A calibration method and apparatus

Abstract

The application relates to a calibration method and device. The method comprises the following steps: acquiring a first point coordinate set corresponding to a target calibration board, the first point coordinate set comprising the coordinates of at least one point on the target calibration board in a to-be-calibrated sensor coordinate system; at least one contour line of the target calibration board is of a preset shape; according to the first point coordinate set, first feature point information corresponding to a first contour line in the at least one contour line is determined; acquiring a second point coordinate set corresponding to the target calibration board, the second point coordinate set comprising the coordinates of at least one point on the target calibration board in a reference sensor coordinate system; according to the second point coordinate set, second feature point information corresponding to the first contour line is determined; and the external parameters of the to-be-calibrated sensor are calibrated according to the first feature point information and the second feature point information. In the application, the contour features of the target calibration board are used for external parameter calibration, so that the calibration efficiency and accuracy are improved.

Description

Technical Field

[0001] This application relates to the field of autonomous driving technology, and in particular to a calibration method and apparatus. Background Technology

[0002] In autonomous driving systems, the perception module is a crucial component. Point cloud data collected by LiDAR is one of the inputs to the perception module. LiDAR can scan the environment around the vehicle and output point cloud data. However, using a single LiDAR has certain blind spots, and the density of point clouds varies at different distances, which may affect the performance of the perception module. Therefore, point cloud data collected by multiple LiDARs distributed at different locations on the vehicle can be fused to improve the performance of the perception module.

[0003] Before fusing point cloud data collected by multiple lidars, it is necessary to calibrate the extrinsic parameters of the multiple lidars, that is, to determine the pose transformation relationship between the multiple lidars; however, the calibration efficiency and calibration accuracy of the existing extrinsic parameter calibration methods need to be improved. Summary of the Invention

[0004] In view of this, a calibration method, apparatus, storage medium and computer program product are proposed.

[0005] In a first aspect, embodiments of this application provide a calibration method, the method comprising: acquiring a first set of point coordinates corresponding to a target calibration plate, the first set of point coordinates including the coordinates of at least one point on the target calibration plate in the coordinate system of the sensor to be calibrated; at least one contour line of the target calibration plate having a preset shape; determining first feature point information corresponding to the first contour line based on the first set of point coordinates, the first contour line being any one of the at least one contour lines; acquiring a second set of point coordinates corresponding to the target calibration plate, the second set of point coordinates including the coordinates of at least one point on the target calibration plate in the coordinate system of a reference sensor; determining second feature point information corresponding to the first contour line based on the second set of point coordinates; calibrating the extrinsic parameters of the sensor to be calibrated based on the first feature point information and the second feature point information; the extrinsic parameters including parameters representing the relative pose relationship between the sensor to be calibrated and the reference sensor.

[0006] Based on the above technical solution, the first contour line is a preset shape. The first feature point information corresponding to the first contour line can be quickly and accurately determined according to the first point coordinate set corresponding to the target calibration plate collected by the sensor to be calibrated. The second feature point information corresponding to the first contour line can be quickly and accurately determined according to the second point coordinate set corresponding to the target calibration plate collected by the reference sensor. Based on the first feature point information and the second feature point information, the extrinsic parameters of the sensor to be calibrated are calibrated. Thus, the extrinsic parameter calibration is achieved by using the contour features of the target calibration plate, which improves the calibration efficiency and accuracy.

[0007] According to the first aspect, in a first possible implementation of the first aspect, the method further includes: obtaining preset constraint information corresponding to the first contour line, the preset constraint information including: length information of the first contour line, and / or, the relative positional relationship between the first contour line and other contour lines in the target calibration plate; determining first feature point information corresponding to the first contour line according to the first set of point coordinates includes: determining the first feature point information according to the first set of point coordinates and the preset constraint information; and / or determining second feature point information corresponding to the first contour line according to the second set of point coordinates includes: determining the second feature point information according to the second set of point coordinates and the preset constraint information.

[0008] Based on the above technical solution, using the first contour line as a preset shape and the preset constraint information corresponding to the first contour line as constraints, the first feature point information corresponding to the first contour line can be determined more accurately based on the set of first point coordinates corresponding to the target calibration plate collected by the sensor to be calibrated, and the second feature point information corresponding to the first contour line can be determined more accurately based on the set of second point coordinates corresponding to the target calibration plate collected by the reference sensor. This achieves full utilization of the contour features of the target calibration plate for external parameter calibration, further improving the calibration accuracy.

[0009] According to the first aspect or the first possible implementation of the first aspect, in the second possible implementation of the first aspect, the step of calibrating the extrinsic parameters of the sensor to be calibrated based on the first feature point information and the second feature point information includes: calibrating the extrinsic parameters of the sensor to be calibrated by registering the first feature point information with the second feature point information.

[0010] Based on the above technical solution, the feature point information corresponding to the first contour line detected by the sensor to be calibrated and the reference sensor is used for registration, thereby quickly and accurately realizing the automatic calibration of the external parameters of the sensor to be calibrated.

[0011] According to the first aspect or various possible implementations of the first aspect, in a third possible implementation of the first aspect, the first feature point information includes: a set of coordinates of a preset number of feature points on the first contour line in the coordinate system of the sensor to be calibrated; the second feature point information includes: a set of coordinates of a preset number of feature points on the first contour line in the coordinate system of the reference sensor; determining the first feature point information corresponding to the first contour line based on the first set of coordinates includes: extracting the coordinates of the points corresponding to the first contour line from the first set of coordinates; fitting the extracted coordinates of the points corresponding to the first contour line from the first set of coordinates to obtain a first expression of the first contour line; determining the set of coordinates of the preset number of feature points on the first contour line in the coordinate system of the sensor to be calibrated based on the first expression; determining the second feature point information corresponding to the first contour line based on the second set of coordinates includes: extracting the set of coordinates of the points corresponding to the first contour line from the second set of coordinates; fitting the extracted coordinates of the points corresponding to the first contour line from the second set of coordinates to obtain a second expression of the first contour line; determining the set of coordinates of the preset number of feature points on the first contour line in the coordinate system of the reference sensor based on the second expression.

[0012] Based on the above technical solution, the first contour line has a preset shape, meaning it can be represented by a specific expression. By extracting the coordinates of the points corresponding to the first contour line from the first set of point coordinates, a first expression that accurately represents the actual shape of the first contour line can be fitted. Based on the first expression, the coordinate set of a preset number of feature points on the first contour line in the coordinate system of the sensor to be calibrated can be accurately obtained. By extracting the coordinates of the points corresponding to the first contour line from the second set of point coordinates, a second expression that accurately represents the actual shape of the first contour line can be fitted. Based on the second expression, the coordinate set of a preset number of feature points on the first contour line in the coordinate system of the reference sensor can be accurately obtained, thereby effectively improving the accuracy of the extrinsic parameter calibration of the sensor to be calibrated.

[0013] According to the third possible implementation of the first aspect, in the fourth possible implementation of the first aspect, fitting the point coordinates corresponding to the first contour line in the extracted first point coordinate set to obtain a first expression of the first contour line includes: obtaining preset constraint information corresponding to the first contour line; fitting the point coordinates corresponding to the first contour line in the extracted first point coordinate set according to the preset constraint information to obtain the first expression; and / or, fitting the point coordinates corresponding to the first contour line in the extracted second point coordinate set to obtain a second expression of the first contour line includes: obtaining preset constraint information corresponding to the first contour line; fitting the point coordinates corresponding to the first contour line in the extracted second point coordinate set according to the preset constraint information to obtain the second expression.

[0014] Based on the above technical solution, since the first contour line can be represented by a specific expression, and the length of the first contour line and the relative position between the first contour line and other contour lines are constrained, the calibration device can obtain a first expression that can accurately represent the actual shape of the first contour line based on the preset constraint information corresponding to the first contour line after extracting the point coordinates corresponding to the first contour line in the first set of point coordinates; and / or, can obtain a second expression that can accurately represent the actual shape of the first contour line.

[0015] According to the first aspect or various possible implementations of the first aspect, in a fifth possible implementation of the first aspect, obtaining the first set of point coordinates corresponding to the target calibration board includes: obtaining first data collected by the sensor to be calibrated; the first data includes the coordinates of multiple points in the coordinate system of the sensor to be calibrated; extracting the first set of point coordinates from the first data according to a preset distance between the sensor to be calibrated and the target calibration board; and / or, obtaining the second set of point coordinates corresponding to the target calibration board includes: obtaining second data collected by the reference sensor; the second data includes the coordinates of multiple points in the coordinate system of the reference sensor; extracting the second set of point coordinates from the second data according to a preset distance between the reference sensor and the target calibration board.

[0016] Based on the above technical solution, according to the preset distance between the sensor to be calibrated and the target calibration board, the coordinates of the points on the target calibration board in the coordinate system of the sensor to be calibrated can be quickly and accurately extracted from the data collected by the sensor to be calibrated, and / or, according to the preset distance between the reference sensor and the target calibration board, the coordinates of the points on the target calibration board in the coordinate system of the reference sensor can be quickly and accurately extracted from the data collected by the reference sensor, thereby improving calibration efficiency while ensuring calibration accuracy.

[0017] According to the first aspect or various possible implementations of the first aspect, in the sixth possible implementation of the first aspect, the preset shape is a straight line.

