulting in them being determined as two different points in the LiDAR coordinate system.

[0098] In one embodiment of the present invention, laser points corresponding to the third calibration object can be identified from the first laser point cloud, a model of the third calibration object can be fitted based on the identified laser points, and then the position of the first calibration point can be determined from the fitted model, thereby determining the first coordinates of the first calibration point.

[0099] In another embodiment of the present invention, similar to the method of determining the first coordinates, laser points corresponding to the third calibration object can be identified from the second laser point cloud, a model of the third calibration object can be fitted based on the identified laser points, and then the position of the second calibration point can be determined from the fitted model, thereby determining the second coordinates of the second calibration point.

[0100] S103A: Based on the perception data and the first distance, determine the conversion relationship between the object coordinate system and the lidar coordinate system to complete the lidar calibration.

[0101] The first distance is the distance between the first calibration point and the origin of the object coordinate system when the moving object is at the initial position.

[0102] Specifically, the value of the coordinate item of the first calibration point corresponding to the target coordinate axis in the object coordinate system can be determined based on the first distance. Since the first calibration point is located on the target coordinate axis, the values ​​of the other two coordinate items of the first calibration point in the object coordinate system, except for the coordinate item corresponding to the target coordinate axis, are 0. Therefore, the complete coordinates of the first calibration point in the object coordinate system can be determined based on the first distance. Since the second calibration point is also located on the target coordinate axis, the values ​​of the two coordinate items of the second calibration point in the object coordinate system, except for the coordinate item corresponding to the target coordinate axis, are also 0.

[0103] By combining the first and second coordinates contained in the perception data, as well as the complete coordinates of the first calibration point in the object coordinate system and the coordinate items of the second calibration point with a value of 0 in the object coordinate system, the conversion relationship between the object coordinate system and the lidar coordinate system can be determined. The specific process can be seen in step S103 above, and will not be repeated in this embodiment.

[0104] S103B: Based on the perception data and the second distance, determine the conversion relationship between the object coordinate system and the lidar coordinate system to complete the lidar calibration.

[0105] The second distance is the distance between the second calibration point and the origin of the object coordinate system after the moving object travels a preset distance along the target coordinate axis.

[0106] Specifically, the value of the coordinate item of the second calibration point corresponding to the target coordinate axis in the object coordinate system can be determined based on the second distance. Since the second calibration point is located on the target coordinate axis, the values ​​of the other two coordinate items of the second calibration point in the object coordinate system, except for the coordinate item corresponding to the target coordinate axis, are 0. Therefore, the complete coordinates of the second calibration point in the object coordinate system can be determined based on the second distance. Since the first calibration point is also located on the target coordinate axis, the values ​​of the two coordinate items of the first calibration point in the object coordinate system, except for the coordinate item corresponding to the target coordinate axis, are also 0.

[0107] By combining the first and second coordinates contained in the perception data, the complete coordinates of the second calibration point in the object coordinate system, and the two coordinate items of the first calibration point with a value of 0 in the object coordinate system, the conversion relationship between the object coordinate system and the lidar coordinate system can be determined. The specific process can be seen in step S103 above, and this embodiment will not be repeated here.

[0108] As can be seen from the above, this embodiment only requires one third calibration object, and the same point on the third calibration object is used as the first calibration point and the second calibration point to complete the laser radar calibration process. The number of calibration objects required is small, and the laser radar calibration process is relatively simple.

[0109] See also Figure 5 , is a flow chart of the third laser radar calibration method provided by an embodiment of the present invention, which is similar to the aforementioned Figure 1 Compared to the embodiment shown, the perception data further includes a plane model of the plane, and step S102 can be implemented by following the steps S102B-S102F.

[0110] S102B: Extracting surface laser points in the laser point cloud corresponding to points on each target surface of the calibration object.

[0111] The target surfaces are connected to each other and do not coincide with the target coordinate axis. The first calibration point and the second calibration point are located at the connection between the target surface and the plane where the calibration object is located.

