Space calibration method, device, computer equipment and storage medium

Abstract

The embodiment of the present application discloses a spatial calibration method, device, computer equipment and storage medium, which relates to the field of image processing technology. After obtaining the position and posture information of a camera tracker and a calibration plate tracker, the spatial calibration method connects the local coordinate system of the camera and the world coordinate system of the capture system in series through the calibration plate to obtain the position and posture of the local coordinate system of the camera in the world coordinate system. The problem of low precision of spatial calibration in the prior art is solved, and the accuracy of spatial calibration is improved.

Description

Technical Field

[0001] The present application relates to the field of image processing technology, and in particular, to a spatial calibration method, apparatus, computer equipment and storage medium. Background Art

[0002] With the rapid development of television program production technology, in order to achieve more diverse program production styles, the spatial tracking technology of photographic cameras has become more mature. In the prior art, a tracking device can be installed in the camera, an active positioning device can be fixed to the camera, and the camera can obtain its own position by relying on the positioning device. The camera is fixedly connected to the positioning device to obtain the camera posture. However, this method requires the installation of fixed markers in the scene to determine the camera position. However, due to the limitation of the fixed position, the accurate position of the camera cannot be calculated, which will lead to poor positioning accuracy and poor spatial calibration accuracy. Summary of the invention

[0003] In order to solve the above technical problems, a method, apparatus, computer device and storage medium for spatial calibration are provided in the embodiments of the present application.

[0004] A first aspect of an embodiment of the present application provides a spatial calibration method, the method comprising:

[0005] Get the initial pose of the object to be calibrated in the camera coordinate system of the target camera;

[0006] Get the target camera tracker pose of the target feature point in the current calibration plate in the camera coordinate system, and the calibration plate tracker pose of the reflective point of the target feature point in the calibration plate coordinate system;

[0007] According to the calibration plate tracker pose and the target camera tracker pose corresponding to the target feature point, the camera coordinate system and the calibration plate coordinate system are converted to determine the relative pose of the initial pose in the calibration plate coordinate system;

[0008] According to the position information of the target feature points in the world coordinate system, the target pose of the initial pose of the object to be calibrated in the world coordinate system is determined.

[0009] In an optional embodiment of the present application, determining the target pose of the initial pose of the object to be calibrated in the world coordinate system also includes:

[0010] Get the initial external parameter matrix and initial camera internal parameters of the target camera;

[0011] Calculate the reprojection error of the target feature point in the current calibration plate according to the initial external parameter matrix and the initial camera internal parameter;

[0012] If the reprojection error is greater than or equal to a preset threshold, the attitude of the target camera is adjusted, and the extrinsic parameter matrix and camera intrinsic parameters are recalculated;

[0013] Calculate the reprojection error of the target feature points in the current calibration plate according to the external parameter matrix and the camera internal parameters of the current target camera, until the reprojection error is less than a preset threshold, then determine the current external parameter matrix as the target external parameter matrix, and determine the current camera internal parameters as the target camera internal parameters;

[0014] The target pose is obtained according to the target extrinsic parameter matrix and the target camera intrinsic parameter.

[0015] In an optional embodiment of the present application, obtaining the initial external parameter matrix and initial camera internal parameters of the target camera includes:

[0016] Get the calibration plate image of the current calibration plate;

[0017] Obtaining the position information of the target feature points in the calibration plate image;

[0018] Get the size parameters of the current calibration plate;

[0019] According to the position information and size parameters of the current calibration plate, the initial camera intrinsic parameter and initial extrinsic parameter matrix of the target camera are calculated.

[0020] In an optional embodiment of the present application, obtaining the position information of the preset feature points in the current calibration plate image includes:

[0021] Determine the target area in the current calibration plate image;

[0022] Calculate the position information of the target feature points in the target area;

[0023] The target area is an area in the plurality of image areas of the target plate image that is different from adjacent areas.

[0024] In an optional embodiment of the present application, determining a target area in a calibration plate image includes:

[0025] By performing contrast enhancement processing on the calibration plate image, a characteristic parameter of each area in the calibration plate image is obtained, where the characteristic parameter includes at least one of a color value and a grayscale value;

[0026] Traversing each area in the calibration plate image, calculating the difference between the characteristic parameters of each area and the characteristic parameters of the adjacent areas;

[0027] If the difference of the current area is greater than the preset value, the current area is determined as the target area.

[0028] In an optional embodiment of the present application, obtaining the calibration plate tracker pose of the reflective point of the target feature point in the calibration plate coordinate system includes:

[0029] Obtaining the position information of the reflective point corresponding to at least one feature point in the current calibration plate;

[0030] The calibration plate tracker pose is generated based on the position information of the reflective point in the calibration plate coordinate system.

[0031] In an optional embodiment of the present application, determining the relative posture of the initial posture in the calibration plate coordinate system includes:

[0032] According to the calibration plate tracker pose and the target camera tracker pose corresponding to the target feature points, the coordinate transformation parameters of the target camera tracker pose in the calibration plate coordinate system are calculated;

[0033] According to the coordinate transformation parameters, the relative pose of the initial pose in the calibration plate coordinate system is determined.

[0034] In an optional embodiment of the present application, determining the target posture of the relative posture in the world coordinate system includes:

[0035] Get the initial pose of the target feature points in the calibration plate in the world coordinate system;

[0036] According to the camera internal and external parameter matrices, the target coordinates of the target feature point in the calibration plate coordinate system are calculated;

[0037] The target pose of the relative pose in the world coordinate system is determined by the coordinate conversion between the initial pose and the target coordinates.

[0038] In an optional embodiment of the present application, obtaining a target camera tracker pose of a preset feature point in a camera coordinate system includes:

[0039] According to the position information of the target feature points collected by the target camera tracker;

[0040] Generate the target camera tracker pose based on the pose of the position information in the camera coordinate system.

