Camera external parameter calibration method, system and device and computer storage medium

Abstract

The invention provides a camera external parameter calibration method, system and device and a computer storage medium. The camera external parameter calibration method comprises the steps that a sensor on a vehicle body is used for collecting wall surface point cloud; the geometrical relationship between a camera calibration board and the wall surface is obtained, and the camera calibration board is arranged on the wall surface; acquiring a first pose transformation matrix of the wall point cloud transformed from a wall coordinate system to a camera coordinate system according to the geometrical relationship; acquiring a second pose transformation matrix of the wall surface point cloud transformed from the vehicle body coordinate system to the wall surface coordinate system; according to the first pose transformation matrix and the second pose transformation matrix, obtaining a third pose transformation matrix of the wall surface point cloud transformed from the camera coordinate system to the vehicle body coordinate system; and calculating external parameters of the camera according to the third pose transformation matrix. Through the above mode, the dependence on manual calibration is reduced through the geometrical relationship between the wall surface and the camera calibration plate, and the calibration effect is accurate while the design of a calibration scene is simplified.

Description

TECHNICAL FIELD

[0001] The application relates to the technical field of sensors, in particular to a camera extrinsic parameter calibration method, system and device and a computer storage medium. BACKGROUND

[0002] In a multi-sensor system, the extrinsic parameter calibration of a camera and a laser radar is the basis for data fusion. In the prior art, a specific calibration board such as a checkerboard or an ArUco code is used to calculate the extrinsic parameters by extracting the image and point cloud features of the target, which has the shortcomings of excessive dependence on artificial design of a calibration scene and complex calibration. SUMMARY

[0003] To solve the above technical problems, the application provides a camera extrinsic parameter calibration method, which comprises the following steps: collecting wall point clouds by using a sensor on a vehicle body; obtaining a geometric relationship between a camera calibration board and a wall, wherein the camera calibration board is arranged on the wall; obtaining a first pose transformation matrix of the wall point clouds from a wall coordinate system to a camera coordinate system according to the geometric relationship; obtaining a second pose transformation matrix of the wall point clouds from a vehicle body coordinate system to the wall coordinate system; obtaining a third pose transformation matrix of the wall point clouds from the camera coordinate system to the vehicle body coordinate system according to the first pose transformation matrix and the second pose transformation matrix; and calculating camera extrinsic parameters according to the third pose transformation matrix.

[0004] In the application, the x-axis of the coordinate system in which the initial position of the camera calibration board is located is parallel to the ground, and the y-axis is perpendicular to the intersection line of the wall.

[0005] In the application, the camera extrinsic parameter calibration method further comprises the following steps: obtaining a fourth pose transformation matrix of the wall point clouds from the camera coordinate system to the camera calibration board coordinate system according to the geometric relationship; obtaining a fifth pose transformation matrix of the wall point clouds from the wall coordinate system to the camera calibration board coordinate system; and calculating the first pose transformation matrix according to the fourth pose transformation matrix and the fifth pose transformation matrix.

[0006] In the application, the fourth pose transformation matrix of the wall point clouds from the camera coordinate system to the camera calibration board coordinate system according to the geometric relationship comprises the following steps: rotating the x-axis, the y-axis and the z-axis of the camera calibration board coordinate system; calculating a first rotation matrix component of the pose transformation of the wall point clouds from the wall coordinate system to the camera calibration board coordinate system according to a rotation angle; obtaining a first translation matrix component of the pose transformation of the wall point clouds from the wall coordinate system to the calibration board coordinate system according to the origin coordinates of the wall coordinate system; and obtaining the fifth pose transformation matrix according to the first rotation matrix component and the first translation matrix component.