[0018] Based on the above technical solutions, the shape of the first contour line is a straight line, and the straight line feature is easier to express. As an example, the first expression and the second expression can be fitted more accurately and quickly, thereby improving the calibration accuracy and efficiency. As another example, the straight line feature of the first contour line and the preset constraint relationship corresponding to the first contour line are used as strong constraints, thereby fitting the first expression and the second expression more accurately. As yet another example, registration is performed using the feature point information corresponding to the same straight line detected by the sensor to be calibrated and the reference sensor, which makes convergence easier and thus enables faster and more accurate automatic calibration of the extrinsic parameters of the sensor to be calibrated.

[0019] Secondly, embodiments of this application provide a calibration device, the device comprising: an acquisition module, configured to acquire a first set of point coordinates corresponding to a target calibration plate, the first set of point coordinates including the coordinates of at least one point on the target calibration plate in the coordinate system of the sensor to be calibrated; at least one contour line of the target calibration plate having a preset shape; a processing module, configured to determine first feature point information corresponding to a first contour line based on the first set of point coordinates, the first contour line being any one of the at least one contour lines; the acquisition module is further configured to: acquire a second set of point coordinates corresponding to the target calibration plate, the second set of point coordinates including the coordinates of at least one point on the target calibration plate in the coordinate system of a reference sensor; the processing module is further configured to: determine second feature point information corresponding to the first contour line based on the second set of point coordinates; and calibrate the extrinsic parameters of the sensor to be calibrated based on the first feature point information and the second feature point information; the extrinsic parameters including parameters representing the relative pose relationship between the sensor to be calibrated and the reference sensor.

[0020] Based on the above technical solution, the first contour line is a preset shape. The first feature point information corresponding to the first contour line can be quickly and accurately determined according to the first point coordinate set corresponding to the target calibration plate collected by the sensor to be calibrated. The second feature point information corresponding to the first contour line can be quickly and accurately determined according to the second point coordinate set corresponding to the target calibration plate collected by the reference sensor. Based on the first feature point information and the second feature point information, the extrinsic parameters of the sensor to be calibrated are calibrated. Thus, the extrinsic parameter calibration is achieved by using the contour features of the target calibration plate, which improves the calibration efficiency and accuracy.

[0021] According to the second aspect, in a first possible implementation of the second aspect, the acquisition module is further configured to: acquire preset constraint information corresponding to the first contour line, the preset constraint information including: length information of the first contour line, and / or, the relative positional relationship between the first contour line and other contour lines in the target calibration plate; the processing module is further configured to: determine the first feature point information based on the first point coordinate set and the preset constraint information; and / or, determine the second feature point information based on the second point coordinate set and the preset constraint information.

[0022] Based on the above technical solution, using the first contour line as a preset shape and the preset constraint information corresponding to the first contour line as constraints, the first feature point information corresponding to the first contour line can be determined more accurately based on the set of first point coordinates corresponding to the target calibration plate collected by the sensor to be calibrated, and the second feature point information corresponding to the first contour line can be determined more accurately based on the set of second point coordinates corresponding to the target calibration plate collected by the reference sensor. This achieves full utilization of the contour features of the target calibration plate for external parameter calibration, further improving the calibration accuracy.

[0023] According to the second aspect or the first possible implementation of the second aspect, in the second possible implementation of the second aspect, the processing module is further configured to: calibrate the extrinsic parameters of the sensor to be calibrated by registering the first feature point information with the second feature point information.

[0024] Based on the above technical solution, the feature point information corresponding to the first contour line detected by the sensor to be calibrated and the reference sensor is used for registration, thereby quickly and accurately realizing the automatic calibration of the external parameters of the sensor to be calibrated.

[0025] According to the second aspect or various possible implementations of the second aspect above, in a third possible implementation of the second aspect, the first feature point information includes: a set of coordinates of a preset number of feature points on the first contour line in the coordinate system of the sensor to be calibrated; the second feature point information includes: a set of coordinates of a preset number of feature points on the first contour line in the coordinate system of the reference sensor; the processing module is further configured to: extract the point coordinates corresponding to the first contour line in the first point coordinate set; fit the extracted point coordinates corresponding to the first contour line in the first point coordinate set to obtain a first expression of the first contour line; determine the set of coordinates of the preset number of feature points on the first contour line in the coordinate system of the sensor to be calibrated according to the first expression; extract the set of point coordinates corresponding to the first contour line in the second point coordinate set; fit the extracted point coordinates corresponding to the first contour line in the second point coordinate set to obtain a second expression of the first contour line; determine the set of coordinates of the preset number of feature points on the first contour line in the coordinate system of the reference sensor according to the second expression.

[0026] Based on the above technical solution, the first contour line has a preset shape, meaning it can be represented by a specific expression. By extracting the coordinates of the points corresponding to the first contour line from the first set of point coordinates, a first expression that accurately represents the actual shape of the first contour line can be fitted. Based on the first expression, the coordinate set of a preset number of feature points on the first contour line in the coordinate system of the sensor to be calibrated can be accurately obtained. By extracting the coordinates of the points corresponding to the first contour line from the second set of point coordinates, a second expression that accurately represents the actual shape of the first contour line can be fitted. Based on the second expression, the coordinate set of a preset number of feature points on the first contour line in the coordinate system of the reference sensor can be accurately obtained, thereby effectively improving the accuracy of the extrinsic parameter calibration of the sensor to be calibrated.

[0027] According to the third possible implementation of the second aspect, in the fourth possible implementation of the second aspect, the processing module is further configured to: obtain preset constraint information corresponding to the first contour line; fit the point coordinates corresponding to the first contour line in the extracted first point coordinate set according to the preset constraint information to obtain the first expression; and / or, obtain preset constraint information corresponding to the first contour line; fit the point coordinates corresponding to the first contour line in the extracted second point coordinate set according to the preset constraint information to obtain the second expression.

[0028] Based on the above technical solution, since the first contour line can be represented by a specific expression, and the length of the first contour line and the relative position between the first contour line and other contour lines are constrained, the calibration device can obtain a first expression that can accurately represent the actual shape of the first contour line based on the preset constraint information corresponding to the first contour line after extracting the point coordinates corresponding to the first contour line in the first set of point coordinates; and / or, can obtain a second expression that can accurately represent the actual shape of the first contour line.

[0029] According to the second aspect or various possible implementations of the second aspect above, in a fifth possible implementation of the second aspect, the acquisition module is further configured to: acquire first data collected by the sensor to be calibrated; the first data includes coordinates of multiple points in the coordinate system of the sensor to be calibrated; extract the first set of coordinates of the first points from the first data according to a preset distance between the sensor to be calibrated and the target calibration plate; and / or acquire second data collected by the reference sensor; the second data includes coordinates of multiple points in the coordinate system of the reference sensor; extract the second set of coordinates of the second points from the second data according to a preset distance between the reference sensor and the target calibration plate.

[0030] Based on the above technical solution, according to the preset distance between the sensor to be calibrated and the target calibration board, the coordinates of the points on the target calibration board in the coordinate system of the sensor to be calibrated can be quickly and accurately extracted from the data collected by the sensor to be calibrated, and / or, according to the preset distance between the reference sensor and the target calibration board, the coordinates of the points on the target calibration board in the coordinate system of the reference sensor can be quickly and accurately extracted from the data collected by the reference sensor, thereby improving calibration efficiency while ensuring calibration accuracy.

[0031] According to the second aspect or various possible implementations of the second aspect above, in the sixth possible implementation of the second aspect, the preset shape is a straight line.

[0032] Based on the above technical solutions, the shape of the first contour line is a straight line, and the straight line feature is easier to express. As an example, the first expression and the second expression can be fitted more accurately and quickly, thereby improving the calibration accuracy and efficiency. As another example, the straight line feature of the first contour line and the preset constraint relationship corresponding to the first contour line are used as strong constraints, thereby accurately fitting the first expression and the second expression. As yet another example, registration is performed using the feature point information corresponding to the same straight line detected by the sensor to be calibrated and the reference sensor, which is easier to converge, thereby enabling faster and more accurate automatic calibration of the extrinsic parameters of the sensor to be calibrated.

[0033] Thirdly, embodiments of this application provide a calibration apparatus, comprising: a processor; a memory for storing processor-executable instructions; wherein the processor is configured to implement the calibration method described in the first aspect or one or more of the first aspect when executing the instructions.

[0034] Fourthly, embodiments of this application provide a computer-readable storage medium having computer program instructions stored thereon, characterized in that the computer program instructions, when executed by a processor, implement the first aspect or one or more of the calibration methods of the first aspect.

[0035] Fifthly, embodiments of this application provide a computer program product that, when run on a computer, causes the computer to execute the calibration method described in the first aspect or one or more of the first aspect.

[0036] For the technical effects of the third to fifth aspects mentioned above, please refer to the first aspect mentioned above. Attached Figure Description

[0037] Figure 1 A schematic diagram of a calibration scenario according to an embodiment of this application is shown;

[0038] Figure 2 A schematic diagram showing the side of a calibration plate A1 facing the vehicle C according to an embodiment of this application is shown;

[0039] Figure 3 A flowchart of a calibration method according to an embodiment of this application is shown;

[0040] Figure 4 A schematic diagram of the point cloud corresponding to the calibration board A1 extracted according to an embodiment of this application is shown;

[0041] Figure 5 A schematic diagram of the contour line a1 obtained by fitting according to an embodiment of this application is shown;

[0042] Figure 6 A schematic diagram of external parameter calibration according to an embodiment of this application is shown;

[0043] Figure 7 A flowchart of a calibration method according to an embodiment of this application is shown;

[0044] Figure 8 A schematic diagram of fitted contour lines according to an embodiment of this application is shown;

[0045] Figure 9 This diagram shows a structural diagram of a calibration device according to an embodiment of the present application;

[0046] Figure 10A schematic diagram of a calibration device according to an embodiment of this application is shown. Detailed Implementation

[0047] Various exemplary embodiments, features, and aspects of this application will now be described in detail with reference to the accompanying drawings. The same reference numerals in the drawings denote elements that have the same or similar functions. Although various aspects of the embodiments are shown in the drawings, they are not necessarily drawn to scale unless specifically indicated otherwise.

