Device parameter calibration method and apparatus, automobile detection device, and storage medium

Abstract

The present application is applicable to the technical field of automobiles, and provides a device parameter calibration method and apparatus, an automobile detection device, and a storage medium. The method comprises: on the basis of acquired images which are photographed by measurement units and comprise markers provided in calibration devices on respective sides, images which are respectively photographed by the two calibration devices and comprise the markers, and coordinate position information of the markers in corresponding marker coordinate systems, determining rotation and translation matrixes between camera coordinate systems corresponding to the measurement units and the marker coordinate systems of the markers photographed by the measurement units, and a rotation and translation matrix between respective camera coordinate systems of the two calibration devices; finally, performing parameter calibration on the automobile detection device on the basis of the obtained rotation and translation matrixes. According to the present invention, the positional relationship between measurement units and calibration devices on respective sides, and the positional relationship between the two calibration devices are clearly defined, thereby improving the accuracy of subsequent measurement of tire parameters.

Description

Equipment parameter calibration method, device, automobile testing equipment and storage medium

[0001] This application claims priority to the Chinese patent application filed with the China Patent Office on March 22, 2024, with application number 202410335296.6 and invention name “Equipment parameter calibration method, device, automobile detection equipment and storage medium”, the entire contents of which are incorporated by reference into this application. Technical Field

[0002] The present application belongs to the field of automobile technology, and in particular relates to a device parameter calibration method, apparatus, automobile detection equipment and storage medium. Background Art

[0003] Currently, to obtain the four-wheel alignment parameters of a car, users usually need to use specialized automobile testing equipment (such as a four-wheel alignment device) to measure the parameters of each wheel of the car. However, existing automobile testing equipment includes multiple measuring devices, each using a different coordinate system, and the positional relationship between different measuring devices cannot be determined. As a result, existing automobile testing equipment cannot accurately measure the four-wheel alignment parameters of the car. Technical issues

[0004] The embodiments of the present application provide a device parameter calibration method, apparatus, automobile inspection equipment and storage medium, which can clarify the positional relationship between each measurement unit and the calibration device on the same side, as well as the positional relationship between two calibration devices, thereby improving the subsequent measurement accuracy of tire parameters. Technical Solutions

[0005] In a first aspect, an embodiment of the present application provides a device parameter calibration method, which is applied to an automobile detection device, wherein the automobile detection device includes two first measuring devices for respectively detecting the front wheels and rear wheels on a first side of the vehicle, two second measuring devices for respectively detecting the front wheels and rear wheels on a second side of the vehicle, a first calibration device for performing position calibration on the two first measuring devices on the first side, and a second calibration device for performing position calibration on the two second measuring devices on the second side; the first calibration device is provided with a first marker, and the second calibration device is provided with a second marker. The method includes:

[0006] Acquire first images corresponding to the first marker, respectively, obtained by the two first measuring devices, and second images corresponding to the second marker, respectively, obtained by the two second measuring devices; and acquire a third image of the second marker, respectively, obtained by the first calibration device, and a fourth image of the first marker, respectively, obtained by the second calibration device;

[0007] Determining first coordinate position information of the first marker in a preset first marker coordinate system and second coordinate position information of the second marker in a preset second marker coordinate system; both the first marker coordinate system and the second marker coordinate system are world coordinate systems;

[0008] Determine, based on the two first images and the first coordinate position information, a first rotation and translation matrix between a first camera coordinate system corresponding to each of the two first measuring devices and the first marker coordinate system; and determine, based on the two second images and the second coordinate position information, a second rotation and translation matrix between a second camera coordinate system corresponding to each of the two second measuring devices and the second marker coordinate system;

[0009] Determine a third rotation and translation matrix between a third camera coordinate system of the first calibration device and a fourth camera coordinate system of the second calibration device according to the third image, the fourth image, the first coordinate position information, and the second coordinate position information;

[0010] Parameter calibration is performed on the automobile detection equipment based on the two first rotation and translation matrices, the two second rotation and translation matrices, and the third rotation and translation matrix.

[0011] In a second aspect, an embodiment of the present application provides an equipment parameter calibration device, which is applied to automobile detection equipment, wherein the automobile detection equipment includes two first measuring devices for respectively detecting the front wheels and rear wheels on a first side of the vehicle, two second measuring devices for respectively detecting the front wheels and rear wheels on a second side of the vehicle, a first calibration device for performing position calibration on the two first measuring devices on the first side, and a second calibration device for performing position calibration on the two second measuring devices on the second side; the first calibration device is provided with a first marker, and the second calibration device is provided with a second marker, and the device includes:

[0012] a first acquisition unit, configured to acquire first images corresponding to the first markers, respectively, obtained by the two first measuring devices, and second images corresponding to the second markers, respectively, obtained by the two second measuring devices; and acquire a third image corresponding to the second markers, respectively, obtained by the first calibration device, and a fourth image corresponding to the first markers, respectively, obtained by the second calibration device;

[0013] a position determination unit, configured to determine first coordinate position information of the first marker in a preset first marker coordinate system and second coordinate position information of the second marker in a preset second marker coordinate system; the first marker coordinate system and the second marker coordinate system are both world coordinate systems;

[0014] a first matrix determining unit, configured to determine, based on the two first images and the first coordinate position information, a first rotation and translation matrix between a first camera coordinate system corresponding to each of the two first measuring devices and the first marker coordinate system, and to determine, based on the two second images and the second coordinate position information, a second rotation and translation matrix between a second camera coordinate system corresponding to each of the two second measuring devices and the second marker coordinate system;

[0015] a second matrix determining unit, configured to determine a third rotation and translation matrix between a third camera coordinate system of the first calibration device and a fourth camera coordinate system of the second calibration device according to the third image, the fourth image, the first coordinate position information, and the second coordinate position information;

[0016] A calibration unit is used to perform parameter calibration on the automobile detection equipment based on the two first rotation and translation matrices, the two second rotation and translation matrices, and the third rotation and translation matrix.

[0017] In a third aspect, an embodiment of the present application provides an automobile detection device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the device parameter calibration method as described in any one of the first aspects above is implemented.

[0018] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the device parameter calibration method as described in any one of the above-mentioned first aspects is implemented. Beneficial effects

[0019] Compared with the prior art, the embodiments of the present application have the following beneficial effects:

[0020] An embodiment of the present application provides a device parameter calibration method, which is applied to automobile inspection equipment. The automobile inspection equipment includes two first measuring devices for respectively inspecting the front and rear wheels of a first side of the vehicle, two second measuring devices for respectively inspecting the front and rear wheels of a second side of the vehicle, a first calibration device for performing position calibration on the two first measuring devices on the first side, and a second calibration device for performing position calibration on the two second measuring devices on the second side. The first calibration device is provided with a first marker, and the second calibration device is provided with a second marker. The method determines, based on acquired images captured by each measuring unit containing markers set in the calibration device on the same side, images containing markers captured by each of the two calibration devices, and coordinate position information of each marker in its corresponding marker coordinate system, a rotation and translation matrix between a camera coordinate system corresponding to each measuring unit and a marker coordinate system captured by each measuring unit, as well as a rotation and translation matrix between the camera coordinate systems corresponding to each of the two calibration devices. Finally, the automobile inspection equipment can be calibrated according to the rotation and translation matrices obtained above. This method clarifies the positional relationship between each measurement unit and the calibration device on the same side, as well as the positional relationship between two calibration devices, thereby improving the accuracy of subsequent tire parameter measurements. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the embodiments or descriptions of the prior art. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0022] FIG1 is a schematic structural diagram of an automobile detection device provided in one embodiment of the present application;

[0023] FIG2 is a flowchart of an implementation method of a device parameter calibration method provided in an embodiment of the present application;

[0024] FIG3 is a flowchart of an implementation method of a device parameter calibration method provided in another embodiment of the present application;

[0025] FIG4 is a flowchart of an implementation method of a device parameter calibration method provided in yet another embodiment of the present application;

[0026] FIG5 is a flowchart of an implementation method of a device parameter calibration method provided in another embodiment of the present application;

[0027] FIG6 is a flowchart of an implementation method of a device parameter calibration method provided in another embodiment of the present application;

[0028] FIG7 is a schematic structural diagram of a device parameter calibration apparatus provided in an embodiment of the present application;

[0029] FIG8 is a schematic structural diagram of an automobile detection device provided in one embodiment of the present application. Modes for Carrying Out the Invention

[0030] In the following description, specific details such as specific system structures and techniques are provided for purposes of illustration rather than limitation to facilitate a thorough understanding of the embodiments of the present application. However, it will be apparent to those skilled in the art that the present application may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid obscuring the description of the present application with unnecessary detail.

[0031] Please refer to FIG1 , which is a schematic diagram of the structure of an automobile detection device provided in one embodiment of the present application. For ease of explanation, only the parts related to this embodiment are shown, which are described in detail as follows:

[0032] As shown in Figure 1, the vehicle inspection device 1 includes a processing unit 10, two first measuring devices 20, two second measuring devices 30, a first calibration device 40, and a second calibration device 50. The processing unit 10 is in communication with the two first measuring devices 20, the two second measuring devices 30, the first calibration device 40, and the second calibration device 50, respectively.

[0033] In some possible embodiments, the automobile detection device may be a four-wheel alignment device.

[0034] It should be noted that the processing unit 10 may be a central processing unit (CPU).

[0035] In the embodiment of the present application, the two first measuring devices 20 are respectively used to detect the front wheels and the rear wheels on the first side of the vehicle.

[0036] The two second measuring devices 30 are respectively used to detect the front wheels and the rear wheels on the second side of the vehicle.

[0037] It should be noted that when the first side is the left side, the second side is the right side; when the first side is the right side, the second side is the left side.

[0038] Exemplarily, as shown in FIG1 , two first measuring devices 20 are respectively used to detect the left front wheel and the left rear wheel of the vehicle, and the second measuring device 30 is respectively used to detect the right front wheel and the right rear wheel of the vehicle.

[0039] In the embodiment of the present application, each first measuring device 20 includes a first camera and a fifth camera, and each first camera is used to photograph the first marker in the first calibration device 40 .

[0040] It should be noted that there is an angle between the plane where each first camera is located and the plane where the fifth camera in the same first measuring device 20 is located.

