Spatial calibration method, device, medium and equipment for virtual production

Abstract

The present application discloses a spatial calibration method, apparatus, medium, and equipment for virtual production, which relates to the field of virtual reality. The method includes: obtaining first position information of a target marker in a pixel coordinate system and second position information of the target marker in a first physical space coordinate system corresponding to a display screen; determining a first spatial calibration result based on the first position information and the second position information; obtaining third position information of a tracking device in a corresponding second physical space coordinate system when a camera shoots a display screen; determining a second spatial calibration result based on the third position information; determining a target spatial calibration result based on the first spatial calibration result and the second spatial calibration result, wherein the target spatial calibration result is a conversion relationship between the first physical space coordinate system and the second physical space coordinate system. The present application can accurately calibrate the spatial relationship between a display screen and a tracking device in a virtual production scenario.

Description

Technical Field

[0001] The present application relates to the field of virtual reality technology, and in particular to a space calibration method, apparatus, medium, and equipment for virtual production. Background Art

[0002] With the development of technology, virtual production technology based on LED (Light-Emitting Diode) background walls is increasingly being applied. Using LED screens as a backdrop, combined with real-time engine rendering, virtual production creates an environment within which performers can perform. During the real-time production process, creators provide feedback and process digital content, fusing virtual computer graphics with the performances of real performers. The final special effects are then visualized on set, allowing creators to see a near-final film-like effect.

[0003] Before the formal shooting, the space where the LED display screen is located needs to be calibrated. The accuracy and precision of the calibration results directly determine the visual effect of the virtual production. Summary of the Invention

[0004] In order to improve the accuracy of spatial calibration, this application provides a spatial calibration method, device, medium and equipment for virtual production. The technical solution is as follows:

[0005] In a first aspect, the present application provides a spatial calibration method for virtual film production, the method comprising:

[0006] Obtaining first position information of at least one target mark in a pixel coordinate system and second position information of the at least one target mark in a first physical space coordinate system corresponding to a display screen, wherein the display screen displays a plurality of binary square reference marks; the plurality of binary square reference marks includes the at least one target mark;

[0007] Determining a first spatial calibration result based on the first position information and the second position information, where the first spatial calibration result represents a conversion relationship between the first physical space coordinate system and a camera coordinate system corresponding to the camera;

[0008] obtaining third position information of the tracking device in a second physical space coordinate system corresponding to the tracking device when the camera photographs the display screen; the tracking device is used to track the camera in virtual production; the camera is used to photograph a real scene with the display screen as a background in the virtual production;

[0009] determining a second space calibration result based on the third position information, where the second space calibration result represents a conversion relationship between the second physical space coordinate system and the camera coordinate system;

[0010] A target space calibration result is determined based on the first space calibration result and the second space calibration result, where the target space calibration result represents a conversion relationship between the first physical space coordinate system and the second physical space coordinate system.

[0011] Optionally, obtaining first position information of at least one target mark in a pixel coordinate system and second position information of the at least one target mark in a first physical space coordinate system corresponding to the display screen includes:

[0012] Acquire at least one calibrated two-dimensional image obtained by photographing the display screen with the camera;

[0013] determining the at least one target marker included in the at least one calibration two-dimensional image;

[0014] The first position information of the at least one target mark in the pixel coordinate system is determined according to the image area corresponding to the at least one target mark, where the first position information includes pixel coordinate data of a corner point corresponding to the at least one target mark.

[0015] Optionally, the acquiring of first position information of at least one target mark in a pixel coordinate system and second position information of the at least one target mark in a first physical space coordinate system corresponding to the display screen further includes:

[0016] Acquiring three-dimensional model information corresponding to the display screen in a virtual space coordinate system;

[0017] Determining unit position information corresponding to each of the plurality of display units of the display screen according to the three-dimensional model information; wherein the plurality of display units correspond one-to-one to the plurality of binary square reference marks;

[0018] Obtaining the second position information of the at least one target mark according to the unit position information corresponding to each of the display units; the second position information includes spatial coordinate data of a corner point corresponding to the at least one target mark;

[0019] The virtual space coordinate system corresponds to the first physical space coordinate system.