[0048] The term “exemplary” as used herein means “serving as an example, embodiment, or illustration.” Any embodiment illustrated herein as “exemplary” is not necessarily to be construed as superior to or better than other embodiments.

[0049] Figure 1 A schematic diagram of a calibration scenario according to an embodiment of this application is shown. Figure 1 As shown, the calibration scenario may include: sensor L1, sensor L2, calibration board A1, and vehicle C.

[0050] At least one contour line of the calibration plate A1 can be a preset shape. For example, the preset shape can be a straight line, a circle, or other curves that can be represented by a specific expression. For example, the side of the calibration plate A1 facing the vehicle C is located within the field of view of both sensor L1 and sensor L2. This side of the calibration plate A1 facing the vehicle C can include at least one contour line of a preset shape, thereby ensuring that both sensor L1 and sensor L2 can acquire data from the same or multiple contour lines of the preset shape in the calibration plate A1. For example, each contour line on the side of the calibration plate A1 facing the vehicle C can be a straight line, and the corresponding side of the calibration plate A1 facing the vehicle C can be a triangle, rectangle, polygon, etc.; as an example, the calibration plate A1 can be a cuboid. Figure 2 A schematic diagram showing the side of calibration plate A1 facing vehicle C according to an embodiment of this application is shown, as follows. Figure 2 As shown, the side of calibration plate A1 facing vehicle C is a rectangle composed of contour lines a1, a2, a3, and a4. Contour lines a1, a2, a3, and a4 are all straight lines, and all of them are located within the field of view of sensor L1 and sensor L2.

[0051] For example, this calibration scenario may also include more calibration boards, such as... Figure 1As shown, calibration plates A2, A3, and A4 may also be included. Exemplarily, calibration plates A2, A3, and A4 may each include contour lines of a preset shape. For example, the side of calibration plates A2, A3, and A4 facing vehicle C may include multiple contour lines of a preset shape, all located within the field of view of sensor L1 and sensor L2. The preset shapes of the different contour lines in calibration plates A1, A2, A3, and A4 may be the same or different, and this is not limited. As an example, calibration plates A1, A2, A3, and A4 may be placed around vehicle C; for example, calibration plates A1, A2, A3, and A4 may be evenly distributed in different locations on vehicle C.

[0052] It should be noted that in this calibration scenario, there are no restrictions on the placement of calibration plates A1, A2, A3, or A4. For example, calibration plates A1, A2, A3, or A4 can be placed perpendicular to the ground or tilted, as long as both sensor L1 and sensor L2 can collect data from the side of calibration plates A1, A2, A3, or A4 facing vehicle C.

[0053] For example, vehicle C can be located in the middle of the calibration field, and calibration plates A1, A2, A3, and A4 can be placed near the edge of the calibration field. As an example, the calibration field can be a rectangular area, for example, a rectangular area with a length and width between 10m and 50m.

[0054] In this calibration scenario, sensors L1 and L2 can be installed at different locations on vehicle C. Exemplarily, the data collected by sensors L1 and L2 can serve as input to the perception module in the autonomous driving system of vehicle C. Exemplarily, sensor L1 or sensor L2 can include any of the following: LiDAR, millimeter-wave radar, or image acquisition devices, etc. Sensors L1 and L2 can be the same type of sensor or different types of sensors. As an example, sensor L1 can be a main LiDAR installed on vehicle C, and sensor L2 can be a secondary LiDAR installed on vehicle C; as another example, sensor L1 can be a LiDAR installed on vehicle C, and sensor L2 can be an image acquisition device installed on vehicle C. It should be noted that this calibration scenario only uses sensors L1 and L2 as examples; more sensors can be installed on vehicle C, and this is not a limitation.

[0055] For example, Figure 1The calibration scenario shown may also include a calibration device (not shown in the figure). As an example, sensor L1 and sensor L2 can collect data from one or more of calibration plates A1, A2, A3, or A4. The collected data includes data of the same or multiple contour lines of a preset shape. After obtaining the data collected by sensor L1 and sensor L2, the calibration device performs calibration on the external parameters of sensor L1 or sensor L2 by executing the calibration method provided in the embodiments of this application (detailed description below).

[0056] The embodiments of this application do not limit the type of calibration device.

[0057] For example, the calibration device can be the vehicle C mentioned above, or other components in vehicle C with data processing functions, such as: vehicle terminal, vehicle controller, vehicle module, vehicle assembly, vehicle component, vehicle chip, vehicle unit, vehicle sensor, etc. The vehicle can calibrate the external parameters of sensor L1 or sensor L2 through the vehicle terminal, vehicle controller, vehicle module, vehicle assembly, vehicle component, vehicle chip, vehicle unit, vehicle sensor, etc.

[0058] For example, the calibration device can be integrated into the Automated Driving System (ADS), Advanced Driver Assistant Systems (ADAS), or onboard computing platform of vehicle C.

[0059] For example, the calibration device can also be a smart terminal with data processing capabilities other than vehicle C, or a component or chip installed in the smart terminal. For instance, the smart terminal can be a device equipped with sensors, such as smart transportation equipment, smart wearable devices, smart home devices, smart assisted aircraft, robots, or unmanned aerial vehicles.

[0060] For example, the calibration device can be a general-purpose device or a special-purpose device. In specific implementations, the device can also be a desktop computer, a laptop computer, a web server, a handheld computer (PDA), a mobile phone, a tablet computer, a wireless terminal device, an embedded device, or other devices with data processing capabilities, or a component or chip within these devices.

[0061] For example, the calibration device can also be a chip or processor with processing capabilities, and the calibration device may include multiple processors. The processor can be a single-core (single-CPU) processor or a multi-core (multi-CPU) processor. The chip or processor with processing capabilities can be installed in the vehicle-mounted sensor, such as in sensor L1 or sensor L2, or it can be installed at the receiving end of the vehicle-mounted sensor's output signal instead of in the vehicle-mounted sensor.

[0062] It should be noted that the calibration scenarios described in the embodiments of this application are for the purpose of more clearly illustrating the technical solutions of the embodiments of this application, and do not constitute a limitation on the technical solutions provided in the embodiments of this application. Those skilled in the art will recognize that the technical solutions provided in the embodiments of this application are also applicable to similar or new calibration scenarios. For example, scenarios requiring calibration of the extrinsic parameters of multiple sensors, such as 3D reconstruction, terrain detection, autonomous driving mapping, and autonomous driving perception, or scenarios requiring calibration of the extrinsic parameters of a single sensor, are also applicable to similar technical problems.

[0063] The calibration method provided in the embodiments of this application will be described in detail below.

[0064] Figure 3 A flowchart of a calibration method according to an embodiment of this application is shown; exemplarily, the method can be performed by the aforementioned calibration device; as... Figure 3 As shown, the method may include the following steps:

[0065] Step 301: Obtain the first point coordinate set corresponding to the target calibration board; the first point coordinate set includes the coordinates of at least one point on the target calibration board in the coordinate system of the sensor to be calibrated.

[0066] In this design, at least one contour line of the target calibration plate is a preset shape. For example, one side of the target calibration plate located within the field of view of the sensor to be calibrated includes at least one contour line of this preset shape; for instance, the target calibration plate can be as described above. Figure 1 The calibration board is any one of calibration board A, calibration board A2, calibration board A3 or calibration board A4.

[0067] The sensor to be calibrated can be any of the on-board sensors; for example, the sensor to be calibrated can be one of the above-mentioned sensors. Figure 1 The sensor L1 or sensor L2 shown. It is understood that for the same sensor, based on different calibration tasks, it can be used as the sensor to be calibrated, or as a reference sensor (also called a reference sensor); for example, in calibrating the above... Figure 1 When determining the extrinsic parameters of sensor L2, sensor L2 becomes the sensor to be calibrated, and sensor L1 can be used as the reference sensor; in calibrating the above... Figure 1 When the extrinsic parameters of sensor L1 are determined, sensor L1 is the sensor to be calibrated, and sensor L2 can be used as the reference sensor.

[0068] For example, the coordinate system of the sensor to be calibrated can be a Cartesian coordinate system with the centroid of the sensor to be calibrated as the origin.

[0069] For example, the first set of point coordinates may include the coordinates of all points on the target calibration plate detected by the sensor to be calibrated in the coordinate system of the sensor to be calibrated. For example, taking the sensor to be calibrated as... Figure 1 Taking the sensor L1 as the target calibration plate and the calibration plate A1 as an example, the first set of coordinates can include the coordinates of all points on the side of the calibration plate A1 facing the sensor L1 in the coordinate system of the sensor to be calibrated.

[0070] In one possible implementation, the step may include: the calibration device can acquire first data collected by the sensor to be calibrated; the first data includes the coordinates of multiple points in the coordinate system of the sensor to be calibrated; and extract a first set of point coordinates from the first data according to a preset distance between the sensor to be calibrated and the target calibration plate.

[0071] The preset distance between the sensor to be calibrated and the target calibration board can be predetermined based on the position of the sensor to be calibrated and the position of the target calibration board.