[0041] In some possible embodiments, the angle may be a right angle, that is, the plane where each first camera is located is perpendicular to the plane where the fifth camera in the same first measuring device 20 is located.

[0042] Among them, the fifth camera in the first measuring device 20 for detecting the front wheel on the first side of the vehicle is used to collect the first tire point cloud data of the front wheel on the first side; the fifth camera in the first measuring device 20 for detecting the rear wheel on the first side of the vehicle is used to collect the first tire point cloud data of the rear wheel on the first side.

[0043] Each second measuring device 30 includes a second camera and a sixth camera, and each second camera is used to photograph the second marker in the second calibration device 50 .

[0044] It should be noted that the plane where each second camera is located has an angle with the plane where the sixth camera in the same second measuring device 30 is located.

[0045] In some possible embodiments, the angle may be a right angle, that is, the plane where each second camera is located is perpendicular to the plane where the sixth camera is located in the same second measuring device 30. Of course, it may also be other angles, which are not limited here.

[0046] Among them, the sixth camera in the second measuring device 30 for detecting the front wheel on the second side of the vehicle is used to collect the second tire point cloud data of the front wheel on the second side; the sixth camera in the second measuring device 30 for detecting the rear wheel on the second side of the vehicle is used to collect the second tire point cloud data of the rear wheel on the second side.

[0047] In the embodiment of the present application, the first calibration device 40 is used to calibrate the positions of the two first measuring devices 20 located on the first side of the vehicle.

[0048] The second calibration device 50 is used to calibrate the positions of the two second measuring devices 30 located on the second side of the vehicle.

[0049] It should be noted that the first calibration device 40 is located opposite to the second calibration device 50. For example, as shown in FIG1 , when the first calibration device 40 is located at the center between the left front wheel and the left rear wheel of the vehicle, the second calibration device 50 is located at the center between the right front wheel and the right rear wheel of the vehicle.

[0050] The first marking device 40 is provided with a third camera and a first marker, and the second marking device 50 is provided with a fourth camera and a second marker that is identical to and opposite to the first marker.

[0051] There are multiple first and second markers.

[0052] In the embodiment of the present application, the third camera of the first calibration device 40 is used to photograph the second marker, and the fourth camera of the second calibration device 50 is used to photograph the first marker.

[0053] Please refer to Figure 2, which is a flowchart of an implementation method of a device parameter calibration method provided in an embodiment of the present application. In the embodiment of the present application, the execution subject of the device parameter calibration method is the automobile detection device, and can also be a processing unit in the automobile detection device.

[0054] As shown in FIG2 , the device parameter calibration method provided in one embodiment of the present application may include S101 to S105 , which are described in detail as follows:

[0055] In S101, the first images corresponding to the first marker respectively photographed by the two first measuring devices and the second images corresponding to the second marker respectively photographed by the two second measuring devices are obtained; and the third image of the second marker photographed by the first calibration device and the fourth image of the first marker photographed by the second calibration device are obtained.

[0056] In actual applications, when a user needs to obtain tire parameters of a vehicle, in order to improve the accuracy of the obtained tire parameters, the user can send a parameter calibration request to the vehicle detection equipment.

[0057] In an embodiment of the present application, the vehicle inspection device detecting a parameter calibration request may be caused by detecting a preset operation for the vehicle inspection device. The preset operation can be set based on actual needs and is not limited herein. For example, the preset operation may be clicking a preset control on the vehicle inspection device. Based on this, when the vehicle inspection device detects that a preset control on its own has been clicked, it indicates that it has detected a preset operation for the vehicle inspection device, i.e., a parameter calibration request.

[0058] After detecting a parameter calibration request, the automobile detection device can obtain the corresponding first images obtained by the two first measuring devices respectively photographing the first marker and the corresponding second images obtained by the two second measuring devices respectively photographing the second marker; and obtain the third image obtained by the first calibration device photographing the second marker and the fourth image obtained by the second calibration device photographing the first marker.

[0059] That is, each first measuring device corresponds to a first image, and each second measuring device corresponds to a second image.

[0060] In some possible embodiments, when both the first marker and the second marker include multiple ones, the first marker included in the two first images and the fourth image is the same, and the second marker included in the two second images and the third image is the same.

[0061] It should be noted that each first marker is provided with its corresponding first marker identifier, wherein the first marker identifier includes but is not limited to a number or a serial number.

[0062] Based on this, the two first images and the fourth image both contain the first marker identifier corresponding to the photographed first marker.

[0063] Each second marker is provided with a corresponding second marker identifier, wherein the second marker identifier includes but is not limited to a number or a serial number.

[0064] Based on this, the two second images and the third image both contain the second marker identifier corresponding to the photographed second marker.

[0065] In S102, first coordinate position information of the first marker in a preset first marker coordinate system and second coordinate position information of the second marker in a preset second marker coordinate system are determined; the first marker coordinate system and the second marker coordinate system are both world coordinate systems.

[0066] It should be noted that the first coordinate position information refers to the first three-dimensional coordinates of the first marker in a preset first marker coordinate system. The preset first marker coordinate system refers to a world coordinate system with the set position of the first marker as the origin, or it can be a world coordinate system with the position of another point on the first calibration device as the origin.

[0067] The second coordinate position information refers to the second three-dimensional coordinates of the second marker in a preset second marker coordinate system. The preset second marker coordinate system refers to a world coordinate system with the set position of the second marker as the origin, or may be a world coordinate system with the position of another point on the second calibration device as the origin.

[0068] In an embodiment of the present application, the automobile detection device pre-stores the correspondence between the first coordinate position information of different first markers and the different first marker identifiers. Therefore, the automobile detection device can determine the first coordinate position information of the first marker based on the first marker identifier contained in the fourth image captured by the second calibration device and the correspondence between the first coordinate position information of different first markers and the different first marker identifiers.

[0069] The automobile detection device pre-stores the correspondence between the second coordinate position information of different second markers and different second marker identifiers. Therefore, the automobile detection device can determine the second coordinate position information of the second marker based on the second marker identifier contained in the third image taken by the first calibration device and the correspondence between the second coordinate position information of different second markers and different second marker identifiers.

[0070] In S103, based on the two first images and the first coordinate position information, the first rotation and translation matrix between the first camera coordinate system corresponding to each of the two first measuring devices and the first marker coordinate system is determined, and based on the two second images and the second coordinate position information, the second rotation and translation matrix between the second camera coordinate system corresponding to each of the two second measuring devices and the second marker coordinate system is determined.

[0071] In an embodiment of the present application, the automobile detection equipment can specifically determine the first rotation and translation matrix between the first camera coordinate system corresponding to the first camera of the first measuring device used to detect the front wheel on the first side of the vehicle and the first marker coordinate system based on the first image captured by the first camera of the first measuring device used to detect the front wheel on the first side of the vehicle and the first coordinate position information of the first marker.

[0072] The automobile detection equipment can specifically determine the first rotation and translation matrix between the first camera coordinate system corresponding to the first camera of the first measuring device used to detect the rear wheel on the first side of the vehicle and the first marker coordinate system based on the first image captured by the first camera of the first measuring device used to detect the rear wheel on the first side of the vehicle and the first coordinate position information of the first marker.

[0073] The automobile detection equipment can specifically determine the second rotation and translation matrix between the second camera coordinate system corresponding to the second camera of the second measuring device used to detect the front wheel on the second side of the vehicle and the second marker coordinate system based on the second image captured by the second camera of the second measuring device used to detect the front wheel on the second side of the vehicle and the second coordinate position information of the second marker.

[0074] The automobile detection equipment can specifically determine the second rotation and translation matrix between the second camera coordinate system corresponding to the second camera of the second measuring device used to detect the rear wheel on the second side of the vehicle and the second marker coordinate system based on the second image captured by the second camera of the second measuring device used to detect the rear wheel on the second side of the vehicle and the second coordinate position information of the second marker.

[0075] In one embodiment of the present application, both first measurement devices include a first camera for photographing a first marker in a first calibration device, and both second measurement devices include a second camera for photographing a second marker in a second calibration device. The first coordinate position information refers to the first three-dimensional coordinates of the first marker in the first marker coordinate system, and the second coordinate position information refers to the second three-dimensional coordinates of the second marker in the second marker coordinate system. Therefore, the vehicle inspection device can specifically determine the first rotation and translation matrices and the second rotation and translation matrices through steps S201 to S204 as shown in Figure 3, as detailed below:

[0076] In S201 , the two-dimensional coordinates of the first marker in the image coordinate systems corresponding to the two first cameras are determined based on the two first images.

[0077] In this embodiment, the automobile detection equipment can determine the two-dimensional coordinates of the first marker in the image coordinate system corresponding to the first camera in the first measuring equipment used to detect the front wheel on the first side of the vehicle based on the first image captured by the first camera in the first measuring equipment used to detect the front wheel on the first side of the vehicle.

[0078] The automobile detection equipment can determine the two-dimensional coordinates of the first marker in the image coordinate system corresponding to the first camera in the first measuring equipment used to detect the rear wheel on the first side of the vehicle based on the first image captured by the first camera in the first measuring equipment used to detect the rear wheel on the first side of the vehicle.

[0079] In S202 , based on the two second images, the two-dimensional coordinates of the second marker in the image coordinate systems corresponding to the two second cameras are determined.

[0080] In this embodiment, the automobile detection equipment can determine the two-dimensional coordinates of the second marker in the image coordinate system corresponding to the second camera in the second measuring device used to detect the front wheel on the second side of the vehicle based on the second image captured by the second camera in the second measuring device used to detect the front wheel on the second side of the vehicle.

[0081] The automobile detection equipment can determine the two-dimensional coordinates of the second marker in the image coordinate system corresponding to the second camera in the second measuring device used to detect the rear wheels on the second side of the vehicle based on the second image captured by the second camera in the second measuring device used to detect the rear wheels on the second side of the vehicle.

[0082] In S203, based on the two-dimensional coordinates and the first three-dimensional coordinates of the first marker in the image coordinate systems corresponding to the two first cameras, a first rotation and translation matrix between the first camera coordinate systems corresponding to the two first measuring devices and the first marker coordinate system is determined.