[0020] Optionally, determining the at least one target marker included in the at least one calibrated two-dimensional image includes:

[0021] performing marker detection on the at least one calibrated two-dimensional image to determine at least one candidate marker;

[0022] Perform point recognition and matching on the at least one candidate marker to determine the at least one target marker.

[0023] Optionally, determining a first spatial calibration result based on the first position information and the second position information includes:

[0024] Determining a coordinate correspondence between the target markers based on the pixel coordinate data of the corner points corresponding to the target markers in the first position information and the spatial coordinate data of the corner points corresponding to the target markers in the second position information;

[0025] Determining at least one coordinate transformation matrix according to the coordinate correspondence of each target marker;

[0026] Determining target parameter information of the camera according to the at least one coordinate transformation matrix; the target parameter information represents a transformation relationship between the camera coordinate system and the pixel coordinate system;

[0027] The first spatial calibration result is determined based on the first position information, the second position information, and the target parameter information.

[0028] Optionally, the method further includes:

[0029] Acquire a real-time two-dimensional image captured by the camera with the display screen as the background and first real-time position information of the tracking device in the second physical space coordinate system when the camera captures the image;

[0030] determining first real-time relative posture information between the display screen and the camera according to the first real-time position information and the target space calibration result;

[0031] projecting the three-dimensional virtual model corresponding to the display screen onto a two-dimensional simulation plane to obtain a projected two-dimensional image according to the first real-time relative posture information;

[0032] According to the projected two-dimensional image and the real-time two-dimensional image, a position comparison is performed on the corner points of the display screen to obtain a comparison result, and the comparison result is used to indicate whether to retain the target calibration result.

[0033] Optionally, the method further includes:

[0034] Acquire second real-time position information of the tracking device in the second physical space coordinate system when the camera is shooting;

[0035] determining second real-time relative posture information between the display screen and the camera according to the second real-time position information and the target space calibration result;

[0036] projecting the three-dimensional virtual scene model according to the second real-time relative posture information to obtain a two-dimensional virtual scene image;

[0037] The two-dimensional virtual scene image is displayed on the display screen, and a target image captured by the camera with the display screen as the background is acquired.

[0038] In a second aspect, the present application provides a spatial calibration device for virtual film production, the device comprising:

[0039] a first acquisition module, configured to acquire first position information of at least one target mark in a pixel coordinate system and second position information of the at least one target mark in a first physical space coordinate system corresponding to a display screen, wherein the display screen displays a plurality of binary square reference marks; the plurality of binary square reference marks includes the at least one target mark;

[0040] a first calibration module, configured to determine a first spatial calibration result based on the first position information and the second position information, wherein the first spatial calibration result represents a conversion relationship between the first physical space coordinate system and a camera coordinate system corresponding to the camera;

[0041] a second acquisition module, configured to acquire third position information of the tracking device in a second physical space coordinate system corresponding to the tracking device when the camera is photographing the display screen; the tracking device is configured to track the camera in virtual production; and the camera is configured to photograph a real scene with the display screen as a background in virtual production;

[0042] a second calibration module, configured to determine a second space calibration result based on the third position information, where the second space calibration result represents a conversion relationship between the second physical space coordinate system and the camera coordinate system;

[0043] The target calibration module is used to determine a target space calibration result based on the first space calibration result and the second space calibration result, where the target space calibration result represents a conversion relationship between the first physical space coordinate system and the second physical space coordinate system.

[0044] In a third aspect, the present application provides a computer-readable storage medium, which stores at least one instruction or at least one program, and the at least one instruction or at least one program is loaded and executed by a processor to implement the spatial calibration method applied to virtual production as described in the first aspect.

[0045] In a fourth aspect, the present application provides a computer device, comprising a processor and a memory, wherein the memory stores at least one instruction or at least one program, and the at least one instruction or at least one program is loaded and executed by the processor to implement the spatial calibration method applied to virtual production as described in the first aspect.