[0007] The wall surface is L-shaped, the wall surface comprises a first wall surface and a second wall surface, and the first wall surface and the second wall surface intersect; the second pose transformation matrix of the wall surface point cloud from the wall body coordinate system to the wall surface coordinate system is obtained by: acquiring a fitting straight line of at least one group of the first wall surface and the second wall surface respectively, and solving an intersection point of each group of the fitting straight line of the first wall surface and the second wall surface; calculating a yaw angle of the pose transformation of the wall surface point cloud from the wall body coordinate system to the wall surface coordinate system according to the coordinates of the intersection point; acquiring a second translation matrix component of the pose transformation of the wall surface point cloud from the wall surface coordinate system to the wall body coordinate system; calculating a second rotation matrix component of the pose transformation of the wall surface point cloud from the wall surface coordinate system to the wall body coordinate system according to the yaw angle; and acquiring the second pose transformation matrix according to the second rotation matrix component and the second translation matrix component.

[0008] The third pose transformation matrix comprises a third rotation matrix component and a third translation matrix component; the camera extrinsic parameter is calculated according to the third rotation matrix component and the third translation matrix component.

[0009] The camera extrinsic parameter comprises Euler angles and position parameters; the camera extrinsic parameter is calculated according to the third rotation matrix component and the third translation matrix component, which comprises: calculating the position parameters according to the third translation matrix component; and calculating the Euler angles according to the third rotation matrix component.

[0010] To solve the above technical problems, the application provides a camera extrinsic parameter calibration system, which comprises a vehicle body, a sensor, a camera calibration board, a processor, the sensor is arranged on the vehicle body, and the camera calibration board is arranged on a wall surface; the vehicle body collects wall surface point cloud by using the sensor on the vehicle body; the processor is used to: acquire the geometric relationship between the camera calibration board and the wall surface, wherein the camera calibration board is arranged on the wall surface; acquire a first pose transformation matrix of the wall surface point cloud from a wall surface coordinate system to a camera coordinate system according to the geometric relationship; acquire a second pose transformation matrix of the wall surface point cloud from a vehicle body coordinate system to the wall surface coordinate system based on the wall surface point cloud; acquire a third pose transformation matrix of the wall surface point cloud from the camera coordinate system to the vehicle body coordinate system according to the first pose transformation matrix and the second pose transformation matrix; and calculate a camera extrinsic parameter according to the third pose transformation matrix.

[0011] To solve the above technical problems, the application provides a camera extrinsic parameter calibration device, which comprises a memory and a processor coupled with the memory; wherein the memory is used for storing program data, and the processor is used for executing the program data to realize the camera extrinsic parameter calibration method.

[0012] To solve the above technical problems, the application provides a computer storage medium, which is used for storing program data, and the program data is used to realize the camera extrinsic parameter calibration method when executed by a computer.

[0013] Distinguished from the prior art, the application has the beneficial effects that: the camera extrinsic parameter calibration device uses the sensor on the vehicle body to collect the wall point cloud; the geometric relationship between the camera calibration board and the wall is obtained, wherein the camera calibration board is arranged on the wall; the first pose transformation matrix of the wall point cloud from the wall coordinate system to the camera coordinate system is obtained according to the geometric relationship; the second pose transformation matrix of the wall point cloud from the vehicle body coordinate system to the wall coordinate system is obtained; the third pose transformation matrix of the wall point cloud from the camera coordinate system to the vehicle body coordinate system is obtained according to the first pose transformation matrix and the second pose transformation matrix; and the camera extrinsic parameter is calculated according to the third pose transformation matrix. In the above manner, through the geometric relationship between the wall and the camera calibration board, the dependence on manual calibration is reduced, and the design of the calibration scene can be simplified while the calibration effect is accurate. BRIEF DESCRIPTION OF DRAWINGS

[0014] In order to more clearly illustrate the technical solutions in the embodiments of the application, the following will briefly introduce the drawings needed to be used in the embodiment description. Obviously, the drawings in the following description are only some embodiments of the application, and other drawings can be obtained by those skilled in the art without creative labor.