[0083] In this embodiment, the automobile detection equipment can specifically obtain the first rotation and translation matrix between the first camera coordinate system corresponding to the first camera of the first measuring device for detecting the front wheel on the first side of the vehicle and the first marker coordinate system based on the two-dimensional coordinates of the first marker in the image coordinate system corresponding to the first camera in the first measuring device for detecting the front wheel on the first side of the vehicle and the above-mentioned first three-dimensional coordinates (i.e., the first coordinate position information).

[0084] The automobile detection equipment can specifically obtain the first rotation and translation matrix between the first camera coordinate system corresponding to the first camera of the first measuring device used to detect the rear wheel on the first side of the vehicle and the first marker coordinate system based on the two-dimensional coordinates of the first marker in the image coordinate system corresponding to the first camera in the first measuring device used to detect the rear wheel on the first side of the vehicle and the above-mentioned first three-dimensional coordinates (i.e., the first coordinate position information).

[0085] It should be noted that, when the first marker is a spherical calibration ball, the above-mentioned first three-dimensional coordinates (i.e., the first coordinate position information) specifically refer to the three-dimensional coordinates of the center of the spherical calibration ball in the preset first marker coordinate system, and the two-dimensional coordinates of the first marker in the image coordinate system corresponding to each first camera specifically refer to the two-dimensional coordinates of the center of the spherical surface formed by the projection of the center of the spherical calibration ball in each first camera.

[0086] Since the image coordinate system corresponding to each first camera specifically refers to the image coordinate system constructed from the images captured by each first camera, after the automobile detection device captures each first image containing the first marker, the automobile detection device can determine any position point in each first image (such as the center of each first image, or any one of the four corner points of each first image) as the first origin. Thereafter, the automobile detection device can construct the image coordinate system corresponding to each first camera based on the first origin. Based on this, the automobile detection device can determine the coordinate position of the center of the sphere formed by the projection of the spherical calibration ball in each first image based on the above-mentioned image coordinate system constructed, and determine the coordinate position as the two-dimensional coordinate of the first marker in the image coordinate system corresponding to each first camera.

[0087] In some possible embodiments, the automobile detection device may import the above two-dimensional coordinates and the first three-dimensional coordinates into the solvepnp algorithm to calculate the first rotation and translation matrix between each first camera coordinate system and the first marker coordinate system.

[0088] In other possible embodiments, when there are multiple first markers, each first marker corresponds to a set of two-dimensional coordinates, and each first marker corresponds to a set of first three-dimensional coordinates. Therefore, the automobile detection device can also determine each first rotation and translation matrix according to the following steps, as detailed below:

[0089] Obtaining intrinsic parameters and distortion parameters of each of the two first cameras;

[0090] Determining, based on the intrinsic parameters and distortion parameters of each of the two first cameras, first mapping relationships between the two-dimensional coordinates of the plurality of first markers in the image coordinate systems corresponding to the two first cameras and the plurality of first three-dimensional coordinates;

[0091] Based on the first mapping relationship, a first rotation and translation matrix between the first camera coordinate system corresponding to each of the two first measuring devices and the first marker coordinate system is determined.

[0092] In this embodiment, the intrinsic parameters of each first camera, also referred to as an intrinsic parameter matrix or an intrinsic parameter, are properties of each first camera itself and can be obtained by calibrating each first camera.

[0093] The distortion parameters of each first camera include, but are not limited to, a radial distortion coefficient and a tangential distortion coefficient.

[0094] In an implementation of this embodiment, the intrinsic parameters and distortion parameters of each first camera may be obtained by performing camera calibration processing on each first camera.

[0095] In practical applications, camera calibration methods include but are not limited to: linear calibration method, nonlinear calibration method and two-step calibration method.

[0096] Afterwards, the automobile detection equipment can determine the first mapping relationship between the two-dimensional coordinates of each first marker in the image coordinate system corresponding to each first camera and the first three-dimensional coordinates of each first marker based on the intrinsic parameters and distortion parameters of each first camera.

[0097] Specifically, the automobile detection equipment can determine the first mapping relationship between the two-dimensional coordinates of each first marker in the image coordinate system corresponding to the first camera of the first measuring device used to detect the front wheel of the first side of the vehicle and the first three-dimensional coordinates of each first marker based on the internal parameters and distortion parameters of the first camera of the first measuring device used to detect the front wheel of the first side of the vehicle.

[0098] The automobile detection equipment can determine the first mapping relationship between the two-dimensional coordinates of each first marker in the image coordinate system corresponding to the first camera of the first measuring device used to detect the rear wheel on the first side of the vehicle and the first three-dimensional coordinates of each first marker based on the internal parameters and distortion parameters of the first camera of the first measuring device used to detect the rear wheel on the first side of the vehicle.

[0099] Based on this, the automobile detection equipment can determine the first rotation and translation matrix between the first camera coordinate system corresponding to the first camera of the first measuring equipment used to detect the front wheel on the first side of the vehicle and the first marker coordinate system according to the first mapping relationship between the two-dimensional coordinates of each of the above-mentioned first markers in the image coordinate system corresponding to the first camera of the first measuring equipment used to detect the front wheel on the first side of the vehicle and the first three-dimensional coordinates of each first marker.

[0100] The automobile detection equipment can determine the first rotation and translation matrix between the first camera coordinate system corresponding to the first camera of the first measuring device used to detect the rear wheel on the first side of the vehicle and the first marker coordinate system based on the first mapping relationship between the two-dimensional coordinates of each of the above-mentioned first markers in the image coordinate system corresponding to the first camera of the first measuring device used to detect the rear wheel on the first side of the vehicle and the first three-dimensional coordinates of each first marker.

[0101] In S204, based on the two-dimensional coordinates and the second three-dimensional coordinates of the second marker in the image coordinate systems corresponding to the two second cameras, a second rotation and translation matrix between the second camera coordinate systems corresponding to the two second measuring devices and the second marker coordinate system is determined.

[0102] In this embodiment, the automobile detection equipment can specifically obtain the second rotation and translation matrix between the second camera coordinate system corresponding to the second camera of the second measuring device used to detect the front wheel on the second side of the vehicle and the second marker coordinate system based on the two-dimensional coordinates of the second marker in the image coordinate system corresponding to the second camera in the second measuring device used to detect the front wheel on the second side of the vehicle and the above-mentioned second three-dimensional coordinates (i.e., the second coordinate position information).

[0103] The automobile detection equipment can specifically obtain the second rotation and translation matrix between the second machine coordinate system corresponding to the second camera of the second measuring device used to detect the rear wheel on the second side of the vehicle and the second marker coordinate system based on the two-dimensional coordinates of the second marker in the image coordinate system corresponding to the second camera in the second measuring device used to detect the rear wheel on the second side of the vehicle and the above-mentioned second three-dimensional coordinates (i.e., the second coordinate position information).

[0104] It should be noted that, when the second marker is a spherical calibration ball, the above-mentioned second three-dimensional coordinates (i.e., the second coordinate position information) specifically refer to the three-dimensional coordinates of the center of the spherical calibration ball in the preset second marker coordinate system, and the two-dimensional coordinates of the second marker in the image coordinate system corresponding to each second camera specifically refer to the two-dimensional coordinates of the center of the spherical surface formed by the projection of the center of the spherical calibration ball in each second camera.

[0105] Since the image coordinate system corresponding to each second camera specifically refers to the image coordinate system constructed by the images captured by each second camera, after the automobile detection device captures each second image containing the second marker, the automobile detection device can determine any position point in each second image (such as the center of each second image, or any one of the four corner points of each second image) as the second origin. Thereafter, the automobile detection device can construct the image coordinate system corresponding to each second camera based on the second origin. Based on this, the automobile detection device can determine the coordinate position of the center of the sphere formed by the projection of the spherical calibration ball in each second image based on the above-mentioned image coordinate system constructed, and determine the coordinate position as the two-dimensional coordinate of the second marker in the image coordinate system corresponding to each second camera.

[0106] In some possible embodiments, the automobile detection device may import the above two-dimensional coordinates and the second three-dimensional coordinates into the solvepnp algorithm to calculate the second rotation and translation matrix between each second camera coordinate system and the second marker coordinate system.

[0107] In some other possible embodiments, when there are multiple second markers, each second marker corresponds to a set of two-dimensional coordinates, and each second marker corresponds to a set of second three-dimensional coordinates. Therefore, the automobile detection device can also determine each first rotation and translation matrix according to the following steps, as detailed below:

[0108] Obtaining intrinsic parameters and distortion parameters of each of the two second cameras;

[0109] Determining, based on the intrinsic parameters and distortion parameters of each of the two second cameras, second mapping relationships between the two-dimensional coordinates of the plurality of second markers in the image coordinate systems corresponding to the two second cameras and the plurality of second three-dimensional coordinates;

[0110] Based on the second mapping relationship, a second rotation and translation matrix between the second camera coordinate system corresponding to each of the two second measuring devices and the second marker coordinate system is determined.

[0111] In this embodiment, the intrinsic parameters of each second camera, also referred to as an intrinsic parameter matrix or an intrinsic parameter, are properties of each second camera itself and can be obtained by calibrating each second camera.

[0112] The distortion parameters of each second camera include, but are not limited to, a radial distortion coefficient and a tangential distortion coefficient.

[0113] In an implementation of this embodiment, the intrinsic parameters and distortion parameters of each second camera may be obtained by performing camera calibration processing on each second camera.

[0114] In practical applications, camera calibration methods include but are not limited to: linear calibration method, nonlinear calibration method and two-step calibration method.

[0115] Afterwards, the automobile detection equipment can determine the second mapping relationship between the two-dimensional coordinates of each second marker in the image coordinate system corresponding to each second camera and the second three-dimensional coordinates of each second marker based on the intrinsic parameters and distortion parameters of each second camera.

[0116] Specifically, the automobile detection equipment can determine the second mapping relationship between the two-dimensional coordinates of each second marker in the image coordinate system corresponding to the second camera of the second measuring device used to detect the front wheel on the second side of the vehicle and the second three-dimensional coordinates of each second marker based on the internal parameters and distortion parameters of the second camera of the second measuring device used to detect the front wheel on the second side of the vehicle.