[0112] For example, the calibration object is composed of two calibration plates, the edges of the two calibration plates are connected and there is a fixed angle, the surface of the two calibration plates facing the driving object is the target surface, the first calibration point and the second calibration point are located at one end of the connecting edge of the two calibration plates connected to the plane where the calibration object is located, and the angle of the fixed angle is less than 180 degrees and greater than 0 degrees.

[0113] In one embodiment of the present invention, each target surface is perpendicular to the plane where the calibration object is located.

[0114] Since the target surface is perpendicular to the plane of the calibration object, the projection area of ​​the target surface toward the laser radar is larger, and the number of laser points corresponding to the target surface collected by the laser radar is larger, so that the model of the target surface on the fitted three-dimensional model of the calibration object is more accurate, and the positions of the first calibration point and the second calibration point identified from the three-dimensional model are more accurate, and the first coordinate and the second coordinate obtained are more accurate.

[0115] Specifically, the user may manually select surface laser points from the laser point cloud, or may identify surface laser points using algorithms in the prior art.

[0116] If the calibration object includes a first calibration object and a second calibration object, the surface laser points corresponding to the target surface connected to the first calibration point on the first calibration object and the surface laser points corresponding to the target surface connected to the second calibration point on the second calibration object can be extracted from the laser point cloud respectively.

[0117] If the calibration object is the third calibration object, the laser point cloud is divided into a first laser point cloud and a second laser point cloud. The surface laser points corresponding to the target surface connected to the first calibration point can be extracted from the first laser point cloud, and the surface laser points corresponding to the target surface connected to the second calibration point can be extracted from the second laser point cloud.

[0118] S102C: Fitting surface models of each target surface based on surface laser points.

[0119] Specifically, a surface model of the target surface connected to the first calibration point and a surface model of the target surface connected to the second calibration point may be fitted respectively.

[0120] The surface model may be obtained by fitting based on any fitting algorithm in the prior art, and this embodiment does not limit this.

[0121] S102D: Extract the planar laser points corresponding to the points on the plane where the calibration object is located in the laser point cloud.

[0122] Specifically, the user may manually select a planar laser point from the laser point cloud, or may identify the planar laser point using an algorithm in the prior art.

[0123] S102E: Fitting a planar model of a plane based on planar laser points.

[0124] The plane model obtained by fitting and the first coordinate and the second coordinate obtained in step S102F together constitute the perception data.

[0125] S102F: Determine the coordinates of the intersection of the surface model and the plane model in the laser radar coordinate system, and determine the first coordinates of the first calibration point and the second coordinates of the second calibration point based on the coordinates of the intersection.

[0126] Specifically, since the first calibration point is connected to the target surface and is located on a plane, the intersection of the surface model of the target surface connected to the first calibration point and the plane model is the first calibration point.

[0127] Since the second calibration point is also connected to the target surface and located on the plane, the intersection of the surface model of the target surface connected to the second calibration point and the plane model is the second calibration point.

[0128] There are multiple intersection points between the surface model and the plane model, which are first calibration points and second calibration points. The coordinates of the intersection points are first coordinates of the first calibration point and second coordinates of the second calibration point.

[0129] In one embodiment of the present invention, step S102F may be implemented based on the following steps A-B.

[0130] Step A: Determine the intersection lines between the surface models of the respective target surfaces.

[0131] Specifically, the intersection line between the surface models of the target surface connected to the first calibration point is connected to the first calibration point, and the intersection line between the surface models of the target surface connected to the second calibration point is connected to the second calibration point.

[0132] Step B: Determine the coordinates of the intersection point of the intersection line and the plane model in the lidar coordinate system, and use them as the coordinates of the intersection point of the surface model and the plane model in the lidar coordinate system.

[0133] As can be seen from the above, in this embodiment, the surface laser points corresponding to the target surface connected to the calibration points are first identified, and then a surface model of the target surface is fitted based on the surface laser points, and a plane model of the plane where the calibration object is located is fitted. Since the calibration point is both connected to the target surface and is the intersection of the calibration object and the plane, the intersection between the fitted plane model and the surface model is the calibration point. The calibration point includes a first calibration point and a second calibration point. Through this embodiment, perception data including the first coordinate, the second coordinate, and the plane model can be obtained based on the laser point cloud.