[0015] Figure 1 is a flowchart of the first embodiment of the camera extrinsic parameter calibration method provided by the application;

[0016] Figure 2 is a connection model schematic diagram of the vehicle body and the sensor module provided by the application;

[0017] Figure 3 is a calibration scene schematic diagram provided by the application;

[0018] Figure 4 is a wall point cloud overhead view in the vehicle body coordinate system provided by the application;

[0019] Figure 5 is a flowchart of the second embodiment of the camera extrinsic parameter calibration method provided by the application;

[0020] Figure 6 is a schematic diagram of an embodiment of the camera extrinsic parameter calibration method provided by the present application. Figure 5 is a flowchart of a sub-step of step S22 in the embodiment of the camera extrinsic parameter calibration method provided by the present application.

[0021] Figure 7 is a schematic diagram of an embodiment of the camera extrinsic parameter calibration system provided by the present application.

[0022] Figure 8 is a structural schematic diagram of an embodiment of the camera extrinsic parameter calibration device provided by the present application.

[0023] Figure 9 is a structural schematic diagram of an embodiment of the computer storage medium provided by the present application. DETAILED DESCRIPTION

[0024] The technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work fall within the scope of protection of the present application.

[0025] To solve the above technical problems, the present application provides a camera extrinsic parameter calibration method. In the embodiment, the camera extrinsic parameter calibration method provided by the present application is applied to a camera extrinsic parameter calibration device. The camera extrinsic parameter calibration device can be a server or a system composed of a server and a local terminal. Correspondingly, each part of the camera extrinsic parameter calibration device, such as each unit, sub-unit, module, and sub-module, can be arranged in the server or arranged in the server and the local terminal respectively.

[0026] Further, the server can be hardware or software. When the server is hardware, it can be implemented as a distributed server cluster composed of multiple servers or as a single server. When the server is software, it can be implemented as multiple software or software modules, such as software or software modules for providing a distributed server, or as a single software or software module, which is not limited here. In some possible implementation manners, the camera extrinsic parameter calibration method provided by the embodiments of the present application can be implemented by a processor calling computer readable instructions stored in a memory.

[0027] Please refer to Figures 1-4 , Figure 1 is a flowchart of the first embodiment of the camera extrinsic parameter calibration method provided by the present application, Figure 2 is a schematic diagram of a connection model of a vehicle body and a sensor module, Figure 3is a calibration scene schematic diagram provided by the present application, Figure 4 is a wall point cloud top view in the vehicle body coordinate system provided by the present application.

[0028] As Figure 1 shown, the specific steps are as follows:

[0029] Step S11: Collecting wall point cloud by using sensors on the vehicle body.

[0030] As Figure 2 shown, the vehicle body 100 is provided with sensors, which can include a laser radar 101 and a camera 102, wherein the types, number and position of the laser radar and the camera are not specifically limited in the present application, and in some embodiments, a binocular camera can also be used.

[0031] Specifically, the camera extrinsic calibration device scans by using sensors on the vehicle body, collects wall point cloud, and collects a group of synchronous data of laser radar point cloud and camera image in a static manner when the vehicle body faces the wall, in the embodiment of the present application, the wall can be as Figures 3-4 shown, the present application takes the wall shape as shown in Figures 3-4 as an example, in other embodiments of the present application, any position and shape of wall can be used.

[0032] Step S12: Obtain the geometric relationship between the camera calibration board and the wall.

[0033] The geometric relationship is that the camera calibration board is pasted or placed on the wall to generate a relative position relationship with the wall.

[0034] In the embodiment of the present application, the camera calibration board is arranged on the wall, please continue to refer to Figure 3 , wherein the dashed line in the figure is the wall point cloud obtained by the laser radar, O X′Y′Z′ is the camera calibration board coordinate system, O XYZ is the wall coordinate system.

[0035] In the specific embodiment of the present application, the x-axis of the coordinate system where the initial position of the camera calibration board is located is parallel to the ground, and the y-axis is perpendicular to the intersection line of the wall.

[0036] In a specific embodiment of the present application, as Figure 3 shown, the camera calibration board is pasted on the left wall of the L-shaped wall, and the x-axis of the camera calibration board coordinate system O X′Y′Z′ is perpendicular to the ground and the y-axis is perpendicular to the intersection line of the wall by drawing a line on the wall in advance. The distance from the origin of the calibration board coordinate system to the ground is dx, and the distance to the intersection line of the wall is dy.