[0072] For example, the first data may include the coordinates of all points detected by the sensor to be calibrated within the calibration site in the coordinate system of the sensor to be calibrated. The calibration device can determine the coordinate range of the target calibration plate in the coordinate system of the sensor to be calibrated based on a preset distance; then, from the coordinates of all points detected by the sensor to be calibrated in the coordinate system of the sensor to be calibrated, it can filter out the coordinates within that range to obtain the first set of point coordinates. In this way, based on the preset distance between the sensor to be calibrated and the target calibration plate, the coordinates of points on the target calibration plate in the coordinate system of the sensor to be calibrated can be extracted quickly and accurately from the data collected by the sensor to be calibrated, thereby improving calibration efficiency while ensuring the accuracy of external parameter calibration.

[0073] For example, taking the sensor to be calibrated as... Figure 1 Taking sensor L1, which is a lidar, as an example, during the scanning process within the calibration area, sensor L1 can emit a laser beam, receive reflected signals, and determine the three-dimensional coordinates of the scanning point in the sensor L1 coordinate system based on the reflected signals, thereby obtaining the collected point cloud data. The calibration device can acquire the point cloud data collected by sensor L1 and, based on the preset distance between sensor L1 and calibration plate A1, extract the point cloud corresponding to calibration plate A1 from the point cloud data. The extracted point cloud corresponding to calibration plate A1 can be processed as follows: Figure 4As shown.

[0074] Step 302: Determine the first feature point information corresponding to the first contour line based on the first set of point coordinates.

[0075] The first contour line is any one of the contour lines of a preset shape in the target calibration plate. For example, the first contour line can be... Figure 2 Any one of the contour lines a1, a2, a3, or a4 in the calibration plate A1.

[0076] For example, the first feature point information may include: a set of coordinates of a preset number of feature points on the first contour line in the coordinate system of the sensor to be calibrated. The feature points may include the intersection points of the first contour line with other contour lines, the midpoint of the first contour line, or a number of points evenly spaced on the first contour line, etc. The preset number can be set according to actual needs and is not limited thereto; for example, the preset number may be greater than or equal to 500.

[0077] In one possible implementation, this step may include: extracting the point coordinates corresponding to the first contour line from the first set of point coordinates; fitting the extracted point coordinates corresponding to the first contour line to obtain a first expression for the first contour line; and determining the coordinate set of a preset number of feature points on the first contour line in the coordinate system of the sensor to be calibrated based on the first expression. Since the first contour line is a straight line, a circle, or other curve that can be represented by a specific expression, where straight lines and circles can both be represented by specific expressions, the calibration device can fit a first expression that can accurately represent the actual shape of the first contour line based on the extracted point coordinates corresponding to the first contour line in the first set of point coordinates; and then, based on the first expression, the coordinate set of a preset number of feature points on the first contour line in the coordinate system of the sensor to be calibrated can be accurately obtained.

[0078] It is understandable that the first contour line is located at the edge of the target calibration plate, and the coordinates of the point corresponding to the first contour line can include the coordinates of the point on the edge of the target calibration plate detected by the sensor to be calibrated in the coordinate system of the sensor to be calibrated.

[0079] For example, the calibration device can obtain the coordinates of the center point on the side of the target calibration plate facing the sensor to be calibrated based on the first set of point coordinates, and extract the coordinates of the points on the edge of the first contour line in the first set of point coordinates, thereby obtaining the coordinates of the points corresponding to the first contour line. For example, the coordinates of the center point on the side of the target calibration plate facing the sensor to be calibrated can be obtained according to the following formula (1):

[0080]

[0081] Where n represents the number of points in the first set of coordinates, and xi, yi, and zi represent the coordinates of the i-th point in the first set of coordinates in the coordinate system of the sensor to be calibrated. x0, y0, and z0 represent the coordinates of the center point on the side of the target calibration plate facing the sensor to be calibrated.

[0082] Furthermore, the calibration device can fit the point coordinates corresponding to the extracted first contour line to obtain the first expression of the first contour line.

[0083] As an example, the calibration device can fit the point coordinates corresponding to the first contour line extracted from the first point coordinate set according to the preset shape of the first contour line, thereby obtaining the first expression of the first contour line more quickly and accurately. For example, the shape of the first contour line can be a straight line, and the features of a straight line are easier to express, thus allowing for a more accurate and faster fitting of the first expression.

[0084] As another example, since the first contour line is located on the side of the target calibration plate facing the sensor to be calibrated, the calibration device can obtain the fitting plane on the side of the target calibration plate facing the sensor to be calibrated. Then, based on the positional relationship between the fitting plane and the first contour line, and the preset shape of the first contour line, the device can fit the point coordinates corresponding to the first contour line extracted from the first point coordinate set, thereby obtaining the first expression of the first contour line more quickly and accurately.

[0085] For example, the calibration device can use existing fitting techniques, such as random sampling consensus algorithm, least squares method, principal component analysis, singular value decomposition, etc., based on the first set of coordinates to obtain the fitting plane of the side of the target calibration plate facing the sensor to be calibrated; for example, the expression of the fitting plane can be as shown in the following formula (2):

[0086] A·x+B·y+C·z+D=0............(2)

[0087] Where A, B, C, and D are constants, and A, B, and C are not all zero at the same time. x, y, and z represent the coordinates of any point in the fitting plane on the x-axis, y-axis, and z-axis of the sensor coordinate system to be calibrated, respectively.

[0088] For example, the calibration device fits the point coordinates corresponding to the first contour line extracted from the first point coordinate set based on the preset shape of the first contour line and with the first contour line lying on the fitting plane as a constraint; for example, taking the first contour line as a straight line, the straight line lies on the fitting plane, thereby accurately fitting the expression of the straight line. For instance, taking the first contour line as contour line a1 in calibration plate A1 as an example, regarding the above... Figure 4The point cloud corresponding to the calibration plate A1 is extracted as shown. The point coordinates corresponding to the contour line a1 are extracted and fitted. The fitted contour line a1 is... Figure 5 This is a schematic diagram of the fitted contour line a1, as shown below. Figure 5 As shown, the fitted contour line a1 is located at the upper edge of the calibration plate A1.

[0089] Step 303: Obtain the second point coordinate set corresponding to the target calibration board; the second point coordinate set includes the coordinates of at least one point on the target calibration board in the reference sensor coordinate system.

[0090] The reference sensor can be any sensor that has a fixed pose relationship with the sensor to be calibrated. For example, if the above-mentioned... Figure 1 If sensor L1 is the sensor to be calibrated, then sensor L2 can be the reference sensor.

[0091] For example, the reference sensor coordinate system can be a Cartesian coordinate system with the centroid of the reference sensor as the origin.

[0092] For example, the second set of point coordinates may include the coordinates of all points on the target calibration plate detected by the reference sensor in the reference sensor coordinate system. For instance, taking the reference sensor as... Figure 1 Taking the sensor L2 as the target calibration plate and the calibration plate A1 as an example, the second set of coordinates can include the coordinates of all points on the side of the calibration plate A1 facing the sensor L2 in the reference sensor coordinate system.

[0093] In one possible implementation, the step may include: acquiring second data collected by a reference sensor; the second data may include the coordinates of multiple points in the coordinate system of the reference sensor; and extracting a set of second point coordinates from the second data based on a preset distance between the reference sensor and the target calibration plate.

[0094] The preset distance between the reference sensor and the target calibration board can be predetermined based on the position of the reference sensor and the position of the target calibration board.

[0095] For example, the first data may include the coordinates of all points detected by the reference sensor within the calibration site in the reference sensor coordinate system. The calibration device can determine the coordinate range of the target calibration board in the reference sensor coordinate system based on a preset distance; then, from the coordinates of all points detected by the reference sensor in the reference sensor coordinate system, coordinates within this range are selected to obtain the first set of point coordinates. In this way, based on the preset distance between the reference sensor and the target calibration board, the coordinates of points on the target calibration board in the reference sensor coordinate system can be extracted quickly and accurately from the data collected by the reference sensor, thereby improving calibration efficiency while ensuring calibration accuracy.

[0096] Step 304: Determine the information of the second feature points corresponding to the first contour line based on the second set of point coordinates.

[0097] For example, the second feature point information may include: a set of coordinates of a predetermined number of feature points on the first contour line in the reference sensor coordinate system. For example, the second feature point information may be determined in the same manner as the determination of the first feature point information in step 302 above.

[0098] In one possible implementation, this step may include: extracting the set of point coordinates corresponding to the first contour line from the second set of point coordinates; fitting the extracted point coordinates corresponding to the first contour line from the second set of point coordinates to obtain a second expression for the first contour line; and determining the coordinate set of a preset number of feature points on the first contour line in the reference sensor coordinate system based on the second expression. The specific process of this implementation can be referred to in step 302 above, which describes the extraction of the point coordinates corresponding to the first contour line from the first set of point coordinates and the relevant description of obtaining the first expression for the first contour line, and will not be repeated here. Since the first contour line is a straight line, a circle, or other curve that can be represented by a specific expression, where straight lines and circles can both be represented by specific expressions, the calibration device, based on extracting the point coordinates corresponding to the first contour line from the second set of point coordinates, can fit a second expression that accurately represents the actual shape of the first contour line; and then, based on this second expression, the coordinate set of a preset number of feature points on the first contour line in the reference sensor coordinate system can be accurately obtained.

[0099] It should be noted that steps 303-304 can also be performed before steps 301-302 above, and there is no limitation on this.

[0100] Step 305: Based on the first feature point information and the second feature point information, calibrate the extrinsic parameters of the sensor to be calibrated.

