WO2023150961A1 - 一种标定方法及装置 - Google Patents

一种标定方法及装置 Download PDF

Info

Publication number
WO2023150961A1
WO2023150961A1 PCT/CN2022/075813 CN2022075813W WO2023150961A1 WO 2023150961 A1 WO2023150961 A1 WO 2023150961A1 CN 2022075813 W CN2022075813 W CN 2022075813W WO 2023150961 A1 WO2023150961 A1 WO 2023150961A1
Authority
WO
WIPO (PCT)
Prior art keywords
contour line
point
sensor
coordinate set
calibrated
Prior art date
Application number
PCT/CN2022/075813
Other languages
English (en)
French (fr)
Inventor
毕舒展
凌璐祥
Original Assignee
华为技术有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 华为技术有限公司 filed Critical 华为技术有限公司
Priority to CN202280006244.3A priority Critical patent/CN116897300A/zh
Priority to PCT/CN2022/075813 priority patent/WO2023150961A1/zh
Publication of WO2023150961A1 publication Critical patent/WO2023150961A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S7/00—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00
    • G01S7/02—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00
    • G01S7/40—Means for monitoring or calibrating

Definitions

  • the present application relates to the technical field of automatic driving, and in particular to a calibration method and device.
  • the perception module is an important part.
  • the point cloud data collected by the lidar is one of the inputs of the perception module.
  • the lidar can scan the surrounding environment of the vehicle and output point cloud data. There is a certain blind area when using a single lidar, and the density of point clouds at different distances is different, which may affect Therefore, the point cloud data collected by multiple lidars distributed in different positions of the vehicle can be fused to improve the performance of the perception module.
  • an embodiment of the present application provides a calibration method, the method comprising: obtaining a first point coordinate set corresponding to the target calibration plate, the first point coordinate set including at least one point on the target calibration plate Coordinates in the coordinate system of the sensor to be calibrated; at least one contour line of the target calibration plate is a preset shape; according to the first point coordinate set, determine the first feature point information corresponding to the first contour line, the first The contour line is any contour line in the at least one contour line; the second point coordinate set corresponding to the target calibration plate is obtained, and the second point coordinate set includes at least one point on the target calibration plate in the reference sensor coordinate system The coordinates below; according to the second point coordinate set, determine the second feature point information corresponding to the first contour line; according to the first feature point information and the second feature point information, the to-be-calibrated The external parameters of the sensor are calibrated; the external parameters include parameters representing the relative pose relationship between the sensor to be calibrated and the reference sensor.
  • 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 point coordinate set corresponding to the target calibration plate collected by the sensor can quickly and accurately determine the second feature point information corresponding to the first contour line, and according to the first feature point information and the second feature point information, the outer surface of the sensor to be calibrated
  • the external parameters are calibrated by using the contour features of the target calibration board, which improves the calibration efficiency and accuracy.
  • the method further includes: acquiring preset constraint information corresponding to the first contour line, where the preset constraint information includes: the 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; according to the first point coordinate set, determine the The first feature point information corresponding to the first contour line includes: determining the first feature point information according to the first point coordinate set and the preset constraint information; and/or, according to the second The point coordinate set, and determining the second feature point information corresponding to the first contour line includes: determining the second feature point information according to the second point coordinate set and the preset constraint information.
  • the first point coordinate set corresponding to the target calibration plate collected by the sensor to be calibrated can be determined more accurately
  • the first feature point information corresponding to the first contour line can more accurately determine the second feature point information corresponding to the first contour line according to the second point coordinate set corresponding to the target calibration plate collected by the reference sensor, so as to realize the full use of the target
  • the contour features of the calibration plate are calibrated with external parameters, which further improves the calibration accuracy.
  • calibrating the extrinsic parameters of the sensor to be calibrated including: calibrating the extrinsic parameters of the sensor to be calibrated by registering the first feature point information with the second feature point information.
  • registration is performed through the feature point information corresponding to the first contour detected by the sensor to be calibrated and the reference sensor, so as to quickly and accurately realize the automatic calibration of the external parameters of the sensor to be calibrated.
  • the first feature point information includes: Set the coordinate set of the number of feature points in the coordinate system of the sensor to be calibrated; the second feature point information includes: the coordinate set of the preset number of feature points on the first contour line in the coordinate system of the reference sensor;
  • the determining the first feature point information corresponding to the first contour line according to the first point coordinate set includes: extracting the point coordinates corresponding to the first contour line in the first point coordinate set; 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; according to the first expression, determine the first A set of coordinates of a preset number of feature points on the contour line in the coordinate system of the sensor to be calibrated; the determination of the second feature point information corresponding to the first contour line according to the second point coordinate set includes: extracting A point coordinate set corresponding to the first contour line in the second point coordinate set; fitting
  • the first contour line is a preset shape, that is, the first contour line can be expressed by a specific expression; on the basis of extracting the point coordinates corresponding to the first contour line in the first point coordinate set, it can be fitted to obtain The first expression that can accurately represent the actual shape of the first contour line; according to the first expression, the coordinate set of the preset number of feature points on the first contour line in the coordinate system of the sensor to be calibrated can be accurately obtained; Based on the point coordinates corresponding to the first contour line in the two-point coordinate set, the second expression that can accurately represent the actual shape of the first contour line can be obtained by fitting; according to the second expression, the first contour line can be accurately obtained A set of coordinates of the preset number of feature points in the reference sensor coordinate system, thereby effectively improving the accuracy of external parameter calibration of the sensor to be calibrated.
  • the first contour line corresponding to the extracted first point coordinate set Fitting the point coordinates of the first contour line to obtain the first expression of the first contour line including: obtaining the preset constraint information corresponding to the first contour line; according to the preset constraint information, the extracted Fitting the point coordinates corresponding to the first contour line in the first point coordinate set to obtain the first expression; and/or, the pair of the extracted second point coordinate set in the first Fitting the point coordinates corresponding to the contour line to obtain the second expression of the first contour line includes: obtaining the preset constraint information corresponding to the first contour line; according to the preset constraint information, the extracted Fitting the point coordinates corresponding to the first contour line in the second point coordinate set to obtain the second expression.
  • the calibration device extracts the first point On the basis of the point coordinates corresponding to the first contour line in the coordinate set, and based on the preset constraint information corresponding to the first contour line, a first expression that can accurately represent the actual shape of the first contour line can be obtained by fitting; and/or, it can be Fitting results in a second expression that can accurately represent the actual shape of the first contour line.
  • the acquiring the first point coordinate set corresponding to the target calibration board includes: acquiring The first data collected by the sensor to be calibrated; the first data includes the coordinates of a plurality of points in the coordinate system of the sensor to be calibrated; according to the preset distance between the sensor to be calibrated and the target calibration plate , extracting the first point coordinate set from the first data; and/or, the acquiring the second point coordinate set corresponding to the target calibration plate includes: acquiring second data collected by the reference sensor; The second data includes coordinates of a plurality of points in the reference sensor coordinate system; according to the preset distance between the reference sensor and the target calibration plate, the second data is extracted from the second data. A collection of point coordinates.
  • the coordinates of the points on the target calibration plate in the coordinate system of the sensor to be calibrated are 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 plate, in the data collected by the reference sensor, the coordinates of the points on the target calibration plate in the reference sensor coordinate system are quickly and accurately extracted, so that the While ensuring the calibration accuracy, the calibration efficiency is improved.
  • the preset shape is a straight line.
  • the shape of the first contour line is a straight line, and the features of the straight line are easier to express.
  • the first expression and the second expression can be obtained by fitting more accurately and quickly, thereby improving the calibration accuracy and efficiency; as
  • the straight line feature of the first contour line and the preset constraint relationship corresponding to the first contour line are used as stronger constraints, so that the first expression and the second expression can be fitted more accurately; as another For example, using the feature point information corresponding to the same line detected by the sensor to be calibrated and the reference sensor for registration is easier to converge, so that the automatic calibration of the external parameters of the sensor to be calibrated can be realized more quickly and accurately.
  • an embodiment of the present application provides a calibration device, the device comprising: an acquisition module, configured to acquire a first point coordinate set corresponding to a target calibration plate, the first point coordinate set including the target calibration plate The coordinates of at least one point on the board under the coordinate system of the sensor to be calibrated; at least one contour line of the target calibration board is a preset shape; the processing module is used to determine the corresponding position of the first contour line according to the set of coordinates of the first point The first feature point information, the first contour line is any contour line in the at least one contour line; the acquisition module is also used to: acquire the second point coordinate set corresponding to the target calibration plate, the The second point coordinate set 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 first contour line corresponding to the second point coordinate set according to the second point coordinate set Two feature point information; according to the first feature point information and the second feature point information, calibrate the external parameters of the sensor to be calibrated; the external parameters
  • 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 point coordinate set corresponding to the target calibration plate collected by the sensor can quickly and accurately determine the second feature point information corresponding to the first contour line, and according to the first feature point information and the second feature point information, the outer surface of the sensor to be calibrated
  • the external parameters are calibrated by using the contour features of the target calibration board, which improves the calibration efficiency and accuracy.
  • the acquiring module is further configured to: acquire preset constraint information corresponding to the first contour line, the preset constraint information Including: 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; the processing module is further configured to: according to the The first point coordinate set and the preset constraint information, determine the first feature point information; and/or, according to the second point coordinate set and the preset constraint information, determine the second feature point information.
  • the first point coordinate set corresponding to the target calibration plate collected by the sensor to be calibrated can be determined more accurately
  • the first feature point information corresponding to the first contour line can more accurately determine the second feature point information corresponding to the first contour line according to the second point coordinate set corresponding to the target calibration plate collected by the reference sensor, so as to realize the full use of the target
  • the contour features of the calibration plate are calibrated with external parameters, which further improves the calibration accuracy.
  • the processing module is further configured to: use the first feature point The information is registered with the second feature point information, and the extrinsic parameters of the sensor to be calibrated are calibrated.
  • registration is performed through the feature point information corresponding to the first contour detected by the sensor to be calibrated and the reference sensor, so as to quickly and accurately realize the automatic calibration of the external parameters of the sensor to be calibrated.
  • the first feature point information includes: Set the coordinate set of the number of feature points in the coordinate system of the sensor to be calibrated; the second feature point information includes: the coordinate set of the 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; and the point corresponding to the first contour line in the extracted first point coordinate set Coordinates are fitted to obtain a first expression of the first contour line; according to the first expression, determine the coordinates of a preset number of feature points on the first contour line in the coordinate system of the sensor to be calibrated Set; extract the point coordinate set corresponding to the first contour line in the second point coordinate set; fit 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; according to the second expression, determine a set of coordinates of a preset
  • the first contour line is a preset shape, that is, the first contour line can be expressed by a specific expression; on the basis of extracting the point coordinates corresponding to the first contour line in the first point coordinate set, it can be fitted to obtain The first expression that can accurately represent the actual shape of the first contour line; according to the first expression, the coordinate set of the preset number of feature points on the first contour line in the coordinate system of the sensor to be calibrated can be accurately obtained; Based on the point coordinates corresponding to the first contour line in the two-point coordinate set, the second expression that can accurately represent the actual shape of the first contour line can be obtained by fitting; according to the second expression, the first contour line can be accurately obtained A set of coordinates of the preset number of feature points in the reference sensor coordinate system, thereby effectively improving the accuracy of external parameter calibration of the sensor to be calibrated.
  • the processing module is further configured to: acquire a preset constraint corresponding to the first contour line information; according to the preset constraint information, fitting the point coordinates corresponding to the first contour line in the extracted first point coordinate set to obtain the first expression; and/or, obtaining the The preset constraint information corresponding to the first contour line; according to the preset constraint information, fitting the point coordinates corresponding to the first contour line in the extracted second point coordinate set to obtain the first contour line Two expressions.
  • the calibration device extracts the first point On the basis of the point coordinates corresponding to the first contour line in the coordinate set, and based on the preset constraint information corresponding to the first contour line, a first expression that can accurately represent the actual shape of the first contour line can be obtained by fitting; and/or, it can be Fitting results in a second expression that can accurately represent the actual shape of the first contour line.
  • the acquisition module is further configured to: acquire the data collected by the sensor to be calibrated First data; the first data includes the coordinates of a plurality of points in the coordinate system of the sensor to be calibrated; according to the preset distance between the sensor to be calibrated and the target calibration plate, in the first data Extract the first point coordinate set; and/or, acquire the second data collected by the reference sensor; the second data includes the coordinates of a plurality of points in the reference sensor coordinate system; according to the reference sensor The preset distance between the target calibration board and the second point coordinate set is extracted from the second data.
  • the coordinates of the points on the target calibration plate in the coordinate system of the sensor to be calibrated are 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 plate, in the data collected by the reference sensor, the coordinates of the points on the target calibration plate in the reference sensor coordinate system are quickly and accurately extracted, so that the While ensuring the calibration accuracy, the calibration efficiency is improved.
  • the preset shape is a straight line.
  • the shape of the first contour line is a straight line, and the features of the straight line are easier to express.
  • the first expression and the second expression can be obtained by fitting more accurately and quickly, thereby improving the calibration accuracy and efficiency; as in 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, so that the first expression and the second expression can be accurately fitted; as another example , use the feature point information corresponding to the same line detected by the sensor to be calibrated and the reference sensor to perform registration, which is easier to converge, so that the automatic calibration of the external parameters of the sensor to be calibrated can be realized more quickly and accurately.
  • an embodiment of the present application provides a calibration device, including: a processor; a memory for storing processor-executable instructions; wherein, the processor is configured to implement the above-mentioned first Aspect or one or more calibration methods of the first aspect.
  • the embodiments of the present application provide a computer-readable storage medium, on which computer program instructions are stored, wherein, when the computer program instructions are executed by a processor, the first aspect or the first aspect are implemented.
  • One or several calibration methods are provided.
  • the embodiments of the present application provide a computer program product.
  • the computer program product When the computer program product is run on a computer, it enables the computer to perform the above-mentioned first aspect or one or more calibrations of the first aspect. method.
  • FIG. 1 shows a schematic diagram of a calibration scene according to an embodiment of the present application
  • FIG. 2 shows a schematic diagram of the side of the calibration plate A1 facing the vehicle C according to an embodiment of the present application
  • Fig. 3 shows a flow chart of a calibration method according to an embodiment of the present application
  • FIG. 4 shows a schematic diagram of a point cloud corresponding to the extracted calibration plate A1 according to an embodiment of the present application
  • FIG. 5 shows a schematic diagram of a contour line a1 obtained through fitting according to an embodiment of the present application
  • FIG. 6 shows a schematic diagram of external parameter calibration according to an embodiment of the present application
  • FIG. 7 shows a flow chart of a calibration method according to an embodiment of the present application.
  • FIG. 8 shows a schematic diagram of fitted contour lines according to an embodiment of the present application.
  • FIG. 9 shows a structural diagram of a calibration device according to an embodiment of the present application.
  • Fig. 10 shows a schematic structural diagram of a calibration device according to an embodiment of the present application.
  • Fig. 1 shows a schematic diagram of a calibration scene according to an embodiment of the present application.
  • the calibration scene may include: a sensor L1 , a sensor L2 , a calibration board A1 , and a vehicle C.
  • At least one contour line of the calibration plate A1 may be a preset shape.
  • the preset shape may be a straight line, a circle, or other curves that may be represented by a specific expression.
  • the side facing the vehicle C in the calibration plate A1 is located within the field of view angle of the sensor L1 and the field of view of the sensor L2, and the side of the calibration plate A1 facing the vehicle C may include at least one contour line of a preset shape, In this way, it is ensured that both the sensor L1 and the sensor L2 can collect the data of the same or multiple contour lines of the preset shape in the calibration plate A1.
  • each contour line of the side facing the vehicle C in the calibration plate A1 can be a straight line
  • the corresponding side of the calibration plate A1 facing the vehicle C can be a triangle, a rectangle, a polygon, etc.
  • the calibration plate A1 can be a cuboid
  • FIG. 2 shows a schematic diagram of the side of the calibration plate A1 facing the vehicle C according to an embodiment of the present application.
  • the rectangle formed by a3 and contour line a4, contour line a1, contour line a2, contour line a3 and contour line a4 are all straight lines, and contour line a1, contour line a2, contour line a3 and contour line a4 are all located in the field of view of sensor L1.
  • calibration board A2, calibration board A3, and calibration board A4 may also be included;
  • A3, calibration plate A4 can all comprise the contour line of preset shape, for example, one side facing vehicle C in calibration plate A2, calibration plate A3, calibration plate A4 can comprise a plurality of contour lines of preset shape, and all are located in the sensor The field of view of L1 and the field of view of sensor L2.
  • the preset shapes of different contour lines in the calibration plate A1 , the calibration plate A2 , the calibration plate A3 , and the calibration plate A4 may be the same or different, which is not limited.
  • the calibration plate A1, the calibration plate A2, the calibration plate A3, and the calibration plate A4 can be respectively placed around the vehicle C; Different orientations of vehicle C.
  • the calibration board A1, the calibration board A2, the calibration board A3 or the calibration board A4 It should be noted that, in this calibration scene, there is no limitation on the placement posture of the calibration board A1, the calibration board A2, the calibration board A3 or the calibration board A4, for example, the calibration board A1, the calibration board A2, the calibration board A3 or the calibration board A4 It can be placed perpendicular to the ground or inclined, as long as the sensor L1 and sensor L2 can collect the data of the side facing the vehicle C in the calibration board A1, calibration board A2, calibration board A3 or calibration board A4.
  • the vehicle C may be located in the middle of the calibration field, and the above-mentioned calibration boards A1 , A2 , A3 , and A4 may be placed close to the edge of the calibration field.
  • the calibration site may be a rectangular area, for example, a rectangular area with a length and a width between 10m and 50m.
  • the sensor L1 and the sensor L2 may be installed in different positions of the vehicle C.
  • the data collected by the sensor L1 and the sensor L2 can be used as the input of the perception module in the automatic driving system of the vehicle C.
  • the sensor L1 or the sensor L2 may include any one of lidar, millimeter-wave radar, or image acquisition device, etc.