[0037] It should be noted that the size, dimension or shape of the camera calibration board is not limited in the embodiment of the present application.

[0038] Step S13: Obtain a first pose transformation matrix of the wall point cloud from the wall coordinate system to the camera coordinate system according to the geometric relationship.

[0039] Specifically, please refer to Figure 5 , Figure 5 is a flowchart of a second embodiment of the camera extrinsic parameter calibration method provided in the present application.

[0040] As Figure 5 indicated, the specific steps are as follows:

[0041] Step S21: Obtain a fourth pose transformation matrix of the wall point cloud from the camera coordinate system to the camera calibration board coordinate system according to the geometric relationship.

[0042] Specifically, the camera extrinsic parameter calibration device obtains a fourth pose transformation matrix of the wall point cloud from the camera coordinate system to the camera calibration board coordinate system according to the positions of the camera calibration board and the wall. In the embodiment of the present application, the camera extrinsic parameter calibration device performs a de-distortion operation on the collected camera calibration board image according to the previously calibrated intrinsic parameters and distortion coefficients of the camera, and then calculates the pose transformation of the camera coordinate system to the camera calibration board coordinate system by recognizing the pose of the apriltag two-dimensional code.

[0043] Specifically, the pose transformation of the wall coordinate system to the camera calibration board coordinate system is as follows:

[0044]

[0045] wherein, is a transformation matrix of the wall point cloud from the wall coordinate system to the camera calibration board coordinate system. is a rotation matrix of the wall coordinate system to the camera calibration board coordinate system, is a translation matrix of the wall coordinate system to the camera calibration board coordinate system.

[0046] Step S22: Obtain a fifth pose transformation matrix of the wall point cloud from the wall coordinate system to the camera calibration board coordinate system.

[0047] The specific steps are described in steps S221-S224.

[0048] Step S23: Calculate the first pose transformation matrix according to the fourth pose transformation matrix and the fifth pose transformation matrix.

[0049] Specifically, the pose transformation of the wall coordinate system to the camera coordinate system is as follows:

[0050]

[0051] wherein, a pose transformation matrix of the wall surface point cloud from the wall surface coordinate system to the camera coordinate system, a pose transformation matrix of the wall surface point cloud from the camera calibration board coordinate system to the camera coordinate system, a transformation matrix of the wall surface point cloud from the wall surface coordinate system to the camera calibration board coordinate system.

[0052] Please refer to Figure 6 , Figure 6 is the camera extrinsic calibration method provided by the present application Figure 5 the flowchart of the sub-step of step S22 in the method.

[0053] As Figure 6 shown, the specific steps are as follows:

[0054] Step S221: rotating the x-axis, y-axis and z-axis of the camera calibration board coordinate system.

[0055] Specifically, the camera extrinsic calibration device specifies R axis (alpha) is a rotation matrix of rotating alpha radian around axis. As Figure 3 shown, the step of rotating the calibration board coordinate system to be parallel to the wall surface coordinate system is: rotating the calibration board coordinate system around the z-axis by radian; rotating the calibration board coordinate system around the y-axis by 0 radian; and rotating the calibration board coordinate system around the x-axis by radian.

[0056] In other embodiments of the present application, other angles can also be rotated according to the geometric relationship between the camera calibration board and the wall surface, which is determined according to the positions of the two, and will not be described in detail here.

[0057] Step S222: calculating a first rotation matrix component of the pose transformation of the wall surface point cloud from the wall surface coordinate system to the camera calibration board coordinate system according to the rotation angle.

[0058] Specifically,

[0059]

[0060] wherein, is the rotation matrix component of the pose transformation from the wall surface coordinate system to the calibration board coordinate system. The coordinates of the origin of the wall surface coordinate system in the camera calibration board coordinate system are (dx, dy, 0).