[0101] The extrinsic parameters may include parameters representing the relative pose relationship between the sensor to be calibrated and the reference sensor. For example, these parameters may include: pitch angle, roll angle, yaw angle, and x-axis translation (t). x Translation of the y-axis (t) y Translation of the z-axis (t) zOne or more of the following, wherein the pitch angle represents the angle of rotation about the y-axis in the coordinate system of the sensor to be calibrated, the yaw angle represents the angle of rotation about the z-axis in the coordinate system of the sensor to be calibrated, the roll angle represents the angle of rotation about the x-axis in the coordinate system of the sensor to be calibrated, the x-axis translation represents the distance translated along the x-axis in the coordinate system of the sensor to be calibrated, the y-axis translation represents the distance translated along the y-axis in the coordinate system of the sensor to be calibrated, and the z-axis translation represents the distance translated along the z-axis in the coordinate system of the sensor to be calibrated.

[0102] For example, the extrinsic parameters of the sensor to be calibrated can be represented by a rotation matrix and a translation matrix, where the rotation matrix represents the rotational transformation relationship between the coordinate system of the sensor to be calibrated and the coordinate system of the reference sensor. As an example, the rotation matrix can be a 3x3 matrix, including 3 degrees of freedom, which correspond to the x-axis, y-axis and z-axis of the sensor to be calibrated, respectively. The rotation matrix represents the rotational transformation about the three axes of x, y and z. For example, the rotation matrix R can be expressed in the form of the following formula (3):

[0103]

[0104] Where α represents the yaw angle, β represents the pitch angle, and γ represents the roll angle.

[0105] The translation matrix represents the translation transformation relationship between the coordinate system of the sensor to be calibrated and the coordinate system of the reference sensor. As an example, the rotation matrix can be a matrix with one row and three columns, and the translation matrix includes three degrees of freedom, which correspond to the x-axis, y-axis and z-axis of the sensor to be calibrated, respectively. The translation matrix represents the translation transformation along the three axes of x-axis, y-axis and z-axis. For example, the translation matrix T can be expressed in the form of the following formula (4):

[0106] T=(t x t y t z ).....................(4)

[0107] Among them, t x t y t z These represent the translation amounts along the x-axis, y-axis, and z-axis, respectively.

[0108] It is understandable that for any point in the coordinate system of the sensor to be calibrated, after transformation by the extrinsic parameters of the sensor to be calibrated, the corresponding point in the coordinate system of the reference sensor can be obtained, or the coordinates of the transformed point and the corresponding point have very small deviations; for example, for any point in the coordinate system of the sensor to be calibrated, after rotating the point using the rotation matrix in the extrinsic parameters of the sensor to be calibrated, and then translating the point using the translation matrix in the extrinsic parameters, the corresponding point in the coordinate system of the reference sensor can be obtained; as shown in the following formula (5):

[0109]

[0110] Where R is the rotation matrix, T is the translation matrix, p2 is a point in the coordinate system of the sensor to be calibrated, and x L2 y L2 z L2 Let p2 be the coordinates of point p2 in the coordinate system of the sensor to be calibrated; p1 is the corresponding point of p2 in the reference sensor coordinate system, x L1 y L1 z L1 Let p1 be the coordinates of point p1 in the reference sensor coordinate system.

[0111] In one possible implementation, this step may include calibrating the extrinsic parameters of the sensor to be calibrated by registering the first feature point information with the second feature point information. In this way, by registering the feature point information corresponding to the first contour line detected by the sensor to be calibrated and the reference sensor, the automatic calibration of the extrinsic parameters of the sensor to be calibrated can be achieved quickly and accurately. For example, the shape of the first contour line can be a straight line. Using the feature point information corresponding to the same straight line detected by the sensor to be calibrated and the reference sensor for registration makes convergence easier, thereby enabling faster and more accurate automatic calibration of the extrinsic parameters of the sensor to be calibrated.

[0112] For example, the calibration device can register the coordinate set of a preset number of feature points on the first contour line in the coordinate system of the sensor to be calibrated with the coordinate set of a preset number of feature points on the first contour line in the coordinate system of the reference sensor to calibrate the extrinsic parameters of the sensor to be calibrated.

[0113] As an example, the optimal solution can be obtained by using an optimization algorithm based on the following formula (6) to obtain the external parameters of the laser radar to be calibrated.

[0114] D=|P1–M*P2|…..…..………..…..…(6)

[0115] Where M is the transformation matrix, R is the rotation matrix, T is the translation matrix, P1 represents the set of coordinates of a preset number of feature points on the first contour line in the reference sensor coordinate system, P2 represents the set of coordinates of a preset number of feature points on the first contour line in the coordinate system of the sensor to be calibrated, and D is the sum of the distances between the new coordinates of each feature point in P2 after transformation by M and the corresponding points in P1.

[0116] Understandably, according to the geometric consistency assumption, the coordinates of any point in P2 will coincide with the coordinates of the corresponding point in P1 after transformation by the transformation matrix M. That is, the spatial distance between the point after transformation by the transformation matrix M and its corresponding point is 0. Therefore, theoretically, when D is 0, the value of M is the final solution. Considering that D cannot be 0 in practical applications, the optimization method can be used to solve formula (6) iteratively. When the iteration conditions are met (e.g., the value of D is small enough, the change of D in consecutive iterations is small enough, or the number of iterations reaches a preset value, etc.), the optimal solution of M is obtained. Then, the parameters representing the relative pose relationship between the sensor to be calibrated and the reference sensor can be calculated from the optimal solution of M. For example, the pitch angle, roll angle, yaw angle, translation of the x-axis, translation of the y-axis or translation of the z-axis can be calculated from the above formula (3) and formula (4) to complete the external parameter calibration of the sensor to be calibrated.

[0117] For example, the calibration device can perform the above operation on each of the preset shape contour lines detected by the sensor to be calibrated and the reference sensor. It can determine the feature point information corresponding to each preset shape contour line detected by the sensor to be calibrated and the reference sensor, and calibrate the extrinsic parameters of the sensor to be calibrated according to the feature point information corresponding to each preset shape contour line.

[0118] For example, Figure 6 A schematic diagram of extrinsic parameter calibration according to an embodiment of this application is shown, such as... Figure 6 As shown, the left side of the arrow represents the relative pose of each contour line of the calibration board A1 detected by the sensor to be calibrated and each contour line of the calibration board A1 detected by the reference sensor, and there is a deviation between the two; the right side of the arrow represents the relative pose of each contour line of the calibration board A1 detected by the sensor to be calibrated and each contour line of the calibration board A1 detected by the reference sensor after extrinsic parameter transformation. If the two coincide or the deviation is within a preset range, then the extrinsic parameter is the extrinsic parameter of the sensor to be calibrated.

[0119] Based on the above technical solution, the first contour line is a preset shape. The first feature point information corresponding to the first contour line can be quickly and accurately determined according to the first point coordinate set corresponding to the target calibration plate collected by the sensor to be calibrated. The second feature point information corresponding to the first contour line can be quickly and accurately determined according to the second point coordinate set corresponding to the target calibration plate collected by the reference sensor. Based on the first feature point information and the second feature point information, the extrinsic parameters of the sensor to be calibrated are calibrated. Thus, the extrinsic parameter calibration is achieved by using the contour features of the target calibration plate, which improves the calibration efficiency and accuracy.

[0120] Furthermore, compared to manual extrinsic parameter calibration based on regular buildings or objects, this embodiment achieves automatic extrinsic parameter calibration based on a pre-defined contour line, independent of the regular calibration scene, effectively improving calibration efficiency and applicability. Compared to extrinsic parameter calibration based on the natural environment, this embodiment eliminates the need to construct a dense point cloud map, effectively reducing the number of point clouds to be processed during calibration, reducing computation time, and improving calibration efficiency. Simultaneously, it eliminates the need for other sensor assistance, such as Real-time Kinematic (RTK), Global Positioning System (GPS), or Inertial Measurement Unit (IMU), broadening its applicability. Compared to extrinsic parameter calibration based on planar normal vectors, this embodiment uses the pre-defined shape of the contour line as a constraint, avoiding weak constraints and the problem of easily getting trapped in local optima, thus improving calibration accuracy.

[0121] Figure 7 A flowchart of a calibration method according to an embodiment of this application is shown; the method can be executed by the aforementioned calibration device; as... Figure 7 As shown, the method may include the following steps:

[0122] Step 701: Obtain the preset constraint information corresponding to the first contour line of the target calibration plate.

[0123] The preset constraint information may include: the length of the first contour line, and / or the relative positional relationship between the first contour line and other contour lines in the target calibration plate. For example, the relative positional relationship may include: perpendicularity, parallelism, or the angle between two contour lines, etc.

[0124] For example, taking the target calibration board as described above Figure 2 The first outline of the standard plate A is: Figure 2Taking the middle contour line a1 as an example; the preset constraint information may include the length information of the contour line a1, or the relative positional relationship between the contour line a1 and the contour lines a2, a3 or a4, such as the contour line a1 being parallel to the contour line a3, the contour line a1 being perpendicular to the contour line a2, the contour line a1 being perpendicular to the contour line a4, etc.

[0125] For example, the calibration device can acquire preset constraint information corresponding to each contour line detected by the sensor to be calibrated and the reference sensor in the target calibration plate.

[0126] Step 702: Obtain the set of coordinates of the first point corresponding to the target calibration plate.

[0127] This step can be referred to step 301 above, and will not be repeated here.

[0128] Step 703: Determine the first feature point information corresponding to the first contour line based on the first point coordinate set and preset constraint information.