  • the sensor L1 and the sensor L2 may be the same type of sensor, or may be different types of sensors, as
  • the sensor L1 can be a master laser radar installed on the vehicle C, and the sensor L2 can be a slave laser radar installed on the vehicle C; as another example, the sensor L1 can be a laser radar installed on the vehicle C, and the sensor L2 can be a slave laser radar installed on the vehicle C; L2 may be an image acquisition device installed on the vehicle C.
  • the sensor L1 and the sensor L2 are only used as an example, and more sensors may be installed on the vehicle C, which is not limited.
  • a calibration device (not shown in the figure) may also be included in the calibration scene shown in FIG.
  • One or more data in A4 the collected data includes the data of the same or multiple contour lines of preset shape, after the calibration device acquires the data collected by the sensor L1 and the sensor L2, it is implemented by executing this application
  • the calibration method provided by the example realizes the calibration of the external parameters of the sensor L1 or sensor L2.
  • the embodiment of the present application does not limit the type of the calibration device.
  • the calibration device can be the above-mentioned vehicle C, or other components with data processing functions in the vehicle C, such as: vehicle-mounted terminal, vehicle-mounted controller, vehicle-mounted module, vehicle-mounted module, vehicle-mounted component, vehicle-mounted chip, vehicle-mounted unit, on-board sensor, the vehicle can calibrate the external parameters of sensor L1 or sensor L2 through the on-board terminal, on-board controller, on-board module, on-board module, on-board component, on-board chip, on-board unit, on-board sensor, etc.
  • the calibration device may be integrated in an automatic driving system (Automated Driving System, ADS) or an advanced driver assistance system (Advanced Driver Assistant Systems, ADAS) of the vehicle C, or an on-board computing platform.
  • ADS Automatic Driving System
  • ADAS Advanced Driver Assistant Systems
  • the calibration device can also be an intelligent terminal with data processing capability other than the vehicle C, or a component or chip set in the intelligent terminal.
  • the smart terminal may be a device equipped with sensors such as smart transportation device, smart wearable device, smart home device, smart auxiliary aircraft, robot (robot) or unmanned aerial vehicle (unmanned aerial vehicle).
  • the calibration device may be a general-purpose device or a special-purpose device.
  • the device can also be a desktop computer, a portable computer, a network server, a handheld computer (personal digital assistant, PDA), a mobile phone, a tablet computer, a wireless terminal device, an embedded device or other devices with data processing functions, Or components or chips within these devices.
  • PDA personal digital assistant
  • the calibration device may also be a chip or a processor with processing functions, and the calibration device may include multiple processors.
  • the processor may be a single-core (single-CPU) processor or a multi-core (multi-CPU) processor.
  • the chip or processor with processing function can be set in the vehicle sensor, for example, it can be set in the sensor L1 or the sensor L2, or it can not be set in the vehicle sensor, but can be set at the receiving end of the output signal of the vehicle sensor.
  • Fig. 3 shows a flow chart of a calibration method according to an embodiment of the present application; Exemplarily, the method may be executed by the above-mentioned calibration device; As shown in Fig. 3, the method may include the following steps:
  • Step 301 Obtain a 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 sensor coordinate system to be calibrated.
  • At least one contour line of the target calibration plate is a preset shape.
  • 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 the preset shape; for example, the target calibration plate can be calibration plate A, calibration plate A2, calibration Any calibration plate in plate A3 or calibration plate A4.
  • the sensor to be calibrated may be any sensor in the vehicle sensor, for example, the sensor to be calibrated may be the sensor L1 or the sensor L2 shown in FIG. 1 above. It can be understood that, for the same sensor, based on different calibration tasks, it can be used as a sensor to be calibrated, or as a reference sensor (also called a reference sensor); for example, when calibrating the external parameters of the sensor L2 in Figure 1 above, Then the sensor L2 is the sensor to be calibrated, and the sensor L1 can be used as the reference sensor; when calibrating the external parameters of the sensor L1 in Figure 1 above, the sensor L1 is the sensor to be calibrated, and the sensor L2 can be used as the reference sensor.
  • a reference sensor also called a reference sensor
  • the coordinate system of the sensor to be calibrated may be a Cartesian coordinate system with the center of mass of the sensor to be calibrated as the origin.
  • the first set of point coordinates may include coordinates of all points on the target calibration board detected by the sensor to be calibrated under the coordinate system of the sensor to be calibrated.
  • the first set of point coordinates may include all points on the side of the calibration plate A1 facing the sensor L1 in the coordinate system of the sensor to be calibrated coordinate of.
  • this step may include: the calibration device may acquire the first data collected by the sensor to be calibrated; the first data includes the coordinates of a plurality of points in the coordinate system of the sensor to be calibrated; A preset distance between the calibration boards is used to extract a first set of point coordinates from the first data.
  • the preset distance between the sensor to be calibrated and the target calibration plate can be predetermined based on the position of the sensor to be calibrated and the position of the target calibration plate.
  • the first data may include coordinates of all points detected by the sensor to be calibrated in the calibration site in the coordinate system of the sensor to be calibrated.
  • the calibration device can determine the coordinate range corresponding to the target calibration plate in the coordinate system of the sensor to be calibrated according to the preset distance; and then screen out the coordinates of all points detected by the sensor to be calibrated in the coordinate system of the sensor to be calibrated Coordinates within the range, so as to obtain the first set of point coordinates.
  • the coordinates of the points on the target calibration plate in the coordinate system of the sensor to be calibrated are quickly and accurately extracted from the data collected by the sensor to be calibrated, so that While ensuring the calibration accuracy of external parameters, the calibration efficiency is improved.
  • the sensor to be calibrated is the sensor L1 in Figure 1
  • the sensor L1 is a laser radar as an example
  • the sensor L1 can emit laser beams, receive reflected signals, and determine Scan the three-dimensional coordinates of the point in the sensor L1 coordinate system to obtain the collected point cloud data.
  • the calibration device can obtain the point cloud data collected by the sensor L1.
  • the point cloud According to the preset distance between the sensor L1 and the calibration board A1, the point cloud The point cloud corresponding to the calibration plate A1 is extracted from the data, and the extracted point cloud corresponding to the calibration plate A1 can be shown in FIG. 4 .
  • Step 302 Determine first feature point information corresponding to the first contour line according to the first point coordinate set.
  • the first contour line is any one of the contour lines of the preset shape in the target calibration plate.
  • the first contour line may be any one of contour line a1, contour line a2, contour line a3 or contour line a4 in the calibration plate A1 in FIG. 2 .
  • 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 point may include the intersection point of the first contour line and other contour lines, may also include the midpoint of the first contour line, or may include several points arranged at equal intervals on the first contour line, and so on.
  • the preset number can be set according to actual needs, which is not limited, for example, the preset number can be greater than or equal to 500.
  • this step may include: extracting point coordinates corresponding to the first contour line in the first point coordinate set; Combined, the first expression of the first contour line is obtained; according to the first expression, the coordinate set of the preset number of feature points on the first contour line in the coordinate system of the sensor to be calibrated is determined.
  • the calibration device extracts the first contour in the first point coordinate set Based on the point coordinates corresponding to the line, the first expression that can accurately represent the actual shape of the first contour line can be obtained by fitting; and then according to the first expression, the preset number of feature points on the first contour line can be accurately obtained The set of coordinates in the coordinate system of the sensor to be calibrated.
  • the first contour line is located on the edge of the target calibration plate, and the point coordinates corresponding to the first contour line may include the coordinates of the point on the edge of the target calibration plate detected by the sensor to be calibrated under the coordinate system of the sensor to be calibrated .
  • 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 according to the first point coordinate set, and extract the first contour line in the first point coordinate set according to the coordinates of the center point The coordinates of the points on the edge, so as to obtain the coordinates of the points corresponding to the first contour line.
  • 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):
  • n represents the number of points in the first point coordinate set
  • xi, yi, zi represent the coordinates of the i-th point in the first point coordinate set in the sensor coordinate system to be calibrated
  • x 0 , y 0 , and z 0 represent the coordinates of the center point of the target calibration board on the side facing the sensor to be calibrated.
  • the calibration device may perform fitting on the point coordinates corresponding to the extracted first contour line to obtain a first expression of the first contour line.
  • 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, so that the first contour line can be obtained more quickly and accurately
  • the first expression of the line
  • the shape of the first contour line may be a straight line, and the straight line feature is easier to express, so that the first expression can be obtained by fitting more accurately and quickly.
  • the calibration device can obtain the fitting plane on the side of the target calibration plate facing the sensor to be calibrated, and then according to the fitting plane and The positional relationship of the first contour line and the preset shape of the first contour line are fitted to the point coordinates corresponding to the first contour line extracted from the first point coordinate set, so that the first contour line can be obtained more quickly and accurately.
  • the first expression for the contour line is located on the side of the target calibration plate facing the sensor to be calibrated.
  • the calibration device can use existing fitting techniques based on the first point coordinate set, such as random sampling consensus algorithm, least square method, principal component analysis method, singular value decomposition, etc., to obtain the orientation of the target calibration board
  • the fitting plane where one side of the sensor to be calibrated is located for example, the expression of the fitting plane can be as shown in the following formula (2):
  • A, B, C, and D are constants, and A, B, and C are not zero at the same time, and x, y, and z represent the x-axis, y-axis, and z of any point in the fitting plane in the coordinate system of the sensor to be calibrated, respectively.
  • the marking device is based on the preset shape of the first contour line, and with the first contour line located on the fitting plane as a constraint, the point coordinates corresponding to the first contour line extracted from the first point coordinate set are Fitting; for example, if the first contour line is a straight line as an example, the straight line is located on the fitting plane, so that the expression of the straight line can be accurately fitted.
  • the first contour line is a straight line as an example
  • the straight line is located on the fitting plane, so that the expression of the straight line can be accurately fitted.
  • Fig. 5 is a schematic diagram of the fitted contour line a1. As shown in Fig. 5, the fitted contour line a1 is located on the upper edge of the calibration plate A1.
  • Step 303 acquiring a 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.
  • the reference sensor can be any sensor that has a fixed pose relationship with the sensor to be calibrated.
  • the sensor L1 in FIG. 1 is selected as the sensor to be calibrated, then the sensor L2 can be the reference sensor.
  • the reference sensor coordinate system may be a Cartesian coordinate system with the center of mass of the reference sensor as the origin.
  • the second set of point coordinates may include coordinates of all points on the target calibration plate detected by the reference sensor in the reference sensor coordinate system.
  • the second set of point coordinates may include the coordinates of all points on the side of the calibration plate A1 facing the sensor L2 in the reference sensor coordinate system .
  • this step may include: acquiring second data collected by a reference sensor; the second data may include coordinates of a plurality of points in the reference sensor coordinate system; The preset distance between them is used to extract the second set of point coordinates from the second data.
  • the preset distance between the reference sensor and the target calibration plate can be predetermined based on the position of the reference sensor and the target calibration plate.
  • the first data may include coordinates of all points detected by the reference sensor in the calibration site in the reference sensor coordinate system.
  • the calibration device can determine the coordinate range corresponding to the target calibration plate in the reference sensor coordinate system according to the preset distance; and then filter out the coordinates of all points detected by the reference sensor in the reference sensor coordinate system Coordinates, so as to get the first set of point coordinates.
  • the coordinates of the points on the target calibration plate in the reference sensor coordinate system can be quickly and accurately extracted from the data collected by the reference sensor, so as to ensure accurate calibration At the same time, the calibration efficiency is improved.
  • Step 304 Determine the second feature point information corresponding to the first contour line according to the second point coordinate set.
  • the second feature point information may include: a set of coordinates of a preset number of feature points on the first contour line in the reference sensor coordinate system.
  • the second feature point information may be determined in the same manner as the first feature point information is determined in step 302 above.
  • this step may include: extracting a point coordinate set corresponding to the first contour line in the second point coordinate set; Fitting to obtain a second expression of the first contour line; according to the second expression, determine a set of coordinates of a preset number of feature points on the first contour line in the reference sensor coordinate system.
  • this step refer to the above step 302 for extracting the point coordinates corresponding to the first contour line in the first point coordinate set; and obtaining the first expression of the first contour line, which will not be repeated here.
  • the calibration device extracts the first contour in the second point coordinate set Based on the point coordinates corresponding to the line, the second expression that can accurately represent the actual shape of the first contour line can be obtained by fitting; then according to the second expression, the preset number of feature points on the first contour line can be accurately obtained A collection of coordinates in the reference sensor coordinate system.
  • steps 303-304 may also be performed before the above-mentioned steps 301-302, which is not limited.
  • Step 305 Calibrate the extrinsic parameters of the sensor to be calibrated according to the first feature point information and the second feature point information.
  • the external parameters may include parameters representing the relative pose relationship between the sensor to be calibrated and the reference sensor.
  • the parameters may include: pitch angle (pitch), roll angle (roll), yaw angle (yaw), x-axis translation (t x ), y-axis translation ( ty ), z-axis translation
  • the pitch angle represents the angle of rotation around the y-axis in the coordinate system of the sensor to be calibrated
  • the yaw angle represents the angle of rotation around the z-axis in the coordinate system of the sensor to be calibrated
  • the roll angle represents The angle of rotation around the x-axis in the coordinate system of the sensor to be calibrated
  • the translation of the x-axis represents the translation distance along the x-axis in the coordinate system of the sensor to be calibrated
  • the translation of the y-axis represents the translation distance along the y-axis of the sensor coordinate system to be calibrated
  • the translation of the z-axis represents the translation distance along the y-axis
  • the external parameters of the sensor to be calibrated may be represented by a rotation matrix and a translation matrix, wherein the rotation matrix represents a rotation transformation relationship from the coordinate system of the sensor to be calibrated to the reference sensor coordinate system.
  • the rotation matrix can be a matrix with three rows and three columns.
  • the rotation 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 rotation matrix represents The rotation transformation of the three axes of , y-axis and z-axis.
  • the rotation matrix R can be expressed in the form of the following formula (3):
  • ⁇ represents the yaw angle
  • ⁇ represents the pitch angle
  • ⁇ represents the roll angle
  • the translation matrix represents the translation transformation relationship from the sensor coordinate system to be calibrated to the reference sensor coordinate system.
  • the rotation matrix can be a matrix with one row and three columns.
  • the translation matrix includes 3 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 of the three axis directions of the y-axis and the z-axis.
  • the translation matrix T can be expressed in the form of the following formula (4):
  • t x t y t z are the translation amounts of the x-axis, y-axis and z-axis respectively.
  • the point with the same name in the reference sensor coordinate system can be obtained, or the transformed coordinates have the same name as The coordinate deviation of the point is very small; for example, for any point in the coordinate system of the sensor to be calibrated, use the rotation matrix in the external parameter of the sensor to be calibrated to perform rotation transformation on the point, and use the translation matrix in the external parameter to transform the point After the translation transformation, the point with the same name in the reference sensor coordinate system can be obtained; as shown in the following formula (5):
  • R is the rotation matrix
  • T is the translation matrix
  • p2 is a certain point in the coordinate system of the sensor to be calibrated
  • x L2 , y L2 , z L2 are the coordinates of point p2 in the coordinate system of the sensor to be calibrated
  • p1 is the coordinate of the reference sensor
  • y L1 , z L1 are the coordinates of point p1 in the reference sensor coordinate system.
  • 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.
  • the automatic calibration of the external parameters of the sensor to be calibrated can be quickly and accurately realized.
  • the shape of the first contour line can be a straight line, and the registration is performed by using the feature point information corresponding to the same line detected by the sensor to be calibrated and the reference sensor, which is easier to converge, so that the sensor to be calibrated can be realized more quickly and accurately. Automatic calibration of extrinsic parameters.
  • the calibration device can match the coordinate set of the 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 the preset number of feature points on the first contour line in the reference sensor coordinate system Calibrate the external parameters of the sensor to be calibrated.
  • an optimization algorithm can be used to iteratively obtain the optimal solution, so as to obtain the external parameters of the calibrated lidar to be calibrated.
  • M is the transformation matrix
  • R is the rotation matrix
  • T is the translation matrix
  • P1 represents the coordinate set of the preset number of feature points on the first contour line in the reference sensor coordinate system
  • P2 represents the preset number of feature points on the first contour line in the sensor coordinate system to be calibrated
  • D is the sum of the distances between the corresponding points of the new coordinates and the corresponding points of the same name in P1 after the coordinates of each feature point in P2 are transformed by M;
  • the optimal solution of M can be inversely calculated to represent
  • the parameters of the relative pose relationship between the calibration sensor and the reference sensor for example, the pitch angle, roll angle, yaw angle, x-axis translation, y-axis translation can be calculated according to the above formula (3) and formula (4).
  • the translation amount or the translation amount of the z axis so as to complete the external parameter calibration of the sensor to be calibrated.
  • the calibration device can perform the above operations, and can determine the contours of each preset shape detected by the sensor to be calibrated and the reference sensor
  • the feature point information corresponding to the line, and the external parameters of the sensor to be calibrated are calibrated according to the feature point information corresponding to the contour lines of the preset shapes.
  • FIG. 6 shows a schematic diagram of external parameter calibration according to an embodiment of the present application.
  • the left side of the arrow is the outline of the calibration board A1 detected by the sensor to be calibrated and the reference sensor.
  • the relative pose of each contour line of the detected calibration board A1 has a deviation;
  • the right side of the arrow is the contour line of the calibration board A1 detected by the sensor to be calibrated after the transformation of the external parameters and that detected by the reference sensor. If the relative pose of each contour line of the calibration board A coincides or the deviation is within a preset range, then the extrinsic parameter is the calibrated extrinsic parameter of the sensor to be calibrated.
  • 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 point coordinate set corresponding to the target calibration plate collected by the sensor can quickly and accurately determine the second feature point information corresponding to the first contour line, and according to the first feature point information and the second feature point information, the outer surface of the sensor to be calibrated
  • the external parameters are calibrated by using the contour features of the target calibration board, which improves the calibration efficiency and accuracy.
  • the embodiment of the present application is based on the contour line of the preset shape and does not depend on the regular calibration scene, and realizes automatic calibration of external parameters, effectively improving calibration efficiency and scope of application.
  • the embodiment of the present application there is no need to construct a dense point cloud map, thereby effectively reducing the number of point clouds that need to be processed in the calibration process, reducing the calculation time, and improving the calibration efficiency.
  • the preset shape of the contour line is used as a constraint, which avoids the problem that the constraint is not strong and easily falls into a local optimum, and improves the calibration accuracy.
  • Fig. 7 shows a flow chart of a calibration method according to an embodiment of the present application; the method may be performed by the above-mentioned calibration device; as shown in Fig. 7, the method may include the following steps:
  • Step 701. Obtain preset constraint information corresponding to the first outline of the target calibration plate.
  • the preset constraint information may include: length information of the first contour line, and/or relative positional relationship between the first contour line and other contour lines in the target calibration plate.
  • the relative positional relationship may include: vertical, parallel, or an angle between two contour lines, and the like.
  • the preset constraint information may include the length information of the contour line a1, or the contour line a1
  • the calibration device may acquire preset constraint information corresponding to contour lines detected by the sensor to be calibrated and the reference sensor in the target calibration board.