[0061] Step S223: obtaining a first translation matrix component of the pose transformation of the wall surface point cloud from the wall surface coordinate system to the calibration board coordinate system according to the coordinates of the origin of the wall surface coordinate system.

[0062] Specifically,

[0063]

[0064] wherein, is a translation component of the pose transformation from the wall coordinate system to the calibration board coordinate system

[0065] Step S224: obtaining the fifth pose transformation matrix according to the first rotation matrix component and the first translation matrix component.

[0066] The pose transformation from the wall coordinate system to the camera coordinate system is:

[0067]

[0068] In the above manner, by rotating the camera calibration board coordinate system, the wall point cloud is transformed from the wall coordinate system to the camera calibration board coordinate system without manual intervention, which provides an intermediate condition for transforming the wall point cloud from the wall coordinate system to the camera coordinate system, simplifies the calibration process while ensuring the calibration accuracy.

[0069] Step S14: obtaining a second pose transformation matrix of the wall point cloud from the vehicle body coordinate system to the wall coordinate system.

[0070] In an embodiment of the present application, the wall is L-shaped, and the wall includes a first wall and a second wall, and the first wall and the second wall intersect; the camera external parameter calibration device obtains at least one set of fitting straight lines of the first wall and the second wall respectively, and solves the intersection point of each set of fitting straight lines of the first wall and the second wall; calculates the yaw angle of the pose of the wall point cloud from the wall coordinate system to the vehicle body coordinate system according to the coordinates of the intersection point; obtains a second translation matrix component of the pose transformation of the wall point cloud from the wall coordinate system to the vehicle body coordinate system; calculates a second rotation matrix component of the pose transformation of the wall point cloud from the wall coordinate system to the vehicle body coordinate system according to the yaw angle; and obtains the second pose transformation matrix according to the second rotation matrix component and the second translation matrix component.

[0071] Specifically, considering that the z-axis of the vehicle body coordinate system is always perpendicular to the ground, and the z-axis of the wall coordinate system (i.e. the intersection line of the wall) is also always perpendicular to the ground, the roll angle and the pitch angle of the pose transformation from the vehicle body coordinate system to the wall coordinate system are both 0. Since the origin of the wall coordinate system (i.e. the corner of the wall) is on the XOY plane of the vehicle body coordinate (i.e. the ground), the z component of the pose transformation from the vehicle body coordinate system to the wall coordinate system is 0. At this time, solving the pose transformation between the two coordinate systems degenerates to a two-dimensional case (i.e. solving the pose transformation of O XY to O X′Y′ ).

[0072] As Figure 4As shown, the laser point cloud is converted to the vehicle body coordinate system by laser external parameters, and the wall point cloud is L-shaped. After the wall point cloud is filtered out by the filter method, the ransac method is used to simultaneously fit two straight lines on the left and right walls, the point cloud is projected onto the corresponding straight line, and the intersection D of the two straight lines is solved:

[0073] D = (x Wall ,y wall )

[0074] where D falls on the intersection line of the walls. The yaw angle of the wall coordinate system in the vehicle body coordinate system is calculated:

[0075]

[0076] where l is the direction vector of the straight line fitted by the left wall point cloud.

[0077] Further obtained:

[0078]

[0079] where is the rotation matrix component of the pose transformation from the wall coordinate system to the vehicle body coordinate system, is the translation vector component of the pose transformation from the wall coordinate system to the vehicle body coordinate system. Thus, the pose transformation from the vehicle body coordinate system to the wall coordinate system is obtained:

[0080]

[0081] Step S15: According to the first pose transformation matrix and the second pose transformation matrix, a third pose transformation matrix of the wall point cloud from the camera coordinate system to the vehicle body coordinate system is obtained.

[0082] Through the coupling between the vehicle body-wall-camera coordinate systems, the following is obtained:

[0083]

[0084] Step S16: According to the third pose transformation matrix, the camera external parameters are calculated.

[0085] In the embodiments of the present application, the camera external parameter calibration device obtains the third rotation matrix component and the third translation matrix component of the pose transformation of the wall point cloud from the camera coordinate system to the vehicle body coordinate system; and calculates the camera external parameters according to the third rotation matrix component and the third translation matrix component.