[0129] For a detailed explanation of the first feature point information, please refer to the relevant description in step 302 above.

[0130] In one possible implementation, this step may include: extracting the point coordinates corresponding to the first contour line from the first set of point coordinates; fitting the extracted point coordinates corresponding to the first contour line from the first set of point coordinates according to preset constraint information to obtain a first expression; and determining the coordinate set of a preset number of feature points on the first contour line in the coordinate system of the sensor to be calibrated based on the first expression. Since the first contour line can be represented by a specific expression, and the length of the first contour line and the relative position between the first contour line and other contour lines are constrained, the calibration device can fit a first expression that can accurately represent the actual shape of the first contour line based on the preset constraint information corresponding to the first contour line after extracting the point coordinates corresponding to the first contour line from the first set of point coordinates; and then, based on the first expression, the coordinate set of a preset number of feature points on the first contour line in the coordinate system of the sensor to be calibrated can be obtained more accurately.

[0131] For example, the calibration device can obtain the coordinates of the center point on the side of the target calibration plate facing the sensor to be calibrated based on the first set of point coordinates. Then, based on the coordinates of the center point and preset constraint information, it can extract the coordinates of points on the edge of the first contour line from the first set of point coordinates, thereby obtaining the point coordinates corresponding to the first contour line. For instance, the calibration device can filter out other environmental point clouds, such as the ground, based on the coordinates of the center point and the length information of the first contour line, thereby obtaining the point coordinates corresponding to the first contour line more accurately.

[0132] Furthermore, the calibration device can fit the point coordinates corresponding to the extracted first contour line according to the preset constraint information to obtain the first expression of the first contour line.

[0133] As an example, the calibration device can fit the point coordinates corresponding to the first contour line extracted from the first point coordinate set based on the preset constraint information and preset shape of the first contour line, thereby accurately obtaining the first expression. For example, the shape of the first contour line can be a straight line, and straight line features are easier to express. Using the straight line features of the first contour line and the preset constraint relationship corresponding to the first contour line as strong constraints, the first expression can be fitted more accurately.

[0134] As another example, the calibration device can fit the point coordinates corresponding to the first contour line extracted from the first point coordinate set based on the preset constraint information corresponding to the first contour line, the positional relationship between the fitting plane of the side of the target calibration plate facing the sensor to be calibrated and the first contour line, and the preset shape of the first contour line, so as to obtain the first expression more accurately.

[0135] For example, the calibration device fits the point coordinates corresponding to the first contour line extracted from the first point coordinate set based on the preset shape of the first contour line and with the first contour line located on the fitting plane and the relative positional relationship between the first contour line and other contour lines in the target calibration plate as constraints. For example, if each contour line on the side of the target calibration plate facing the sensor to be calibrated is a straight line, then each straight line is located on the fitting plane, and there are relative positional relationships such as perpendicular and parallel between different straight lines, so that the expression of the first contour line can be accurately fitted.

[0136] In one possible implementation, the calibration device can extract the point coordinates corresponding to each contour line detected by the sensor to be calibrated and the reference sensor in the target calibration plate; fit the extracted point coordinates corresponding to each contour line according to the preset constraint information corresponding to each contour line to obtain the expression of each contour line; and determine the set of coordinates of a preset number of feature points on each contour line in the coordinate system of the sensor to be calibrated according to the expression of each contour line.

[0137] For example, taking the contour lines in calibration plate A1 as an example, contour lines a1, a2, a3, and a4 form a rectangle; regarding the above... Figure 4The point cloud corresponding to the calibration board A1 is shown. The coordinates of points corresponding to contour lines a1, a2, a3, and a4 are extracted. Then, using the relative positional relationships (e.g., contour lines a1 and a3 are parallel, a1 and a2 are perpendicular, a1 and a4 are perpendicular, a3 and a2 are perpendicular) and the equal lengths of contour lines a1 and a3 and a2 and a4 are equal as constraints, contour lines a1, a2, a3, and a4 are fitted to obtain the desired contour lines. Figure 8 Here is a schematic diagram of the fitted contours, as shown below. Figure 8 As shown, the point cloud corresponding to calibration plate A1 is located within the rectangular area enclosed by the fitted contour lines a1, a2, a3, and a4.

[0138] Step 704: Obtain the set of coordinates of the second point corresponding to the target calibration plate.

[0139] This step can be referred to step 303 above, and will not be repeated here.

[0140] Step 705: Determine the second feature point information corresponding to the first contour line based on the second point coordinate set and preset constraint information.

[0141] For a detailed explanation of the second feature point information, please refer to the relevant description in step 304 above.

[0142] In one possible implementation, this step may include: extracting the point coordinates corresponding to the first contour line from the second set of point coordinates; fitting the extracted point coordinates corresponding to the first contour line from the second set of point coordinates according to preset constraint information to obtain a second expression; and determining the coordinate set of a preset number of feature points on the first contour line in the reference sensor coordinate system based on the second expression. The specific process of this implementation can be referred to in step 703 above, which describes the extraction of the point coordinates corresponding to the first contour line from the first set of point coordinates and the relevant description of obtaining the first expression for the first contour line, which will not be repeated here. Thus, based on the extracted point coordinates corresponding to the first contour line from the second set of point coordinates and the preset constraint information corresponding to the first contour line, the calibration device can fit a second expression that accurately represents the actual shape of the first contour line; and then, based on this second expression, the coordinate set of a preset number of feature points on the first contour line in the reference sensor coordinate system can be obtained more accurately.

[0143] In one possible implementation, the calibration device can extract the point coordinates corresponding to each contour line detected by the sensor to be calibrated and the reference sensor on the target calibration plate; fit the extracted point coordinates corresponding to each contour line according to the preset constraint information corresponding to each contour line to obtain the expression of each contour line; and determine the coordinate set of a preset number of feature points on each contour line in the coordinate system of the reference sensor according to the expression of each contour line. The specific process of this implementation can be referred to the relevant description in step 703 above, and will not be repeated here.

[0144] It should be noted that steps 704-705 can also be performed before steps 702-703 above, and there is no limitation on this.

[0145] Step 706: Based on the first feature point information and the second feature point information, calibrate the extrinsic parameters of the sensor to be calibrated.

[0146] This step can be referred to as step 305 above, and will not be repeated here.

[0147] In this embodiment, the first contour line is used as a preset shape and the preset constraint information corresponding to the first contour line is used as constraints. The first feature point information corresponding to the first contour line can be more accurately determined based on the set of first point coordinates corresponding to the target calibration plate collected by the sensor to be calibrated. The second feature point information corresponding to the first contour line can be more accurately determined based on the set of second point coordinates corresponding to the target calibration plate collected by the reference sensor. This achieves full utilization of the contour features of the target calibration plate for extrinsic parameter calibration, further improving the calibration accuracy.

[0148] Based on the same inventive concept as the above method embodiments, embodiments of this application also provide a calibration device for executing the technical solutions described in the above method embodiments. For example, the above... Figure 3 or Figure 7 The steps of the method shown are as follows.

[0149] Figure 9 This diagram shows a structural diagram of a calibration device according to an embodiment of the present application, such as... Figure 9As shown, the calibration device may include: an acquisition module 901, configured to acquire a first set of point coordinates corresponding to a target calibration plate, the first set of point coordinates including the coordinates of at least one point on the target calibration plate in the coordinate system of the sensor to be calibrated; at least one contour line of the target calibration plate is a preset shape; a processing module 902, configured to determine first feature point information corresponding to the first contour line based on the first set of point coordinates, the first contour line being any one of the at least one contour lines; the acquisition module 901 is further configured to: acquire a second set of point coordinates corresponding to the target calibration plate, the second set of point coordinates including the coordinates of at least one point on the target calibration plate in the coordinate system of a reference sensor; the processing module 902 is further configured to: determine second feature point information corresponding to the first contour line based on the second set of point coordinates; calibrate the extrinsic parameters of the sensor to be calibrated based on the first feature point information and the second feature point information; the extrinsic parameters include parameters representing the relative pose relationship between the sensor to be calibrated and the reference sensor.

[0150] Based on the above technical solution, the first contour line is a preset shape. The first feature point information corresponding to the first contour line can be quickly and accurately determined according to the first point coordinate set corresponding to the target calibration plate collected by the sensor to be calibrated. The second feature point information corresponding to the first contour line can be quickly and accurately determined according to the second point coordinate set corresponding to the target calibration plate collected by the reference sensor. Based on the first feature point information and the second feature point information, the extrinsic parameters of the sensor to be calibrated are calibrated. Thus, the extrinsic parameter calibration is achieved by using the contour features of the target calibration plate, which improves the calibration efficiency and accuracy.

[0151] In one possible implementation, the acquisition module 901 is further configured to: acquire preset constraint information corresponding to the first contour line, the preset constraint information including: length information of the first contour line, and / or, the relative positional relationship between the first contour line and other contour lines in the target calibration plate; the processing module 902 is further configured to: determine the first feature point information based on the first point coordinate set and the preset constraint information; and / or, determine the second feature point information based on the second point coordinate set and the preset constraint information.

[0152] In one possible implementation, the processing module 902 is further configured to: calibrate the extrinsic parameters of the sensor to be calibrated by registering the first feature point information with the second feature point information.