[0041] A second aspect of an embodiment of the present application provides a space calibration device, including:

[0042] The positioning module is used to obtain the initial position and posture of the object to be calibrated in the camera coordinate system of the target camera;

[0043] An acquisition module is used to obtain the target camera tracker pose of the target feature point in the current calibration plate in the camera coordinate system, and the calibration plate tracker pose of the reflective point of the target feature point in the calibration plate coordinate system;

[0044] The parameter calculation module is used to convert the camera coordinate system and the calibration plate coordinate system according to the calibration plate tracker pose and the target camera tracker pose corresponding to the target feature point, and determine the relative pose of the initial pose in the calibration plate coordinate system;

[0045] The calibration module is used to determine the target pose of the initial pose of the object to be calibrated in the world coordinate system according to the position information of the target feature point in the world coordinate system.

[0046] According to a third aspect of an embodiment of the present application, a computer device is provided, comprising: a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of any of the above methods when executing the computer program.

[0047] A fourth aspect of an embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program implements the steps of any of the above methods when executed by a processor.

[0048] The above-mentioned spatial calibration method realizes multi-dimensional positioning of the target positioning point through a camera tracker and a calibration plate tracker. The accuracy of calculating the camera intrinsic parameter and extrinsic parameter matrix of the target camera is improved through multi-dimensional positioning. Through the camera intrinsic parameter and extrinsic parameter matrix, the initial position and posture of the target object in the local coordinate system of the camera can be calculated and converted to the position and posture in the world coordinate system, thereby finally improving the accuracy of spatial calibration. The spatial calibration method provided in the embodiment of the present application has a simple calibration process, convenient operation, and high positioning accuracy.

[0049] The embodiment of the present application can obtain the position and posture information of the target camera in the current space by calibrating the space of the target camera, and then process the position and posture information through the virtual rendering engine, so as to provide the virtual camera in the engine with the position and posture information of the real camera in the three-dimensional space, as well as the camera intrinsic and extrinsic parameter matrices of the target camera, and finally rely on real-time rendering and real-time matting and synthesis technology to achieve the synchronization of the movement and composition of the virtual camera and the real camera, so that the real-shot picture and the virtual elements can be synthesized in real time. The embodiment of the present application can make the camera freely move in a large space, and always obtain the camera's own coordinate system in the world coordinate system, which is convenient for the camera to be associated with the virtual scene of broadcasting and television production. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0051] Figure 1 A schematic diagram of an application scenario of a space calibration method provided by an embodiment of the present application;

[0052] Figure 2 The process of the space calibration method provided in one embodiment of the present application Figure 1 ;

[0053] Figure 3 A schematic diagram of a calibration plate in a space calibration method provided in one embodiment of the present application;

[0054] Figure 4 The process of the space calibration method provided in one embodiment of the present application Figure 2 ;

[0055] Figure 5 The process of the space calibration method provided in one embodiment of the present application Figure 3 ;

[0056] Figure 6 The process of the space calibration method provided in one embodiment of the present application Figure 4 ;

[0057] Figure 7 The process of the space calibration method provided in one embodiment of the present application Figure 5 ;

[0058] Figure 8 The process of the space calibration method provided in one embodiment of the present application Figure 6 ;

[0059] Fig. 9 The process of the space calibration method provided in one embodiment of the present application Figure 7 ;

[0060] Fig.10 The process of the space calibration method provided in one embodiment of the present application Figure 8 ;

[0061] Fig.11 The process of the space calibration method provided in one embodiment of the present application Figure 9 ;

[0062] Fig.12 A schematic diagram of the structure of a space calibration device provided in one embodiment of the present application Figure 1 ;

[0063] Fig.13 A schematic diagram of the structure of a space calibration device provided in one embodiment of the present application Figure 2 ;

[0064] Fig.14 A schematic diagram of the computer device structure provided for one embodiment of the present application. DETAILED DESCRIPTION

[0065] In the process of implementing the present application, the inventors found that the current process of spatial calibration of the camera has poor accuracy. In view of the above problem, a spatial calibration method is provided in an embodiment of the present application.

[0066] The solutions in the embodiments of the present application can be implemented using various computer languages, for example, the object-oriented programming language Java and the interpreted scripting language JavaScript.

[0067] In order to make the technical solutions and advantages in the embodiments of the present application more clearly understood, the exemplary embodiments of the present application are further described in detail below in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than an exhaustive list of all the embodiments. It should be noted that the embodiments in the present application and the features in the embodiments can be combined with each other without conflict.

[0068] In the prior art, the active calibration method of the camera can be achieved by fixing the active positioning device to the camera, relying on the positioning device to obtain its own position, and the camera is fixedly connected to the positioning device to obtain the camera pose. When calculating the camera pose, active calibration generally requires installing fixed markers in the scene to determine the camera position, but this calculation method relies on fixed markers and fixed locations. If the number of fixed markers deployed in the scene is small or the markers are scattered, the spatial distance span between the initial position and the current position will be large when calculating the camera pose, resulting in poor positioning accuracy.

[0069] In view of this, in order to solve the current technical problem of low precision of spatial calibration, the embodiment of the present application provides a spatial calibration method. The spatial calibration method provided by the present application deploys a camera tracker on the camera surface, captures the pose information of the camera tracker and the pose information of the calibration plate tracker, connects the local coordinate system and the world coordinate system in the target camera in series through the calibration plate, and finally obtains the pose of the local coordinate system of the camera in the world coordinate system.

[0070] The spatial calibration method provided in the present application realizes fast and accurate calibration of the camera by combining the camera calibration in a passive positioning manner with a passive marker point capture system.

[0071] The following is a brief description of the application environment of the instruction processing method provided in the embodiment of the present application:

[0072] A spatial calibration method provided in an embodiment of the present application is applied to a spatial calibration system 10, which includes a hardware system 101, a software system 102, and an auxiliary system 103, wherein the software system 102 is respectively connected to the hardware system 101 and the auxiliary system 103. The hardware system 101 controls the camera to collect the position information of the feature points in the calibration plate and the image of the calibration plate according to the control instructions of the software system 102, and transmits the collected data to the software system 101.