[0086]

[0087] where, is the rotation matrix component of the pose transformation from the camera coordinate system to the vehicle body coordinate system, is the translation vector component of the pose transformation from the camera coordinate system to the vehicle coordinate system.

[0088] The camera extrinsic parameters include Euler angles and position parameters, and the calculation of the camera extrinsic parameters according to the third rotation matrix component and the third translation matrix component includes: calculating the position parameters according to the third translation matrix component; and calculating the Euler angles according to the third rotation matrix component.

[0089] The position parameters include x, y and z, and the Euler angles include roll, pitch and yaw, and the specific calculation manner is as follows:

[0090]

[0091] x is the x component of the camera-vehicle extrinsic parameters, y is the y component of the camera-vehicle extrinsic parameters, and z is the z component of the camera-vehicle extrinsic parameters.

[0092]

[0093] The roll is the roll angle of the camera-vehicle extrinsic parameters, and the rotation angle around the X axis is calculated through the first column (R[0, 0] and R[1, 0]) of the rotation matrix.

[0094]

[0095] The pitch is the pitch angle of the camera-vehicle extrinsic parameters, and the rotation angle around the Y axis is calculated in combination with the third row (R[2, 0], R[2, 1], R[2, 2]) of the rotation matrix.

[0096]

[0097] The yaw is the yaw angle of the camera-vehicle extrinsic parameters, and the rotation angle around the Z axis is calculated through the third row (R[2, 1] and R[2, 2]) of the rotation matrix.

[0098] Thus, all to-be-solved variables x, y, z, roll, pitch and yaw are obtained.

[0099] In the above manner, the design of the calibration scene is simplified, and no additional complex calibration tool is needed, meanwhile, the camera extrinsic parameters are calibrated with the aid of 2D laser observation, and there is no requirement for the relative pose of the laser-camera, the laser-camera can be completely free of the common viewing area, and the calibration precision is high without manual intervention.

[0100] To solve the above technical problems, the application provides a camera extrinsic parameter calibration system 500, which comprises a vehicle body 51, a sensor 52, a camera calibration board 53 and a processor 54, and specific reference can be made to Figure 7 ,Figure 7 is a schematic diagram of an embodiment of the camera extrinsic calibration system provided by the present application.

[0101] The sensor is arranged on the vehicle body, and the camera calibration board 53 is arranged on the wall surface; the vehicle body 51 collects the wall surface point cloud by using the sensor on the vehicle body; and the processor 54 is configured to obtain a geometric relationship between the camera calibration board and the wall surface, wherein the camera calibration board is arranged on the wall surface; obtain a first pose transformation matrix of the wall surface point cloud from a wall surface coordinate system to a camera coordinate system according to the geometric relationship; obtain a second pose transformation matrix of the wall surface point cloud from a vehicle body coordinate system to the wall surface coordinate system based on the wall surface point cloud; obtain a third pose transformation matrix of the wall surface point cloud from the camera coordinate system to the vehicle body coordinate system according to the first pose transformation matrix and the second pose transformation matrix; and calculate the camera extrinsic parameters according to the third pose transformation matrix.

[0102] In order to realize the camera extrinsic calibration method of the above-mentioned embodiment, the present application further provides a camera extrinsic calibration device, please refer to Figure 8 , Figure 8 is a structural schematic diagram of an embodiment of the camera extrinsic calibration device provided by the present application.

[0103] As shown in Figure 8 , the camera extrinsic calibration device 600 of the present embodiment comprises a processor 61, a memory 62, an input / output device 63 and a bus 64.

[0104] The processor 61, the memory 62 and the input / output device 63 are respectively connected with the bus 64, and the memory 62 stores a computer program, and the processor 61 is configured to execute the computer program to realize the camera extrinsic calibration method of the above-mentioned embodiment.