[0134] In addition, in this embodiment, when determining the first coordinate and the second coordinate, it is necessary to first fit the surface model of each target surface and the plane model of the plane where the calibration object is located, and then determine the coordinates of the intersection of the surface model and the plane model as the first coordinate of the first calibration point and the second coordinate of the second calibration point. It can be seen that the accuracy of the determined first coordinate and the second coordinate is related to the accuracy of the fitted plane model and multiple surface models. Theoretically, the more surface models that need to be fitted in this solution, the higher the possibility of inaccurate surface models, and the higher the probability of inaccurate first coordinates and second coordinates. For this reason, the shape of the calibration object selected in this embodiment can be Figure 3 For the calibration object shown in FIG1 , there are only two target surfaces on the calibration object. In other words, only two surface models need to be fitted to determine the first and second coordinates, thereby improving the accuracy of the first and second coordinates. Furthermore, since only two surface models need to be fitted during this process, the computational complexity required in this embodiment is also low.

[0135] Corresponding to the aforementioned laser radar calibration method, an embodiment of the present invention also provides a laser radar calibration device.

[0136] See also Figure 6 , provides a structural diagram of a first laser radar calibration device according to an embodiment of the present invention, the device comprising:

[0137] The point cloud acquisition module 601 is used to acquire the laser point cloud collected by the laser radar installed on the moving object;

[0138] a coordinate determination module 602 for determining perception data based on the laser point cloud, the perception data comprising a first coordinate of a first calibration point in a laser radar coordinate system, and a second coordinate of a second calibration point in the laser radar coordinate system, wherein the second calibration point and the first calibration point are located on the same target coordinate axis of the object coordinate system;

[0139] The radar calibration module 603 is used to determine the conversion relationship between the object coordinate system and the lidar coordinate system based on the perception data and the distance between the target calibration point and the origin of the object coordinate system to complete the lidar calibration, wherein the target calibration point is: the first calibration point and / or the second calibration point.

[0140] As can be seen from the above, the embodiment of the present invention can determine the perception data including the first coordinate and the second coordinate by extracting the laser point cloud collected by the laser radar. Moreover, since the first calibration point and the second calibration point are both located on a target coordinate axis of the object coordinate system, the values ​​of the two coordinate items of the first calibration point and the second calibration point in the object coordinate system are all 0 except for the coordinate item corresponding to the target coordinate axis. By measuring the distance between the target calibration point and the origin of the object coordinate system, the complete coordinates of the target calibration point in the object coordinate system can be determined. By comparing the coordinates of the target calibration point in the object coordinate system and the perception data, the conversion relationship between the object coordinate system and the laser radar coordinate system can be determined to complete the laser radar calibration.

[0141] Furthermore, obtaining the accurate coordinates of the calibration points in the object's coordinate system is a prerequisite for ensuring LiDAR calibration accuracy. In existing technologies, to determine the accurate coordinates of the calibration points, it is necessary to measure the values ​​of each coordinate item of multiple calibration points separately. Any inaccurate result from any measurement will affect the accuracy of the LiDAR calibration results. However, this solution only requires measuring the distance between the target calibration point and the origin of the object's coordinate system—that is, measuring the value of a single coordinate item of the target calibration point—to complete the LiDAR calibration process. Therefore, the LiDAR calibration results obtained through this solution are more accurate.

[0142] In one embodiment of the present invention, the first calibration point and the second calibration point are located on a calibration object, the calibration object and the driving object are placed on the same plane, the first calibration point and the second calibration point are the intersection points of the calibration object and the plane, the origin of the object coordinate axis is located on the plane, and the line connecting the target calibration point and the origin of the object coordinate axis coincides with the target coordinate axis.

[0143] In one embodiment of the present invention, the calibration object includes a first calibration object and a second calibration object, the first calibration point and the second calibration point are located on the first calibration object and the second calibration object respectively, the volume of the first calibration object is smaller than that of the second calibration object, so that the area projected by the second calibration object in the direction of the moving object is larger than the area projected by the first calibration object in the direction of the moving object, and the distance between the first calibration object and the moving object is smaller than the distance between the second calibration object and the moving object.