[0046] In a fifth aspect, the present application provides a computer program product, which includes computer instructions. When the computer instructions are executed by a processor, they implement the spatial calibration method for virtual production as described in the first aspect.

[0047] The spatial calibration method, device, medium, and equipment provided in this application for virtual film production have the following technical effects:

[0048] The solution provided in the present application is applied to the spatial calibration process of virtual production, where a plurality of binary square reference marks are displayed on a display screen, a camera shoots a real scene with the display screen as the background, and a tracking device tracks the posture of the camera; the solution provided in the present application first obtains first position information of at least one target mark in a pixel coordinate system and second position information of at least one target mark in a first physical space coordinate system corresponding to the display screen, wherein the plurality of binary square reference marks include at least one target mark; based on the first position information and the second position information of the at least one target mark, a first spatial calibration result can be determined, that is, the conversion relationship between the first physical space coordinate system and the camera coordinate system corresponding to the camera can be determined; then the solution provided in the present application obtains third position information of the tracking device in a second physical space coordinate system corresponding to the tracking device when the camera shoots the real screen, and a second spatial calibration result can be determined based on the third position information, that is, the conversion relationship between the second physical space coordinate system and the camera coordinate system can be determined; finally, the solution provided in the present application determines a target calibration result based on the first spatial calibration result and the second spatial calibration result, and the target spatial calibration result represents the conversion relationship between the first physical space coordinate system and the second physical space coordinate system.

[0049] The technical solution provided by this application utilizes some or all of the multiple binary square fiducial markers to calibrate the first physical space coordinate system corresponding to the display screen and the second physical space coordinate system corresponding to the tracking device in virtual production. The resulting target calibration results are accurate and stable. During the virtual production process, accurate and stable target calibration results ensure that the virtual scene and the real scene are accurately matched.

[0050] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become obvious from the description below, or will be learned through practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] In order to more clearly illustrate the technical solutions and advantages of the embodiments of the present application or the prior art, the following is a brief introduction to the drawings required for use in the embodiments or the description 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.

[0052] Figure 1 Schematic diagram of an implementation environment of a spatial calibration method for virtual film production provided in an embodiment of the present application;

[0053] Figure 2 This is a flow chart of a spatial calibration method for virtual film production provided in an embodiment of the present application;

[0054] Figure 3 This is a schematic diagram of a camera provided in an embodiment of the present application photographing a display screen;

[0055] Figure 4 This is a specific flow chart of a spatial calibration method for virtual film production provided by an embodiment of the present application;

[0056] Figure 5 This is a schematic diagram of an embodiment of the present application providing a method of using a graphical interface to set the three-dimensional model parameters and initial camera parameters corresponding to an LED curtain wall;

[0057] Figure 6 This is a schematic diagram of an embodiment of the present application providing a method of using a graphical interface to obtain images of an LED curtain wall captured by four cameras at different positions and angles;

[0058] Figure 7 This is a schematic diagram of an embodiment of the present application providing a method of calculating the relative postures of a camera, a tracking device, and an LED curtain wall using a graphical interface;

[0059] Figure 8 This is a schematic diagram of a real-time calibration result inspection provided by an embodiment of the present application;

[0060] Figure 9 This is a schematic diagram of a corner point matching effect between a projected two-dimensional image of a three-dimensional model and a real-time two-dimensional image captured by a camera, provided in an embodiment of the present application;

[0061] Figure 10 is a schematic diagram of a spatial calibration device for virtual film production provided in an embodiment of the present application;

[0062] Figure 11 This is a schematic diagram of the hardware structure of a device for implementing a spatial calibration method for virtual film production provided in an embodiment of the present application. DETAILED DESCRIPTION

[0063] In order to improve the accuracy of spatial calibration, the embodiments of the present application provide a spatial calibration method, device, medium and equipment for virtual production. The technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application. Examples of the embodiments are shown in the accompanying drawings, where the same or similar numbers throughout represent the same or similar elements or elements with the same or similar functions.