[0105] In this embodiment, the processor 61 can also be referred to as a CPU (Central Processing Unit). The processor 61 can be an integrated circuit chip having a processing capability of signals. The processor 61 can also be a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application-Specific Integrated Circuit), an FPGA (Field Programmable Gate Array) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The processor 61 can also be a GPU (Graphics Processing Unit), also known as a display core, a visual processor, a display chip, which is a microprocessor specially used for image operation on a computer, a workstation, a game console and some mobile devices (such as tablet computers, smart phones, etc.). The purpose of GPU is to convert the display information required by the computer system and provide line scanning signals to the display to control the correct display of the display, which is an important element connecting the display and the computer mainboard. As an important part of the computer host, the display card undertakes the task of outputting display graphics. The general-purpose processor can be a microprocessor, or the processor 61 can be any conventional processor, etc.

[0106] The application also provides a computer storage medium, such as Figure 9 As shown in the figure, the computer storage medium 700 is used to store a computer program 71, which when executed by a processor, is used to implement the camera extrinsic parameter calibration method as described in the application.

[0107] The method involved in the embodiments of the application, when realized in the form of a software functional unit and sold or used as an independent product, can be stored in a device, such as a computer readable storage medium. Based on this understanding, the technical solutions of the application essentially or the part that contributes to the prior art or the whole or part of the technical solutions can be embodied in the form of a software product, which is stored in a storage medium and includes a number of instructions to make a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor execute all or part of the steps of the method described in the embodiments of the application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a ROM (Read-Only Memory), a RAM (Random Access Memory), a magnetic disk or an optical disk, and various media that can store program codes.

[0108] In several embodiments provided in the present application, it should be understood that the disclosed methods and apparatuses can be implemented in other manners. For example, the division of the apparatus embodiments is merely an example, and for other division manners, for example, the division can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the display or discussion of the coupling or direct coupling or communication connection between the modules can be through some interfaces, and can be indirect coupling or communication connection through some interfaces.

[0109] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, i.e., may be located in one place, or may be distributed on network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the present embodiment.

[0110] In addition, the functional units in each embodiment of the present application can be integrated into a processing unit, or each unit can be a physically independent unit, or two or more units can be integrated into a unit. The integrated unit can be implemented in the form of hardware or in the form of a software functional unit.

[0111] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the present application essentially or the part that contributes to the prior art or the whole or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium, and includes a number of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor to execute all or part of the steps of the methods of the various embodiments of the present application.

[0112] The above description is merely an embodiment of the present application, and does not limit the patent scope of the present application, and any equivalent structure or equivalent flow transformation based on the content of the present application specification and drawings, or direct or indirect application in other related technical fields, is also included in the patent protection scope of the present application.

Claims

1. A method for calibrating camera extrinsic parameters, characterized in that, The camera extrinsic parameter calibration method comprises: collecting wall point cloud by using a sensor on a vehicle body; obtaining a geometric relationship between a camera calibration board and a wall, wherein the camera calibration board is arranged on the wall; obtaining a first pose transformation matrix of the wall point cloud from a wall coordinate system to a camera coordinate system according to the geometric relationship; obtaining a second pose transformation matrix of the wall point cloud from a vehicle body coordinate system to the wall coordinate system; obtaining a third pose transformation matrix of the wall point cloud from the camera coordinate system to the vehicle body coordinate system according to the first pose transformation matrix and the second pose transformation matrix; calculating a camera extrinsic parameter according to the third pose transformation matrix.

2. The camera extrinsic parameter calibration method according to claim 1, wherein an x-axis of a coordinate system in which an initial position of the camera calibration board is located is parallel to a ground, and a y-axis is perpendicular to a line intersecting the wall.

3. The camera extrinsic parameter calibration method according to claim 1 or 2, wherein the camera extrinsic parameter calibration method further comprises: obtaining a fourth pose transformation matrix of the wall point cloud from the camera coordinate system to a camera calibration board coordinate system according to the geometric relationship; obtaining a fifth pose transformation matrix of the wall point cloud from the wall coordinate system to the camera calibration board coordinate system; calculating the first pose transformation matrix according to the fourth pose transformation matrix and the fifth pose transformation matrix.