[0117] The automobile detection equipment can determine the second mapping relationship between the two-dimensional coordinates of each second marker in the image coordinate system corresponding to the second camera of the second measuring device used to detect the rear wheels on the second side of the vehicle and the second three-dimensional coordinates of each second marker based on the internal parameters and distortion parameters of the second camera of the second measuring device used to detect the rear wheels on the second side of the vehicle.

[0118] Based on this, the automobile detection equipment can determine the second rotation and translation matrix between the second camera coordinate system corresponding to the second camera of the second measuring device used to detect the front wheel on the second side of the vehicle and the second marker coordinate system according to the second mapping relationship between the two-dimensional coordinates of each second marker in the image coordinate system corresponding to the second camera of the second measuring device used to detect the front wheel on the second side of the vehicle and the second three-dimensional coordinates of each second marker.

[0119] The automobile detection equipment can determine the second rotation and translation matrix between the second camera coordinate system corresponding to the second camera of the second measuring device used to detect the rear wheels on the second side of the vehicle and the second marker coordinate system based on the second mapping relationship between the two-dimensional coordinates of each second marker in the image coordinate system corresponding to the second camera of the second measuring device used to detect the rear wheels on the second side of the vehicle and the second three-dimensional coordinates of each second marker.

[0120] In S104 , a third rotation and translation matrix between a third camera coordinate system of the first calibration device and a fourth camera coordinate system of the second calibration device is determined according to the third image, the fourth image, the first coordinate position information, and the second coordinate position information.

[0121] In an embodiment of the present application, after obtaining the third image, the fourth image, the first coordinate position information and the second coordinate position information, the automobile detection device can obtain a third rotation and translation matrix between the first calibration device and the second calibration device based on the third image, the fourth image, the first coordinate position information and the second coordinate position information.

[0122] In one embodiment of the present application, the first calibration device includes a third camera that photographs the second marker, and the second calibration device includes a fourth camera that photographs the first marker. The first coordinate position information refers to the first three-dimensional coordinates of the first marker in the first marker coordinate system, and the second coordinate position information refers to the second three-dimensional coordinates of the second marker in the second marker coordinate system. Therefore, the vehicle inspection device can specifically determine the third rotation and translation matrix according to the following steps, as detailed below:

[0123] determining, based on the third image, the two-dimensional coordinates of the second marker in the image coordinate system corresponding to the third camera;

[0124] determining, based on the fourth image, the two-dimensional coordinates of the first marker in the image coordinate system corresponding to the fourth camera;

[0125] determining a first sub-rotation and translation matrix based on the two-dimensional coordinates of the second marker in the image coordinate system corresponding to the third camera and the second three-dimensional coordinates;

[0126] determining a second sub-rotation and translation matrix based on the two-dimensional coordinates of the first marker in the image coordinate system corresponding to the fourth camera and the first three-dimensional coordinates;

[0127] The third rotation and translation matrix is ​​determined according to the first sub-rotation and translation matrix and the second sub-rotation and translation matrix.

[0128] In this embodiment, the automobile detection device can determine the two-dimensional coordinates of the second marker in the image coordinate system corresponding to the third camera based on the third image captured by the third camera of the first calibration device.

[0129] The automobile detection device can determine the two-dimensional coordinates of the first marker in the image coordinate system corresponding to the fourth camera based on the fourth image captured by the fourth camera of the second calibration device.

[0130] Afterwards, the automobile detection equipment can obtain the first sub-rotation and translation matrix between the third camera coordinate system and the second marker coordinate system based on the two-dimensional coordinates and the second three-dimensional coordinates (i.e., the second coordinate position information) of the second marker in the image coordinate system corresponding to the third camera.

[0131] It should be noted that, in one embodiment of the present application, when the second marker is a second spherical calibration ball, the above-mentioned second three-dimensional coordinates (i.e., the second coordinate position information) specifically refer to the three-dimensional coordinates of the center of the second spherical calibration ball in the preset second marker coordinate system, and the two-dimensional coordinates of the second marker in the image coordinate system corresponding to the third camera specifically refer to the two-dimensional coordinates of the center of the spherical surface formed by the projection of the center of the second spherical calibration ball in the ninth camera.

[0132] Since the image coordinate system corresponding to the third camera specifically refers to the image coordinate system constructed by the image captured by the third camera, after the automobile detection device captures the third image containing the second marker, the automobile detection device can determine any position point in the third image (such as the center of the third image, or any one of the four corner points of the third image) as the third origin. Thereafter, the automobile detection device can construct the image coordinate system corresponding to the third camera based on the third origin. Based on this, the automobile detection device can determine the coordinate position of the center of the sphere formed by the projection of the second spherical calibration ball in the third image based on the above-mentioned image coordinate system constructed, and determine the coordinate position as the two-dimensional coordinate of the second marker in the image coordinate system corresponding to the third camera.

[0133] In some possible embodiments, the automobile detection device may import the above two-dimensional coordinates and the second three-dimensional coordinates into the solvepnp algorithm to calculate the first sub-rotation and translation matrix between the third camera coordinate system and the second marker coordinate system.

[0134] It should be noted that, in one embodiment of the present application, when the first marker is a first spherical calibration ball, the above-mentioned first three-dimensional coordinates (i.e., the first coordinate position information) specifically refer to the three-dimensional coordinates of the center of the first spherical calibration ball in the preset first marker coordinate system, and the two-dimensional coordinates of the first marker in the image coordinate system corresponding to the fourth camera specifically refer to the two-dimensional coordinates of the center of the spherical surface formed by the projection of the center of the first spherical calibration ball in the fourth camera.

[0135] Since the image coordinate system corresponding to the fourth camera specifically refers to the image coordinate system constructed by the image captured by the fourth camera, after the automobile detection device captures the fourth image containing the first marker, the automobile detection device can determine any position point in the fourth image (such as the center of the fourth image, or any one of the four corner points of the fourth image) as the fourth origin. Thereafter, the automobile detection device can construct the image coordinate system corresponding to the fourth camera based on the fourth origin. Based on this, the automobile detection device can determine the coordinate position of the center of the sphere formed by the projection of the first spherical calibration ball in the fourth image based on the above-mentioned image coordinate system constructed, and determine the coordinate position as the two-dimensional coordinate of the first marker in the image coordinate system corresponding to the fourth camera.

[0136] In some possible embodiments, the automobile detection device may import the above two-dimensional coordinates and the first three-dimensional coordinates into the solvepnp algorithm to calculate the second sub-rotation and translation matrix between the fourth camera coordinate system and the first marker coordinate system.

[0137] In this embodiment, after the automobile detection device obtains the first sub-rotation and translation matrix and the second sub-rotation and translation matrix, since the first calibration device and the second calibration device are in relative positions, the directions of the first sub-rotation and translation matrix and the second sub-rotation and translation matrix are opposite. Therefore, the automobile detection device can arbitrarily select a rotation and translation matrix adjustment direction from the first sub-rotation and translation matrix and the second sub-rotation and translation matrix. Thereafter, the rotation and translation matrix after the adjustment direction and the rotation and translation matrix without the adjustment direction are summed to obtain the sum value, and the sum value is averaged to obtain the rotation and translation matrix after the average processing, and the rotation and translation matrix after the average processing is determined as the third rotation and translation matrix.

[0138] In S105 , parameter calibration is performed on the automobile detection device based on the two first rotation and translation matrices, the two second rotation and translation matrices, and the third rotation and translation matrix.

[0139] In an embodiment of the present application, after the automobile detection equipment obtains two first rotation and translation matrices, two second rotation and translation matrices, and a third rotation and translation matrix, since the two first rotation and translation matrices clarify the positional relationship between the two first measuring device sides on the first side and the first calibration device, the two second rotation and translation matrices clarify the positional relationship between the two second measuring device sides on the second side and the second calibration device, and the third rotation and translation matrix clarifies the positional relationship between the first calibration device and the second calibration device, the automobile detection equipment can realize parameter calibration of the automobile detection equipment based on the above-mentioned rotation and translation matrices.

[0140] As can be seen from the above, an embodiment of the present application provides a device parameter calibration method, which is applied to automobile detection equipment, wherein the automobile detection equipment includes two first measuring devices for respectively detecting the front wheels and rear wheels of a first side of the vehicle, two second measuring devices for respectively detecting the front wheels and rear wheels of a second side of the vehicle, a first calibration device for performing position calibration on the two first measuring devices on the first side, and a second calibration device for performing position calibration on the two second measuring devices on the second side; the first calibration device is provided with a first marker, and the second calibration device is provided with a second marker. The method determines the rotation and translation matrix between the camera coordinate system corresponding to each measuring unit and the marker coordinate system of the marker captured by each measuring unit, as well as the rotation and translation matrix between the camera coordinate systems corresponding to the two calibration devices, based on the images of the markers set in the calibration devices on the same side captured by each measuring unit, the images of the markers captured by each calibration device, and the coordinate position information of each marker in the corresponding marker coordinate system; finally, the automobile detection equipment can be calibrated according to the rotation and translation matrices obtained above. This method clarifies the positional relationship between each measurement unit and the calibration device on the same side, as well as the positional relationship between two calibration devices, thereby improving the accuracy of subsequent tire parameter measurements.

[0141] Please refer to Figure 4, which illustrates a device parameter calibration method provided by another embodiment of the present application. Compared to the embodiment corresponding to Figure 2, in this embodiment, the two first measurement devices further include a fifth camera for respectively collecting first tire point cloud data for the front and rear wheels on the first side; the planes where the first cameras corresponding to the two first measurement devices are located are at an angle to the planes where the fifth cameras corresponding to the two first measurement devices are located; the two second measurement devices further include a sixth camera for respectively collecting second tire point cloud data for the front and rear wheels on the second side; the planes where the second cameras corresponding to the two second measurement devices are located are at an angle to the planes where the sixth cameras corresponding to the two second measurement devices are located. Therefore, after S105, this embodiment may further include S301 to S303, as detailed below:

[0142] In S301 , a target measuring device is determined.

[0143] The automobile inspection equipment can randomly determine a target measurement device from two first measurement devices, two second measurement devices, a first calibration device, and a second calibration device, and determine the coordinate system corresponding to the target measurement device as the target coordinate system, so that the initial tire point cloud data of different wheels in their respective corresponding coordinate systems can be converted to the same coordinate system, that is, the target tire point cloud data in the target coordinate system.