[0144] From the above, it can be seen that the volume of the second calibration object, which is farther away from the moving object, is larger. For the laser radar installed on the moving object, the projection area of ​​the second calibration object is larger, making it easier for the laser radar to accurately obtain the laser point corresponding to the second calibration object at a farther distance.

[0145] In one embodiment of the present invention, the first calibration point coincides with the second calibration point and both are located on a third calibration object;

[0146] The point cloud acquisition module 601 is specifically used to:

[0147] Acquire a first laser point cloud collected by a laser radar installed on the moving object when the moving object is at an initial position, and acquire a second laser point cloud collected by the laser radar after the moving object travels a preset distance along the target coordinate axis toward the third calibration object;

[0148] The coordinate determination module 602 is specifically configured to:

[0149] Determining a first coordinate of a first calibration point in a laser radar coordinate system based on the first laser point cloud, and determining a second coordinate of a second calibration point in the laser radar coordinate system based on the second laser point cloud, and obtaining perception data including the first coordinate and the second coordinate;

[0150] The radar calibration module 603 is specifically configured to:

[0151] Determining a conversion relationship between the object coordinate system and the lidar coordinate system based on the perception data and the first distance to complete lidar calibration, wherein the first distance is the distance between the first calibration point and the origin of the object coordinate system when the moving object is at the initial position;

[0152] and / or,

[0153] Based on the perception data and the second distance, the conversion relationship between the object coordinate system and the lidar coordinate system is determined to complete the lidar calibration, wherein the second distance is: the distance between the second calibration point and the origin of the object coordinate system after the moving object travels a preset distance along the target coordinate axis.

[0154] As can be seen from the above, this embodiment only requires one third calibration object, and the same point on the third calibration object is used as the first calibration point and the second calibration point to complete the laser radar calibration process. The number of calibration objects required is small, and the laser radar calibration process is relatively simple.

[0155] See also Figure 7 , which is a schematic structural diagram of a second laser radar calibration device provided by an embodiment of the present invention, wherein the perception data further includes a plane model of the plane, and the coordinate determination module 602 includes:

[0156] a surface laser point extraction submodule 602A, configured to extract surface laser points in the laser point cloud corresponding to points on target surfaces of the calibration object, wherein the target surfaces are connected to each other and do not coincide with the target coordinate axis, and the calibration points on the calibration object are located at the junction of the target surfaces and the plane of the calibration object;

[0157] A surface model fitting submodule 602B is used to fit the surface model of each target surface based on the surface laser points;

[0158] A plane laser point extraction submodule 602C is used to extract plane laser points corresponding to points on the plane where the calibration object is located in the laser point cloud;

[0159] A plane model fitting submodule 602D is configured to fit a plane model of the plane based on the plane laser points;

[0160] The coordinate determination submodule 602E is used to determine the coordinates of the intersection of the surface model and the plane model in the laser radar coordinate system, and determine the first coordinates of the first calibration point and the second coordinates of the second calibration point based on the coordinates of the intersection.

[0161] As can be seen from the above, in this embodiment, the surface laser points corresponding to the target surface connected to the calibration points are first identified, and then a surface model of the target surface is fitted based on the surface laser points, and a plane model of the plane where the calibration object is located is fitted. Since the calibration point is both connected to the target surface and is the intersection of the calibration object and the plane, the intersection between the fitted plane model and the surface model is the calibration point. The calibration point includes a first calibration point and a second calibration point. Through this embodiment, perception data including the first coordinate, the second coordinate, and the plane model can be obtained based on the laser point cloud.

[0162] In one embodiment of the present invention, the coordinate determination submodule 602E is specifically configured to:

[0163] determining intersection lines between surface models of respective target surfaces;

[0164] Determine the coordinates of the intersection point of the intersection line and the plane model in the laser radar coordinate system as the coordinates of the intersection point of the surface model and the plane model in the laser radar coordinate system;

[0165] A first coordinate of the first calibration point and a second coordinate of the second calibration point are determined based on the coordinates of the intersection point.