  • Step 702. Obtain a set of first point coordinates corresponding to the target calibration board.
  • Step 703 Determine first feature point information corresponding to the first contour line according to the first point coordinate set and preset constraint information.
  • this step may include: extracting point coordinates corresponding to the first contour line in the first point coordinate set; The corresponding point coordinates are fitted to obtain a first expression; according to the first expression, 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 is determined.
  • the calibration device is the first to extract the first point coordinate set
  • the first expression that can accurately represent the actual shape of the first contour line can be obtained by fitting; then according to the first expression, The coordinate set of the preset number of feature points on the first contour line in the coordinate system of the sensor to be calibrated is obtained more accurately.
  • the calibration device can calculate the coordinates of the center point on the side of the target calibration plate facing the sensor to be calibrated according to the first point coordinate set, and extract the first point coordinate set according to the coordinates of the center point and preset constraint information The coordinates of the points on the edge where the first contour line is located, so as to obtain the point coordinates corresponding to the first contour line.
  • the calibration device can filter out other environmental point clouds such as the ground according to the coordinates of the center point and the length information of the first contour line, so as to obtain the point coordinates corresponding to the first contour line more accurately.
  • the marking device may 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.
  • the marking device can fit the point coordinates corresponding to the first contour line extracted from the first point coordinate set according to the preset constraint information corresponding to the first contour line and the preset shape of the first contour line , the first expression can be obtained exactly.
  • the shape of the first contour line can be a straight line, and the straight line feature is easier to express.
  • the straight line feature of the first contour line and the preset constraint relationship corresponding to the first contour line are used as stronger constraints, so that it can be more accurately fitted first expression.
  • the calibration device can be based on the preset constraint information corresponding to the first contour line, the positional relationship between the fitting plane where the side of the target calibration plate facing the sensor to be calibrated is located and the first contour line, and the positional relationship between the first contour line
  • the preset shape is used to fit the point coordinates corresponding to the first contour line extracted from the first point coordinate set, so that the first expression can be obtained more accurately.
  • the marking device is based on the preset shape of the first contour line, and the first contour line is located on the fitting plane, and the relative positional relationship between the first contour line and other contour lines in the target calibration plate is used as constraints , to fit the point coordinates corresponding to the first contour line extracted in the first point coordinate set; On the fitting plane, and there are relative positional relationships such as vertical and parallel between different straight lines, so that the expression of the first contour line can be accurately fitted.
  • the calibration device can extract the point coordinates corresponding to the contour lines detected by the sensor to be calibrated and the reference sensor in the target calibration board; according to the preset constraint information corresponding to each contour line, the extracted The point coordinates corresponding to each contour line are fitted to obtain the expression of each contour line; according to the expression of each contour line, the coordinate set of the preset number of feature points on each contour line in the sensor coordinate system to be calibrated is determined.
  • the contour line a1, the contour line a2, the contour line a3 and the contour line a4 form a rectangle; for the point cloud corresponding to the extracted calibration plate A1 shown in FIG.
  • Fig. 8 is a schematic diagram of each contour line after fitting, as shown in Fig. within the rectangular area surrounded by a4.
  • Step 704 acquiring the second point coordinate set corresponding to the target calibration board.
  • Step 705 Determine the second feature point information corresponding to the first contour line according to the second point coordinate set and preset constraint information.
  • this step may include: extracting point coordinates corresponding to the first contour line in the second point coordinate set; The corresponding point coordinates are fitted to obtain a second expression; according to the second expression, a set of coordinates of a preset number of feature points on the first contour line in the reference sensor coordinate system is determined.
  • step 703 for extracting the point coordinates corresponding to the first contour line in the first point coordinate set; and obtaining the first expression of the first contour line, which will not be repeated here.
  • the calibration device can fit and obtain the first contour line that can accurately represent the actual shape of the first contour line based on the preset constraint information corresponding to the first contour line.
  • the second expression furthermore, according to the second expression, the coordinate set of the preset number of feature points on the first contour line in the reference sensor coordinate system can be obtained more accurately.
  • the calibration device can extract the point coordinates corresponding to the contour lines detected by the sensor to be calibrated and the reference sensor in the target calibration board; according to the preset constraint information corresponding to each contour line, the extracted The point coordinates corresponding to each contour line are fitted to obtain the expression of each contour line; according to the expression of each contour line, the coordinate set of the preset number of feature points on each contour line in the reference sensor coordinate system is determined.
  • the relevant expressions in step 703 above and details are not repeated here.
  • steps 704-705 may also be performed before the above steps 702-703, which is not limited.
  • Step 706 Calibrate the extrinsic parameters of the sensor to be calibrated according to the first feature point information and the second feature point information.
  • step 305 For this step, reference may be made to the above-mentioned step 305, which will not be repeated here.
  • the first point coordinate set corresponding to the target calibration plate collected by the sensor to be calibrated can be more accurately Determine the first feature point information corresponding to the first contour line, and more accurately determine the second feature point information corresponding to the first contour line according to the second point coordinate set corresponding to the target calibration plate collected by the reference sensor, so as to realize full utilization
  • the contour features of the target calibration board are calibrated with external parameters, which further improves the calibration accuracy.
  • embodiments of the present application further provide a calibration device, which is used to implement the technical solutions described in the above method embodiments. For example, each step of the above method shown in FIG. 3 or FIG. 7 may be executed.
  • FIG. 9 shows a structural diagram of a calibration device according to an embodiment of the present application.
  • the calibration device may include: an acquisition module 901, configured to acquire a set of first point coordinates corresponding to the target calibration board, so The first set of point 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 processing module 902 is configured to according to the first A set of coordinates to determine the first feature point information corresponding to the first contour line, the first contour line being any contour line in the at least one contour line; the acquisition module 901 is also used to: acquire 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; the processing module 902 is further configured to The second point coordinate set is used to determine the second feature point information corresponding to the first contour line; and to calibrate the external parameters of the sensor to be calibrated according to the
  • 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 point coordinate set corresponding to the target calibration plate collected by the sensor can quickly and accurately determine the second feature point information corresponding to the first contour line, and according to the first feature point information and the second feature point information, the outer surface of the sensor to be calibrated
  • the external parameters are calibrated by using the contour features of the target calibration board, which improves the calibration efficiency and accuracy.
  • the acquiring module 901 is further configured to: acquire preset constraint information corresponding to the first contour line, where the preset constraint information includes: 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: according to the first point coordinate set and the preset Set constraint information, determine the first feature point information; and/or, determine the second feature point information according to the second point coordinate set and the preset constraint information.
  • the processing module 902 is further configured to perform registration on the external parameters of the sensor to be calibrated by registering the first feature point information with the second feature point information calibration.
  • 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 Including: a coordinate set of a preset number of feature points on the first contour line in the reference sensor coordinate system; the processing module 902 is further configured to: extract the first contour in the first point coordinate set The point coordinates corresponding to the line; fitting the point coordinates corresponding to the first contour line in the extracted first point coordinate set to obtain the first expression of the first contour line; according to the first An expression, determining a coordinate set of a preset number of feature points on the first contour line in the coordinate system of the sensor to be calibrated; extracting a point coordinate set corresponding to the first contour line in the second point coordinate set; 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; according to the second expression, determine the A set of coordinates of a preset number of feature points on the
  • the processing module 902 is further configured to: acquire preset constraint information corresponding to the first contour line; Fitting the point coordinates corresponding to the first contour line in the coordinate set to obtain the first expression; and/or, obtaining preset constraint information corresponding to the first contour line; according to the preset constraint information , fitting the point coordinates corresponding to the first contour line in the extracted second point coordinate set to obtain the second expression.
  • the acquisition module 901 is further configured to: acquire the first data collected by the sensor to be calibrated; the first data includes a plurality of points in the coordinate system of the sensor to be calibrated coordinates; according to the preset distance between the sensor to be calibrated and the target calibration plate, extract the first point coordinate set from the first data; and/or, obtain the second set of coordinates collected by the reference sensor data; the second data includes the coordinates of a plurality of points in the reference sensor coordinate system; according to the preset distance between the reference sensor and the target calibration plate, the second data is extracted from the A collection of second point coordinates.
  • the preset shape is a straight line.
  • each module in the above device is only a division of logical functions, which may be fully or partially integrated into one physical entity or physically separated during actual implementation.
  • the modules in the device can be implemented in the form of a processor calling software; for example, the device includes a processor, the processor is connected to a memory, instructions are stored in the memory, and the processor calls the instructions stored in the memory to implement any of the above methods Or realize the function of each module of the device, wherein the processor is, for example, a general-purpose processor, such as a central processing unit (Central Processing Unit, CPU) or a microprocessor, and the memory is a memory in the device or a memory outside the device.
  • CPU central processing unit
  • microprocessor a microprocessor
  • the modules in the device may be implemented in the form of hardware circuits, and part or all of the functions of the modules may be realized by designing the hardware circuits.
  • the hardware circuits may be understood as one or more processors; for example, in one implementation, The hardware circuit is an application-specific integrated circuit (ASIC), and through the design of the logical relationship between the components in the circuit, the functions of some or all of the above modules are realized; for another example, in another implementation, the hardware circuit is It can be realized by programmable logic device (programmable logic device, PLD). Taking Field Programmable Gate Array (Field Programmable Gate Array, FPGA) as an example, it can include a large number of logic gate circuits, and configure the logic gate circuits through configuration files.
  • programmable logic device programmable logic device
  • All the modules of the above device can be realized in the form of calling software by the processor, or in the form of hardware circuit, or partially realized in the form of calling software by the processor, and the rest can be realized in the form of hardware circuit.
  • the processor is a circuit with signal processing capabilities.
  • the processor may be a circuit with instruction reading and execution capabilities, such as CPU, microprocessor, graphics processor (graphics processing unit, GPU) (can be understood as a microprocessor), or digital signal processor (digital signal processor, DSP), etc.; in another implementation, the processor can realize a certain Function, the logical relationship of the hardware circuit is fixed or reconfigurable, for example, the processor is a hardware circuit implemented by ASIC or PLD, such as FPGA.
  • the process of the processor loading the configuration file to realize the configuration of the hardware circuit can be understood as the process of the processor loading instructions to realize the functions of some or all of the above modules.
  • each module in the above device can be one or more processors (or processing circuits) configured to implement the above method, for example: CPU, GPU, microprocessor, DSP, ASIC, FPGA, or these processor forms A combination of at least two of them.
  • the SOC may include at least one processor for implementing any of the above methods or realizing the functions of each module of the device.
  • the at least one processor may be of different types, such as including CPU and FPGA, CPU and artificial intelligence processor, CPUs and GPUs, etc.
  • An embodiment of the present application also provides a calibration device, including: a processor; a memory for storing processor-executable instructions; wherein, the processor is configured to implement the method of the above-mentioned embodiment when executing the instructions. Exemplarily, each step of the above method shown in FIG. 3 or FIG. 7 can be implemented.
  • FIG. 10 shows a schematic structural diagram of a calibration device according to an embodiment of the present application. As shown in FIG. 10
  • the processor 1001 can be a general-purpose central processing unit (central processing unit, CPU), a microprocessor, a specific application integrated circuit (application-specific integrated circuit, ASIC), or one or more for controlling the execution of the application program program integrated circuit.
  • CPU central processing unit
  • ASIC application-specific integrated circuit
  • Communication line 1002 may include a path for passing information between the above-described components.
  • the communication interface 1004 uses any device such as a transceiver for communicating with other devices or communication networks, such as Ethernet, RAN, wireless local area networks (wireless local area networks, WLAN) and so on.
  • a transceiver for communicating with other devices or communication networks, such as Ethernet, RAN, wireless local area networks (wireless local area networks, WLAN) and so on.
  • the memory 1003 may be a read-only memory (read-only memory, ROM) or other types of static storage devices that can store static information and instructions, random access memory (random access memory, RAM) or other types that can store information and instructions It can also be an electrically erasable programmable read-only memory (EEPROM), compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compact discs, laser discs, optical discs, digital versatile discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or can be used to carry or store desired program code in the form of instructions or data structures and can be programmed by a computer Any other medium accessed, but not limited to.
  • EEPROM electrically erasable programmable read-only memory
  • CD-ROM compact disc read-only memory
  • optical disc storage including compact discs, laser discs, optical discs, digital versatile discs, Blu-ray discs, etc.
  • magnetic disk storage media or other magnetic storage devices or can be used to carry or store
  • the memory may exist independently and be connected to the processor through the communication line 1002 . Memory can also be integrated with the processor.
  • the memory provided by the embodiment of the present application may generally be non-volatile.
  • the memory 1003 is used to store computer-executed instructions for implementing the solutions of the present application, and the execution is controlled by the processor 1001 .
  • the processor 1001 is configured to execute computer-executed instructions stored in the memory 1003, so as to implement the methods provided in the foregoing embodiments of the present application. Exemplarily, each step of the above method shown in FIG. 3 or FIG. 7 can be implemented.
  • the computer-executed instructions in the embodiments of the present application may also be referred to as application program codes, which is not specifically limited in the embodiments of the present application.
  • the processor 1001 may include one or more CPUs, such as CPU0 and CPU1 in FIG. 10 .
  • the calibration device may include multiple processors, such as processor 1001 and processor 1007 in FIG. 10 .
  • processors may be a single-core (single-CPU) processor or a multi-core (multi-CPU) processor.
  • a processor herein may refer to one or more devices, circuits, and/or processing cores for processing data (eg, computer program instructions).
  • the calibration apparatus may further include an output device 1005 and an input device 1006 .
  • Output device 1005 is in communication with processor 1001 and can display information in a variety of ways.
  • the output device 1005 may be a liquid crystal display (liquid crystal display, LCD), a light emitting diode (light emitting diode, LED) display device, a cathode ray tube (cathode ray tube, CRT) display device, or a projector (projector) wait.
  • the input device 1006 communicates with the processor 1001 and can receive user input in various ways.
  • the input device 1006 may be a mouse, a keyboard, a touch screen device, or a sensing device, among others.
  • the acquisition module 901 in FIG. 9 above can be implemented by the communication interface 1004 in FIG. 10; the processing module 902 in FIG. to fulfill.
  • Embodiments of the present application provide a computer-readable storage medium on which computer program instructions are stored, and when the computer program instructions are executed by a processor, the methods in the foregoing embodiments are implemented. Exemplarily, each step of the method shown in FIG. 3 or FIG. 7 can be implemented.
  • Embodiments of the present application provide a computer program product, for example, may include computer readable codes, or a non-volatile computer readable storage medium carrying computer readable codes; when the computer program product is run on a computer , causing the computer to execute the method in the foregoing embodiments. Exemplarily, each step of the above method shown in FIG. 3 or FIG. 7 may be executed.
  • a computer readable storage medium may be a tangible device that can retain and store instructions for use by an instruction execution device.
  • a computer readable storage medium may be, for example, but is not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing.
  • Non-exhaustive list of computer-readable storage media include: portable computer disk, hard disk, random access memory (Random Access Memory, RAM), read only memory (Read Only Memory, ROM), erasable Electrically Programmable Read-Only-Memory (EPROM or flash memory), Static Random-Access Memory (Static Random-Access Memory, SRAM), Portable Compression Disk Read-Only Memory (Compact Disc Read-Only Memory, CD -ROM), Digital Video Disc (DVD), memory sticks, floppy disks, mechanically encoded devices such as punched cards or raised structures in grooves with instructions stored thereon, and any suitable combination of the foregoing .
  • RAM Random Access Memory
  • ROM read only memory
  • EPROM or flash memory erasable Electrically Programmable Read-Only-Memory
  • Static Random-Access Memory SRAM
  • Portable Compression Disk Read-Only Memory Compact Disc Read-Only Memory
  • CD -ROM Compact Disc Read-Only Memory
  • DVD Digital Video Disc
  • Computer readable program instructions or codes described herein may be downloaded from a computer readable storage medium to a respective computing/processing device, or downloaded to an external computer or external storage device over a network, such as the Internet, local area network, wide area network, and/or wireless network.
  • 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 a network interface in each computing/processing device receives computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in a computer-readable storage medium in each computing/processing device .
  • Computer program instructions for performing the operations of the present application may be assembly instructions, instruction set architecture (Instruction Set Architecture, ISA) instructions, machine instructions, machine-related instructions, microcode, firmware instructions, state setting data, or in one or more source or object code written in any combination of programming languages, including object-oriented programming languages—such as Smalltalk, C++, etc., and conventional procedural programming languages—such as the “C” language or similar programming languages.
  • Computer readable program instructions may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer, or entirely on the remote computer or server implement.
  • the remote computer can be connected to the user's computer through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or it can be connected to an external computer such as use an Internet service provider to connect via the Internet).
  • electronic circuits such as programmable logic circuits, field-programmable gate arrays (Field-Programmable Gate Array, FPGA) or programmable logic arrays (Programmable Logic Array, PLA), the electronic circuit can execute computer-readable program instructions, thereby realizing various aspects of the present application.
  • These computer-readable program instructions may be provided to a processor of a general purpose computer, 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 , producing an apparatus for realizing the functions/actions specified in one or more blocks in the flowchart and/or block diagram.
  • These computer-readable program instructions can also be stored in a computer-readable storage medium, and these instructions cause computers, programmable data processing devices and/or other devices to work in a specific way, so that the computer-readable medium storing instructions includes An article of manufacture comprising instructions for implementing various aspects of the functions/acts specified in one or more blocks in flowcharts and/or block diagrams.
  • each block in a flowchart or block diagram may represent a module, a portion of a program segment, or an instruction that includes one or more Executable instructions.
  • the functions noted in the block may occur out of the order noted in the figures. For example, two blocks in succession may, in fact, be executed substantially concurrently, or they may sometimes be executed in the reverse order, depending upon the functionality involved.
  • each block in the block diagrams and/or flowcharts, and combinations of blocks in the block diagrams and/or flowcharts can be implemented with hardware (such as circuits or ASIC (Application Specific Integrated Circuit, application-specific integrated circuit)), or it can be realized by a combination of hardware and software, such as firmware.
  • hardware such as circuits or ASIC (Application Specific Integrated Circuit, application-specific integrated circuit)
  • firmware such as firmware