[0073] See also Figure 1 The hardware system mentioned in this application at least includes a camera, a camera tracker, at least one calibration board and a control system. The camera tracker is deployed on the surface of the camera, and the control system is connected to the camera, the camera tracker and the calibration board respectively. At least reflective feature points are deployed in the calibration board. The control system controls the camera to collect the feature points in the calibration board. The control system collects the reflective points of the target feature points generated when the camera shoots the target feature points in the calibration board, and the reflective points are combined into a rigid body marked as a calibration board tracker.

[0074] The software system in the spatial calibration system provided in the present application is used to control the hardware system to collect the calibration plate image and the position information of the feature points in the calibration plate, and control the auxiliary system to collect the posture data of the feature points in the calibration plate. According to the position information, posture data of the calibration point and the image data of the calibration plate, the position information of the target object in different coordinate systems is converted and processed to realize the spatial calibration of the target object, and the conversion process between the coordinate systems is optimized to improve the accuracy of the spatial calibration.

[0075] The software system in the spatial calibration system provided in the present application includes at least an acquisition controller, an image processor, a camera parameter calculator, a camera parameter optimizer, a camera local pose calculator, a camera local pose optimizer, etc.

[0076] Among them, the acquisition controller is used to control the camera to acquire the calibration plate image that moves freely in the acquisition space, and to control the capture system to obtain the camera tracker pose and the calibration plate tracker pose in real time; the image processor is used to preprocess the calibration plate image acquired by the camera and extract the position coordinates of the checkerboard feature points; the camera parameter calculator is used to calculate the camera intrinsic parameters and multiple relative calibration plate extrinsic parameter matrices of the camera; the camera parameter optimizer is used to optimize the camera intrinsic parameters and extrinsic parameter matrices of the camera to minimize the reprojection error; the camera local pose calculator is used to calculate the pose of the camera's own coordinate system relative to the camera tracker coordinate system; the camera local pose optimizer is used to optimize the camera local pose to obtain the camera pose with the smallest reprojection error.

[0077] The auxiliary capture system in the spatial calibration system provided in the present application is used to capture the pose of the camera tracker and the pose of the calibration plate tracker in the hardware system, and send the pose of the camera tracker and the pose of the calibration plate tracker to the software system. The auxiliary capture system includes an auxiliary hardware system and an auxiliary software system. The auxiliary hardware system includes an infrared camera and a server. The auxiliary software system includes passive point capture software; the auxiliary software system controls the auxiliary hardware system to collect reflective points of the infrared camera in the calibration plate. The infrared camera in the auxiliary hardware system can include multiple near-infrared cameras, and the multiple near-infrared cameras are evenly distributed around the large space where the camera moves, ensuring that the camera movement is in its capture area. When collecting the calibration plate, the near-infrared multi-camera can obtain the coordinates of multiple passive reflective points in real time, such as at a frequency of 120Hz; and track the rigid body pose composed of multiple reflective points.

[0078] See also Figure 2 The following embodiments use the above control system as the execution subject, and apply the spatial calibration method provided by the embodiment of the present application to the above control system. Here, the spatial calibration of the target camera is used as an example for specific description. The spatial calibration method provided by the embodiment of the present application includes the following steps 201 to 204:

[0079] Step 201: Obtain the initial pose of the object to be calibrated in the camera coordinate system of the target camera.

[0080] The camera coordinate system refers to a coordinate system whose origin is the optical center of the lens of the target camera. The target camera coordinate system can be used to determine the position information of the object from the perspective of the camera.

[0081] The initial posture includes at least position information and posture information, so that the displacement and torsion of the object can be described in a three-dimensional space system.

[0082] The object to be calibrated can be a tracker deployed on the surface of the camera. By obtaining the initial pose of the camera tracker, the pose of the camera's local coordinate system in the world coordinate system can be calculated, thereby completing the spatial calibration of the camera.

[0083] Step 202: Obtain the target camera tracker pose of the target feature point in the current calibration plate in the camera coordinate system, and the calibration plate tracker pose of the reflective point of the target feature point in the calibration plate coordinate system.

[0084] The target camera tracker mentioned in the embodiment of the present application refers to a tracker deployed on the surface of the target camera, which can be used to locate the target camera. The target camera tracker pose mentioned in the embodiment of the present application refers to the pose generated by the camera tracker when shooting the target feature points in the calibration plate. The reflective points of the target feature points mentioned in the embodiment of the present application refer to the reflective points generated by the camera when shooting the feature points of the calibration plate. In the embodiment of the present application, it is referred to that the rigid body pose composed of the above-mentioned reflective points can be marked as a calibration plate tracker, and the calibration plate tracker is used to facilitate tracking of the pose information of the reflective points of the calibration plate. The embodiment of the present application determines the pose information of the rigid body pose in the calibration plate coordinate system based on the rigid body pose composed of the reflective points, and generates the calibration plate tracker pose.

[0085] like Figure 3 As shown, the calibration plate mentioned in the embodiment of the present application includes multiple feature points and reflective points corresponding to the feature points. The solid black circles in the figure are feature points, and the hollow white circles in the figure are reflective points corresponding to the feature points.

[0086] The embodiment of the present application can obtain the calibration plate tracker pose and the target camera tracker pose at the same time, ensuring the time domain synchronization of the calibration plate tracker pose and the target camera tracker pose obtained by the system, thereby improving the accuracy of spatial calculation.

[0087] The embodiment of the present application can capture passive feature points that can reflect infrared light in real time by controlling the infrared camera in the auxiliary tracking system, and obtain the position and posture of the target camera tracker by triangulating the positions of the feature points.

[0088] In the method mentioned in the embodiment of the present application, the posture information of multiple target positioning points can be captured by acquiring the posture of the calibration plate tracker and the posture of the target camera tracker. The more posture information captured, the more reference data can be provided for calculating the relative posture of the initial position in the calibration plate coordinate system, ultimately improving the accuracy of the calculation space calibration.