[0166] In one embodiment of the present invention, each target surface is perpendicular to the plane where the calibration object is located.

[0167] From the above, it can be seen that since the target surface is perpendicular to the plane where the calibration object is located, the projection area of ​​the target surface toward the laser radar is larger, and the number of laser points corresponding to the target surface collected by the laser radar is larger, so that the model of the target surface on the fitted three-dimensional model of the calibration object is more accurate, and then the positions of the first calibration point and the second calibration point identified from the three-dimensional model are more accurate, and the first coordinate and the second coordinate obtained are more accurate.

[0168] The embodiment of the present invention further provides an electronic device, such as Figure 8 As shown, it includes a processor 801, a communication interface 802, a memory 803 and a communication bus 804, wherein the processor 801, the communication interface 802, and the memory 803 communicate with each other through the communication bus 804.

[0169] Memory 803, used for storing computer programs;

[0170] The processor 801 is configured to implement any of the method steps described in the laser radar calibration method when executing the program stored in the memory 803 .

[0171] In the case of applying the electronic device provided by the embodiment of the present invention to calibrate the laser radar, the embodiment of the present invention can determine the perception data including the first coordinate and the second coordinate by extracting the laser point cloud collected by the laser radar. Moreover, since the first calibration point and the second calibration point are both located on a target coordinate axis of the object coordinate system, the values ​​of the two coordinate items of the first calibration point and the second calibration point in the object coordinate system are all 0 except for the coordinate item corresponding to the target coordinate axis. By then measuring the distance between the target calibration point and the origin of the object coordinate system, the complete coordinates of the target calibration point in the object coordinate system can be determined. By comparing the coordinates of the target calibration point in the object coordinate system and the perception data, the conversion relationship between the object coordinate system and the laser radar coordinate system can be determined to complete the laser radar calibration.

[0172] Furthermore, obtaining the accurate coordinates of the calibration points in the object's coordinate system is a prerequisite for ensuring LiDAR calibration accuracy. In existing technologies, to determine the accurate coordinates of the calibration points, it is necessary to measure the values ​​of each coordinate item of multiple calibration points separately. Any inaccurate result from any measurement will affect the accuracy of the LiDAR calibration results. However, this solution only requires measuring the distance between the target calibration point and the origin of the object's coordinate system—that is, measuring the value of a single coordinate item of the target calibration point—to complete the LiDAR calibration process. Therefore, the LiDAR calibration results obtained through this solution are more accurate.

[0173] The communication bus mentioned in electronic devices can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. This communication bus can be divided into address buses, data buses, and control buses. For ease of illustration, the figure uses only a single thick line, but this does not mean that there is only one bus or only one type of bus.

[0174] The communication interface is used for communication between electronic devices and other devices.

[0175] The memory may include random access memory (RAM) or non-volatile memory (NVM), such as at least one disk storage. Alternatively, the memory may be at least one storage device located away from the processor.

[0176] The processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, and discrete hardware components.

[0177] In another embodiment provided by the present invention, a computer-readable storage medium is also provided, which stores a computer program. When the computer program is executed by a processor, it implements any step of the laser radar calibration method.

[0178] When executing the computer program stored in the computer-readable storage medium provided by the embodiment of the present invention to calibrate the laser radar, the embodiment of the present invention can determine the perception data including the first coordinate and the second coordinate by extracting the laser point cloud collected by the laser radar. In addition, since the first calibration point and the second calibration point are both located on a target coordinate axis of the object coordinate system, the values ​​of the two coordinate items of the first calibration point and the second calibration point in the object coordinate system are all 0 except for the coordinate item corresponding to the target coordinate axis. By measuring the distance between the target calibration point and the origin of the object coordinate system, the complete coordinates of the target calibration point in the object coordinate system can be determined. By comparing the coordinates of the target calibration point in the object coordinate system and the perception data, the conversion relationship between the object coordinate system and the laser radar coordinate system can be determined to complete the laser radar calibration.