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • Length Measuring Devices By Optical Means (AREA)
  • Image Analysis (AREA)

Abstract

本申请涉及一种标定方法及装置。该方法包括：获取目标标定板对应的第一点坐标集合，第一点坐标集合包括目标标定板上至少一点在待标定传感器坐标系下的坐标；目标标定板的至少一条轮廓线为预设形状；根据第一点坐标集合，确定至少一条轮廓线中第一轮廓线对应的第一特征点信息；获取目标标定板对应的第二点坐标集合，第二点坐标集合包括目标标定板上至少一点在基准传感器坐标系下的坐标；根据第二点坐标集合，确定第一轮廓线对应的第二特征点信息；根据第一特征点信息及第二特征点信息，对待标定传感器的外参进行标定。本申请中，利用目标标定板的轮廓特征进行外参标定，提高了标定效率和精度。

Description

一种标定方法及装置 技术领域
本申请涉及自动驾驶技术领域，尤其涉及一种标定方法及装置。
背景技术
在自动驾驶系统，感知模块是重要的组成部分。激光雷达所采集的点云数据是感知模块的输入之一，激光雷达能够扫描车辆周围环境并输出点云数据，使用单个激光雷达存在一定的盲区，并且不同距离点云密集程度不同，从而可能影响感知模块的性能，因而可以将分布于车辆不同位置的多个激光雷达所采集的点云数据进行融合，从而提升感知模块的性能。
在将多个激光雷达所采集的点云数据进行融合之前，需要对多个激光雷达的外参进行标定，即确定多个激光雷达之间的位姿变换关系；然而，现有外参标定方式中，标定效率及标定精度均有待提高。
发明内容
有鉴于此，提出了一种标定方法、装置、存储介质及计算机程序产品。
第一方面，本申请的实施例提供了一种标定方法，所述方法包括：获取目标标定板对应的第一点坐标集合，所述第一点坐标集合包括所述目标标定板上至少一点在待标定传感器坐标系下的坐标；所述目标标定板的至少一条轮廓线为预设形状；根据所述第一点坐标集合，确定第一轮廓线对应的第一特征点信息，所述第一轮廓线为所述至少一条轮廓线中任一轮廓线；获取所述目标标定板对应的第二点坐标集合，所述第二点坐标集合包括所述目标标定板上至少一点在基准传感器坐标系下的坐标；根据所述第二点坐标集合，确定所述第一轮廓线对应的第二特征点信息；根据所述第一特征点信息及所述第二特征点信息，对所述待标定传感器的外参进行标定；所述外参包括表示所述待标定传感器与所述基准传感器之间的相对位姿关系的参数。
基于上述技术方案，第一轮廓线为预设形状，根据待标定传感器所采集的目标标定板对应的第一点坐标集合可以快速准确地确定第一轮廓线对应的第一特征点信息，根据基准传感器所采集的目标标定板对应的第二点坐标集合可以快速准确地确定第一轮廓线对应的第二特征点信息，并根据第一特征点信息及第二特征点信息，对待标定传感器的外参进行标定；从而实现利用目标标定板的轮廓特征进行外参标定，提高了标定效率和精度。
根据第一方面，在所述第一方面的第一种可能的实现方式中，所述方法还包括：获取所述第一轮廓线对应的预设约束信息，所述预设约束信息包括：所述第一轮廓线的长度信息，和/或，所述第一轮廓线与所述目标标定板中其他轮廓线之间的相对位置关系；所述根据所述第一点坐标集合，确定所述第一轮廓线对应的第一特征点信息， 包括：根据所述第一点坐标集合及所述预设约束信息，确定所述第一特征点信息；和/或，所述根据所述第二点坐标集合，确定所述第一轮廓线对应的第二特征点信息，包括：根据所述第二点坐标集合及所述预设约束信息，确定所述第二特征点信息。
基于上述技术方案，以第一轮廓线为预设形状及第一轮廓线对应的预设约束信息作为约束，根据待标定传感器所采集的目标标定板对应的第一点坐标集合可以更加准确地确定第一轮廓线对应的第一特征点信息，根据基准传感器所采集的目标标定板对应的第二点坐标集合可以更加准确地确定第一轮廓线对应的第二特征点信息，从而实现充分利用目标标定板的轮廓特征进行外参标定，进一步提高了标定精度。
根据第一方面或第一方面的第一种可能的实现方式，在所述第一方面的第二种可能的实现方式中，所述根据所述第一特征点信息及所述第二特征点信息，对所述待标定传感器的外参进行标定，包括：通过将所述第一特征点信息与所述第二特征点信息进行配准，对所述待标定传感器的外参进行标定。
基于上述技术方案，通过待标定传感器及基准传感器所探测到的第一轮廓线对应的特征点信息进行配准，从而快速准确地实现待标定传感器的外参的自动标定。
根据第一方面或上述第一方面的各种可能的实现方式，在所述第一方面的第三种可能的实现方式中，所述第一特征点信息包括：所述第一轮廓线上预设数量特征点在所述待标定传感器坐标系下的坐标集合；所述第二特征点信息包括：所述第一轮廓线上预设数量特征点在所述基准传感器坐标系下的坐标集合；所述根据所述第一点坐标集合，确定所述第一轮廓线对应的第一特征点信息，包括：提取所述第一点坐标集合中所述第一轮廓线对应的点坐标；对所提取的所述第一点坐标集合中所述第一轮廓线对应的点坐标进行拟合，得到所述第一轮廓线的第一表达式；根据所述第一表达式，确定所述第一轮廓线上预设数量特征点在所述待标定传感器坐标系下的坐标集合；所述根据所述第二点坐标集合，确定所述第一轮廓线对应的第二特征点信息，包括：提取所述第二点坐标集合中所述第一轮廓线对应的点坐标集合；对所提取的所述第二点坐标集合中所述第一轮廓线对应的点坐标进行拟合，得到所述第一轮廓线的第二表达式；根据所述第二表达式，确定所述第一轮廓线上预设数量特征点在所述基准传感器坐标系下的坐标集合。
基于上述技术方案，第一轮廓线为预设形状，即第一轮廓线可以采用特定表达式进行表示；在提取第一点坐标集合中第一轮廓线对应的点坐标基础上，可以拟合得到能够准确表示第一轮廓线实际形状的第一表达式；根据第一表达式，从而可以准确的获取第一轮廓线上预设数量特征点在待标定传感器坐标系下的坐标集合；在提取第二点坐标集合中第一轮廓线对应的点坐标基础上，可以拟合得到能够准确表示第一轮廓线实际形状的第二表达式；根据第二表达式，从而可以准确的获取第一轮廓线上预设数量特征点在基准传感器坐标系下的坐标集合，进而有效提高待标定传感器的外参标定的准确性。
根据第一方面的第三种可能的实现方式，在所述第一方面的第四种可能的实现方式中，所述对所提取的所述第一点坐标集合中所述第一轮廓线对应的点坐标进行拟合，得到所述第一轮廓线的第一表达式，包括：获取所述第一轮廓线对应的预设约束信息；根据所述预设约束信息，对所提取的所述第一点坐标集合中所述第一轮廓线对应的点 坐标进行拟合，得到所述第一表达式；和/或，所述对所提取的所述第二点坐标集合中所述第一轮廓线对应的点坐标进行拟合，得到所述第一轮廓线的第二表达式，包括：获取所述第一轮廓线对应的预设约束信息；根据所述预设约束信息，对所提取的所述第二点坐标集合中所述第一轮廓线对应的点坐标进行拟合，得到所述第二表达式。
基于上述技术方案，由于第一轮廓线可以用特定表达式表示，且第一轮廓线的长度及第一轮廓线与其他轮廓线之间的相对位置存在约束，因此，标定装置在提取第一点坐标集合中第一轮廓线对应的点坐标基础上，基于第一轮廓线对应的预设约束信息，可以拟合得到能够准确表示第一轮廓线实际形状的第一表达式；和/或，可以拟合得到能够准确表示第一轮廓线实际形状的第二表达式。
根据第一方面或上述第一方面的各种可能的实现方式，在所述第一方面的第五种可能的实现方式中，所述获取目标标定板对应的第一点坐标集合，包括：获取所述待标定传感器采集的第一数据；所述第一数据包括多个点在所述待标定传感器坐标系下的坐标；根据所述待标定传感器与所述目标标定板之间的预设距离，在所述第一数据中提取所述第一点坐标集合；和/或，所述获取所述目标标定板对应的第二点坐标集合，包括：获取所述基准传感器采集的第二数据；所述第二数据包括多个点在所述基准传感器坐标系下的坐标；根据所述基准传感器与所述目标标定板之间的预设距离，在所述第二数据中提取所述第二点坐标集合。
基于上述技术方案，根据待标定传感器与目标标定板之间的预设距离，在待标定传感器所采集的数据中，快捷准确地提取出目标标定板上的点在待标定传感器坐标系下的坐标，和/或，根据基准传感器与目标标定板之间的预设距离，在基准传感器所采集的数据中，快捷准确地提取出目标标定板上的点在基准传感器坐标系下的坐标，从而在保证标定准确性的同时，提高了标定效率。
根据第一方面或上述第一方面的各种可能的实现方式，在所述第一方面的第六种可能的实现方式中，所述预设形状为直线。
基于上述技术方案，第一轮廓线的形状为直线，直线特征更易表达，作为一个示例，可以更加准确快捷的拟合得到第一表达式及第二表达式，从而提高了标定精度及效率；作为另一个示例，以第一轮廓线的直线特征以及第一轮廓线对应的预设约束关系，作为较强的约束，从而可以更加准确地拟合第一表达式及第二表达式；作为另一个示例，利用待标定传感器及基准传感器所探测到的同一直线对应的特征点信息进行配准，更易收敛，从而可以更加快速准确地实现待标定传感器的外参的自动标定。
第二方面，本申请的实施例提供了一种标定装置，所述装置包括：获取模块，用于获取目标标定板对应的第一点坐标集合，所述第一点坐标集合包括所述目标标定板上至少一点在待标定传感器坐标系下的坐标；所述目标标定板的至少一条轮廓线为预设形状；处理模块，用于根据所述第一点坐标集合，确定第一轮廓线对应的第一特征点信息，所述第一轮廓线为所述至少一条轮廓线中任一轮廓线；所述获取模块，还用于：获取所述目标标定板对应的第二点坐标集合，所述第二点坐标集合包括所述目标标定板上至少一点在基准传感器坐标系下的坐标；所述处理模块，还用于根据所述第二点坐标集合，确定所述第一轮廓线对应的第二特征点信息；根据所述第一特征点信息及所述第二特征点信息，对所述待标定传感器的外参进行标定；所述外参包括表示 所述待标定传感器与所述基准传感器之间的相对位姿关系的参数。
基于上述技术方案，第一轮廓线为预设形状，根据待标定传感器所采集的目标标定板对应的第一点坐标集合可以快速准确地确定第一轮廓线对应的第一特征点信息，根据基准传感器所采集的目标标定板对应的第二点坐标集合可以快速准确地确定第一轮廓线对应的第二特征点信息，并根据第一特征点信息及第二特征点信息，对待标定传感器的外参进行标定；从而实现利用目标标定板的轮廓特征进行外参标定，提高了标定效率和精度。
根据第二方面，在所述第二方面的第一种可能的实现方式中，所述获取模块，还用于：获取所述第一轮廓线对应的预设约束信息，所述预设约束信息包括：所述第一轮廓线的长度信息，和/或，所述第一轮廓线与所述目标标定板中其他轮廓线之间的相对位置关系；所述处理模块，还用于：根据所述第一点坐标集合及所述预设约束信息，确定所述第一特征点信息；和/或，根据所述第二点坐标集合及所述预设约束信息，确定所述第二特征点信息。
基于上述技术方案，以第一轮廓线为预设形状及第一轮廓线对应的预设约束信息作为约束，根据待标定传感器所采集的目标标定板对应的第一点坐标集合可以更加准确地确定第一轮廓线对应的第一特征点信息，根据基准传感器所采集的目标标定板对应的第二点坐标集合可以更加准确地确定第一轮廓线对应的第二特征点信息，从而实现充分利用目标标定板的轮廓特征进行外参标定，进一步提高了标定精度。
根据第二方面或第二方面的第一种可能的实现方式，在所述第二方面的第二种可能的实现方式中，所述处理模块，还用于：通过将所述第一特征点信息与所述第二特征点信息进行配准，对所述待标定传感器的外参进行标定。
基于上述技术方案，通过待标定传感器及基准传感器所探测到的第一轮廓线对应的特征点信息进行配准，从而快速准确地实现待标定传感器的外参的自动标定。
根据第二方面或上述第二方面的各种可能的实现方式，在所述第二方面的第三种可能的实现方式中，所述第一特征点信息包括：所述第一轮廓线上预设数量特征点在所述待标定传感器坐标系下的坐标集合；所述第二特征点信息包括：所述第一轮廓线上预设数量特征点在所述基准传感器坐标系下的坐标集合；所述处理模块，还用于：提取所述第一点坐标集合中所述第一轮廓线对应的点坐标；对所提取的所述第一点坐标集合中所述第一轮廓线对应的点坐标进行拟合，得到所述第一轮廓线的第一表达式；根据所述第一表达式，确定所述第一轮廓线上预设数量特征点在所述待标定传感器坐标系下的坐标集合；提取所述第二点坐标集合中所述第一轮廓线对应的点坐标集合；对所提取的所述第二点坐标集合中所述第一轮廓线对应的点坐标进行拟合，得到所述第一轮廓线的第二表达式；根据所述第二表达式，确定所述第一轮廓线上预设数量特征点在所述基准传感器坐标系下的坐标集合。
基于上述技术方案，第一轮廓线为预设形状，即第一轮廓线可以采用特定表达式进行表示；在提取第一点坐标集合中第一轮廓线对应的点坐标基础上，可以拟合得到能够准确表示第一轮廓线实际形状的第一表达式；根据第一表达式，从而可以准确的获取第一轮廓线上预设数量特征点在待标定传感器坐标系下的坐标集合；在提取第二点坐标集合中第一轮廓线对应的点坐标基础上，可以拟合得到能够准确表示第一轮廓 线实际形状的第二表达式；根据第二表达式，从而可以准确的获取第一轮廓线上预设数量特征点在基准传感器坐标系下的坐标集合，进而有效提高对待标定传感器的外参标定的准确性。
根据第二方面的第三种可能的实现方式，在所述第二方面的第四种可能的实现方式中，所述处理模块，还用于：获取所述第一轮廓线对应的预设约束信息；根据所述预设约束信息，对所提取的所述第一点坐标集合中所述第一轮廓线对应的点坐标进行拟合，得到所述第一表达式；和/或，获取所述第一轮廓线对应的预设约束信息；根据所述预设约束信息，对所提取的所述第二点坐标集合中所述第一轮廓线对应的点坐标进行拟合，得到所述第二表达式。
基于上述技术方案，由于第一轮廓线可以用特定表达式表示，且第一轮廓线的长度及第一轮廓线与其他轮廓线之间的相对位置存在约束，因此，标定装置在提取第一点坐标集合中第一轮廓线对应的点坐标基础上，基于第一轮廓线对应的预设约束信息，可以拟合得到能够准确表示第一轮廓线实际形状的第一表达式；和/或，可以拟合得到能够准确表示第一轮廓线实际形状的第二表达式。
根据第二方面或上述第二方面的各种可能的实现方式，在所述第二方面的第五种可能的实现方式中，所述获取模块，还用于：获取所述待标定传感器采集的第一数据；所述第一数据包括多个点在所述待标定传感器坐标系下的坐标；根据所述待标定传感器与所述目标标定板之间的预设距离，在所述第一数据中提取所述第一点坐标集合；和/或，获取所述基准传感器采集的第二数据；所述第二数据包括多个点在所述基准传感器坐标系下的坐标；根据所述基准传感器与所述目标标定板之间的预设距离，在所述第二数据中提取所述第二点坐标集合。
基于上述技术方案，根据待标定传感器与目标标定板之间的预设距离，在待标定传感器所采集的数据中，快捷准确地提取出目标标定板上的点在待标定传感器坐标系下的坐标，和/或，根据基准传感器与目标标定板之间的预设距离，在基准传感器所采集的数据中，快捷准确地提取出目标标定板上的点在基准传感器坐标系下的坐标，从而在保证标定准确性的同时，提高了标定效率。
根据第二方面或上述第二方面的各种可能的实现方式，在所述第二方面的第六种可能的实现方式中，所述预设形状为直线。
基于上述技术方案，第一轮廓线的形状为直线，直线特征更易表达，作为一个示例，可以更加准确快捷的拟合得到第一表达式及第二表达式，从而提高了标定精度及效率；作为另一个示例，以第一轮廓线的直线特征以及第一轮廓线对应的预设约束关系，作为较强的约束，从而可以准确的拟合第一表达式及第二表达式；作为另一个示例，利用待标定传感器及基准传感器所探测到的同一直线对应的特征点信息进行配准，更易收敛，从而可以更加快速准确的实现待标定传感器的外参的自动标定。
第三方面，本申请的实施例提供了一种标定装置，包括：处理器；用于存储处理器可执行指令的存储器；其中，所述处理器被配置为执行所述指令时实现上述第一方面或者第一方面的一种或几种的标定方法。
第四方面，本申请的实施例提供了一种计算机可读存储介质，其上存储有计算机程序指令，其特征在于，所述计算机程序指令被处理器执行时实现第一方面或者第一 方面的一种或几种的标定方法。