[0064] It should be noted that the terms "first", "second", etc. in the specification and claims of this application and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products, or devices.

[0065] In order to facilitate understanding of the technical solutions and the technical effects produced by the embodiments of the present application, the embodiments of the present application explain the relevant professional terms involved:

[0066] Virtual production based on LED background walls: Using LED displays as the background and combining it with real-time engine rendering, an environmental scene is created, allowing performers to perform in the environmental scene. Creators complete feedback and processing of digital content during the real-time production process, that is, integrating virtual computer images with the performances of real performers, and visually presenting the final special effects on the set, allowing creators to see effects close to the final film on the set.

[0067] ArUco: ArUco markers are binary square fiducial markers that can be used for camera pose estimation. Their main advantages are robust, fast, and simple detection. An ArUco marker has a black border around it and a two-dimensional matrix inside that identifies the marker. The black border speeds up marker detection in the image, while the internal two-dimensional matrix uniquely identifies the marker and allows for error detection and correction.

[0068] Zhang Zhengyou calibration method: It is a camera calibration method based on a two-dimensional plane target. By taking multiple pictures of the calibration plate and then making one-to-one correspondence between multiple actual points (world coordinates) and points on the picture (pixel coordinates), the correspondence between world coordinates and pixel coordinates can be calculated.

[0069] Hand-eye calibration: In virtual production, it can be used to solve the relative offset of the camera attached to the tracking device.

[0070] PNP: Perspective-n-Point, is a method for finding the two-dimensional point corresponding to a three-dimensional point.

[0071] Figure 1 Schematic diagram of an implementation environment of a space calibration method for virtual filming provided in an embodiment of the present application. Figure 1 As shown, the implementation environment may include at least a display screen 01, a camera 02, and a tracking device 03. The display screen 01 may be a non-curved LED curtain wall, including multiple display units, which displays multiple binary square fiducial markers during the spatial calibration phase and displays a two-dimensional virtual scene image projected from a three-dimensional virtual scene during the virtual production process. The camera 02 and the tracking device 03 may be physically connected and communicated to each other. The camera 02 captures the real scene with the display screen 01 as the background, and the tracking device 03 tracks the posture of the camera 02 in real time. The tracking device 03 also has the ability to locate the position in physical space centered on the base. Figure 1 This is an illustration of an implementation environment in which the embodiments of the present application are applied. In other implementation environments, the tracking device 03 may also move along a certain track, and the position of the camera 02 may not be fixed.

[0072] Figure 2 This is a flowchart of a spatial calibration method for virtual production provided by an embodiment of the present application. The present application provides method operation steps as described in the embodiment or flowchart, but may include more or fewer operation steps based on conventional or non-creative labor. The order of steps listed in the embodiment is only one way of executing the steps among many, and does not represent the only execution order. When the actual system or server product is executed, it can be executed sequentially or in parallel according to the method shown in the embodiment or the accompanying drawings (for example, in a parallel processor or multi-threaded processing environment). Please refer to Figure 2 A spatial calibration method for virtual film production provided in an embodiment of the present application may include the following steps:

[0073] S210: Acquire first position information of at least one target mark in a pixel coordinate system and second position information of at least one target mark in a first physical space coordinate system corresponding to a display screen.

[0074] In this embodiment of the present application, during spatial calibration, the display screen displays multiple binary square fiducial markers. These are ArUco markers. Each ArUco marker is surrounded by a black border and contains a two-dimensional matrix that can determine the marker's identity. The black border accelerates ArUco marker detection, and the two-dimensional matrix inside uniquely identifies the ArUco marker. At least one target marker is part or all of the multiple binary square fiducial markers.

[0075] In one embodiment of the present application, based on an image captured by a camera of a display screen, at least one target marker is identified and first position information of the at least one target marker in a pixel coordinate system corresponding to the image is determined. The first position information includes pixel coordinate data of corner points of each target marker. Specifically, step S210 may include the following steps:

[0076] S211: Acquire at least one calibrated two-dimensional image obtained by photographing a display screen with a camera.