[0153] In one possible implementation, the first feature point information includes: a set of coordinates of a predetermined number of feature points on the first contour line in the coordinate system of the sensor to be calibrated; the second feature point information includes: a set of coordinates of a predetermined number of feature points on the first contour line in the coordinate system of the reference sensor; the processing module 902 is further configured to: extract the point coordinates corresponding to the first contour line from the first point coordinate set; fit the extracted point coordinates corresponding to the first contour line in the first point coordinate set to obtain a first expression of the first contour line; determine the set of coordinates of the predetermined number of feature points on the first contour line in the coordinate system of the sensor to be calibrated according to the first expression; extract the set of point coordinates corresponding to the first contour line from the second point coordinate set; fit the extracted point coordinates corresponding to the first contour line in the second point coordinate set to obtain a second expression of the first contour line; and determine the set of coordinates of the predetermined number of feature points on the first contour line in the reference sensor coordinate system according to the second expression.

[0154] In one possible implementation, the processing module 902 is further configured to: obtain preset constraint information corresponding to the first contour line; fit the point coordinates corresponding to the first contour line in the extracted first point coordinate set according to the preset constraint information to obtain the first expression; and / or, obtain preset constraint information corresponding to the first contour line; fit the point coordinates corresponding to the first contour line in the extracted second point coordinate set according to the preset constraint information to obtain the second expression.

[0155] In one possible implementation, the acquisition module 901 is further configured to: acquire first data collected by the sensor to be calibrated; the first data includes coordinates of multiple points in the coordinate system of the sensor to be calibrated; extract the first set of point coordinates from the first data according to a preset distance between the sensor to be calibrated and the target calibration plate; and / or acquire second data collected by the reference sensor; the second data includes coordinates of multiple points in the coordinate system of the reference sensor; extract the second set of point coordinates from the second data according to a preset distance between the reference sensor and the target calibration plate.

[0156] In one possible implementation, the preset shape is a straight line.

[0157] The above Figure 9 The technical effects and specific descriptions of the calibration device and its various possible implementations can be found in the calibration method described above, and will not be repeated here.

[0158] It should be understood that the division of modules in the above device is only a logical functional division. In actual implementation, they can be fully or partially integrated into a single physical entity, or they can be physically separated. Furthermore, the modules in the device can be implemented by a processor calling software; for example, the device includes a processor connected to a memory containing instructions. The processor calls the instructions stored in the memory to implement any of the above methods or to implement the functions of each module in the device. The processor can be, for example, a general-purpose processor, such as a Central Processing Unit (CPU) or a microprocessor, and the memory can be internal or external to the device. Alternatively, the modules in the device can be implemented as hardware circuits. The functionality of some or all modules can be achieved through the design of these hardware circuits, which can be understood as one or more processors. For example, in one implementation, the hardware circuit is an application-specific integrated circuit (ASIC). The functionality of some or all of the modules is achieved through the design of the logical relationships between the components within the circuit. In another implementation, the hardware circuit can be implemented using a programmable logic device (PLD). Taking a field-programmable gate array (FPGA) as an example, it can include a large number of logic gates. The connection relationships between these logic gates are configured through configuration files, thereby achieving the functionality of some or all of the modules. All modules of the above device can be implemented entirely through processor-invoked software, entirely through hardware circuits, or partially through processor-invoked software with the remaining parts implemented through hardware circuits.

[0159] In this application embodiment, a processor is a circuit with signal processing capabilities. In one implementation, the processor can be a circuit with instruction read and execute capabilities, such as a CPU, microprocessor, graphics processing unit (GPU) (which can be understood as a type of microprocessor), or digital signal processor (DSP). In another implementation, the processor can implement certain functions through the logical relationships of hardware circuits. These logical relationships of hardware circuits are fixed or reconfigurable. For example, the processor is a hardware circuit implemented by an ASIC or PLD, such as an FPGA. In a reconfigurable hardware circuit, the process of the processor loading a configuration document and configuring the hardware circuit can be understood as the process of the processor loading instructions to implement the functions of some or all of the above modules.

[0160] As can be seen, each module in the above device can be one or more processors (or processing circuits) configured to implement the above methods, such as: CPU, GPU, microprocessor, DSP, ASIC, FPGA, or a combination of at least two of these processor forms.

[0161] Furthermore, the modules in the above devices can be integrated in whole or in part, or they can be implemented independently. In one implementation, these modules are integrated together and implemented in the form of a System-on-Chip (SoC). The SoC may include at least one processor for implementing any of the above methods or implementing the functions of the modules of the device. The at least one processor may be of different types, such as CPU and FPGA, CPU and artificial intelligence processor, CPU and GPU, etc.

[0162] Embodiments of this application also provide a calibration apparatus, including: a processor; a memory for storing processor-executable instructions; wherein the processor is configured to implement the method of the above embodiments when executing the instructions. Exemplarily, the above can be implemented. Figure 3 or Figure 7 The steps of the method shown are as follows.

[0163] Figure 10 This diagram illustrates the structure of a calibration device according to an embodiment of the present application, as shown below. Figure 10 As shown, the calibration device may include at least one processor 1001, a communication line 1002, a memory 1003, and at least one communication interface 1004.

[0164] The processor 1001 may be a general-purpose central processing unit (CPU), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits used to control the execution of the program of the present application.

[0165] The communication line 1002 may include a path for transmitting information between the aforementioned components.

[0166] Communication interface 1004 uses any transceiver-like device for communicating with other devices or communication networks, such as Ethernet, RAN, wireless local area networks (WLAN), etc.

[0167] The memory 1003 may be a read-only memory (ROM) or other type of static storage device capable of storing static information and instructions, random access memory (RAM) or other type of dynamic storage device capable of storing information and instructions, or it may be an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but is not limited thereto. The memory may exist independently and be connected to the processor via communication line 1002. The memory may also be integrated with the processor. The memory provided in the embodiments of this application may generally be non-volatile. The memory 1003 is used to store computer execution instructions for executing the scheme of this application and is controlled by the processor 1001 for execution. The processor 1001 is used to execute computer execution instructions stored in the memory 1003, thereby implementing the method provided in the above embodiments of this application. Exemplarily, the above can be implemented... Figure 3 or Figure 7 The steps of the method shown are as follows.

[0168] Optionally, the computer execution instructions in the embodiments of this application may also be referred to as application code, and the embodiments of this application do not specifically limit this.

[0169] For example, processor 1001 may include one or more CPUs, such as Figure 10 CPU0 and CPU1 in the CPU.

[0170] For example, the calibration device may include multiple processors, such as Figure 10 Processors 1001 and 1007 are mentioned. Each of these processors can be a single-core (single-CPU) processor or a multi-core (multi-CPU) processor. A processor here can refer to one or more devices, circuits, and / or processing cores used to process data (e.g., computer program instructions).

[0171] In a specific implementation, as one embodiment, the calibration device may further include an output device 1005 and an input device 1006. The output device 1005 communicates with the processor 1001 and can display information in various ways. For example, the output device 1005 may be a liquid crystal display (LCD), a light-emitting diode (LED) display device, a cathode ray tube (CRT) display device, or a projector, etc. The input device 1006 communicates with the processor 1001 and can receive user input in various ways. For example, the input device 1006 may be a mouse, keyboard, touchscreen device, or sensing device, etc.

[0172] As an example, combined Figure 10 The calibration device shown above Figure 9 The acquisition module 901 in the middle can be obtained by Figure 10 This is implemented through the communication interface 1004; the above Figure 9 The processing module 902 in the middle can be made by Figure 10 It is implemented using processor 1001.

[0173] Embodiments of this application provide a computer-readable storage medium storing computer program instructions thereon, which, when executed by a processor, implement the methods described in the above embodiments. Exemplarily, it can implement... Figure 3 or Figure 7 The steps of the method shown are as follows.

[0174] Embodiments of this application provide a computer program product, which may include, for example, computer-readable code or a non-volatile computer-readable storage medium carrying computer-readable code; when the computer program product is run on a computer, the computer performs the methods described in the above embodiments. Exemplarily, the above... Figure 3 or Figure 7 The steps of the method shown are as follows.

[0175] Computer-readable storage media can be tangible devices capable of holding and storing instructions for use by an instruction execution device. Computer-readable storage media can be, for example—but not limited to—electrical storage devices, magnetic storage devices, optical storage devices, electromagnetic storage devices, semiconductor storage devices, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of computer-readable storage media include: portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), electrically programmable read-only memory (EPROM or flash memory), static random access memory (SRAM), compact disc read-only memory (CD-ROM), digital video disc (DVD), memory sticks, floppy disks, mechanical encoding devices, such as punch cards or recessed protrusions storing instructions thereon, and any suitable combination of the foregoing.

[0176] The computer-readable program instructions or code described herein can be downloaded from computer-readable storage media to various computing / processing devices, or downloaded via a network, such as the Internet, local area network, wide area network, and / or wireless network, to an external computer or external storage device. The network may include copper transmission cables, fiber optic transmission, wireless transmission, routers, firewalls, switches, gateway computers, and / or edge servers. A network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards them to the computer-readable storage media in the respective computing / processing device.

[0177] The computer program instructions used to perform the operations of this application may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, status setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Smalltalk, C++, etc., and conventional procedural programming languages ​​such as "C" or similar languages. The computer-readable program instructions may be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer may be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or may be connected to an external computer (e.g., via the Internet using an Internet service provider). In some embodiments, electronic circuits, such as programmable logic circuits, field-programmable gate arrays (FPGAs), or programmable logic arrays (PLAs), are personalized by utilizing state information from computer-readable program instructions. These electronic circuits can execute computer-readable program instructions to implement various aspects of this application.

[0178] Various aspects of this application are described herein with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer-readable program instructions.