第五方面，本申请的实施例提供了一种计算机程序产品，当所述计算机程序产品在计算机上运行时，使得所述计算机执行上述第一方面或者第一方面的一种或几种的标定方法。
上述第三方面至第五方面的技术效果，参见上述第一方面。
附图说明
图1示出了根据本申请一实施例一种标定场景的示意图；
图2示出了根据本申请一实施例的标定板A1朝向车辆C的一面的示意图；
图3示出了根据本申请一实施例中一种标定方法的流程图；
图4示出了根据本申请一实施例的提取出的标定板A1对应的点云的示意图；
图5示出了根据本申请一实施例的拟合得到轮廓线a1的示意图；
图6示出了根据本申请一实施例的外参标定的示意图；
图7示出了根据本申请一实施例中一种标定方法的流程图；
图8示出了根据本申请一实施例的拟合后的各轮廓线的示意图；
图9示出根据本申请一实施例的一种标定装置的结构图；
图10示出根据本申请一实施例的一种标定装置的结构示意图。
具体实施方式
以下将参考附图详细说明本申请的各种示例性实施例、特征和方面。附图中相同的附图标记表示功能相同或相似的元件。尽管在附图中示出了实施例的各种方面，但是除非特别指出，不必按比例绘制附图。
在这里专用的词“示例性”意为“用作例子、实施例或说明性”。这里作为“示例性”所说明的任何实施例不必解释为优于或好于其它实施例。
图1示出了根据本申请一实施例一种标定场景的示意图。如图1所示，该标定场景中可以包括：传感器L1、传感器L2、标定板A1、车辆C。
其中，标定板A1的至少一条轮廓线可以为预设形状，示例性地，预设形状可以为直线、圆、或者其他可以用特定表达式所表示的曲线等等。示例性地，标定板A1中朝向车辆C的一面位于传感器L1的视场角及传感器L2的视场角内，标定板A1中朝向车辆C的一面可以包括至少一条为预设形状的轮廓线，从而保证传感器L1及传感器L2均可以采集到标定板A1中预设形状的同一条或多条轮廓线的数据。例如，标定板A1中朝向车辆C的一面的各轮廓线可以为直线，对应的标定板A1中朝向车辆C的一面可以为三角形、长方形、多边形等等；作为一个示例，标定板A1可以为长方体，图2示出了根据本申请一实施例的标定板A1朝向车辆C的一面的示意图，如图2所示，标定板A1朝向车辆C的一面为由轮廓线a1、轮廓线a2、轮廓线a3、轮廓线a4组成的长方形，轮廓线a1、轮廓线a2、轮廓线a3、轮廓线a4均为直线，且轮廓线a1、轮廓线a2、轮廓线a3、轮廓线a4均位于传感器L1的视场角及传感器L2的视场角内。
示例性地，该标定场景中还可以包括更多的标定板，例如，如图1所示，还可以 包括标定板A2、标定板A3、标定板A4；示例性地，标定板A2、标定板A3、标定板A4均可以包括预设形状的轮廓线，例如，标定板A2、标定板A3、标定板A4中朝向车辆C的一面可以包括多条为预设形状的轮廓线，且均位于传感器L1的视场角及传感器L2的视场角内。其中，标定板A1、标定板A2、标定板A3、标定板A4中不同轮廓线的预设形状可以相同也可以不同，对此不作限定。作为一个示例，标定板A1、标定板A2、标定板A3、标定板A4可以分别放置在车辆C的四周；例如，标定板A1、标定板A2、标定板A3、标定板A4可以均匀的分布在车辆C的不同方位。
需要说明的是，该标定场景中，对标定板A1、标定板A2、标定板A3或标定板A4的摆放姿态不作限定，例如，标定板A1、标定板A2、标定板A3或标定板A4可以垂直于地面放置，也可以倾斜放置，只要保证传感器L1及传感器L2均可以采集到标定板A1、标定板A2、标定板A3或标定板A4中朝向车辆C的一面的数据即可。
示例性地，车辆C可以位于标定场地的中间，上述标定板A1、标定板A2、标定板A3、标定板A4可以靠近标定场地的边缘放置。作为一个示例，该标定场地可以为长方形区域，例如，可以为长与宽均在10m-50m之间的长方形区域。
其中，传感器L1与传感器L2可以安装在车辆C的不同位置。示例性地，传感器L1及传感器L2所采集的数据可以作为车辆C自动驾驶系统中感知模块的输入。示例性地，传感器L1或传感器L2可以包括激光雷达、毫米波雷达或图像采集装置等等中的任一种，传感器L1与传感器L2可以为同一类型的传感器，也可以为不同类型的传感器，作为一个示例，传感器L1可以为安装在车辆C上的主激光雷达，传感器L2可以为安装在车辆C上的从激光雷达；作为另一个示例，传感器L1可以为安装在车辆C上的激光雷达，传感器L2可以为安装在车辆C上的图像采集装置。需要说明的是，该标定场景中仅以传感器L1及传感器L2作为示例，车辆C上还可以安装有更多的传感器，对此不作限定。
示例性地，图1所示的标定场景中还可以包括标定装置(图中未示出)，作为一个示例，传感器L1及传感器L2可以采集标定板A1、标定板A2、标定板A3或标定板A4中一个或多个的数据，所采集的数据中包括预设形状的同一条或多条轮廓线的数据，标定装置在获取到传感器L1及传感器L2所采集的数据后，通过执行本申请实施例提供的标定方法(详细描述参见下文)，实现对传感器L1或传感器L2的外参进行标定。
本申请实施例不限定该标定装置的类型。
示例性地，该标定装置可以为上述车辆C，或者，车辆C中的其他具有数据处理功能的部件，例如：车载终端、车载控制器、车载模块、车载模组、车载部件、车载芯片、车载单元、车载传感器，车辆可通过该车载终端、车载控制器、车载模块、车载模组、车载部件、车载芯片、车载单元、车载传感器等对传感器L1或传感器L2的外参进行标定。
示例性地，该标定装置可以集成在车辆C的自动驾驶系统(Automated Driving System，ADS)或高级驾驶辅助系统(Advanced Driver Assistant Systems，ADAS)或车载计算平台等中。
示例性地，该标定装置还可以为除了车辆C之外的其他具有数据处理能力的智能 终端，或设置在智能终端中的部件或者芯片。例如，该智能终端可以为智能运输设备、智能穿戴设备、智能家居设备、智能辅助飞机、机器人(robot)或无人机(unmanned aerial vehicle)等安装有传感器的设备。
示例性地，该标定装置可以是一个通用设备或者是一个专用设备。在具体实现中，该装置还可以台式机、便携式电脑、网络服务器、掌上电脑(personal digital assistant，PDA)、移动手机、平板电脑、无线终端设备、嵌入式设备或其他具有数据处理功能的设备，或者为这些设备内的部件或者芯片。
示例性地，该标定装置还可以是具有处理功能的芯片或处理器，该标定装置可以包括多个处理器。处理器可以是一个单核(single-CPU)处理器，也可以是一个多核(multi-CPU)处理器。该具有处理功能的芯片或处理器可以设置在车载传感器中，如可以设置在传感器L1或传感器L2中，也可以不设置在车载传感器中，而设置在车载传感器输出信号的接收端。
需要说明的是，本申请实施例描述的上述标定场景是为了更加清楚的说明本申请实施例的技术方案，并不构成对于本申请实施例提供的技术方案的限定，本领域普通技术人员可知，针对其他相似的或新的标定场景的出现。例如，三维重建、地形探测、自动驾驶建图、自动驾驶感知等等需要对多个传感器的外参进行标定的场景，或者针对单个传感器的外参标定的场景，本申请实施例提供的技术方案对于类似的技术问题，同样适用。
下面对本申请实施例提供的标定方法进行详细说明。
图3示出了根据本申请一实施例中一种标定方法的流程图；示例性地，该方法可以由上述标定装置执行；如图3所示，该方法可以包括以下步骤：
步骤301、获取目标标定板对应的第一点坐标集合；第一点坐标集合包括目标标定板上至少一点在待标定传感器坐标系下的坐标。
其中，目标标定板的至少一条轮廓线为预设形状。示例性地，目标标定板中位于待标定传感器的视场角内的一面包括该预设形状的至少一条轮廓线；例如，目标标定板可以为上述图1中标定板A、标定板A2、标定板A3或标定板A4中的任一标定板。
其中，待标定传感器可以车载传感器中的任一传感器，例如，待标定传感器可以为上述图1所示的传感器L1或传感器L2。可以理解的是，对于同一传感器，基于不同的标定任务，可以作为待标定传感器，也可以作为基准传感器(也可称为参考传感器)；例如，在标定上述图1中传感器L2的外参时，则传感器L2为待标定传感器，并可以将传感器L1作为基准传感器；在标定上述图1中传感器L1的外参时，则传感器L1为待标定传感器，并可以将传感器L2作为基准传感器。
示例性地，待标定传感器坐标系可以为以待标定传感器的质心为原点的笛卡尔坐标系。
示例性地，第一点坐标集合可以包括待标定传感器所探测到的目标标定板上的所有点在待标定传感器坐标系下的坐标。例如，以待标定传感器为图1中传感器L1，目标标定板为标定板A1为例，第一点坐标集合可以包括标定板A1中朝向传感器L1的一面上的所有点在待标定传感器坐标系下的坐标。
在一种可能的实现方式中，该步骤可以包括：标定装置可以获取待标定传感器采 集的第一数据；第一数据包括多个点在待标定传感器坐标系下的坐标；根据待标定传感器与目标标定板之间的预设距离，在第一数据中提取第一点坐标集合。
其中，待标定传感器与目标标定板之间的预设距离可以基于待标定传感器的位置及目标标定板的位置预先确定。
示例性地，第一数据可以包括待标定传感器在标定场地内所探测到的所有点在待标定传感器坐标系下的坐标。标定装置可以根据预设距离，确定目标标定板在待标定传感器坐标系下对应的坐标范围；进而在待标定传感器所探测到的所有点在待标定传感器坐标系下的坐标中，筛选出该坐标范围内的坐标，从而得到第一点坐标集合。这样，根据待标定传感器与目标标定板之间的预设距离，在待标定传感器所采集的数据中，快捷准确地提取出目标标定板上的点在待标定传感器坐标系下的坐标，从而在保证外参标定准确性的同时，提高了标定效率。
举例来说，以待标定传感器为图1中的传感器L1，且传感器L1为激光雷达为例，传感器L1在标定场地内扫描的过程中，可以发射激光线束、接收反射信号，并根据反射信号确定扫描点在传感器L1坐标系下的三维坐标，从而得到采集的点云数据，标定装置可以获取传感器L1所采集的点云数据，根据传感器L1与标定板A1之间的预设距离，在点云数据中提取标定板A1对应的点云，所提取出的标定板A1对应的点云可以如图4所示。
步骤302、根据第一点坐标集合，确定第一轮廓线对应的第一特征点信息。
其中，第一轮廓线为目标标定板中为预设形状的轮廓线中任一轮廓线。例如，第一轮廓线可以为图2中标定板A1中轮廓线a1、轮廓线a2、轮廓线a3或轮廓线a4中任一轮廓线。
示例性地，第一特征点信息可以包括：第一轮廓线上预设数量特征点在待标定传感器坐标系下的坐标集合。其中，特征点可以包括第一轮廓线与其他轮廓线的交点、也可以包括第一轮廓线的中点、或者可以包括第一轮廓线上等间距排列的若干点等等。预设数量可以根据实际需要进行设定，对此不作限定，例如，预设数量可以大于或等于500。
在一种可能的实现方式中，该步骤可以包括：提取第一点坐标集合中第一轮廓线对应的点坐标；对所提取的第一点坐标集合中第一轮廓线对应的点坐标进行拟合，得到第一轮廓线的第一表达式；根据第一表达式，确定第一轮廓线上预设数量特征点在待标定传感器坐标系下的坐标集合。由于第一轮廓线为直线、圆、或者其他可以用特定表达式所表示的曲线，其中，直线、圆均可以用特定表达式表示，因此，标定装置在提取第一点坐标集合中第一轮廓线对应的点坐标基础上，可以拟合得到能够准确表示第一轮廓线实际形状的第一表达式；进而根据该第一表达式，即可准确的获取第一轮廓线上预设数量特征点在待标定传感器坐标系下的坐标集合。
可以理解的是，第一轮廓线位于目标标定板的边缘，第一轮廓线对应的点坐标可以包括待标定传感器所探测到的目标标定板该边缘上的点在待标定传感器坐标系下的坐标。
示例性地，标定装置可以根据第一点坐标集合，求取目标标定板中朝向待标定传感器的一面上中心点的坐标，根据该中心点的坐标，提取第一点坐标集合中第一轮廓 线所在边缘上的点的坐标，从而得到第一轮廓线对应的点坐标。例如，可以根据下述公式(1)求取目标标定板中朝向待标定传感器的一面上中心点的坐标：
Figure PCTCN2022075813-appb-000001
其中，n表示第一点坐标集合中点数量，xi、yi、zi表示第一点坐标集合中第i个点在待标定传感器坐标系下的坐标。x 0、y 0、z 0表示目标标定板中朝向待标定传感器的一面上中心点的坐标。
进而，标定装置可以对上述所提取的第一轮廓线对应的点坐标进行拟合，得到第一轮廓线的第一表达式。
作为一个示例，标定装置可以根据第一轮廓线的预设形状，对在第一点坐标集合中所提取的第一轮廓线对应的点坐标进行拟合，从而可以更加快速准确地得到第一轮廓线的第一表达式。例如，第一轮廓线的形状可以为直线，直线特征更易表达，从而可以更加准确快捷的拟合得到第一表达式。
作为另一个示例，由于第一轮廓线位于目标标定板中朝向待标定传感器的一面，标定装置可以求取目标标定板中朝向待标定传感器的一面所在的拟合平面，进而根据该拟合平面与第一轮廓线的位置关系，及第一轮廓线的预设形状，对在第一点坐标集合中所提取的第一轮廓线对应的点坐标进行拟合，从而可以更加快速准确地得到第一轮廓线的第一表达式。
示例性地，标定装置可以根据第一点坐标集合，采用现有拟合技术，例如，随机抽样一致性算法、最小二乘法、主成分分析法、奇异值分解等等，得到目标标定板中朝向待标定传感器的一面所在的拟合平面；例如，该拟合平面的表达式可以如下述公式(2)所示：
A·x+B·y+C·z+D＝0............................(2)
其中，A、B、C、D为常数，且A、B、C不同时为零，x、y、z分别表示拟合平面中任一点在待标定传感器坐标系中x轴、y轴、z轴对应的坐标。
示例性地，标定装置基于第一轮廓线的预设形状，并以第一轮廓线位于该拟合平面上作为约束，对第一点坐标集合中所提取的第一轮廓线对应的点坐标进行拟合；例如，以第一轮廓线为直线为例，该直线位于该拟合平面上，从而可以准确拟合出该直线的表达式。举例来说，以第一轮廓线为标定板A1中轮廓线a1为例，针对上述图4所示提取出的标定板A1对应的点云，提取轮廓线a1对应的点坐标进行拟合，拟合得到的轮廓线a1，图5为拟合后的轮廓线a1的示意图，如图5所示，拟合后的轮廓线a1位于标定板A1的上边缘。
步骤303、获取目标标定板对应的第二点坐标集合；第二点坐标集合包括目标标定板上至少一点在基准传感器坐标系下的坐标。
其中，基准传感器可以为与待标定传感器具有固定位姿关系的任一传感器。例如，若选取上述图1中传感器L1为待标定传感器，则传感器L2可以为基准传感器。
示例性地，基准传感器坐标系可以为以基准传感器的质心为原点的笛卡尔坐标系。
示例性地，第二点坐标集合可以包括基准传感器所探测到的目标标定板上的所有 点在基准传感器坐标系下的坐标。例如，以基准传感器为图1中传感器L2，目标标定板为标定板A1为例，第二点坐标集合可以包括标定板A1中朝向传感器L2的一面上的所有点在基准传感器坐标系下的坐标。
在一种可能的实现方式中，该步骤可以包括：获取基准传感器采集的第二数据；第二数据可以包括多个点在所述基准传感器坐标系下的坐标；根据基准传感器与目标标定板之间的预设距离，在第二数据中提取第二点坐标集合。
其中，基准传感器与目标标定板之间的预设距离可以基于基准传感器的位置及目标标定板的位置预先确定。
示例性地，第一数据可以包括基准传感器在标定场地内所探测到的所有点在基准传感器坐标系下的坐标。标定装置可以根据预设距离，确定目标标定板在基准传感器坐标系下对应的坐标范围；进而在基准传感器所探测到的所有点在基准传感器坐标系下的坐标中，筛选出该坐标范围内的坐标，从而得到第一点坐标集合。这样，根据基准传感器与目标标定板之间的预设距离，在基准传感器所采集的数据中，快捷准确地提取出目标标定板上的点在基准传感器坐标系下的坐标，从而在保证标定准确性的同时，提高了标定效率。
步骤304、根据第二点坐标集合，确定第一轮廓线对应的第二特征点信息。