[0077] Feasibly, if Figure 3 As shown, the camera is placed at different positions or at different angles to shoot the display screen to obtain multiple calibrated two-dimensional images. Each calibrated two-dimensional image does not need to capture the entire display screen. Each calibrated two-dimensional image can be a picture containing a partial display screen.

[0078] S212: Determine at least one target marker included in at least one calibrated two-dimensional image.

[0079] Alternatively, marker detection may be performed on at least one calibrated two-dimensional image to determine at least one candidate marker, and point recognition and matching may be performed on the at least one candidate marker to determine at least one target marker. The marker identifier corresponding to each target marker in the at least one target marker may also be determined.

[0080] Exemplarily, marker detection is performed on one of the calibrated two-dimensional images to determine at least one candidate area, each candidate area corresponds to a candidate marker, color extraction is performed on the candidate markers in each candidate area, and the identification code corresponding to the candidate marker is determined based on the extracted color information. If the identification code corresponding to the candidate marker is the identification code of a marker in a preset marker identification code dictionary, the candidate marker can be determined as a target marker; if the identification code corresponding to the candidate marker is not the identification code of any marker in the preset marker identification code dictionary, the candidate marker can be discarded.

[0081] Using target markers of the binary square fiducial marker type can provide enough position correspondences to improve the accuracy of calibration. At the same time, the binary coding matrix inside the target marker can improve the robustness of the algorithm (the algorithm's ability to respond to and handle unreasonable data input, also known as algorithm fault tolerance), allowing the application of error detection and correction technology, that is, more effective target markers can be obtained and the target markers can be positioned more accurately.

[0082] S213: Determine first position information of the at least one target mark in a pixel coordinate system according to the image area corresponding to the at least one target mark.

[0083] The first position information includes pixel coordinate data of a corner point corresponding to at least one target marker. Specifically, if the image region corresponding to each target marker is a quadrilateral, each target marker has four corresponding corner points. Based on the positions of the four corresponding corner points of each target marker in the image, the pixel coordinate data of the corner points of each target marker in the pixel coordinate system corresponding to the image is obtained.

[0084] In the above embodiment, a display screen displaying multiple binary square fiducial markers is photographed, and pixel coordinate data for the corner points of each target marker contained therein is determined based on the captured image. This allows for rapid and accurate acquisition of pixel information for a sufficient number of corner points. Furthermore, the display screen can be photographed with a camera positioned at different positions or angles, and the resulting calibration 2D images do not need to capture the entire display screen. This is particularly applicable to situations where the display screen is very large or curved.

[0085] In one embodiment of the present application, a three-dimensional model is established for the display screen. The three-dimensional model can be used to determine second position information of at least one target marker in a first physical space coordinate system corresponding to the display screen. The second position information includes spatial coordinate data of corner points of each target marker. Specifically, step S210 may further include the following steps:

[0086] S214: Acquire three-dimensional model information corresponding to the display screen in the virtual space coordinate system.

[0087] It is feasible to create a three-dimensional model of the display screen installed at the filming site in UE4 (Unreal Engine 4). The virtual space coordinate system corresponding to the space where the three-dimensional model is located corresponds to the first physical space coordinate system corresponding to the space where the display screen is located. For example, the origin of the virtual space coordinate system is the UE4 model origin, and the origin of the first physical space coordinate system is the center point of the performance area in front of the display screen. The units of the virtual space coordinate system are consistent with the units of the first physical space coordinate system. The position of the three-dimensional model relative to the UE4 model origin is consistent with the position of the display screen relative to the center point of the performance area in front, which is equivalent to a one-to-one restoration of the position of the display screen in the first physical space coordinate system.

[0088] S215: Determine unit position information corresponding to each display unit in the plurality of display units of the display screen according to the three-dimensional model information; the plurality of display units correspond one-to-one to the plurality of binary square reference marks.