[0144] In one embodiment of the present application, in order to improve the working efficiency of the automobile detection equipment and reduce the number of coordinate conversions, the automobile detection equipment may determine the first calibration device or the second calibration device as the target measurement device.

[0145] In S302 , a set of first tire point cloud data collected by the two fifth cameras and a set of second tire point cloud data collected by the two sixth cameras are obtained.

[0146] In one implementation of this embodiment, the automobile inspection equipment can collect a set of first tire point cloud data of the front wheel on the first side in real time through the fifth camera in the first measuring equipment for inspecting the front wheel on the first side of the vehicle, which is wirelessly connected to it, and collect a set of first tire point cloud data of the rear wheel on the first side in real time through the fifth camera in the first measuring equipment for inspecting the rear wheel on the first side of the vehicle, which is wirelessly connected to it.

[0147] In another implementation of this embodiment, the automobile inspection equipment can collect a set of second tire point cloud data of the front wheels on the second side in real time through the sixth camera in the second measuring equipment for inspecting the front wheels on the second side of the vehicle, which is wirelessly connected to it, and collect a set of second tire point cloud data of the rear wheels on the second side in real time through the sixth camera in the second measuring equipment for inspecting the rear wheels on the second side of the vehicle, which is wirelessly connected to it.

[0148] In S303, coordinate transformation processing is performed on each group of the first tire point cloud data and each group of the second tire point cloud data based on the two first rotation and translation matrices, the two second rotation and translation matrices, the third rotation and translation matrix, a fourth rotation and translation matrix between the first camera coordinate system corresponding to each of the two first cameras and the fifth camera coordinate system corresponding to each of the five cameras, and a fifth rotation and translation matrix between the second camera coordinate system corresponding to each of the two second cameras and the sixth camera coordinate system corresponding to each of the six cameras, to obtain first target tire point cloud data corresponding to each of the front and rear wheels of the first side, and second target tire point cloud data corresponding to each of the front and rear wheels of the second side, in the target coordinate system. The target coordinate system refers to the coordinate system corresponding to the target measurement device.

[0149] In this embodiment, after obtaining two sets of first tire point cloud data and two sets of second tire point cloud data, the automobile inspection equipment can perform coordinate transformation processing on each set of first tire point cloud data and each set of second tire point cloud data according to the two first rotation and translation matrices, the two second rotation and translation matrices, the third rotation and translation matrix, the fourth rotation and translation matrix between the first camera coordinate systems corresponding to each of the two first cameras and the fifth camera coordinate systems corresponding to each of the five cameras corresponding to each of the two second cameras and the sixth camera coordinate systems corresponding to each of the six cameras corresponding to each of the two second cameras, to obtain first target tire point cloud data corresponding to each of the front wheels and the rear wheels on the first side, and second target tire point cloud data corresponding to each of the front wheels and the rear wheels on the second side in the target coordinate system.

[0150] In one embodiment of the present application, when the target measurement device is any one of the first measurement devices, the target coordinate system is the fifth camera coordinate system corresponding to the fifth camera in the any one of the first measurement devices. Therefore, the automobile inspection device can specifically obtain two sets of first target tire point cloud data and two sets of second target tire point cloud data through steps S401 to S402 as shown in FIG5 , as detailed below:

[0151] In S401 , coordinate transformation processing is performed on each set of the first tire point cloud data according to the two first rotation and translation matrices, the two fourth rotation and translation matrices, and the third rotation and translation matrix to obtain two sets of the first target tire point cloud data.

[0152] In this embodiment, when the target measurement device is a first measurement device used to detect the front wheel on the first side, the automobile detection device can directly determine the first tire point cloud data collected by the fifth camera in the first measurement device used to detect the front wheel on the first side as a set of first target tire point cloud data, that is, the first target tire point cloud data corresponding to the front wheel on the first side in the target coordinate system.

[0153] Regarding the first tire point cloud data collected by the fifth camera in the first measuring device for detecting the rear wheel on the first side, the automobile inspection device can convert the first tire point cloud data collected by the fifth camera in the first measuring device for detecting the rear wheel on the first side into first point cloud data in the first camera coordinate system of the first camera in the first measuring device for detecting the rear wheel on the first side based on the fourth rotation and translation matrix between the first camera coordinate system of the first camera in the first measuring device for detecting the rear wheel on the first side and the fifth camera coordinate system of the fifth camera in the first measuring device for detecting the rear wheel on the first side.

[0154] Afterwards, the automobile inspection device can convert the above-mentioned first point cloud data into second point cloud data in the first marker coordinate system of the first calibration device based on the first rotation and translation matrix between the first camera coordinate system of the first camera in the first measuring device used to inspect the rear wheel on the first side and the first marker coordinate system.

[0155] Afterwards, the automobile inspection device can convert the above-mentioned second point cloud data into third point cloud data in the first camera coordinate system of the first camera in the first measuring device used to inspect the front wheel on the first side based on the first rotation and translation matrix between the first camera coordinate system of the first camera in the first measuring device used to inspect the front wheel on the first side and the first marker coordinate system.

[0156] Finally, the automobile inspection equipment can convert the above-mentioned third point cloud data into first target tire point cloud data in the fifth camera coordinate system of the fifth camera in the first measuring device used to detect the front wheel of the first side, that is, the first target tire point cloud data corresponding to the rear wheel of the first side in the target coordinate system, based on the fourth rotation and translation matrix between the first camera coordinate system of the first camera in the first measuring device used to detect the front wheel of the first side and the fifth camera coordinate system of the fifth camera in the first measuring device used to detect the front wheel of the first side.

[0157] In S402, coordinate transformation processing is performed on each set of the second tire point cloud data according to the two first rotation and translation matrices, the two second rotation and translation matrices, the two fourth rotation and translation matrices, the two fifth rotation and translation matrices, and the third rotation and translation matrix to obtain two sets of the second target tire point cloud data.

[0158] In this embodiment, with respect to the second tire point cloud data collected by the sixth camera in the second measuring device for detecting the front wheel on the second side, the automobile inspection device can convert the second tire point cloud data collected by the sixth camera in the second measuring device for detecting the front wheel on the second side into fourth point cloud data in the second camera coordinate system of the second camera in the second measuring device for detecting the front wheel on the second side based on the fifth rotation and translation matrix between the second camera coordinate system of the second camera in the second measuring device for detecting the front wheel on the second side and the sixth camera coordinate system of the sixth camera in the second measuring device for detecting the front wheel on the second side.

[0159] Afterwards, the automobile inspection device can convert the above-mentioned fourth point cloud data into fifth point cloud data in the second marker coordinate system of the second calibration device based on the second rotation and translation matrix between the second camera coordinate system of the second camera in the second measuring device used to inspect the front wheel on the second side and the second marker coordinate system.

[0160] Afterwards, the automobile detection device can convert the fifth point cloud data into sixth point cloud data in the first marker coordinate system of the first calibration device according to the third rotation and translation matrix.

[0161] Afterwards, the automobile inspection device can convert the above-mentioned sixth point cloud data into seventh point cloud data in the first camera coordinate system of the first camera in the first measuring device used to inspect the front wheel of the first side based on the first rotation and translation matrix between the first camera coordinate system of the first camera in the first measuring device used to inspect the front wheel of the first side and the first marker coordinate system.

[0162] Finally, the automobile inspection device can convert the above-mentioned seventh point cloud data into second target tire point cloud data in the fifth camera coordinate system of the fifth camera in the first measuring device used to detect the front wheel on the first side, that is, the second target tire point cloud data corresponding to the front wheel on the second side in the target coordinate system, based on the fourth rotation and translation matrix between the first camera coordinate system of the first camera in the first measuring device used to detect the front wheel on the first side and the fifth camera coordinate system of the fifth camera in the first measuring device used to detect the front wheel on the first side.

[0163] In this embodiment, with respect to the second tire point cloud data collected by the sixth camera in the second measuring device for detecting the rear wheel on the second side, the automobile inspection device can convert the second tire point cloud data collected by the sixth camera in the second measuring device for detecting the rear wheel on the second side into eighth point cloud data in the second camera coordinate system of the second camera in the second measuring device for detecting the rear wheel on the second side based on the fifth rotation and translation matrix between the second camera coordinate system of the second camera in the second measuring device for detecting the rear wheel on the second side and the sixth camera coordinate system of the sixth camera in the second measuring device for detecting the rear wheel on the second side.

[0164] Afterwards, the automobile inspection device can convert the above-mentioned eighth point cloud data into ninth point cloud data in the second marker coordinate system of the second calibration device based on the second rotation and translation matrix between the second camera coordinate system of the second camera in the second measuring device used to inspect the rear wheel on the second side and the second marker coordinate system.

[0165] Afterwards, the automobile detection device can convert the ninth point cloud data into tenth point cloud data in the first marker coordinate system of the first calibration device according to the third rotation and translation matrix.

[0166] Afterwards, the automobile inspection device can convert the above-mentioned tenth point cloud data into the eleventh point cloud data in the first camera coordinate system of the first camera in the first measuring device used to inspect the front wheel of the first side based on the first rotation and translation matrix between the first camera coordinate system of the first camera in the first measuring device used to inspect the front wheel of the first side and the first marker coordinate system.

[0167] Finally, the automobile inspection device can convert the above-mentioned eleventh point cloud data into second target tire point cloud data in the fifth camera coordinate system of the fifth camera in the first measuring device used to detect the front wheel of the first side, that is, the second target tire point cloud data corresponding to the rear wheel on the second side in the target coordinate system, based on the fourth rotation and translation matrix between the first camera coordinate system of the first camera in the first measuring device used to detect the front wheel of the first side and the fifth camera coordinate system of the fifth camera in the first measuring device used to detect the front wheel of the first side.

[0168] In another embodiment of the present application, when the target measurement device is a first calibration device, the target coordinate system is the first marker coordinate system in the first calibration device. Therefore, the automobile inspection device can specifically obtain two sets of first target tire point cloud data and two sets of second target tire point cloud data through steps S501 to S502 as shown in FIG6 , as detailed below:

[0169] In S501 , coordinate transformation processing is performed on each set of the first tire point cloud data according to the two first rotation and translation matrices and the two fourth rotation and translation matrices to obtain two sets of the first target tire point cloud data.