[0179] These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine such that, when executed by the processor of the computer or other programmable data processing apparatus, they create means for implementing the functions / actions specified in one or more blocks of the flowchart and / or block diagram. These computer-readable program instructions can also be stored in a computer-readable storage medium that causes a computer, programmable data processing apparatus, and / or other device to operate in a particular manner; thus, the computer-readable medium storing the instructions comprises an article of manufacture that includes instructions for implementing aspects of the functions / actions specified in one or more blocks of the flowchart and / or block diagram.

[0180] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other device to perform the functions / actions specified in one or more boxes of a flowchart and / or block diagram.

[0181] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of apparatus, systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of an instruction containing one or more executable instructions for implementing a specified logical function. In some alternative implementations, the functions marked in the blocks may occur in a different order than those shown in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved.

[0182] It should also be noted that each block in the block diagram and / or flowchart, as well as combinations of blocks in the block diagram and / or flowchart, can be implemented using hardware (such as circuits or ASICs (Application Specific Integrated Circuits)) that performs the corresponding function or action, or using a combination of hardware and software, such as firmware.

[0183] Although the invention has been described herein in conjunction with various embodiments, those skilled in the art will understand and implement other variations of the disclosed embodiments by reviewing the accompanying drawings, disclosure, and appended claims in carrying out the claimed invention. In the claims, the word "comprising" does not exclude other components or steps, and "a" or "an" does not exclude a plurality. A single processor or other unit can implement several functions listed in the claims. While different dependent claims may recite certain measures, this does not mean that these measures cannot be combined to produce good results.

[0184] In the various embodiments of this application, unless otherwise specified or in case of logical conflict, the terminology and / or descriptions between the various embodiments are consistent and can be referenced by each other. Technical features in different embodiments can be combined to form new embodiments according to their inherent logical relationships.

[0185] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

[0186] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A calibration method, characterized in that, The method includes: Obtain the first set of coordinates corresponding to the target calibration board, the first set of coordinates includes the coordinates of at least one point on the target calibration board in the coordinate system of the sensor to be calibrated; at least one contour line of the target calibration board is a preset shape; the first contour line is any one of the at least one contour lines; Obtain the preset constraint information corresponding to the first contour line; Based on the first set of point coordinates and the preset constraint information, determine the first feature point information corresponding to the first contour line; Obtain the second set of coordinates corresponding to the target calibration board, wherein the second set of coordinates includes the coordinates of at least one point on the target calibration board in the reference sensor coordinate system; Based on the second set of point coordinates and the preset constraint information, determine the second feature point information corresponding to the first contour line; The extrinsic parameters of the sensor to be calibrated are calibrated based on the first feature point information and the second feature point information; the extrinsic parameters include parameters representing the relative pose relationship between the sensor to be calibrated and the reference sensor.

2. The method according to claim 1, characterized in that, The preset constraint information includes: the length information of the first contour line, and / or the relative positional relationship between the first contour line and other contour lines in the target calibration plate.

3. The method according to claim 1 or 2, characterized in that, The step of calibrating the extrinsic parameters of the sensor to be calibrated based on the first feature point information and the second feature point information includes: The extrinsic parameters of the sensor to be calibrated are calibrated by registering the first feature point information with the second feature point information.

4. The method according to any one of claims 1-3, characterized in that, The first feature point information includes: a set of coordinates of a predetermined number of feature points on the first contour line in the coordinate system of the sensor to be calibrated; the second feature point information includes: a set of coordinates of a predetermined number of feature points on the first contour line in the coordinate system of the reference sensor. The step of determining the first feature point information corresponding to the first contour line based on the first set of point coordinates includes: Extract the coordinates of the points corresponding to the first contour line from the first set of point coordinates; Fit the coordinates of the points corresponding to the first contour line in the extracted first set of point coordinates to obtain the first expression of the first contour line; Based on the first expression, determine the set of coordinates of a preset number of feature points on the first contour line in the coordinate system of the sensor to be calibrated; The step of determining the second feature point information corresponding to the first contour line based on the second set of point coordinates includes: Extract the set of point coordinates corresponding to the first contour line from the second set of point coordinates; Fit the coordinates of the points corresponding to the first contour line in the extracted second set of point coordinates to obtain a second expression for the first contour line; Based on the second expression, determine the set of coordinates of a preset number of feature points on the first contour line in the reference sensor coordinate system.

5. The method according to claim 4, characterized in that, The step of fitting the coordinates of the points corresponding to the first contour line in the extracted set of first point coordinates to obtain the first expression of the first contour line includes: Obtain the preset constraint information corresponding to the first contour line; Based on the preset constraint information, the coordinates of the points corresponding to the first contour line in the extracted first set of point coordinates are fitted to obtain the first expression; And / or, The step of fitting the coordinates of the points corresponding to the first contour line in the extracted second set of point coordinates to obtain a second expression for the first contour line includes: Obtain the preset constraint information corresponding to the first contour line; Based on the preset constraint information, the coordinates of the points corresponding to the first contour line in the extracted second set of point coordinates are fitted to obtain the second expression.

6. The method according to any one of claims 1-5, characterized in that, The acquisition of the first set of coordinates corresponding to the target calibration board includes: Acquire the first data collected by the sensor to be calibrated; the first data includes the coordinates of multiple points in the coordinate system of the sensor to be calibrated; Based on the preset distance between the sensor to be calibrated and the target calibration plate, the first point coordinate set is extracted from the first data; And / or, The step of obtaining the set of coordinates of the second point corresponding to the target calibration board includes: Acquire second data collected by the reference sensor; the second data includes the coordinates of multiple points in the coordinate system of the reference sensor. Based on the preset distance between the reference sensor and the target calibration plate, the second set of point coordinates is extracted from the second data.

7. The method according to any one of claims 1-6, characterized in that, The preset shape is a straight line.

8. A calibration device, characterized in that, The device includes: The acquisition module is used to acquire a first set of coordinates corresponding to the target calibration board. The first set of coordinates includes the coordinates of at least one point on the target calibration board in the coordinate system of the sensor to be calibrated. At least one contour line of the target calibration board is a preset shape. The first contour line is any one of the at least one contour lines. The acquisition module is further configured to acquire preset constraint information corresponding to the first contour line; The processing module is used to determine the first feature point information corresponding to the first contour line based on the first point coordinate set and the preset constraint information. The acquisition module is further configured to: acquire a second set of coordinates corresponding to the target calibration board, wherein the second set of coordinates includes the coordinates of at least one point on the target calibration board in the reference sensor coordinate system; The processing module is further configured to determine the second feature point information corresponding to the first contour line based on the second set of point coordinates and the preset constraint information; and to calibrate the extrinsic parameters of the sensor to be calibrated based on the first feature point information and the second feature point information; the extrinsic parameters include parameters representing the relative pose relationship between the sensor to be calibrated and the reference sensor.

9. The apparatus according to claim 8, characterized in that, The preset constraint information includes: the length information of the first contour line, and / or the relative positional relationship between the first contour line and other contour lines in the target calibration plate.

10. The apparatus according to claim 8 or 9, characterized in that, The processing module is further configured to: calibrate the extrinsic parameters of the sensor to be calibrated by registering the first feature point information with the second feature point information.

11. The apparatus according to any one of claims 8-10, characterized in that, The first feature point information includes: a set of coordinates of a predetermined number of feature points on the first contour line in the coordinate system of the sensor to be calibrated; the second feature point information includes: a set of coordinates of a predetermined number of feature points on the first contour line in the coordinate system of the reference sensor. The processing module is further configured to: extract the point coordinates corresponding to the first contour line from the first set of point coordinates; fit the extracted point coordinates corresponding to the first contour line from the first set of point coordinates to obtain a first expression for the first contour line; determine the coordinate set of a preset number of feature points on the first contour line in the coordinate system of the sensor to be calibrated based on the first expression; extract the point coordinate set corresponding to the first contour line from the second set of point coordinates; fit the extracted point coordinates corresponding to the first contour line from the second set of point coordinates to obtain a second expression for the first contour line; and determine the coordinate set of a preset number of feature points on the first contour line in the reference sensor coordinate system based on the second expression.

12. The apparatus according to claim 11, characterized in that, The processing module is further configured to: obtain preset constraint information corresponding to the first contour line; fit the point coordinates corresponding to the first contour line in the extracted first point coordinate set according to the preset constraint information to obtain the first expression; and / or, obtain preset constraint information corresponding to the first contour line; fit the point coordinates corresponding to the first contour line in the extracted second point coordinate set according to the preset constraint information to obtain the second expression.

13. The apparatus according to any one of claims 8-12, characterized in that, The acquisition module is further configured to: acquire first data collected by the sensor to be calibrated; the first data includes the coordinates of multiple points in the coordinate system of the sensor to be calibrated; extract the first set of point coordinates from the first data according to a preset distance between the sensor to be calibrated and the target calibration plate; and / or acquire second data collected by the reference sensor; the second data includes the coordinates of multiple points in the coordinate system of the reference sensor; extract the second set of point coordinates from the second data according to a preset distance between the reference sensor and the target calibration plate.

14. The apparatus according to any one of claims 8-13, characterized in that, The preset shape is a straight line.

15. A calibration device, characterized in that, include: processor; Memory used to store processor-executable instructions; The processor is configured to implement the method of any one of claims 1-7 when executing the instructions.

16. A computer-readable storage medium having computer program instructions stored thereon, characterized in that, When the computer program instructions are executed by the processor, they implement the method described in any one of claims 1-7.

17. A computer program product containing instructions, characterized in that, When it is run on a computer, it causes the computer to perform the method as described in any one of claims 1-7.

Images