[0089] In one embodiment of the present application, a display screen includes multiple display units, each of which is square in shape. Each display unit is filled with a binary square fiducial marker, and the binary square fiducial markers displayed by different display units are different. Therefore, based on the position information of the display units simulated in the virtual space coordinate system in the three-dimensional model, the unit position information of each display unit in the display screen in the first physical space coordinate system can be obtained. This unit position information may include the spatial coordinate data of the four corner points of the display unit.

[0090] S216: Obtain the second position information of at least one target mark according to the unit position information corresponding to each display unit.

[0091] Since each display unit displays a binary square reference mark in a filled manner, the unit position information of each display unit in the first physical space coordinate system can be used to obtain the second position information of at least one target mark in the first physical space coordinate system, wherein the second position information includes the corner point space coordinate data corresponding to each target mark in at least one target mark.

[0092] In the above embodiment, for a display screen displaying multiple binary square reference marks, manually measuring the position of each mark in the first physical space coordinate system is too time-consuming and the measurement results are inaccurate. By using a virtual engine to perform proportional modeling of the display screen, the second position information of each target mark in the first physical space coordinate system can be quickly and accurately determined, which can further improve work efficiency when the display screen is large or the display screen is a curved surface.

[0093] S230: Determine a first space calibration result based on the first position information and the second position information, where the first space calibration result represents a conversion relationship between the first physical space coordinate system and the camera coordinate system corresponding to the camera.

[0094] In an embodiment of the present application, the first position information includes the pixel coordinate data of the corner points of each target mark, and the second position information includes the spatial coordinate data of the corner points of each target mark. The conversion relationship between the first physical space coordinate system and the camera coordinate system can be calibrated based on the first position information and the second position information. In this process, the calibration of the camera parameters can also be completed.

[0095] Specifically, step S230 may be implemented as follows:

[0096] S231: Determine the coordinate correspondence between each target marker based on the pixel coordinate data of the corner point corresponding to each target marker in the first position information and the spatial coordinate data of the corner point corresponding to each target marker in the second position information.

[0097] That is, with the target mark as the object, the pixel coordinate data of the corner points and the corresponding spatial coordinate data of the corner points corresponding to the target mark are extracted to form a set of coordinate correspondences corresponding to the target mark.

[0098] S232: Determine at least one coordinate transformation matrix according to the coordinate correspondence of each target marker.

[0099] It is feasible to group each target marker according to the calibration two-dimensional image to which it belongs. Then, based on the least squares method, a corresponding coordinate transformation matrix is determined from the coordinate correspondence of one or more target markers contained in each calibration two-dimensional image.

[0100] S233: Determine target parameter information of the camera according to at least one coordinate transformation matrix.

[0101] According to the coordinate transformation matrix corresponding to each calibrated two-dimensional image, the target parameter information of the camera can be solved under certain constraints. The target parameter information represents the conversion relationship between the camera coordinate system and the pixel coordinate system, that is, it can represent the intrinsic parameter information of the camera. The intrinsic parameter information, such as the focal length, determines the projection position of the actual position of the object on the imaging plane.

[0102] S234: Determine a first spatial calibration result based on the first position information, the second position information, and the target parameter information.

[0103] Specifically, a Perspective-n-Point (PNP) solution is performed based on the camera's target parameter information, the first position information of at least one target marker, and the second position information of at least one target marker. This solution obtains a first spatial calibration result that represents the conversion relationship between the first physical space coordinate system and the camera coordinate system corresponding to the camera. The first spatial calibration result can also represent the position of the display screen relative to the camera. When the first physical space coordinate system is regarded as a world coordinate system, the first spatial calibration result can also represent the camera's extrinsic parameter information.

[0104] Furthermore, when the display screen includes multiple display units, each target mark corresponds to a display unit. According to the target parameter information of the camera, the first position information corresponding to each target mark and the second position information corresponding to each target mark, the position of each display unit relative to the camera can be determined.

[0105] In the above embodiment, the camera intrinsic parameters are calibrated using the Zhang Zhengyou calibration method based on the first position information and the second position information, and then the conversion relationship between the first physical space coordinate system and the camera coordinate system can be determined. In this process, sufficient coordinate correspondences brought by multiple corner points of at least one target marker can improve the accuracy of the calibration.