[0089] Step 203: According to the calibration plate tracker pose and the target camera tracker pose corresponding to the target feature point, the camera coordinate system and the calibration plate coordinate system are converted to determine the relative pose of the initial pose in the calibration plate coordinate system.

[0090] The embodiment of the present application can clarify the transformation relationship of the feature point from the camera coordinate system to the calibration plate coordinate system through the pose information of the same feature point in different coordinate systems, that is, how to obtain the relative pose information in the calibration plate coordinate system by translating and twisting the initial position information.

[0091] Step 204: Determine the target pose of the initial pose of the object to be calibrated in the world coordinate system according to the position information of the target feature point in the world coordinate system.

[0092] The local coordinate system of the camera and the world coordinate system of the capture system are connected in series through the calibration plate to obtain the pose of the local coordinate system of the camera in the world coordinate system. The spatial calibration method provided in the embodiment of the present application deploys a camera tracker in the target camera, obtains the pose information of the camera tracker and the calibration plate tracker, and connects the local coordinate system of the camera and the world coordinate system of the capture system in series through the calibration plate to obtain the pose of the local coordinate system of the camera in the world coordinate system. The spatial calibration method provided in the embodiment of the present application realizes multi-dimensional positioning of the target positioning point through the camera tracker and the calibration plate tracker, and improves the accuracy of calculating the camera intrinsic parameter and extrinsic parameter matrix of the target camera through multi-dimensional positioning. Through the camera intrinsic parameter and extrinsic parameter matrix, the initial pose of the target object in the local coordinate system of the camera can be calculated and converted to the pose in the world coordinate system, and finally the accuracy of the spatial calibration is improved. The spatial calibration method provided in the embodiment of the present application has a simple calibration process, convenient operation, and high positioning accuracy.

[0093] The embodiment of the present application can obtain the position and posture information of the target camera in the current space by calibrating the space of the target camera, and then process the position and posture information through the virtual rendering engine, so as to provide the virtual camera in the engine with the position and posture information of the real camera in the three-dimensional space, as well as the camera intrinsic and extrinsic parameter matrices of the target camera, and finally rely on real-time rendering and real-time matting and synthesis technology to achieve the synchronization of the movement and composition of the virtual camera and the real camera, so that the real-shot picture and the virtual elements can be synthesized in real time. The embodiment of the present application can make the camera freely move in a large space, and always obtain the camera's own coordinate system in the world coordinate system, which is convenient for the camera to be associated with the virtual scene of broadcasting and television production.

[0094] See also Figure 4 In an optional embodiment of the present application, the above step 202 obtains the target camera tracker pose of the target feature point in the camera coordinate system, including the following steps 401-403:

[0095] Step 401: Obtain location information of target feature points collected by a target camera tracker.

[0096] The target feature points mentioned in the embodiment of the present application may be multiple feature points in the current calibration plate. The embodiment of the present application may deploy multiple calibration plates in the current space, i.e., in the large environment, and by capturing the position information of the feature points in the calibration plate, it is convenient to calculate the relative position and posture of the target camera relative to the calibration plate.

[0097] Step 402: Generate a target camera tracker pose according to the pose of the position information in the camera coordinate system.

[0098] The embodiment of the present application can establish a conversion relationship between the camera coordinate system and the calibration plate coordinate system by capturing the position and posture of the target camera tracker, so that the relative position and posture in the calibration plate coordinate system can be clarified according to the initial position and posture in the camera coordinate system, and then the target position and posture of the target object in the world coordinate system can be determined through the calibration plate, and finally the spatial calibration is completed; by obtaining the position and posture of the target camera tracker, multi-dimensional positioning can be achieved, thereby improving the accuracy of spatial calibration.

[0099] See also Figure 5 In an optional embodiment of the present application, the above step 202 obtains the calibration plate tracker pose of the reflective point of the target feature point in the calibration plate coordinate system, including the following steps 501-502:

[0100] Step 501: Obtain position information of a reflective point corresponding to at least one feature point in the current calibration plate.

[0101] The above-mentioned reflection points refer to the reflection points generated by the target feature points when the target camera captures the target feature points in the current calibration plate.

[0102] Step 502: Generate the calibration plate tracker pose according to the position information of the reflective point in the calibration plate coordinate system.

[0103] Determine the specific parameter values ​​of the reflective point position information in the calibration plate coordinate system and generate the calibration plate tracker pose.

[0104] The embodiment of the present application can establish a conversion relationship between the camera coordinate system and the calibration plate coordinate system by capturing the position and posture of the calibration plate tracker, so that the relative position and posture in the calibration plate coordinate system can be clarified according to the initial position and posture in the camera coordinate system, and then the target position and posture of the target object in the world coordinate system can be determined through the calibration plate, thereby finally completing the spatial calibration; by obtaining the position and posture of the calibration plate tracker, multi-dimensional positioning can be achieved, thereby improving the accuracy of spatial calibration; and by connecting the local coordinate system of the camera and the world coordinate system of the capture system in series through the calibration plate, it is convenient to calculate the position and posture of the same object in different coordinate systems, thereby improving the efficiency of spatial calibration.

[0105] See also Figure 6 In an optional embodiment of the present application, determining the relative posture of the initial posture in the calibration plate coordinate system in the above step 203 includes the following steps 601-602:

[0106] Step 601: Calculate the coordinate transformation parameters of the target camera tracker pose in the calibration plate coordinate system according to the calibration plate tracker pose and the target camera tracker pose corresponding to the target feature point.

[0107] The coordinate transformation parameters include at least rotation, translation and scale parameters.

[0108] The target feature points are converted from the target camera coordinate system to the calibration board coordinate system by calculating the coordinate transformation, that is, the three-dimensional point is projected onto the two-dimensional imaging plane to become an image point. The displacement vector and rotation matrix of the transformation process are obtained, and the coordinate transformation parameters of the target camera tracker posture in the calibration board coordinate system are calculated.

[0109] Step 602: Determine the relative position of the initial position in the calibration plate coordinate system according to the coordinate conversion parameters.