示例性地，第二特征点信息可以包括：第一轮廓线上预设数量特征点在基准传感器坐标系下的坐标集合。示例性地，可以按照与上述步骤302中确定第一特征点信息相同的方式，确定第二特征点信息。
在一种可能的实现方式中，该步骤可以包括：提取第二点坐标集合中第一轮廓线对应的点坐标集合；对所提取的第二点坐标集合中第一轮廓线对应的点坐标进行拟合，得到第一轮廓线的第二表达式；根据第二表达式，确定第一轮廓线上预设数量特征点在基准传感器坐标系下的坐标集合。该实现方式的具体过程可参照上述步骤302中提取第一点坐标集合中第一轮廓线对应的点坐标；以及得到第一轮廓线的第一表达式的相关表述，在此不再赘述。由于第一轮廓线为直线、圆、或者其他可以用特定表达式所表示的曲线，其中，直线、圆均可以用特定表达式表示，因此，标定装置在提取第二点坐标集合中第一轮廓线对应的点坐标基础上，可以拟合得到能够准确表示第一轮廓线实际形状的第二表达式；进而根据该第二表达式，即可准确的获取第一轮廓线上预设数量特征点在基准传感器坐标系下的坐标集合。
需要说明的是，步骤303-304也可以在上述步骤301-302之前执行，对此不作限定。
步骤305、根据第一特征点信息及第二特征点信息，对待标定传感器的外参进行标定。
其中，外参可以包括表示待标定传感器与基准传感器之间的相对位姿关系的参数。例如，该参数可以包括：俯仰角(pitch)、翻滚角(roll)、偏航角(yaw)、x轴的平移量(t x)、y轴的平移量(t y)、z轴的平移量(t z)的一项或多项，其中，俯仰角表示围绕待标定传感器坐标系中y轴旋转的角度，偏航角表示围绕待标定传感器坐标系中z轴旋转的角度，翻滚角表示围绕待标定传感器坐标系中x轴旋转的角度，x轴的平移量表示沿待标定传感器坐标系中x轴平移的距离，y轴的平移量表示沿待标 定传感器坐标系中y轴平移的距离，z轴的平移量表示沿待标定传感器坐标系中z轴平移的距离。
示例性地，待标定传感器的外参可以用旋转矩阵及平移矩阵表示，其中，旋转矩阵表示从待标定传感器坐标系到基准传感器坐标系之间的旋转变换关系。作为一个示例，旋转矩阵可以为三行三列的矩阵，旋转矩阵包括3个自由度，这3个自由度分别对应于待标定传感器的x轴、y轴和z轴，旋转矩阵表示绕x轴、y轴和z轴这三个轴的旋转变换。例如，旋转矩阵R可以表示为下述公式(3)的形式：
Figure PCTCN2022075813-appb-000002
其中，α表示偏航角，β表示俯仰角，γ表示翻滚角。
平移矩阵表示从待标定传感器坐标系到基准传感器坐标系之间的平移变换关系。作为一个示例，旋转矩阵可以为一行三列的矩阵，平移矩阵包括3个自由度，这3个自由度分别对应于待标定传感器的x轴、y轴和z轴，平移矩阵表示沿x轴、y轴和z轴这三个轴方向的平移变换。例如，平移矩阵T可以表示为下述公式(4)的形式：
T＝(t x t y t z)........................................(4)
其中，t x t y t z分别为x轴、y轴和z轴的平移量。
可以理解的是，对于待标定传感器坐标系中的任一点而言，经由待标定传感器的外参进行变换后，可以得到该点在基准传感器坐标系中的同名点，或者变换后的坐标与同名点的坐标偏差很小；例如，对于待标定传感器坐标系中的任一点而言，利用待标定传感器的外参中旋转矩阵对该点进行旋转变换，并利用外参中的平移矩阵对该点进行平移变换后，能够得到该点在基准传感器坐标系中的同名点；如下述公式(5)所示：
Figure PCTCN2022075813-appb-000003
其中，R为旋转矩阵，T为平移矩阵，p2为待标定传感器坐标系中的某一点，x L2、y L2、z L2为点p2在待标定传感器坐标系中的坐标；p1为基准传感器坐标系中的p2的同名点，x L1、y L1、z L1为点p1在基准传感器坐标系中的坐标。
在一种可能的实现方式中，该步骤可以包括：通过将第一特征点信息与第二特征点信息进行配准，对待标定传感器的外参进行标定。这样，通过待标定传感器及基准传感器所探测到的第一轮廓线对应的特征点信息进行配准，从而快速准确地实现待标定传感器的外参的自动标定。示例性地，第一轮廓线的形状可以为直线，利用待标定传感器及基准传感器所探测到的同一直线对应的特征点信息进行配准，更易收敛，从而可以更加快速准确地实现待标定传感器的外参的自动标定。
示例性地，标定装置可以将第一轮廓线上预设数量特征点在待标定传感器坐标系下的坐标集合与第一轮廓线上预设数量特征点在基准传感器坐标系下的坐标集合进行配准，对待标定传感器的外参进行标定。
作为一个示例，可以根据下述公式(6)，采用最优化算法，迭代求取最优解，从而得到所标定的待标定激光雷达的外参。
D＝|P1–M*P2|................................(6)
其中，M为转换矩阵，
Figure PCTCN2022075813-appb-000004
R为旋转矩阵，T为平移矩阵，P1表示第一轮廓线上预设数量特征点在基准传感器坐标系下的坐标集合，P2表示第一轮廓线上预设数量特征点在待标定传感器坐标系下的坐标集合，D为P2中各特征点的坐标经由M变换后所得到新坐标对应点与P1中对应同名点的距离之和；
可以理解的是，根据几何一致性假设，P2中任一点的坐标经过转换矩阵M变换后，将与P1中对应同名点的坐标重合，即经过转换矩阵M变换后的点与其同名点之间的空间距离为0。因此，理论上当D为0时，此时的M的值即为最终解，考虑到实际应用中D不可能为0，对于公式(6)，可以采用最优化方法迭代求解，当满足迭代条件时(例如，D的数值足够小、连续多次迭代D的变化量足够小或迭代次数达到预设值等等)，从而得到M的最优解；进而可以由M的最优解反算出表示待标定传感器与基准传感器之间的相对位姿关系的参数，例如，可以根据上述公式(3)及公式(4)反算出俯仰角、翻滚角、偏航角、x轴的平移量、y轴的平移量或z轴的平移量，从而完成待标定传感器的外参标定。
示例性地，对于待标定传感器及基准传感器所探测到的各条预设形状的轮廓线，标定装置均可以执行上述操作，可以确定待标定传感器及基准传感器所探测的各条预设形状的轮廓线对应的特征点信息，并根据上述各条预设形状的轮廓线对应的特征点信息对待标定传感器的外参进行标定。
举例来说，图6示出了根据本申请一实施例的外参标定的示意图，如图6所示，箭头左侧为待标定传感器所探测到的标定板A1的各轮廓线与基准传感器所探测到的标定板A1的各轮廓线的相对位姿，两者存在偏差；箭头右侧为经由外参变换后待标定传感器所探测到的标定板A1的各轮廓线与基准传感器所探测到的标定板A的各轮廓线的相对位姿，若两者相重合或偏差在预设范围内时，则该外参即为所标定的待标定传感器的外参。
基于上述技术方案，第一轮廓线为预设形状，根据待标定传感器所采集的目标标定板对应的第一点坐标集合可以快速准确地确定第一轮廓线对应的第一特征点信息，根据基准传感器所采集的目标标定板对应的第二点坐标集合可以快速准确地确定第一轮廓线对应的第二特征点信息，并根据第一特征点信息及第二特征点信息，对待标定传感器的外参进行标定；从而实现利用目标标定板的轮廓特征进行外参标定，提高了标定效率和精度。
此外，相对于基于规整建筑或物体，采用手动进行外参标定的方式，本申请实施例基于预设形状的轮廓线，不依赖于规整的标定场景，实现了外参自动标定，有效提高了标定效率及适用范围。相对于基于自然环境进行外参标定的方式中，本申请实施例中无需构建稠密的点云地图，从而有效减少了标定过程中所需处理的点云数量，减少了计算时长，提高了标定效率；同时，无需其他传感器辅助，如无需实时差分定位(Real-time kinematic，RTK)、全球定位系统(Global Positioning System，GPS)、惯性测量单元(Inertial Measurement Unit，IMU)等，适用范围更加广泛。相对于基于平面法向量进行外参标定的方式，本申请实施例中以轮廓线的预设形状作为约束，避免了约束不强，容易陷入局部最优的问题，提高了标定的精度。
图7示出了根据本申请一实施例中一种标定方法的流程图；该方法可以由上述标定装置执行；如图7所示，该方法可以包括以下步骤：
步骤701、获取目标标定板的第一轮廓线对应的预设约束信息。
其中，预设约束信息可以包括：第一轮廓线的长度信息，和/或，第一轮廓线与目标标定板中其他轮廓线之间的相对位置关系。示例性地，相对位置关系可以包括：垂直、平行、或两条轮廓线之间的夹角等等。
举例来说，以目标标定板为上述图2中标定板A、第一轮廓线为图2中轮廓线a1为例；预设约束信息可以包括轮廓线a1的长度信息，也可以包括轮廓线a1与轮廓线a2、轮廓线a3或轮廓线a4之间的相对位置关系，例如，轮廓线a1与轮廓线a3平行、轮廓线a1与轮廓线a2垂直、轮廓线a1与轮廓线a4垂直等等。
示例性地，标定装置可以获取目标标定板中待标定传感器及基准传感器所探测到的各轮廓线对应的预设约束信息。
步骤702、获取目标标定板对应的第一点坐标集合。
该步骤可参照上述步骤301，在此不再赘述。
步骤703、根据第一点坐标集合及预设约束信息，确定第一轮廓线对应的第一特征点信息。
其中，第一特征点信息的具体说明可参照上述步骤302中相关表述。
在一种可能的实现方式中，该步骤可以包括：提取第一点坐标集合中第一轮廓线对应的点坐标；根据预设约束信息，对所提取的第一点坐标集合中第一轮廓线对应的点坐标进行拟合，得到第一表达式；根据第一表达式，确定第一轮廓线上预设数量特征点在待标定传感器坐标系下的坐标集合。由于第一轮廓线可以用特定表达式表示，且第一轮廓线的长度及第一轮廓线与其他轮廓线之间的相对位置存在约束，因此，标定装置在提取第一点坐标集合中第一轮廓线对应的点坐标基础上，基于第一轮廓线对应的预设约束信息，可以拟合得到能够准确表示第一轮廓线实际形状的第一表达式；进而根据该第一表达式，即可更加准确地获取第一轮廓线上预设数量特征点在待标定传感器坐标系下的坐标集合。
示例性地，标定装置可以根据第一点坐标集合，求取目标标定板中朝向待标定传感器的一面上中心点的坐标，根据该中心点的坐标以及预设约束信息，提取第一点坐标集合中第一轮廓线所在边缘上的点的坐标，从而得到第一轮廓线对应的点坐标。例如，标定装置可以根据中心点的坐标及第一轮廓线的长度信息，过滤掉地面等其他环境点云，从而更加准确的得到第一轮廓线对应的点坐标。
进而，标定装置可以根据预设约束信息对上述所提取的第一轮廓线对应的点坐标进行拟合，得到第一轮廓线的第一表达式。
作为一个示例，标定装置可以根据第一轮廓线对应的预设约束信息、第一轮廓线的预设形状，对在第一点坐标集合中所提取的第一轮廓线对应的点坐标进行拟合，可以准确地得到第一表达式。例如，第一轮廓线的形状可以为直线，直线特征更易表达，以第一轮廓线的直线特征以及第一轮廓线对应的预设约束关系，作为较强的约束，从而可以更加准确地拟合第一表达式。
作为另一个示例，标定装置可以根据第一轮廓线对应的预设约束信息、目标标定 板中朝向待标定传感器的一面所在的拟合平面与第一轮廓线的位置关系，及第一轮廓线的预设形状，对在第一点坐标集合中所提取的第一轮廓线对应的点坐标进行拟合，从而可以更加准确地得到第一表达式。
示例性地，标定装置基于第一轮廓线的预设形状，并以第一轮廓线位于该拟合平面上，以及第一轮廓线与目标标定板中其他轮廓线之间的相对位置关系作为约束，对第一点坐标集合中所提取的第一轮廓线对应的点坐标进行拟合；例如，以目标标定板中朝向待标定传感器的一面上各轮廓线为直线为例，则各直线位于该拟合平面上，且不同直线之间存在垂直、平行等相对位置关系，从而可以准确拟合出第一轮廓线的表达式。
在一种可能的实现方式中，标定装置可以提取目标标定板中待标定传感器及基准传感器所探测到的各轮廓线对应的点坐标；根据各轮廓线对应的预设约束信息，对所提取的各轮廓线对应的点坐标进行拟合，得到各轮廓线的表达式；根据各轮廓线的表达式，确定各轮廓线上预设数量特征点在待标定传感器坐标系下的坐标集合。
举例来说，以标定板A1中各轮廓线为例，轮廓线a1、轮廓线a2、轮廓线a3及轮廓线a4组成长方形；针对上述图4所示提取出的标定板A1对应的点云，提取出轮廓线a1、轮廓线a2、轮廓线a3、轮廓线a4对应的点坐标，进而以轮廓线a1与轮廓线a3平行、轮廓线a1与轮廓线a2垂直、轮廓线a1与轮廓线a4垂直、轮廓线a3与轮廓线a2垂直等相对位置关系以及轮廓线a1与轮廓线a3长度相等、轮廓线a2与轮廓线a4长度相等作为约束，拟合得到轮廓线a1、轮廓线a2、轮廓线a3、轮廓线a4，图8为拟合后的各轮廓线的示意图，如图8所示，标定板A1对应的点云位于拟合后的轮廓线a1、轮廓线a2、轮廓线a3、轮廓线a4所围成的长方形区域内。
步骤704、获取目标标定板对应的第二点坐标集合。
该步骤可参照上述步骤303，在此不再赘述。
步骤705、根据第二点坐标集合及预设约束信息，确定第一轮廓线对应的第二特征点信息。
其中，第二特征点信息的具体说明可参照上述步骤304中相关表述。
在一种可能的实现方式中，该步骤可以包括：提取第二点坐标集合中第一轮廓线对应的点坐标；根据预设约束信息，对所提取的第二点坐标集合中第一轮廓线对应的点坐标进行拟合，得到第二表达式；根据第二表达式，确定第一轮廓线上预设数量特征点在基准传感器坐标系下的坐标集合。该实现方式的具体过程可参照上述步骤703中提取第一点坐标集合中第一轮廓线对应的点坐标；以及得到第一轮廓线的第一表达式的相关表述，在此不再赘述。这样，标定装置在提取第二点坐标集合中第一轮廓线对应的点坐标基础上，基于第一轮廓线对应的预设约束信息，可以拟合得到能够准确表示第一轮廓线实际形状的第二表达式；进而根据该第二表达式，即可更加准确地获取第一轮廓线上预设数量特征点在基准传感器坐标系下的坐标集合。
在一种可能的实现方式中，标定装置可以提取目标标定板中待标定传感器及基准传感器所探测到的各轮廓线对应的点坐标；根据各轮廓线对应的预设约束信息，对所提取的各轮廓线对应的点坐标进行拟合，得到各轮廓线的表达式；根据各轮廓线的表达式，确定各轮廓线上预设数量特征点在基准传感器坐标系下的坐标集合。该实现方 式的具体过程可参照上述步骤703中的相关表述，在此不再赘述。
需要说明的是，步骤704-705也可以在上述步骤702-703之前执行，对此不作限定。
步骤706、根据第一特征点信息及第二特征点信息，对待标定传感器的外参进行标定。
该步骤可参照上述步骤305，在此不再赘述。
本申请实施例中，以第一轮廓线为预设形状及第一轮廓线对应的预设约束信息作为约束，根据待标定传感器所采集的目标标定板对应的第一点坐标集合可以更加准确地确定第一轮廓线对应的第一特征点信息，根据基准传感器所采集的目标标定板对应的第二点坐标集合可以更加准确地确定第一轮廓线对应的第二特征点信息，从而实现充分利用目标标定板的轮廓特征进行外参标定，进一步提高了标定精度。
基于上述方法实施例的同一发明构思，本申请的实施例还提供了一种标定装置，该标定装置用于执行上述方法实施例所描述的技术方案。例如，可以执行上述图3或图7中所示方法的各步骤。
图9示出根据本申请一实施例的一种标定装置的结构图，如图9所示，该标定装置可以包括：获取模块901，用于获取目标标定板对应的第一点坐标集合，所述第一点坐标集合包括所述目标标定板上至少一点在待标定传感器坐标系下的坐标；所述目标标定板的至少一条轮廓线为预设形状；处理模块902，用于根据所述第一点坐标集合，确定所述第一轮廓线对应的第一特征点信息，所述第一轮廓线为所述至少一条轮廓线中任一轮廓线；所述获取模块901，还用于：获取所述目标标定板对应的第二点坐标集合，所述第二点坐标集合包括所述目标标定板上至少一点在基准传感器坐标系下的坐标；所述处理模块902，还用于根据所述第二点坐标集合，确定所述第一轮廓线对应的第二特征点信息；根据所述第一特征点信息及所述第二特征点信息，对所述待标定传感器的外参进行标定；所述外参包括表示所述待标定传感器与所述基准传感器之间的相对位姿关系的参数。