[0179] Furthermore, obtaining the accurate coordinates of the calibration points in the object's coordinate system is a prerequisite for ensuring LiDAR calibration accuracy. In existing technologies, to determine the accurate coordinates of the calibration points, it is necessary to measure the values ​​of each coordinate item of multiple calibration points separately. Any inaccurate result from any measurement will affect the accuracy of the LiDAR calibration results. However, this solution only requires measuring the distance between the target calibration point and the origin of the object's coordinate system—that is, measuring the value of a single coordinate item of the target calibration point—to complete the LiDAR calibration process. Therefore, the LiDAR calibration results obtained through this solution are more accurate.

[0180] In another embodiment provided by the present invention, a computer program product containing instructions is also provided, which, when executed on a computer, enables the computer to execute the steps of any lidar calibration method in the embodiment.

[0181] When executing the computer program provided by the embodiment of the present invention to calibrate the laser radar, the embodiment of the present invention can determine the perception data including the first coordinate and the second coordinate by extracting the laser point cloud collected by the laser radar. Moreover, since the first calibration point and the second calibration point are both located on a target coordinate axis of the object coordinate system, the values ​​of the two coordinate items of the first calibration point and the second calibration point in the object coordinate system are all 0 except for the coordinate item corresponding to the target coordinate axis. By then measuring the distance between the target calibration point and the origin of the object coordinate system, the complete coordinates of the target calibration point in the object coordinate system can be determined. By comparing the coordinates of the target calibration point in the object coordinate system and the perception data, the conversion relationship between the object coordinate system and the laser radar coordinate system can be determined to complete the laser radar calibration.

[0182] Furthermore, obtaining the accurate coordinates of the calibration points in the object's coordinate system is a prerequisite for ensuring LiDAR calibration accuracy. In existing technologies, to determine the accurate coordinates of the calibration points, it is necessary to measure the values ​​of each coordinate item of multiple calibration points separately. Any inaccurate result from any measurement will affect the accuracy of the LiDAR calibration results. However, this solution only requires measuring the distance between the target calibration point and the origin of the object's coordinate system—that is, measuring the value of a single coordinate item of the target calibration point—to complete the LiDAR calibration process. Therefore, the LiDAR calibration results obtained through this solution are more accurate.

[0183] In an embodiment, the present invention may be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, the present invention may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present invention is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via a wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) method. The computer-readable storage medium may be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more available media integrated therein. The available medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state drive (SSD)).

[0184] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply the existence of any such actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article, or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or device. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or device comprising the element.

[0185] Each embodiment in this specification is described in a related manner. Similar portions between the various embodiments can be referenced to each other. Each embodiment focuses on the differences between the other embodiments. In particular, since the apparatus, electronic device, computer-readable storage medium, and computer program product are generally similar to the method embodiments, their descriptions are relatively simplified. For related portions, reference can be made to the descriptions of the method embodiments.

[0186] The above description is only a preferred embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present invention are included in the scope of protection of the present invention.

Claims

1. A laser radar calibration method, characterized in that: The method comprises: Acquire a first laser point cloud collected by a laser radar mounted on a moving object when the moving object is at an initial position, and acquire a second laser point cloud collected by the laser radar after the moving object travels a preset distance along a target coordinate axis toward a third calibration object; Determining perception data based on the first laser point cloud and the second laser point cloud, the perception data including a first coordinate of a first calibration point in a laser radar coordinate system and a second coordinate of a second calibration point in the laser radar coordinate system, wherein the second calibration point and the first calibration point are located on the same target coordinate axis of an object coordinate system; and the first calibration point and the second calibration point coincide with each other and are both located on a third calibration object; Determining a conversion relationship between the object coordinate system and the lidar coordinate system based on the perception data and a first distance, wherein the first distance is the distance between the first calibration point and the origin of the object coordinate system when the moving object is at the initial position, thereby completing lidar calibration; and / or, Determining a conversion relationship between the object coordinate system and the lidar coordinate system based on the perception data and a second distance, wherein the second distance is the distance between the second calibration point and the origin of the object coordinate system after the moving object travels a preset distance along the target coordinate axis, and completing lidar calibration, wherein the target calibration point is the first calibration point and / or the second calibration point; The determining of perception data based on the first laser point cloud and the second laser point cloud includes: Based on the first laser point cloud, determine the first coordinate of the first calibration point in the laser radar coordinate system, and based on the second laser point cloud, determine the second coordinate of the second calibration point in the laser radar coordinate system, and obtain perception data including the first coordinate and the second coordinate.