[0110] By obtaining the coordinate transfer parameters, it is possible to calculate how the initial posture is rotated and translated, and finally obtain the relative posture in the calibration plate coordinate system.

[0111] The embodiment of the present application establishes a conversion relationship between different coordinate systems through the pose of the same feature point in the calibration plate and the pose in the camera coordinate system, thereby improving the efficiency of calculating the initial pose of the target object in the local coordinate system of the camera and converting it to the pose in the world coordinate system.

[0112] See also Figure 7 In an optional embodiment of the present application, the present application embodiment further discloses optimizing the calculation accuracy of the target posture, including the following steps 701 to 705:

[0113] Step 701: Obtain the initial extrinsic parameter matrix and initial camera intrinsic parameters of the target camera.

[0114] The camera intrinsic parameters are used to indicate the physical parameters of the target camera imaging. The camera intrinsic parameters include at least: principal point, focal length, radial lens distortion, off-axis lens distortion and other system error parameters.

[0115] Camera extrinsics are used to indicate the conversion relationship between coordinate systems. Camera extrinsics include at least: rotation matrix and relative displacement. The rotation matrix is ​​the rotation angle of the camera in the world coordinate system, that is, the camera can be parallel to the world coordinate system after the rotation matrix transformation; the relative displacement is the displacement of the camera in the world coordinate system, that is, the camera can obtain the world coordinate system after the rotation matrix and then the relative translation.

[0116] The embodiment of the present application can calculate the initial extrinsic parameter matrix and initial camera intrinsic parameters of the target camera by obtaining the coordinates of the feature points in the calibration plate in the calibration plate coordinate system and the real physical size coordinates of the calibration plate.

[0117] For example, the Zhang Zhengyou plane calibration algorithm can be used to solve the initial external parameter matrix and initial camera internal parameters of the target camera. The calculation steps include:

[0118] First, establish the homography matrix H equation between the calibration plate plane and the camera imaging plane; secondly, solve the homography matrix H. The H matrix is ​​independent of the scale and has 8 degrees of freedom. Therefore, at least 4 points are required on the calibration plate to establish the equation for solution. Generally, the number of feature points on the calibration plate is much greater than 4 points, so redundant equations are established for solution; then, according to the orthogonality constraints of each component of the rotation matrix, K is obtained. -T K -1 , where K represents the camera internal parameter; finally, the square root method is used to decompose the matrix and decompose K -T K -1 , the internal parameter matrix is ​​obtained, and finally the rotation matrix and translation vector of each calibration plate image are obtained.

[0119] Step 702: Calculate the reprojection error of the target feature points in the current calibration plate according to the initial extrinsic parameter matrix and the initial camera intrinsic parameter.

[0120] The reprojection error refers to the difference between the projection value of the real three-dimensional space point on the calibration plate image plane and the reprojection value.

[0121] The reprojection error of the target feature point can be obtained by calculating the residual value of the coordinate point of the calibration plate in the camera coordinate system reprojected to the image plane and the image coordinate in the calibration plate coordinate system.

[0122] Step 703: If the reprojection error is greater than or equal to a preset threshold, the posture of the target camera is adjusted, and the extrinsic parameter matrix and the camera intrinsic parameters are recalculated.

[0123] The posture of the target camera is adjusted to make the projection points of the calibration plate in the current calibration plate coincide as much as possible.

[0124] After adjusting the attitude of the target camera, the position and attitude information of the calibration plate are re-acquired, and the target extrinsic parameter matrix and the target camera intrinsic parameter are calculated.

[0125] The embodiment of the present application can optimize the posture of the target camera by using a bundle adjustment nonlinear optimization algorithm to obtain a camera posture with the minimum reprojection error. For example, it can be optimized by using an LM (Levenberg-Marquardt) algorithm.

[0126] Step 704: Calculate the reprojection error of the target feature points in the current calibration plate according to the extrinsic parameter matrix and camera intrinsic parameters of the current target camera, until the reprojection error is less than a preset threshold, then determine the current extrinsic parameter matrix as the target extrinsic parameter matrix, and determine the current camera intrinsic parameters as the target camera intrinsic parameters.

[0127] The embodiment of the present application takes the reprojection error less than a preset threshold as the optimization goal, that is, the residual value of the reprojection of the 3D coordinate point of the calibration plate to the image plane and the 2D image coordinate is minimized as the optimization goal, thereby reducing the error of the feature point when converting the target pose from the calibration plate coordinate system to the world coordinate system.

[0128] Step 705: Obtain the target pose according to the target extrinsic parameter matrix and the target camera intrinsic parameter.

[0129] The method provided in the embodiment of the present application uses the initial pose as the initial value and as the optimization parameter, the 3D feature point coordinates in the coordinate system of the checkerboard calibration plate itself as the true value, and the 3D feature point coordinate distance error as the objective function, and obtains the final local pose of the camera through iterative optimization.

[0130] The optimization process provided in the embodiment of the present application can optimize the accuracy of the camera's intrinsic and extrinsic parameter matrices by adjusting the camera's posture, and calculate the initial pose of the target object in the camera's local coordinate system through the optimized camera's intrinsic and extrinsic parameter matrices, and convert it to the pose in the world coordinate system, thereby further improving the accuracy of spatial calibration.

[0131] See also Figure 8 In an optional embodiment of the present application, the above step 701 obtains the initial external parameter matrix and initial camera internal parameters of the target camera, including the following steps 801-804:

[0132] Step 801: Obtain a calibration plate image of the current calibration plate.

[0133] Capture the calibration plate image of the current calibration plate within the camera's acquisition range.

[0134] Step 802: Obtain the position information of the target feature points in the calibration plate image.

[0135] The position information of the target feature point refers to the position information of the target feature point in the calibration plate coordinate system.

[0136] Step 803: Obtain the size parameters of the current calibration plate.

[0137] This size parameter refers to the actual physical size of the current calibration plate.