[0170] In this embodiment, with respect to the first tire point cloud data collected by the fifth camera in the first measuring device for detecting the front wheel on the first side, the automobile inspection device can convert the first tire point cloud data collected by the fifth camera in the first measuring device for detecting the front wheel on the first side into twelfth point cloud data in the first camera coordinate system of the first camera in the first measuring device for detecting the front wheel on the first side based on the fourth rotation and translation matrix between the first camera coordinate system of the first camera in the first measuring device for detecting the front wheel on the first side and the fifth camera coordinate system of the fifth camera in the first measuring device for detecting the front wheel on the first side.

[0171] Afterwards, the automobile inspection device can convert the above-mentioned twelfth point cloud data into a set of first target tire point cloud data in the first marker coordinate system of the first calibration device based on the first rotation and translation matrix between the first camera coordinate system of the first camera in the first measuring device used to inspect the front wheel on the first side and the first marker coordinate system, that is, the first target tire point cloud data corresponding to the front wheel on the first side in the target coordinate system.

[0172] In this embodiment, with respect to the first tire point cloud data collected by the fifth camera in the first measuring device for detecting the rear wheel on the first side, the automobile inspection device can convert the first tire point cloud data collected by the fifth camera in the first measuring device for detecting the rear wheel on the first side into thirteenth point cloud data in the first camera coordinate system of the first camera in the first measuring device for detecting the rear wheel on the first side based on the fourth rotation and translation matrix between the first camera coordinate system of the first camera in the first measuring device for detecting the rear wheel on the first side and the fifth camera coordinate system of the fifth camera in the first measuring device for detecting the rear wheel on the first side.

[0173] Afterwards, the automobile inspection device can convert the above-mentioned thirteenth point cloud data into a set of first target tire point cloud data in the first marker coordinate system of the first calibration device based on the first rotation and translation matrix between the first camera coordinate system of the first camera in the first measuring device used to inspect the rear wheel on the first side and the first marker coordinate system, that is, the first target tire point cloud data corresponding to the rear wheel on the first side in the target coordinate system.

[0174] In S502 , coordinate transformation processing is performed on each set of the second tire point cloud data according to the two second rotation and translation matrices, the two fifth rotation and translation matrices, and the third rotation and translation matrix to obtain two sets of the second target tire point cloud data.

[0175] In this embodiment, with respect to the second tire point cloud data collected by the sixth camera in the second measuring device for detecting the front wheel on the second side, the automobile inspection device can convert the second tire point cloud data collected by the sixth camera in the second measuring device for detecting the front wheel on the second side into fourteenth point cloud data in the second camera coordinate system of the second camera in the second measuring device for detecting the front wheel on the second side based on the fifth rotation and translation matrix between the second camera coordinate system of the second camera in the second measuring device for detecting the front wheel on the second side and the sixth camera coordinate system of the sixth camera in the second measuring device for detecting the front wheel on the second side.

[0176] Afterwards, the automobile inspection device can convert the above-mentioned fourteenth point cloud data into fifteenth point cloud data in the second marker coordinate system of the second calibration device based on the second rotation and translation matrix between the second camera coordinate system of the second camera in the second measuring device used to inspect the front wheel on the second side and the second marker coordinate system.

[0177] Afterwards, the automobile detection equipment can convert the above-mentioned fifteenth point cloud data into a set of second target tire point cloud data in the first marker coordinate system of the first calibration device according to the third rotation and translation matrix, that is, the second target tire point cloud data corresponding to the front wheel on the second side in the target coordinate system.

[0178] In this embodiment, with respect to the second tire point cloud data collected by the sixth camera in the second measuring device for detecting the rear wheel on the second side, the automobile inspection device can convert the second tire point cloud data collected by the sixth camera in the second measuring device for detecting the rear wheel on the second side into sixteenth point cloud data in the second camera coordinate system of the second camera in the second measuring device for detecting the rear wheel on the second side based on the fifth rotation and translation matrix between the second camera coordinate system of the second camera in the second measuring device for detecting the rear wheel on the second side and the sixth camera coordinate system of the sixth camera in the second measuring device for detecting the rear wheel on the second side.

[0179] Afterwards, the automobile inspection device can convert the above-mentioned fourteenth point cloud data into the seventeenth point cloud data in the second marker coordinate system of the second calibration device based on the second rotation and translation matrix between the second camera coordinate system of the second camera in the second measuring device used to inspect the rear wheel on the second side and the second marker coordinate system.

[0180] Afterwards, the automobile detection equipment can convert the above-mentioned seventeenth point cloud data into a set of second target tire point cloud data in the first marker coordinate system of the first calibration device according to the third rotation and translation matrix, that is, the second target tire point cloud data corresponding to the rear wheel on the second side in the target coordinate system.

[0181] As can be seen from the above, the device parameter calibration method provided in this embodiment can combine the two first rotation and translation matrices, the two second rotation and translation matrices, the third rotation and translation matrix, the fourth rotation and translation matrix between the first camera coordinate system corresponding to each of the two first cameras and the fifth camera coordinate system corresponding to each of the five cameras, and the fifth rotation and translation matrix between the second camera coordinate system corresponding to each of the two second cameras and the sixth camera coordinate system corresponding to each of the six cameras after the vehicle detection equipment is calibrated. Coordinate transformation processing is performed on the tire point cloud data of each front wheel and each rear wheel of the vehicle to obtain two sets of first target tire point cloud data pairs and two sets of second target tire point cloud data in the same coordinate system (i.e., the target coordinate system corresponding to the target measurement device). This ensures that the tire point cloud data of each front wheel and each rear wheel of the vehicle are in the same coordinate system, further improving the accuracy and efficiency of subsequent tire parameter measurement.

[0182] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0183] Corresponding to the device parameter calibration method described in the above embodiment, FIG7 shows a schematic diagram of the structure of a device parameter calibration apparatus provided in an embodiment of the present application. For ease of explanation, only the parts relevant to the embodiment of the present application are shown. Referring to FIG7 , the device parameter calibration apparatus 700 includes: a first acquisition unit 71, a position determination unit 72, a first matrix determination unit 73, a second matrix determination unit 74, and a calibration unit 75. Among them:

[0184] The first acquisition unit 71 is used to acquire the first images corresponding to the first marker respectively photographed by the two first measuring devices and the second images corresponding to the second marker respectively photographed by the two second measuring devices; and to acquire the third image obtained by the first calibration device photographing the second marker and the fourth image obtained by the second calibration device photographing the first marker.

[0185] The position determination unit 72 is used to determine the first coordinate position information of the first marker in a preset first marker coordinate system and the second coordinate position information of the second marker in a preset second marker coordinate system; the first marker coordinate system and the second marker coordinate system are both world coordinate systems.

[0186] The first matrix determination unit 73 is used to determine the first rotation and translation matrix between the first camera coordinate system corresponding to each of the two first measuring devices and the first marker coordinate system based on the two first images and the first coordinate position information, and to determine the second rotation and translation matrix between the second camera coordinate system corresponding to each of the two second measuring devices and the second marker coordinate system based on the two second images and the second coordinate position information.

[0187] The second matrix determination unit 74 is used to determine a third rotation and translation matrix between the third camera coordinate system of the first calibration device and the fourth camera coordinate system of the second calibration device according to the third image, the fourth image, the first coordinate position information and the second coordinate position information.

[0188] A calibration unit is used to perform parameter calibration on the automobile detection device based on the two first rotation and translation matrices, the two second rotation and translation matrices, and the third rotation and translation matrix 75.

[0189] In one embodiment of the present application, the two first measuring devices each include a first camera for photographing the first marker in the first calibration device, and the two second measuring devices each include a second camera for photographing the second marker in the second calibration device. The first coordinate position information refers to the first three-dimensional coordinates of the first marker in the first marker coordinate system, and the second coordinate position information refers to the second three-dimensional coordinates of the second marker in the second marker coordinate system. The first matrix determination unit 73 specifically includes: a first coordinate determination unit, a second coordinate determination unit, a third matrix determination unit, and a fourth matrix determination unit. Wherein:

[0190] The first coordinate determining unit is used to determine the two-dimensional coordinates of the first marker in the image coordinate systems corresponding to the two first cameras according to the two first images.

[0191] The second coordinate determining unit is used to determine the two-dimensional coordinates of the second marker in the image coordinate systems corresponding to the two second cameras according to the two second images.

[0192] The third matrix determination unit is used to determine the first rotation and translation matrix between the first camera coordinate system corresponding to each of the two first measuring devices and the first marker coordinate system based on the two-dimensional coordinates and the first three-dimensional coordinates of the first marker in the image coordinate systems corresponding to the two first cameras.

[0193] The fourth matrix determination unit is used to determine the second rotation and translation matrix between the second camera coordinate system corresponding to each of the two second measuring devices and the second marker coordinate system based on the two-dimensional coordinates and the second three-dimensional coordinates of the second marker in the image coordinate systems corresponding to the two second cameras.

[0194] In one embodiment of the present application, the first calibration device includes a third camera for photographing the second marker, the second calibration device includes a fourth camera for photographing the first marker, the first coordinate position information refers to the first three-dimensional coordinates of the first marker in the first marker coordinate system, and the second coordinate position information refers to the second three-dimensional coordinates of the second marker in the second marker coordinate system; the second matrix determination unit 74 specifically includes: a third coordinate determination unit, a fourth coordinate determination unit, a first sub-matrix determination unit, a second sub-matrix determination unit, and a fifth matrix determination unit. Wherein:

[0195] The third coordinate determining unit is configured to determine the two-dimensional coordinates of the second marker in the image coordinate system corresponding to the third camera according to the third image.

[0196] The fourth coordinate determining unit is configured to determine, based on the fourth image, the two-dimensional coordinates of the first marker in the image coordinate system corresponding to the fourth camera.

[0197] The first sub-matrix determination unit is configured to determine a first sub-rotation and translation matrix based on the two-dimensional coordinates of the second marker in the image coordinate system corresponding to the third camera and the second three-dimensional coordinates.