基于上述技术方案，第一轮廓线为预设形状，根据待标定传感器所采集的目标标定板对应的第一点坐标集合可以快速准确地确定第一轮廓线对应的第一特征点信息，根据基准传感器所采集的目标标定板对应的第二点坐标集合可以快速准确地确定第一轮廓线对应的第二特征点信息，并根据第一特征点信息及第二特征点信息，对待标定传感器的外参进行标定；从而实现利用目标标定板的轮廓特征进行外参标定，提高了标定效率和精度。
在一种可能的实现方式中，所述获取模块901，还用于：获取所述第一轮廓线对应的预设约束信息，所述预设约束信息包括：所述第一轮廓线的长度信息，和/或，所述第一轮廓线与所述目标标定板中其他轮廓线之间的相对位置关系；所述处理模块902，还用于：根据所述第一点坐标集合及所述预设约束信息，确定所述第一特征点信息；和/或，根据所述第二点坐标集合及所述预设约束信息，确定所述第二特征点信息。
在一种可能的实现方式中，所述处理模块902，还用于：通过将所述第一特征点信息与所述第二特征点信息进行配准，对所述待标定传感器的外参进行标定。
在一种可能的实现方式中，所述第一特征点信息包括：所述第一轮廓线上预设数 量特征点在所述待标定传感器坐标系下的坐标集合；所述第二特征点信息包括：所述第一轮廓线上预设数量特征点在所述基准传感器坐标系下的坐标集合；所述处理模块902，还用于：提取所述第一点坐标集合中所述第一轮廓线对应的点坐标；对所提取的所述第一点坐标集合中所述第一轮廓线对应的点坐标进行拟合，得到所述第一轮廓线的第一表达式；根据所述第一表达式，确定所述第一轮廓线上预设数量特征点在所述待标定传感器坐标系下的坐标集合；提取所述第二点坐标集合中所述第一轮廓线对应的点坐标集合；对所提取的所述第二点坐标集合中所述第一轮廓线对应的点坐标进行拟合，得到所述第一轮廓线的第二表达式；根据所述第二表达式，确定所述第一轮廓线上预设数量特征点在所述基准传感器坐标系下的坐标集合。
在一种可能的实现方式中，所述处理模块902，还用于：获取所述第一轮廓线对应的预设约束信息；根据所述预设约束信息，对所提取的所述第一点坐标集合中所述第一轮廓线对应的点坐标进行拟合，得到所述第一表达式；和/或，获取所述第一轮廓线对应的预设约束信息；根据所述预设约束信息，对所提取的所述第二点坐标集合中所述第一轮廓线对应的点坐标进行拟合，得到所述第二表达式。
在一种可能的实现方式中，所述获取模块901，还用于：获取所述待标定传感器采集的第一数据；所述第一数据包括多个点在所述待标定传感器坐标系下的坐标；根据所述待标定传感器与所述目标标定板之间的预设距离，在所述第一数据中提取所述第一点坐标集合；和/或，获取所述基准传感器采集的第二数据；所述第二数据包括多个点在所述基准传感器坐标系下的坐标；根据所述基准传感器与所述目标标定板之间的预设距离，在所述第二数据中提取所述第二点坐标集合。
在一种可能的实现方式中，所述预设形状为直线。
上述图9所示的标定装置及其各种可能的实现方式的技术效果及具体描述可参见上述标定方法，此处不再赘述。
应理解以上装置中各模块的划分仅是一种逻辑功能的划分，实际实现时可以全部或部分集成到一个物理实体上，也可以物理上分开。此外，装置中的模块可以以处理器调用软件的形式实现；例如装置包括处理器，处理器与存储器连接，存储器中存储有指令，处理器调用存储器中存储的指令，以实现以上任一种方法或实现该装置各模块的功能，其中处理器例如为通用处理器，例如中央处理单元(Central Processing Unit，CPU)或微处理器，存储器为装置内的存储器或装置外的存储器。或者，装置中的模块可以以硬件电路的形式实现，可以通过对硬件电路的设计实现部分或全部模块的功能，该硬件电路可以理解为一个或多个处理器；例如，在一种实现中，该硬件电路为专用集成电路(application-specific integrated circuit，ASIC)，通过对电路内元件逻辑关系的设计，实现以上部分或全部模块的功能；再如，在另一种实现中，该硬件电路为可以通过可编程逻辑器件(programmable logic device，PLD)实现，以现场可编程门阵列(Field Programmable Gate Array，FPGA)为例，其可以包括大量逻辑门电路，通过配置文件来配置逻辑门电路之间的连接关系，从而实现以上部分或全部模块的功能。以上装置的所有模块可以全部通过处理器调用软件的形式实现，或全部通过硬件电路的形式实现，或部分通过处理器调用软件的形式实现，剩余部分通过硬件电路的形式实现。
在本申请实施例中，处理器是一种具有信号的处理能力的电路，在一种实现中，处理器可以是具有指令读取与运行能力的电路，例如CPU、微处理器、图形处理器(graphics processing unit，GPU)(可以理解为一种微处理器)、或数字信号处理器(digital signal processor，DSP)等；在另一种实现中，处理器可以通过硬件电路的逻辑关系实现一定功能，该硬件电路的逻辑关系是固定的或可以重构的，例如处理器为ASIC或PLD实现的硬件电路，例如FPGA。在可重构的硬件电路中，处理器加载配置文档，实现硬件电路配置的过程，可以理解为处理器加载指令，以实现以上部分或全部模块的功能的过程。
可见，以上装置中的各模块可以是被配置成实施以上方法的一个或多个处理器(或处理电路)，例如：CPU、GPU、微处理器、DSP、ASIC、FPGA，或这些处理器形式中至少两种的组合。
此外，以上装置中的各模块可以全部或部分可以集成在一起，或者可以独立实现。在一种实现中，这些模块集成在一起，以SOC的形式实现。该SOC中可以包括至少一个处理器，用于实现以上任一种方法或实现该装置各模块的功能，该至少一个处理器的种类可以不同，例如包括CPU和FPGA，CPU和人工智能处理器，CPU和GPU等。
本申请的实施例还提供了一种标定装置，包括：处理器；用于存储处理器可执行指令的存储器；其中，所述处理器被配置为执行所述指令时实现上述实施例的方法。示例性地，可以实现上述图3或图7中所示方法的各步骤。
图10示出根据本申请一实施例的一种标定装置的结构示意图，如图10所示，该标定装置可以包括：至少一个处理器1001，通信线路1002，存储器1003以及至少一个通信接口1004。
处理器1001可以是一个通用中央处理器(central processing unit，CPU)，微处理器，特定应用集成电路(application-specific integrated circuit，ASIC)，或一个或多个用于控制本申请方案程序执行的集成电路。
通信线路1002可包括一通路，在上述组件之间传送信息。
通信接口1004，使用任何收发器一类的装置，用于与其他设备或通信网络通信，如以太网，RAN，无线局域网(wireless local area networks，WLAN)等。
存储器1003可以是只读存储器(read-only memory，ROM)或可存储静态信息和指令的其他类型的静态存储设备，随机存取存储器(random access memory，RAM)或者可存储信息和指令的其他类型的动态存储设备，也可以是电可擦可编程只读存储器(electrically erasable programmable read-only memory，EEPROM)、只读光盘(compact disc read-only memory，CD-ROM)或其他光盘存储、光碟存储(包括压缩光碟、激光碟、光碟、数字通用光碟、蓝光光碟等)、磁盘存储介质或者其他磁存储设备、或者能够用于携带或存储具有指令或数据结构形式的期望的程序代码并能够由计算机存取的任何其他介质，但不限于此。存储器可以是独立存在，通过通信线路1002与处理器相连接。存储器也可以和处理器集成在一起。本申请实施例提供的存储器通常可以具有非易失性。其中，存储器1003用于存储执行本申请方案的计算机执行指令，并由处理器1001来控制执行。处理器1001用于执行存储器1003中存储的计算机执行指令， 从而实现本申请上述实施例中提供的方法。示例性地，可以实现上述图3或图7中所示方法的各步骤。
可选的，本申请实施例中的计算机执行指令也可以称之为应用程序代码，本申请实施例对此不作具体限定。
示例性地，处理器1001可以包括一个或多个CPU，例如图10中的CPU0和CPU1。
示例性地，标定装置可以包括多个处理器，例如图10中的处理器1001和处理器1007。这些处理器中的每一个可以是一个单核(single-CPU)处理器，也可以是一个多核(multi-CPU)处理器。这里的处理器可以指一个或多个设备、电路、和/或用于处理数据(例如计算机程序指令)的处理核。
在具体实现中，作为一种实施例，标定装置还可以包括输出设备1005和输入设备1006。输出设备1005和处理器1001通信，可以以多种方式来显示信息。例如，输出设备1005可以是液晶显示器(liquid crystal display，LCD)，发光二级管(light emitting diode，LED)显示设备，阴极射线管(cathode ray tube，CRT)显示设备，或投影仪(projector)等。输入设备1006和处理器1001通信，可以以多种方式接收用户的输入。例如，输入设备1006可以是鼠标、键盘、触摸屏设备或传感设备等。
作为一个示例，结合图10所示的标定装置，上述图9中的获取模块901可以由图10中的通信接口1004来实现；上述图9中的处理模块902可以由图10中的处理器1001来实现。
本申请的实施例提供了一种计算机可读存储介质，其上存储有计算机程序指令，所述计算机程序指令被处理器执行时实现上述实施例中的方法。示例性地，可以实现图3或图7中所示方法的各步骤。
本申请的实施例提供了一种计算机程序产品，例如，可以包括计算机可读代码，或者承载有计算机可读代码的非易失性计算机可读存储介质；当所述计算机程序产品在计算机上运行时，使得所述计算机执行上述实施例中的方法。示例性地，可以执行上述图3或图7中所示方法的各步骤。
计算机可读存储介质可以是可以保持和存储由指令执行设备使用的指令的有形设备。计算机可读存储介质例如可以是――但不限于――电存储设备、磁存储设备、光存储设备、电磁存储设备、半导体存储设备或者上述的任意合适的组合。计算机可读存储介质的更具体的例子(非穷举的列表)包括：便携式计算机盘、硬盘、随机存取存储器(Random Access Memory，RAM)、只读存储器(Read Only Memory，ROM)、可擦式可编程只读存储器(Electrically Programmable Read-Only-Memory，EPROM或闪存)、静态随机存取存储器(Static Random-Access Memory，SRAM)、便携式压缩盘只读存储器(Compact Disc Read-Only Memory，CD-ROM)、数字多功能盘(Digital Video Disc，DVD)、记忆棒、软盘、机械编码设备、例如其上存储有指令的打孔卡或凹槽内凸起结构、以及上述的任意合适的组合。
这里所描述的计算机可读程序指令或代码可以从计算机可读存储介质下载到各个计算/处理设备，或者通过网络、例如因特网、局域网、广域网和/或无线网下载到外部计算机或外部存储设备。网络可以包括铜传输电缆、光纤传输、无线传输、路由器、防火墙、交换机、网关计算机和/或边缘服务器。每个计算/处理设备中的网络适配卡 或者网络接口从网络接收计算机可读程序指令，并转发该计算机可读程序指令，以供存储在各个计算/处理设备中的计算机可读存储介质中。
用于执行本申请操作的计算机程序指令可以是汇编指令、指令集架构(Instruction Set Architecture，ISA)指令、机器指令、机器相关指令、微代码、固件指令、状态设置数据、或者以一种或多种编程语言的任意组合编写的源代码或目标代码，所述编程语言包括面向对象的编程语言—诸如Smalltalk、C++等，以及常规的过程式编程语言—诸如“C”语言或类似的编程语言。计算机可读程序指令可以完全地在用户计算机上执行、部分地在用户计算机上执行、作为一个独立的软件包执行、部分在用户计算机上部分在远程计算机上执行、或者完全在远程计算机或服务器上执行。在涉及远程计算机的情形中，远程计算机可以通过任意种类的网络—包括局域网(Local Area Network，LAN)或广域网(Wide Area Network，WAN)—连接到用户计算机，或者，可以连接到外部计算机(例如利用因特网服务提供商来通过因特网连接)。在一些实施例中，通过利用计算机可读程序指令的状态信息来个性化定制电子电路，例如可编程逻辑电路、现场可编程门阵列(Field-Programmable Gate Array，FPGA)或可编程逻辑阵列(Programmable Logic Array，PLA)，该电子电路可以执行计算机可读程序指令，从而实现本申请的各个方面。
这里参照根据本申请实施例的方法、装置(系统)和计算机程序产品的流程图和/或框图描述了本申请的各个方面。应当理解，流程图和/或框图的每个方框以及流程图和/或框图中各方框的组合，都可以由计算机可读程序指令实现。
这些计算机可读程序指令可以提供给通用计算机、专用计算机或其它可编程数据处理装置的处理器，从而生产出一种机器，使得这些指令在通过计算机或其它可编程数据处理装置的处理器执行时，产生了实现流程图和/或框图中的一个或多个方框中规定的功能/动作的装置。也可以把这些计算机可读程序指令存储在计算机可读存储介质中，这些指令使得计算机、可编程数据处理装置和/或其他设备以特定方式工作，从而，存储有指令的计算机可读介质则包括一个制造品，其包括实现流程图和/或框图中的一个或多个方框中规定的功能/动作的各个方面的指令。
也可以把计算机可读程序指令加载到计算机、其它可编程数据处理装置、或其它设备上，使得在计算机、其它可编程数据处理装置或其它设备上执行一系列操作步骤，以产生计算机实现的过程，从而使得在计算机、其它可编程数据处理装置、或其它设备上执行的指令实现流程图和/或框图中的一个或多个方框中规定的功能/动作。
附图中的流程图和框图显示了根据本申请的多个实施例的装置、系统、方法和计算机程序产品的可能实现的体系架构、功能和操作。在这点上，流程图或框图中的每个方框可以代表一个模块、程序段或指令的一部分，所述模块、程序段或指令的一部分包含一个或多个用于实现规定的逻辑功能的可执行指令。在有些作为替换的实现中，方框中所标注的功能也可以以不同于附图中所标注的顺序发生。例如，两个连续的方框实际上可以基本并行地执行，它们有时也可以按相反的顺序执行，这依所涉及的功能而定。
也要注意的是，框图和/或流程图中的每个方框、以及框图和/或流程图中的方框的组合，可以用执行相应的功能或动作的硬件(例如电路或ASIC(Application  Specific Integrated Circuit，专用集成电路))来实现，或者可以用硬件和软件的组合，如固件等来实现。
尽管在此结合各实施例对本发明进行了描述，然而，在实施所要求保护的本发明过程中，本领域技术人员通过查看所述附图、公开内容、以及所附权利要求书，可理解并实现所述公开实施例的其它变化。在权利要求中，“包括”(comprising)一词不排除其他组成部分或步骤，“一”或“一个”不排除多个的情况。单个处理器或其它单元可以实现权利要求中列举的若干项功能。相互不同的从属权利要求中记载了某些措施，但这并不表示这些措施不能组合起来产生良好的效果。
在本申请的各个实施例中，如果没有特殊说明以及逻辑冲突，各个实施例之间的术语和/或描述具有一致性、且可以相互引用，不同的实施例中的技术特征根据其内在的逻辑关系可以组合形成新的实施例。
以上所述，仅为本发明的具体实施方式，但本发明的保护范围并不局限于此，任何熟悉本技术领域的技术人员在本发明揭露的技术范围内，可轻易想到变化或替换，都应涵盖在本发明的保护范围之内。因此，本发明的保护范围应以所述权利要求的保护范围为准。
以上所述，仅为本发明的具体实施方式，但本发明的保护范围并不局限于此，任何熟悉本技术领域的技术人员在本发明揭露的技术范围内，可轻易想到变化或替换，都应涵盖在本发明的保护范围之内。因此，本发明的保护范围应以所述权利要求的保护范围为准。