[0138] The size parameters of the current calibration plate can be obtained through actual measurement, or by deploying a calibration plate of preset size in advance and obtaining it by reading the preset size.

[0139] Step 804: Calculate the camera intrinsic parameter and extrinsic parameter matrix of the initial target camera according to the position information of the current calibration plate and the size parameters of the current calibration plate.

[0140] Among them, the camera intrinsic parameters are used to indicate the imaging parameters of the camera; the extrinsic parameter matrix is ​​used to indicate how to transform the position of the target object in the world coordinate system and the calibration plate coordinate system.

[0141] The specific calculation process can be as recorded in the above step 701, and will not be repeated here.

[0142] The method provided in the embodiment of the present application can calculate the initial pose of the target object in the local coordinate system of the camera through the camera intrinsic parameter and extrinsic parameter matrix, and convert it to the pose in the world coordinate system, thereby further improving the accuracy of spatial calibration.

[0143] See also Fig. 9 In an optional embodiment of the present application, the above step 802 obtains the position information of the target feature point in the calibration plate image, including the following steps 901-902:

[0144] Step 901: determine the target area in the calibration plate image.

[0145] The calibration plate image is generated by collecting the calibration plate moving in the space.

[0146] The calibration plate image can be divided into multiple regions. Among the multiple regions of the calibration plate image, the target region refers to a region in the calibration plate image that is significantly different from adjacent regions, such as a region whose grayscale value is greater than that of the adjacent regions.

[0147] When calculating the target area, the target area in the calibration plate, such as the elliptical spot area, can be extracted by using a spot detection algorithm.

[0148] Step 902: Calculate the position information of the target feature points in the target area.

[0149] For example, the coordinates of the center of mass of a spot can be calculated by the image moment; and the position information of the target feature point can be obtained by the coordinates of the spot mass point.

[0150] The image moment can be used to indicate the global features of the calibration plate image, and can also indicate the image information of the calibration plate image, where the image information at least includes information such as image size, position, direction, and shape.

[0151] Among them, the centroid coordinates refer to the position of a point in a figure relative to each vertex.

[0152] The embodiment provided in the present application can quickly distinguish areas different from other areas of the calibration plate image by determining the target area in the calibration plate image, and calculate the position information of the target feature points in the target area, so as to more accurately identify the target feature points.

[0153] See also Fig.10In an optional embodiment of the present application, the above step 901 determines the target area in the calibration plate image, including the following steps 1001 to 1003:

[0154] Step 1001: Obtain characteristic parameters of each area in the calibration plate image by performing contrast enhancement processing on the calibration plate image.

[0155] The contrast enhancement processing can be used to improve the contrast between light and dark in the picture or to improve the overall balance of the picture.

[0156] For example, the contrast of the calibration plate image can be enhanced by image grayscale transformation or histogram mapping processing.

[0157] The calibration plate image is divided into N regions according to preset rules, and the characteristic parameters of each of the N regions are calculated in turn.

[0158] The characteristic parameter includes at least one of a color value and a grayscale value.

[0159] Step 1002: traverse each region in the calibration plate image, and calculate the difference between the characteristic parameters of each region and the characteristic parameters of the adjacent regions.

[0160] The difference in calculating the feature parameters can be calculated by calculating the grayscale value or pixel value of each area.

[0161] The route for traversing the calibration plate image may be a zigzag traversal or a traversal according to a preset route.

[0162] Step 1003: If the difference value of the current area is greater than a preset value, the current area is determined as a target area.

[0163] The preset value can be set by the user or according to historical comparison results.

[0164] The embodiment provided in the present application can more accurately determine the target area in the calibration plate image and highlight the contrast of the target feature points in the calibration plate image by enhancing the contrast of the calibration plate image, thereby improving the recognition in the calibration plate and more efficiently calculating the coordinates of the feature points.

[0165] See also Fig.11 In an optional embodiment of the present application, determining the target posture of the relative posture in the world coordinate system includes the following steps 1101 to 1103:

[0166] Step 1101: Obtain the initial position and posture of the target feature points in the calibration plate in the world coordinate system.

[0167] The infrared camera is used to collect the initial pose of the target feature point in the world coordinate system, that is, the initial pose in the current space.

[0168] Step 1102: Calculate the target coordinates of the target feature point in the calibration plate coordinate system according to the camera intrinsic parameter and extrinsic parameter matrix.

[0169] By calculating the position of the target feature point when it is projected onto the current calibration plate, the target coordinates of the target feature point in the calibration plate coordinate system are obtained.

[0170] When calculating the pose of the target camera's own coordinate system in the capture system coordinate system, the calibration plate can be used as a bridge to associate the target camera with the capture system pose, and the camera coordinates with the world coordinates. By actually measuring the position of the target feature point projection, the relative pose relationship between the calibration plate tracker and the calibration plate's own coordinate system can be obtained, thereby establishing a complete relationship, and obtaining the relative pose of the target camera's own coordinate system relative to the camera tracker coordinate system, that is, the local pose of the camera, and the pose of the target camera's own coordinate system in the world coordinate system in the current space.

[0171] Step 1103: Determine the target pose of the relative pose in the world coordinate system by coordinate conversion between the initial pose and the target coordinates.

[0172] Coordinate transformation refers to the process of transforming from one coordinate system to another. Through the transformation process, it is determined how to transform the position of the calibration plate coordinate system after rotation and translation to the position in the world coordinate system, thereby determining the target position of the relative position in the world coordinate system.

[0173] The embodiment provided in the present application can achieve multi-dimensional positioning by acquiring the position and posture of the calibration plate tracker, thereby improving the accuracy of spatial calibration; and by connecting the camera local coordinate system and the capture system world coordinate system in series through the calibration plate, it is convenient to calculate the position and posture of the same object in different coordinate systems, thereby improving the efficiency of spatial calibration.