[0198] The second sub-matrix determination unit is configured to determine a second sub-rotation and translation matrix based on the two-dimensional coordinates of the first marker in the image coordinate system corresponding to the fourth camera and the first three-dimensional coordinates.

[0199] The fifth matrix determination unit is configured to determine the third rotation and translation matrix according to the first sub-rotation and translation matrix and the second sub-rotation and translation matrix.

[0200] In one embodiment of the present application, the first marker includes multiple items, and accordingly, the two-dimensional coordinates corresponding to the first marker include multiple items, and the first three-dimensional coordinates include multiple items; the second marker includes multiple items, and accordingly, the two-dimensional coordinates corresponding to the second marker include multiple items, and the second three-dimensional coordinates of the second marker include multiple items; the third matrix determination unit specifically includes: a second acquisition unit, a first relationship determination unit, and a sixth matrix determination unit. Wherein:

[0201] The second acquisition unit is used to acquire the intrinsic parameters and distortion parameters of each of the two first cameras.

[0202] The first relationship determination unit is used to determine the first mapping relationship between the two-dimensional coordinates of multiple first markers in the image coordinate systems corresponding to the two first cameras and the multiple first three-dimensional coordinates based on the intrinsic parameters and distortion parameters of the two first cameras.

[0203] The sixth matrix determination unit is configured to determine, based on the first mapping relationship, a first rotation and translation matrix between the first camera coordinate system corresponding to each of the two first measurement devices and the first marker coordinate system.

[0204] Accordingly, the fourth matrix determination unit specifically includes: a third acquisition unit, a second relationship determination unit and a seventh matrix determination unit.

[0205] The third acquisition unit is used to acquire the intrinsic parameters and distortion parameters of each of the two second cameras.

[0206] The second relationship determination unit is used to determine the second mapping relationship between the two-dimensional coordinates of multiple first markers in the image coordinate systems corresponding to the two second cameras and the multiple second three-dimensional coordinates based on the intrinsic parameters and distortion parameters of the two second cameras.

[0207] The seventh matrix determination unit is configured to determine, based on the second mapping relationship, a second rotation and translation matrix between the second camera coordinate system corresponding to each of the two second measurement devices and the second marker coordinate system.

[0208] In one embodiment of the present application, the two first measurement devices further include a fifth camera for respectively collecting first tire point cloud data of the front wheel and the rear wheel on the first side; the plane where the first camera corresponding to each of the two first measurement devices is located is at an angle to the plane where the fifth camera corresponding to each of the two first measurement devices is located; the two second measurement devices further include a sixth camera for respectively collecting second tire point cloud data of the front wheel and the rear wheel on the second side; the device parameter calibration apparatus 700 further includes: a device determination unit, a fourth acquisition unit, and a target data determination unit. Among them:

[0209] The device determining unit is used to determine a target measuring device.

[0210] The fourth acquiring unit is configured to acquire a set of first tire point cloud data acquired by each of the two fifth cameras, and a set of second tire point cloud data acquired by each of the two sixth cameras.

[0211] The target data determination unit is configured to perform coordinate conversion processing on each group of the first tire point cloud data and each group of the second tire point cloud data based on the two first rotation and translation matrices, the two second rotation and translation matrices, the third rotation and translation matrix, a fourth rotation and translation matrix between the first camera coordinate system corresponding to each of the two first cameras and the fifth camera coordinate system corresponding to each of the five cameras, and a fifth rotation and translation matrix between the second camera coordinate system corresponding to each of the two second cameras and the sixth camera coordinate system corresponding to each of the six cameras, to obtain first target tire point cloud data corresponding to each of the front wheels and the rear wheels on the first side, and second target tire point cloud data corresponding to each of the front wheels and the rear wheels on the second side, in the target coordinate system; wherein the target coordinate system refers to the coordinate system corresponding to the target measurement device.

[0212] In one embodiment of the present application, the target measurement device is any one of the first measurement devices, and the target coordinate system is the fifth camera coordinate system corresponding to the fifth camera in any one of the first measurement devices; the target data determination unit specifically includes: a first processing unit and a second processing unit.

[0213] The first processing unit is configured to perform coordinate transformation processing on each set of the first tire point cloud data according to the two first rotation and translation matrices, the two fourth rotation and translation matrices, and the third rotation and translation matrix to obtain two sets of the first target tire point cloud data.

[0214] The second processing unit is configured to perform coordinate transformation processing on each set of the second tire point cloud data according to the two first rotation and translation matrices, the two second rotation and translation matrices, the two fourth rotation and translation matrices, the two fifth rotation and translation matrices, and the third rotation and translation matrix to obtain two sets of the second target tire point cloud data.

[0215] In one embodiment of the present application, the target measurement device is the first calibration device, the target coordinate system is the first marker coordinate system in the first calibration device; the target data determination unit specifically includes: a third processing unit and a fourth processing unit.

[0216] The third processing unit is configured to perform coordinate transformation processing on each set of the first tire point cloud data according to the two first rotation and translation matrices and the two fourth rotation and translation matrices to obtain two sets of the first target tire point cloud data.

[0217] The fourth processing unit is configured to perform coordinate transformation processing on each set of the second tire point cloud data according to the two second rotation and translation matrices, the two fifth rotation and translation matrices, and the third rotation and translation matrix to obtain two sets of the second target tire point cloud data.

[0218] It should be noted that the information interaction, execution process, etc. between the above-mentioned devices / units are based on the same concept as the method embodiment of this application. Their specific functions and technical effects can be found in the method embodiment section and will not be repeated here.

[0219] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0220] FIG8 is a schematic diagram of the structure of an automobile testing device provided in one embodiment of the present application. As shown in FIG8 , the automobile testing device 8 of this embodiment includes: at least one processor 80 (only one is shown in FIG8 ), a memory 81, and a computer program 82 stored in the memory 81 and executable on the at least one processor 80. When the processor 80 executes the computer program 82, it implements the steps of any of the above-described device parameter calibration method embodiments.

[0221] The vehicle detection device may include, but is not limited to, a processor 80 and a memory 81. Those skilled in the art will appreciate that FIG8 is merely an example of the vehicle detection device 8 and does not limit the vehicle detection device 8 . The vehicle detection device 8 may include more or fewer components than shown in the figure, or may combine certain components or different components. For example, the vehicle detection device may further include input and output devices, network access devices, etc.

[0222] The processor 80 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. A general-purpose processor may be a microprocessor or any conventional processor.

[0223] In some embodiments, the memory 81 can be an internal storage unit of the automobile detection device 8, such as the internal memory of the automobile detection device 8. In other embodiments, the memory 81 can also be an external storage device of the automobile detection device 8, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the automobile detection device 8. Furthermore, the memory 81 can also include both the internal storage unit of the automobile detection device 8 and an external storage device. The memory 81 is used to store an operating system, an application program, a boot loader (BootLoader), data, and other programs, such as the program code of the computer program. The memory 81 can also be used to temporarily store data that has been output or is about to be output.

[0224] An embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in the above-mentioned various method embodiments can be implemented.

[0225] An embodiment of the present application provides a computer program product. When the computer program product is run on an automobile testing device, the automobile testing device can implement the steps in the above-mentioned various method embodiments when executing the computer program product.

[0226] 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 present application implements all or part of the processes in the above-mentioned embodiment method, which can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and when the computer program is executed by the processor, it can implement the steps of the above-mentioned various method embodiments. Wherein, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may at least include: any entity or device capable of carrying the computer program code to the automobile detection equipment, a recording medium, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electric carrier signal, a telecommunication signal and a software distribution medium. For example, a USB flash drive, a mobile hard disk, a magnetic disk or an optical disk. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electric carrier signals and telecommunication signals.

[0227] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant description of other embodiments.

[0228] The above-described embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present application, and should all be included in the scope of protection of the present application.

Claims

1. A device parameter calibration method, characterized in that: Applicable to automobile testing equipment, the automobile testing equipment comprising two first measuring devices for respectively testing the front wheels and rear wheels on a first side of the vehicle, two second measuring devices for respectively testing the front wheels and rear wheels on a second side of the vehicle, a first calibration device for performing position calibration on the two first measuring devices on the first side, and a second calibration device for performing position calibration on the two second measuring devices on the second side; The first calibration device is provided with a first marker, the second calibration device is provided with a second marker, and the method includes: Acquire first images corresponding to the first marker, respectively, obtained by the two first measuring devices, and second images corresponding to the second marker, respectively, obtained by the two second measuring devices; and acquire a third image of the second marker, respectively, obtained by the first calibration device, and a fourth image of the first marker, respectively, obtained by the second calibration device; Determining first coordinate position information of the first marker in a preset first marker coordinate system and second coordinate position information of the second marker in a preset second marker coordinate system; both the first marker coordinate system and the second marker coordinate system are world coordinate systems; Determine, based on the two first images and the first coordinate position information, a first rotation and translation matrix between a first camera coordinate system corresponding to each of the two first measuring devices and the first marker coordinate system; and determine, based on the two second images and the second coordinate position information, a second rotation and translation matrix between a second camera coordinate system corresponding to each of the two second measuring devices and the second marker coordinate system; Determine a third rotation and translation matrix between a third camera coordinate system of the first calibration device and a fourth camera coordinate system of the second calibration device according to the third image, the fourth image, the first coordinate position information, and the second coordinate position information; Parameter calibration is performed on the automobile detection equipment based on the two first rotation and translation matrices, the two second rotation and translation matrices, and the third rotation and translation matrix.

2. The device parameter calibration method according to claim 1, characterized in that: The two first measuring devices each include a first camera for photographing the first marker in the first calibration device, and the two second measuring devices each include a second camera for photographing the second marker in the second calibration device. The first coordinate position information refers to the first three-dimensional coordinate of the first marker in the first marker coordinate system, and the second coordinate position information refers to the second three-dimensional coordinate of the second marker in the second marker coordinate system. Determining, based on the two first images and the first coordinate position information, a first rotation and translation matrix between the first camera coordinate system corresponding to each of the two first measuring devices and the first marker coordinate system, and determining, based on the two second images and the second coordinate position information, a second rotation and translation matrix between the second camera coordinate system corresponding to each of the two second measuring devices and the second marker coordinate system, includes: determining, based on the two first images, the two-dimensional coordinates of the first marker in the image coordinate systems corresponding to the two first cameras; determining, based on the two second images, the two-dimensional coordinates of the second marker in the image coordinate systems corresponding to the two second cameras; determining a first rotation and translation matrix between the first camera coordinate system corresponding to each of the two first measuring devices and the first marker coordinate system based on the two-dimensional coordinates and the first three-dimensional coordinates of the first marker in the image coordinate systems corresponding to the two first cameras; Based on the two-dimensional coordinates and the second three-dimensional coordinates of the second marker in the image coordinate systems corresponding to the two second cameras, a second rotation and translation matrix between the second camera coordinate system corresponding to each of the two second measuring devices and the second marker coordinate system is determined.