2. The method according to claim 1, characterized in that The second calibration point and the first calibration point are located on the same target coordinate axis of the object coordinate system, including: The first calibration point and the second calibration point are located on the calibration object, the calibration object and the driving object are placed on the same plane, the origin of the object coordinate axis and the target coordinate axis both coincide with the plane, and the first calibration point and the second calibration point intersect with the plane at the target coordinate axis.

3. The method according to claim 2, characterized in that The perception data further includes a plane model of the plane, and determining the perception data based on the first laser point cloud and the second laser point cloud includes: Extracting surface laser points corresponding to points on target surfaces of the calibration object from the first laser point cloud and the second laser point cloud, wherein the target surfaces are connected to each other and do not coincide with the target coordinate axis, and the first calibration point and the second calibration point are located at the connection between the target surface and the plane; Fitting a surface model of each target surface based on the surface laser points; Extracting planar laser points corresponding to points on the plane in the first laser point cloud and the second laser point cloud; Fitting a planar model of the plane based on the planar laser points; The coordinates of the intersection point of the surface model and the plane model in the laser radar coordinate system are determined, and the first coordinate and the second coordinate are determined based on the coordinates of the intersection point.

4. The method according to claim 3, characterized in that Determining the coordinates of the intersection of the surface model and the plane model in the laser radar coordinate system includes: determining intersection lines between surface models of respective target surfaces; The coordinates of the intersection point of the intersection line and the plane model in the laser radar coordinate system are determined as the coordinates of the intersection point of the surface model and the plane model in the laser radar coordinate system.

5. The method according to claim 3, characterized in that Each of the target surfaces is perpendicular to the plane.

6. A laser radar calibration device, characterized in that: The device comprises: a point cloud acquisition module, configured to acquire a first laser point cloud acquired by a laser radar mounted on a moving object when the moving object is at an initial position, and to acquire a second laser point cloud acquired by the laser radar after the moving object travels a preset distance along a target coordinate axis toward a third calibration object; a coordinate determination module, configured to determine perception data based on the first laser point cloud and the second laser point cloud, the perception data comprising a first coordinate of a first calibration point in a laser radar coordinate system and a second coordinate of a second calibration point in the laser radar coordinate system, wherein the second calibration point and the first calibration point are located on the same target coordinate axis of the object coordinate system; and the first calibration point and the second calibration point coincide with each other and are both located on a third calibration object; a radar calibration module, configured to determine a conversion relationship between the object coordinate system and the lidar coordinate system based on the perception data and a first distance, wherein the first distance is the distance between the first calibration point and the origin of the object coordinate system when the moving object is at the initial position, to complete lidar calibration; and / or, Determining a conversion relationship between the object coordinate system and the lidar coordinate system based on the perception data and a second distance, wherein the second distance is the distance between the second calibration point and the origin of the object coordinate system after the moving object travels a preset distance along the target coordinate axis, and completing lidar calibration, wherein the target calibration point is the first calibration point and / or the second calibration point; The coordinate determination module is specifically used to: Based on the first laser point cloud, determine the first coordinate of the first calibration point in the laser radar coordinate system, and based on the second laser point cloud, determine the second coordinate of the second calibration point in the laser radar coordinate system, and obtain perception data including the first coordinate and the second coordinate.

7. An electronic device, characterized in that: It includes a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus; Memory for storing computer programs; A processor, configured to implement the method steps described in any one of claims 1 to 5 when executing a program stored in a memory.

8. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method steps described in any one of claims 1 to 5 are implemented.

Images