[0174] In the embodiments provided in the present application, the accuracy of the local pose of the camera can also be optimized, such as taking the local pose of the camera as the initial value and as the optimization parameter, the 3D feature point coordinates in the checkerboard's own coordinate system as the true value, and the 3D feature point coordinate distance error as the objective function, and using the calibration plate coordinate system to the camera coordinate system to the camera tracker coordinate system to the capture system coordinate system to the calibration plate tracker coordinate system to the calibration plate coordinate system to calculate the transformation matrix, and transform the 3D feature point coordinates to the coordinate system to obtain the observation value; through iterative optimization, the final local pose of the camera is obtained.

[0175] It should be understood that, although the various steps in the flow chart are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear description in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a portion of the steps in the figure may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these sub-steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a portion of the sub-steps or stages of other steps.

[0176] See also Fig.12 , an embodiment of the present application provides a space calibration device 120, including:

[0177] The positioning module 1201 is used to obtain the initial position and posture of the object to be calibrated in the camera coordinate system of the target camera;

[0178] The acquisition module 1202 is used to obtain the target camera tracker pose of the target feature point in the current calibration plate in the camera coordinate system, and the calibration plate tracker pose of the reflective point of the target feature point in the calibration plate coordinate system;

[0179] The parameter calculation module 1203 is used to convert the camera coordinate system and the calibration plate coordinate system according to the calibration plate tracker pose and the target camera tracker pose corresponding to the target feature point, and determine the relative pose of the initial pose in the calibration plate coordinate system;

[0180] The calibration module 1204 is used to determine the target posture of the initial posture of the object to be calibrated in the world coordinate system according to the position information of the target feature point in the world coordinate system.

[0181] See also Fig.13 In an optional embodiment of the present application, the space calibration device 120 further includes an optimization module 1205, and the optimization module 1205 is used to:

[0182] Get the initial external parameter matrix and initial camera internal parameters of the target camera;

[0183] Calculate the reprojection error of the target feature point in the current calibration plate according to the initial external parameter matrix and the initial camera internal parameter;

[0184] If the reprojection error is greater than or equal to a preset threshold, the attitude of the target camera is adjusted, and the extrinsic parameter matrix and camera intrinsic parameters are recalculated;

[0185] The reprojection error of the target feature points in the current calibration plate is calculated according to the external parameter matrix and the camera internal parameter of the current target camera, until the reprojection error is less than a preset threshold, then the current target camera external parameter matrix is ​​determined as the target external matrix, and the current internal parameter is determined as the target internal parameter;

[0186] The target pose is obtained according to the target extrinsic parameter matrix and the target camera intrinsic parameter.

[0187] In an optional embodiment of the present application, the optimization module 1205 in the space calibration device 120 is further used for:

[0188] Get the calibration plate image of the current calibration plate;

[0189] Obtain the position information of the target feature points in the calibration plate image;

[0190] Get the size parameters of the current calibration plate;

[0191] According to the position information and size parameters of the current calibration plate, the camera intrinsic parameter and extrinsic parameter matrix of the target camera are calculated.

[0192] In an optional embodiment of the present application, the optimization module 1205 in the space calibration device 120 is further used to:

[0193] Determine the target area in the current calibration plate image;

[0194] Calculate the position information of the target feature points in the target area;

[0195] The target area is an area in the plurality of image areas of the target plate image that is different from adjacent areas.

[0196] In an optional embodiment of the present application, the optimization module 1205 in the space calibration device 120 is further used to:

[0197] By performing contrast enhancement processing on the calibration plate image, a characteristic parameter of each area in the calibration plate image is obtained, where the characteristic parameter includes at least one of a color value and a grayscale value;

[0198] Traverse each area in the calibration plate image and calculate the difference between the characteristic parameters of each area and the characteristic parameters of the adjacent areas;

[0199] If the difference of the current area is greater than the preset value, the current area is determined as the target area.

[0200] In an optional embodiment of the present application, the acquisition module 1202 in the space calibration device 120 is further used to:

[0201] Obtaining position information of a reflective point corresponding to at least one feature point in the current calibration plate;

[0202] The calibration plate tracker pose is generated based on the position information of the reflective point in the calibration plate coordinate system.

[0203] In an optional embodiment of the present application, the acquisition module 1202 in the space calibration device 120 is further used to:

[0204] According to the position information of the target feature points collected by the target camera tracker;

[0205] Generate the target camera tracker pose based on the pose of the position information in the camera coordinate system.

[0206] In an optional embodiment of the present application, the parameter calculation module 1203 in the space calibration device 120 is further used to:

[0207] According to the calibration plate tracker pose and the target camera tracker pose corresponding to the target feature points, the coordinate transformation parameters of the target camera tracker pose in the calibration plate coordinate system are calculated;

[0208] According to the coordinate transformation parameters, the relative pose of the initial pose in the calibration plate coordinate system is determined.

[0209] In an optional embodiment of the present application, the calibration module 1204 in the space calibration device 120 is further used to:

[0210] Get the initial pose of the target feature points in the calibration plate in the world coordinate system;

[0211] According to the camera internal and external parameter matrices, the target coordinates of the target feature point in the calibration plate coordinate system are calculated;

[0212] According to the coordinate transformation between the initial pose and the target coordinates, the target pose of the relative pose in the world coordinate system is determined.

[0213] Through the spatial positioning device provided by the present application, the multi-dimensional positioning of the target positioning point can be achieved through the camera tracker and the calibration plate tracker. The accuracy of calculating the camera intrinsic parameter and extrinsic parameter matrix of the target camera is improved through multi-dimensional positioning. Through the camera intrinsic parameter and extrinsic parameter matrix, the initial position and posture of the target object in the local coordinate system of the camera can be calculated and converted to the position and posture in the world coordinate system, and finally the accuracy of spatial calibration is improved. The spatial calibration method provided by the present application has a simple calibration process, convenient operation, and high positioning accuracy.