Claims (17)

  1. 一种标定方法，其特征在于，所述方法包括：
    获取目标标定板对应的第一点坐标集合，所述第一点坐标集合包括所述目标标定板上至少一点在待标定传感器坐标系下的坐标；所述目标标定板的至少一条轮廓线为预设形状；
    根据所述第一点坐标集合，确定第一轮廓线对应的第一特征点信息；所述第一轮廓线为所述至少一条轮廓线中任一轮廓线；
    获取所述目标标定板对应的第二点坐标集合，所述第二点坐标集合包括所述目标标定板上至少一点在基准传感器坐标系下的坐标；
    根据所述第二点坐标集合，确定所述第一轮廓线对应的第二特征点信息；
    根据所述第一特征点信息及所述第二特征点信息，对所述待标定传感器的外参进行标定；所述外参包括表示所述待标定传感器与所述基准传感器之间的相对位姿关系的参数。
  2. 根据权利要求1所述的方法，其特征在于，所述方法还包括：
    获取所述第一轮廓线对应的预设约束信息，所述预设约束信息包括：所述第一轮廓线的长度信息，和/或，所述第一轮廓线与所述目标标定板中其他轮廓线之间的相对位置关系；
    所述根据所述第一点坐标集合，确定所述第一轮廓线对应的第一特征点信息，包括：
    根据所述第一点坐标集合及所述预设约束信息，确定所述第一特征点信息；
    和/或，
    所述根据所述第二点坐标集合，确定所述第一轮廓线对应的第二特征点信息，包括：
    根据所述第二点坐标集合及所述预设约束信息，确定所述第二特征点信息。
  3. 根据权利要求1或2所述的方法，其特征在于，所述根据所述第一特征点信息及所述第二特征点信息，对所述待标定传感器的外参进行标定，包括：
    通过将所述第一特征点信息与所述第二特征点信息进行配准，对所述待标定传感器的外参进行标定。
  4. 根据权利要求1-3中任一项所述的方法，其特征在于，所述第一特征点信息包括：所述第一轮廓线上预设数量特征点在所述待标定传感器坐标系下的坐标集合；所述第二特征点信息包括：所述第一轮廓线上预设数量特征点在所述基准传感器坐标系下的坐标集合；
    所述根据所述第一点坐标集合，确定所述第一轮廓线对应的第一特征点信息，包括：
    提取所述第一点坐标集合中所述第一轮廓线对应的点坐标；
    对所提取的所述第一点坐标集合中所述第一轮廓线对应的点坐标进行拟合，得到所述第一轮廓线的第一表达式；
    根据所述第一表达式，确定所述第一轮廓线上预设数量特征点在所述待标定传感器坐标系下的坐标集合；
    所述根据所述第二点坐标集合，确定所述第一轮廓线对应的第二特征点信息，包括：
    提取所述第二点坐标集合中所述第一轮廓线对应的点坐标集合；
    对所提取的所述第二点坐标集合中所述第一轮廓线对应的点坐标进行拟合，得到所述第一轮廓线的第二表达式；
    根据所述第二表达式，确定所述第一轮廓线上预设数量特征点在所述基准传感器坐标系下的坐标集合。
  5. 根据权利要求4所述的方法，其特征在于，所述对所提取的所述第一点坐标集合中所述第一轮廓线对应的点坐标进行拟合，得到所述第一轮廓线的第一表达式，包括：
    获取所述第一轮廓线对应的预设约束信息；
    根据所述预设约束信息，对所提取的所述第一点坐标集合中所述第一轮廓线对应的点坐标进行拟合，得到所述第一表达式；
    和/或，
    所述对所提取的所述第二点坐标集合中所述第一轮廓线对应的点坐标进行拟合，得到所述第一轮廓线的第二表达式，包括：
    获取所述第一轮廓线对应的预设约束信息；
    根据所述预设约束信息，对所提取的所述第二点坐标集合中所述第一轮廓线对应的点坐标进行拟合，得到所述第二表达式。
  6. 根据权利要求1-5中任一项所述的方法，其特征在于，所述获取目标标定板对应的第一点坐标集合，包括：
    获取所述待标定传感器采集的第一数据；所述第一数据包括多个点在所述待标定传感器坐标系下的坐标；
    根据所述待标定传感器与所述目标标定板之间的预设距离，在所述第一数据中提取所述第一点坐标集合；
    和/或，
    所述获取所述目标标定板对应的第二点坐标集合，包括：
    获取所述基准传感器采集的第二数据；所述第二数据包括多个点在所述基准传感器坐标系下的坐标；
    根据所述基准传感器与所述目标标定板之间的预设距离，在所述第二数据中提取所述第二点坐标集合。
  7. 根据权利要求1-6中任一项所述的方法，其特征在于，所述预设形状为直线。
  8. 一种标定装置，其特征在于，所述装置包括：
    获取模块，用于获取目标标定板对应的第一点坐标集合，所述第一点坐标集合包括所述目标标定板上至少一点在待标定传感器坐标系下的坐标；所述目标标定板的至少一条轮廓线为预设形状；
    处理模块，用于根据所述第一点坐标集合，确定第一轮廓线对应的第一特征点信息； 所述第一轮廓线为所述至少一条轮廓线中任一轮廓线；
    所述获取模块，还用于：获取所述目标标定板对应的第二点坐标集合，所述第二点坐标集合包括所述目标标定板上至少一点在基准传感器坐标系下的坐标；
    所述处理模块，还用于根据所述第二点坐标集合，确定所述第一轮廓线对应的第二特征点信息；根据所述第一特征点信息及所述第二特征点信息，对所述待标定传感器的外参进行标定；所述外参包括表示所述待标定传感器与所述基准传感器之间的相对位姿关系的参数。
  9. 根据权利要求8所述的装置，其特征在于，所述获取模块，还用于：获取所述第一轮廓线对应的预设约束信息，所述预设约束信息包括：所述第一轮廓线的长度信息，和/或，所述第一轮廓线与所述目标标定板中其他轮廓线之间的相对位置关系；
    所述处理模块，还用于：根据所述第一点坐标集合及所述预设约束信息，确定所述第一特征点信息；和/或，根据所述第二点坐标集合及所述预设约束信息，确定所述第二特征点信息。
  10. 根据权利要求8或9所述的装置，其特征在于，所述处理模块，还用于：通过将所述第一特征点信息与所述第二特征点信息进行配准，对所述待标定传感器的外参进行标定。
  11. 根据权利要求8-10中任一项所述的装置，其特征在于，所述第一特征点信息包括：所述第一轮廓线上预设数量特征点在所述待标定传感器坐标系下的坐标集合；所述第二特征点信息包括：所述第一轮廓线上预设数量特征点在所述基准传感器坐标系下的坐标集合；
    所述处理模块，还用于：提取所述第一点坐标集合中所述第一轮廓线对应的点坐标；对所提取的所述第一点坐标集合中所述第一轮廓线对应的点坐标进行拟合，得到所述第一轮廓线的第一表达式；根据所述第一表达式，确定所述第一轮廓线上预设数量特征点在所述待标定传感器坐标系下的坐标集合；提取所述第二点坐标集合中所述第一轮廓线对应的点坐标集合；对所提取的所述第二点坐标集合中所述第一轮廓线对应的点坐标进行拟合，得到所述第一轮廓线的第二表达式；根据所述第二表达式，确定所述第一轮廓线上预设数量特征点在所述基准传感器坐标系下的坐标集合。
  12. 根据权利要求11所述的装置，其特征在于，所述处理模块，还用于：获取所述第一轮廓线对应的预设约束信息；根据所述预设约束信息，对所提取的所述第一点坐标集合中所述第一轮廓线对应的点坐标进行拟合，得到所述第一表达式；和/或，获取所述第一轮廓线对应的预设约束信息；根据所述预设约束信息，对所提取的所述第二点坐标集合中所述第一轮廓线对应的点坐标进行拟合，得到所述第二表达式。
  13. 根据权利要求8-12中任一项所述的装置，其特征在于，所述获取模块，还用于：获取所述待标定传感器采集的第一数据；所述第一数据包括多个点在所述待标定传感 器坐标系下的坐标；根据所述待标定传感器与所述目标标定板之间的预设距离，在所述第一数据中提取所述第一点坐标集合；和/或，获取所述基准传感器采集的第二数据；所述第二数据包括多个点在所述基准传感器坐标系下的坐标；根据所述基准传感器与所述目标标定板之间的预设距离，在所述第二数据中提取所述第二点坐标集合。
  14. 根据权利要求8-13中任一项所述的装置，其特征在于，所述预设形状为直线。
  15. 一种标定装置，其特征在于，包括：
    处理器；
    用于存储处理器可执行指令的存储器；
    其中，所述处理器被配置为执行所述指令时实现权利要求1-7中任意一项所述的方法。
  16. 一种计算机可读存储介质，其上存储有计算机程序指令，其特征在于，所述计算机程序指令被处理器执行时实现权利要求1-7中任意一项所述的方法。
  17. 一种包含指令的计算机程序产品，其特征在于，当其在计算机上运行时，使得所述计算机执行如权利要求1-7中任意一项所述的方法。
PCT/CN2022/075813 2022-02-10 2022-02-10 一种标定方法及装置 WO2023150961A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
CN202280006244.3A CN116897300A (zh) 2022-02-10 2022-02-10 一种标定方法及装置
PCT/CN2022/075813 WO2023150961A1 (zh) 2022-02-10 2022-02-10 一种标定方法及装置

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2022/075813 WO2023150961A1 (zh) 2022-02-10 2022-02-10 一种标定方法及装置

Publications (1)

Publication Number Publication Date
WO2023150961A1 true WO2023150961A1 (zh) 2023-08-17

Family

ID=87563431

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/075813 WO2023150961A1 (zh) 2022-02-10 2022-02-10 一种标定方法及装置

Country Status (2)

Country Link
CN (1) CN116897300A (zh)
WO (1) WO2023150961A1 (zh)

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110161485A (zh) * 2019-06-13 2019-08-23 同济大学 一种激光雷达与视觉相机的外参标定装置及标定方法
CN110221275A (zh) * 2019-05-21 2019-09-10 菜鸟智能物流控股有限公司 一种激光雷达与相机之间的标定方法和装置
US20210003684A1 (en) * 2019-07-05 2021-01-07 DeepMap Inc. Online sensor calibration for autonomous vehicles
CN112465915A (zh) * 2020-11-26 2021-03-09 广州敏视数码科技有限公司 一种车载环视系统标定方法
CN112859022A (zh) * 2021-01-22 2021-05-28 上海西井信息科技有限公司 多种雷达和相机联合标定方法、系统、设备及存储介质
CN113870366A (zh) * 2021-10-18 2021-12-31 中国科学院长春光学精密机械与物理研究所 基于位姿传感器的三维扫描系统的标定方法及其标定系统

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110221275A (zh) * 2019-05-21 2019-09-10 菜鸟智能物流控股有限公司 一种激光雷达与相机之间的标定方法和装置
CN110161485A (zh) * 2019-06-13 2019-08-23 同济大学 一种激光雷达与视觉相机的外参标定装置及标定方法
US20210003684A1 (en) * 2019-07-05 2021-01-07 DeepMap Inc. Online sensor calibration for autonomous vehicles
CN112465915A (zh) * 2020-11-26 2021-03-09 广州敏视数码科技有限公司 一种车载环视系统标定方法
CN112859022A (zh) * 2021-01-22 2021-05-28 上海西井信息科技有限公司 多种雷达和相机联合标定方法、系统、设备及存储介质
CN113870366A (zh) * 2021-10-18 2021-12-31 中国科学院长春光学精密机械与物理研究所 基于位姿传感器的三维扫描系统的标定方法及其标定系统

Also Published As

Publication number Publication date
CN116897300A (zh) 2023-10-17

Similar Documents

Publication Publication Date Title
US11030803B2 (en) Method and apparatus for generating raster map
CN109297510B (zh) 相对位姿标定方法、装置、设备及介质
Kumar et al. A LiDAR and IMU integrated indoor navigation system for UAVs and its application in real-time pipeline classification
CN110780285B (zh) 激光雷达与组合惯导的位姿标定方法、系统及介质
CN112654886B (zh) 外参标定方法、装置、设备及存储介质
WO2022156176A1 (zh) 多种雷达和相机联合标定方法、系统、设备及存储介质
CN109946680B (zh) 探测系统的外参数标定方法、装置、存储介质及标定系统
CN110264502B (zh) 点云配准方法和装置
CN109270545B (zh) 一种定位真值校验方法、装置、设备及存储介质
CN110470333B (zh) 传感器参数的标定方法及装置、存储介质和电子装置
CN112379352B (zh) 一种激光雷达标定方法、装置、设备及存储介质
CN108326845B (zh) 基于双目相机和激光雷达的机器人定位方法、装置及系统
CN111913169B (zh) 激光雷达内参、点云数据的修正方法、设备及存储介质
CN111179351B (zh) 一种参数标定方法及其装置、处理设备
JP2018096969A (ja) ジオアーク（ｇｅｏａｒｃ）を使用したビークルの二次元位置の特定
CN111080682A (zh) 点云数据的配准方法及装置
JP2018072316A (ja) ジオアーク（ｇｅｏａｒｃ）を使用したビークルの二次元位置の特定
CN113436233A (zh) 自动驾驶车辆的配准方法、装置、电子设备和车辆
WO2021081958A1 (zh) 地形检测方法、可移动平台、控制设备、系统及存储介质
WO2023150961A1 (zh) 一种标定方法及装置
WO2022160879A1 (zh) 一种转换参数的确定方法和装置
CN114910892A (zh) 一种激光雷达的标定方法、装置、电子设备及存储介质
Zhang et al. PVL-Cartographer: panoramic vision-aided lidar cartographer-based slam for maverick mobile mapping system
CN114545377A (zh) 一种激光雷达标定方法及装置
Asl Sabbaghian Hokmabadi et al. Shaped-Based Tightly Coupled IMU/Camera Object-Level SLAM

Legal Events

Date Code Title Description
WWE Wipo information: entry into national phase

Ref document number: 202280006244.3

Country of ref document: CN

121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 22925323

Country of ref document: EP

Kind code of ref document: A1