3. The device parameter calibration method according to claim 1, wherein: The first calibration device includes a third camera for photographing the second marker, the second calibration device includes a fourth camera for photographing the first marker, the first coordinate position information refers to a first three-dimensional coordinate of the first marker in the first marker coordinate system, and the second coordinate position information refers to a second three-dimensional coordinate of the second marker in the second marker coordinate system, and determining a third rotation and translation matrix between the third camera coordinate system of the first calibration device and the fourth camera coordinate system of the second calibration device based on the third image, the fourth image, the first coordinate position information, and the second coordinate position information includes: determining, based on the third image, the two-dimensional coordinates of the second marker in the image coordinate system corresponding to the third camera; determining, based on the fourth image, the two-dimensional coordinates of the first marker in the image coordinate system corresponding to the fourth camera; determining a first sub-rotation and translation matrix based on the two-dimensional coordinates of the second marker in the image coordinate system corresponding to the third camera and the second three-dimensional coordinates; determining a second sub-rotation and translation matrix based on the two-dimensional coordinates of the first marker in the image coordinate system corresponding to the fourth camera and the first three-dimensional coordinates; The third rotation and translation matrix is ​​determined according to the first sub-rotation and translation matrix and the second sub-rotation and translation matrix.

4. The device parameter calibration method according to claim 2, wherein: The first markers include a plurality of markers, and correspondingly, the two-dimensional coordinates corresponding to the first markers include a plurality of markers, and the first three-dimensional coordinates include a plurality of markers; the second markers include a plurality of markers, and correspondingly, the two-dimensional coordinates corresponding to the second markers include a plurality of markers, and the second three-dimensional coordinates of the second markers include a plurality of markers; and determining a first rotation and translation matrix between the first camera coordinate system corresponding to each of the two first measuring devices and the first marker coordinate system based on the two-dimensional coordinates and the first three-dimensional coordinates of the first marker in the image coordinate systems corresponding to the two first cameras, respectively, includes: Obtaining intrinsic parameters and distortion parameters of each of the two first cameras; Determining, based on the intrinsic parameters and distortion parameters of each of the two first cameras, first mapping relationships between the two-dimensional coordinates of the plurality of first markers in the image coordinate systems corresponding to the two first cameras and the plurality of first three-dimensional coordinates; Determining, based on the first mapping relationship, a first rotation and translation matrix between the first camera coordinate system corresponding to each of the two first measuring devices and the first marker coordinate system; The determining, based on the two-dimensional coordinates and the second three-dimensional coordinates of the second marker in the image coordinate systems corresponding to the two second cameras, a second rotation and translation matrix between the second camera coordinate systems corresponding to the two second measuring devices and the second marker coordinate system, includes: Obtaining intrinsic parameters and distortion parameters of each of the two second cameras; Determining, based on the intrinsic parameters and distortion parameters of each of the two second cameras, second mapping relationships between the two-dimensional coordinates of the plurality of first markers in the image coordinate systems corresponding to the two second cameras and the plurality of second three-dimensional coordinates; Based on the second mapping relationship, a second rotation and translation matrix between the second camera coordinate system corresponding to each of the two second measuring devices and the second marker coordinate system is determined.

5. The device parameter calibration method according to any one of claims 2 to 4, characterized in that: The two first measuring devices further include a fifth camera for respectively collecting first tire point cloud data of the front wheel and the rear wheel on the first side; a plane where the first camera corresponding to each of the two first measuring devices is located is at an angle to a plane where the fifth camera corresponding to each of the two first measuring devices is located; the two second measuring devices further include a sixth camera for respectively collecting second tire point cloud data of the front wheel and the rear wheel on the second side; a plane where the second camera corresponding to each of the two second measuring devices is located is at an angle to a plane where the sixth camera corresponding to each of the two second measuring devices is located; after calibrating the parameters of the vehicle detection device based on the two first rotation and translation matrices, the two second rotation and translation matrices, and the third rotation and translation matrix, the method further includes: Identify target measurement equipment; Acquire a set of first tire point cloud data collected by each of the two fifth cameras, and a set of second tire point cloud data collected by each of the two sixth cameras; According to the two first rotation and translation matrices, the two second rotation and translation matrices, the third rotation and translation matrix, the fourth rotation and translation matrix between the first camera coordinate system corresponding to each of the two first cameras and the fifth camera coordinate system corresponding to each of the five cameras, and the fifth rotation and translation matrix between the second camera coordinate system corresponding to each of the two second cameras and the sixth camera coordinate system corresponding to each of the six cameras, the first rotation and translation matrices of each group are respectively calculated. Coordinate conversion processing is performed on the tire point cloud data and each group of the second tire point cloud data to obtain first target tire point cloud data corresponding to each of the front wheels and the rear wheels on the first side, and second target tire point cloud data corresponding to each of the front wheels and the rear wheels on the second side, in a target coordinate system; wherein the target coordinate system refers to the coordinate system corresponding to the target measurement device.

6. The device parameter calibration method according to claim 5, characterized in that: The target measurement device is any one of the first measurement devices, and the target coordinate system is a fifth camera coordinate system corresponding to the fifth camera in the any one of the first measurement devices; the method further comprises performing coordinate transformation processing on each group of the first tire point cloud data and each group of the second tire point cloud data according to the two first rotation and translation matrices, the two second rotation and translation matrices, the third rotation and translation matrix, a fourth rotation and translation matrix between the first camera coordinate systems corresponding to the two first cameras and the fifth camera coordinate systems corresponding to the two fifth cameras, and a fifth rotation and translation matrix between the second camera coordinate systems corresponding to the two second cameras and the sixth camera coordinate systems corresponding to the six cameras, to obtain first target tire point cloud data corresponding to each of the front wheels and the rear wheels of the first side, and second target tire point cloud data corresponding to each of the front wheels and the rear wheels of the second side in the target coordinate system, including: performing coordinate transformation processing on each set of the first tire point cloud data according to the two first rotation and translation matrices, the two fourth rotation and translation matrices, and the third rotation and translation matrix, to obtain two sets of the first target tire point cloud data; Coordinate transformation processing is performed on each set of the second tire point cloud data according to the two first rotation and translation matrices, the two second rotation and translation matrices, the two fourth rotation and translation matrices, the two fifth rotation and translation matrices, and the third rotation and translation matrix to obtain two sets of the second target tire point cloud data.

7. The device parameter calibration method according to claim 5, characterized in that: The target measurement device is the first calibration device, and the target coordinate system is the first marker coordinate system in the first calibration device. The method further comprises performing coordinate transformation processing on each group of the first tire point cloud data and each group of the second tire point cloud data according to the two first rotation and translation matrices, the two second rotation and translation matrices, the third rotation and translation matrix, a fourth rotation and translation matrix between the first camera coordinate system corresponding to each of the two first cameras and the fifth camera coordinate system corresponding to each of the five cameras, and a fifth rotation and translation matrix between the second camera coordinate system corresponding to each of the two second cameras and the sixth camera coordinate system corresponding to each of the six cameras, to obtain first target tire point cloud data corresponding to each of the front wheels and the rear wheels of the first side, and second target tire point cloud data corresponding to each of the front wheels and the rear wheels of the second side in the target coordinate system, including: performing coordinate transformation processing on each set of the first tire point cloud data according to the two first rotation and translation matrices and the two fourth rotation and translation matrices, to obtain two sets of the first target tire point cloud data; Coordinate transformation processing is performed on each set of the second tire point cloud data according to the two second rotation and translation matrices, the two fifth rotation and translation matrices, and the third rotation and translation matrix to obtain two sets of the second target tire point cloud data.

8. A device parameter calibration device, characterized in that: Applicable to automobile testing equipment, the automobile testing equipment comprising two first measuring devices for respectively testing the front wheels and rear wheels on a first side of the vehicle, two second measuring devices for respectively testing the front wheels and rear wheels on a second side of the vehicle, a first calibration device for performing position calibration on the two first measuring devices on the first side, and a second calibration device for performing position calibration on the two second measuring devices on the second side; The first calibration device is provided with a first marker, the second calibration device is provided with a second marker, and the apparatus comprises: a first acquisition unit, configured to acquire first images corresponding to the first markers, respectively, obtained by the two first measuring devices, and second images corresponding to the second markers, respectively, obtained by the two second measuring devices; and acquire a third image corresponding to the second markers, respectively, obtained by the first calibration device, and a fourth image corresponding to the first markers, respectively, obtained by the second calibration device; a position determination unit, configured to determine first coordinate position information of the first marker in a preset first marker coordinate system and second coordinate position information of the second marker in a preset second marker coordinate system; the first marker coordinate system and the second marker coordinate system are both world coordinate systems; a first matrix determining unit for determining a first rotation between the first camera coordinate system corresponding to each of the two first measuring devices and the first marker coordinate system according to the two first images and the first coordinate position information; a translation matrix, and determining a second rotation and translation matrix between the second camera coordinate system corresponding to each of the two second measurement devices and the second marker coordinate system according to the two second images and the second coordinate position information; a second matrix determining unit, configured to determine a third rotation and translation matrix between a third camera coordinate system of the first calibration device and a fourth camera coordinate system of the second calibration device according to the third image, the fourth image, the first coordinate position information, and the second coordinate position information; A calibration unit is used to perform parameter calibration on the automobile detection equipment based on the two first rotation and translation matrices, the two second rotation and translation matrices, and the third rotation and translation matrix.

9. An automobile detection device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the device parameter calibration method according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the device parameter calibration method according to any one of claims 1 to 7 is implemented.

Images