[0214] For the specific definition of the above-mentioned space calibration device, please refer to the definition of the space calibration method above, which will not be repeated here. Each module in the above-mentioned space calibration device can be implemented in whole or in part by software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0215] In one embodiment, a computer device is provided, the internal structure diagram of which can be as follows: Fig.14 As shown. The computer device includes a processor, a memory, a network interface and a database connected via a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store data. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a spatial calibration method as described above is implemented. It includes: a memory and a processor, the memory stores a computer program, and when the processor executes the computer program, any step in the spatial calibration method as described above is implemented.

[0216] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, any step in the above spatial calibration method can be implemented.

[0217] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0218] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0219] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable spatial calibration device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0220] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0221] Although the preferred embodiments of the present application have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the present application.

[0222] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. A spatial calibration method, characterized in that: include: Obtain a first initial pose of the object to be calibrated in the camera coordinate system of the target camera; Obtain the target camera tracker pose of the target feature point in the current calibration plate in the camera coordinate system, and the calibration plate tracker pose of the reflective point of the target feature point in the calibration plate coordinate system; According to the calibration plate tracker pose and the target camera tracker pose corresponding to the target feature point, convert the camera coordinate system and the calibration plate coordinate system to determine the relative pose of the first initial pose in the calibration plate coordinate system; According to the position information of the target feature point in the world coordinate system, the target pose of the first initial pose of the object to be calibrated in the world coordinate system is determined, including: obtaining the second initial pose of the target feature point in the current calibration plate in the world coordinate system; calculating the target coordinates of the target feature point in the calibration plate coordinate system according to the camera intrinsic parameter and extrinsic parameter matrix; and determining the target pose of the relative pose in the world coordinate system by coordinate conversion between the second initial pose and the target coordinates.

2. The spatial calibration method according to claim 1, characterized in that: The step of determining a target pose of the first initial pose of the object to be calibrated in the world coordinate system further includes: Obtaining an initial extrinsic parameter matrix and initial camera intrinsic parameters of the target camera; Calculate the reprojection error of the target feature point in the current calibration plate according to the initial extrinsic parameter matrix and the initial camera intrinsic parameter; If the reprojection error is greater than or equal to a preset threshold, the posture of the target camera is adjusted, and the extrinsic parameter matrix and the camera intrinsic parameters are recalculated; Calculate the reprojection error of the target feature points in the current calibration plate according to the extrinsic parameter matrix and the camera intrinsic parameter of the current target camera, until the reprojection error is less than a preset threshold, then determine the current extrinsic parameter matrix as the target extrinsic parameter matrix, and determine the current camera intrinsic parameter as the target camera intrinsic parameter; The target pose is obtained according to the target extrinsic parameter matrix and the target camera intrinsic parameter.

3. The spatial calibration method according to claim 2, characterized in that: The obtaining of the initial external parameter matrix and initial camera internal parameters of the target camera includes: Acquire a calibration plate image of the current calibration plate; Obtaining position information of the target feature points in the calibration plate image; Obtaining the size parameters of the current calibration plate; The initial camera intrinsic parameters and the initial extrinsic parameter matrix of the target camera are calculated according to the position information and size parameters of the current calibration plate.

4. The spatial calibration method according to claim 3, characterized in that: The obtaining the position information of the target feature point in the calibration plate image includes: Determine the target area in the current calibration plate image; Calculate the position information of the target feature point in the target area; The target area is an area in the plurality of image areas of the target plate image that is different from adjacent areas.

5. The spatial calibration method according to claim 4, characterized in that: The step of determining the target area in the current calibration plate image includes: Acquire characteristic parameters of each area in the calibration plate image by performing contrast enhancement processing on the calibration plate image, wherein the characteristic parameters include at least one of a color value and a grayscale value; Traversing each area in the calibration plate image, and calculating the difference between the characteristic parameters of each area and the characteristic parameters of the adjacent area; If the difference value of the current area is greater than a preset value, the current area is determined as the target area.

6. The spatial calibration method according to claim 1, characterized in that: Obtaining the calibration plate tracker pose of the reflective point of the target feature point in the calibration plate coordinate system, including: Obtaining position information of a reflective point corresponding to at least one feature point in the current calibration plate; The calibration plate tracker posture is generated according to the position information of the reflective point in the calibration plate coordinate system.

7. The spatial calibration method according to claim 1, characterized in that: Determining the relative posture of the first initial posture in the calibration plate coordinate system includes: Calculate the coordinate conversion parameters of the target camera tracker pose in the calibration plate coordinate system according to the calibration plate tracker pose and the target camera tracker pose corresponding to the target feature point; According to the coordinate conversion parameters, a relative posture of the first initial posture in the calibration plate coordinate system is determined.

8. The spatial calibration method according to claim 1, characterized in that: Obtaining the target camera tracker pose, including: According to the position information of the target feature points collected by the target camera tracker; The target camera tracker pose is generated according to the pose of the position information in the camera coordinate system.

9. A spatial calibration device, characterized in that: include: A positioning module, used to obtain a first initial pose of the object to be calibrated in the camera coordinate system of the target camera; An acquisition module, used to obtain the target camera tracker pose of the target feature point in the current calibration plate in the camera coordinate system, and the calibration plate tracker pose of the reflective point of the target feature point in the calibration plate coordinate system; a parameter calculation module, configured to convert the camera coordinate system and the calibration plate coordinate system according to the calibration plate tracker pose and the target camera tracker pose corresponding to the target feature point, and determine the relative pose of the first initial pose in the calibration plate coordinate system; A calibration module is used to determine the target pose of the first initial pose of the object to be calibrated in the world coordinate system according to the position information of the target feature point in the world coordinate system, including: obtaining the second initial pose of the target feature point in the current calibration plate in the world coordinate system; calculating the target coordinates of the target feature point in the calibration plate coordinate system according to the camera intrinsic parameter and extrinsic parameter matrix; and determining the target pose of the relative pose in the world coordinate system by coordinate conversion between the second initial pose and the target coordinates.

10. A computer device comprising: The method comprises a memory and a processor, wherein the memory stores a computer program, and wherein the processor implements the steps of the method according to any one of claims 1 to 8 when executing the computer program.

11. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 8 are implemented.

Images