4. The camera extrinsic parameter calibration method according to claim 3, wherein the obtaining the fourth pose transformation matrix of the wall point cloud from the camera coordinate system to the camera calibration board coordinate system according to the geometric relationship comprises: rotating an x-axis, a y-axis and a z-axis of the camera calibration board coordinate system; calculating a first rotation matrix component of a pose transformation of the wall point cloud from the wall coordinate system to the camera calibration board coordinate system according to a rotation angle; obtaining a first translation matrix component of the pose transformation of the wall point cloud from the wall coordinate system to the calibration board coordinate system according to an origin coordinate of the wall coordinate system; obtaining the fifth pose transformation matrix according to the first rotation matrix component and the first translation matrix component.

5. The camera extrinsic parameter calibration method according to claim 2, wherein the wall is L-shaped, the wall comprises a first wall and a second wall, and the first wall and the second wall intersect; the obtaining the second pose transformation matrix of the wall point cloud from the vehicle body coordinate system to the wall coordinate system comprises: obtaining at least one set of fitting straight lines of the first wall and the second wall respectively, and solving an intersection point of each set of the fitting straight lines of the first wall and the second wall; calculating a yaw angle of a pose of the wall point cloud from the wall body coordinate system to the vehicle body coordinate system according to a coordinate of the intersection point; obtaining a second translation matrix component of the pose transformation of the wall point cloud from the wall coordinate system to the vehicle body coordinate system; calculating a second rotation matrix component of the pose transformation of the wall point cloud from the wall coordinate system to the vehicle body coordinate system according to the yaw angle; obtaining the second pose transformation matrix according to the second rotation matrix component and the second translation matrix component. ​ ​ ​ ​ 6. The camera extrinsic calibration method of claim 1, wherein the calculating the camera extrinsic parameter based on the third pose transformation matrix comprises: obtaining a third rotation matrix component and a third translation matrix component of a pose transformation of the wall point cloud from the camera coordinate system to the vehicle coordinate system; and calculating the camera extrinsic parameter based on the third rotation matrix component and the third translation matrix component.

7. The camera extrinsic calibration method of claim 6, wherein the camera extrinsic parameter comprises Euler angles and a position parameter; and the calculating the camera extrinsic parameter based on the third rotation matrix component and the third translation matrix component comprises: calculating the position parameter based on the third translation matrix component; and calculating the Euler angles based on the third rotation matrix component. The camera extrinsic calibration system comprises a vehicle, a sensor, a camera calibration board, and a processor, wherein the sensor is arranged on the vehicle, and the camera calibration board is arranged on a wall surface. The vehicle collects wall point cloud by using the sensor arranged on the vehicle.

8. A camera extrinsic parameter calibration system, comprising: The processor is configured to obtain a geometric relationship between the camera calibration board and the wall surface, wherein the camera calibration board is arranged on the wall surface. The processor is configured to obtain a first pose transformation matrix of the wall point cloud from a wall coordinate system to a camera coordinate system based on the geometric relationship. The processor is configured to obtain a second pose transformation matrix of the wall point cloud from a vehicle coordinate system to the wall coordinate system based on the wall point cloud. The processor is configured to obtain a third pose transformation matrix of the wall point cloud from the camera coordinate system to the vehicle coordinate system based on the first pose transformation matrix and the second pose transformation matrix. The processor is configured to calculate a camera extrinsic parameter based on the third pose transformation matrix. The camera extrinsic calibration device comprises a memory and a processor coupled to the memory.

9. A camera extrinsic parameter calibration apparatus, characterized in that, The memory is configured to store program data, and the processor is configured to execute the program data to implement the camera extrinsic calibration method of any one of claims 1 to 7. The computer storage medium is configured to store program data, and the program data, when executed by a computer, is configured to implement the camera extrinsic calibration method of any one of claims 1 to 7.

10. A computer storage medium, characterized in that, ​

Images