[0106] S250: Acquire third position information of the tracking device in a second physical space coordinate system corresponding to the tracking device when the camera shoots the display screen.

[0107] Among them, the tracking device is used to track the camera in virtual production; the camera is used to shoot the real scene with the display screen as the background in virtual production.

[0108] In one embodiment of the present application, the tracking device has positioning capabilities, such as Figure 1 As shown, a second physical space coordinate system can be established with the base of the tracking device as the center and the moving camera can be tracked to obtain the third position information in the second physical space coordinate system when the camera captures at least one calibrated two-dimensional image of the display screen, that is, the position of the camera relative to the tracking device.

[0109] S270: Determine a second space calibration result based on the third position information, where the second space calibration result represents a conversion relationship between the second physical space coordinate system and the camera coordinate system.

[0110] In one embodiment of the present application, Figure 1As shown, the posture of the camera relative to the end of the tracking device remains unchanged. According to the posture of the end of the tracking device (also known as the robot arm) in the second physical space coordinate system and the posture of the camera relative to the end of the tracking device, the posture of the camera relative to the tracking device is obtained using the hand-eye calibration method. The posture of the camera relative to the tracking device can be used to determine the second space calibration result that represents the conversion relationship between the second physical space coordinate system and the camera coordinate system.

[0111] S290: Determine a target space calibration result based on the first space calibration result and the second space calibration result, where the target space calibration result represents a conversion relationship between the first physical space coordinate system and the second physical space coordinate system.

[0112] In an embodiment of the present application, the first space calibration result represents the conversion relationship between the first physical space coordinate system and the camera coordinate system corresponding to the camera, and the second space calibration result represents the conversion relationship between the second physical space coordinate system and the camera coordinate system. Therefore, based on the conversion relationship of the coordinate systems, the target space calibration result representing the conversion relationship between the first physical space coordinate system and the second physical space coordinate system can be obtained.

[0113] Furthermore, the target space calibration result is a spatial transformation matrix, which is decomposed using the singular value decomposition (SVD) method to obtain multiple spatial transformation sub-matrices. For example, three sub-matrices are obtained by decomposition, representing the three spatial transformation operations of rotation, scaling, and projection respectively.

[0114] In one embodiment of the present application, the position of the display screen remains unchanged, the tracking device can have a certain motion path, and the tracking device has a positioning capability centered on itself, and determines the conversion relationship between the first physical space coordinate system of the space where the display screen is located and the second physical space coordinate system of the space where the tracking device is located. That is, the stable and unchanging conversion relationship between the space where the display screen is located and the space where the tracking device is located is calibrated, which does not change with the posture of the camera during the virtual process, and then combined with the camera tracking technology of the tracking device, the posture of the camera relative to the display screen can be accurately determined.

[0115] In the above embodiment, the solution provided by the present application is applied to the spatial calibration process of virtual production, where a plurality of binary square fiducial markers are displayed on a display screen, a camera shoots a real scene with the display screen as the background, and a tracking device tracks the posture of the camera; the solution provided by the present application first obtains first position information of at least one target marker in a pixel coordinate system and second position information of at least one target marker in a first physical space coordinate system corresponding to the display screen, wherein the plurality of binary square fiducial markers include at least one target marker; based on the first position information and the second position information of the at least one target marker, a first spatial calibration result can be determined, that is, a conversion relationship between the first physical space coordinate system and the camera coordinate system corresponding to the camera can be determined; then, the solution provided by the present application obtains third position information of the tracking device in a second physical space coordinate system corresponding to the tracking device when the camera shoots the real screen, and a second spatial calibration result can be determined based on the third position information, that is, a conversion relationship between the second physical space coordinate system and the camera coordinate system can be determined; finally, the solution provided by the present application determines a target calibration result based on the first spatial calibration result and the second spatial calibration result, where the target spatial calibration result represents the conversion relationship between the first physical space coordinate system and the second physical space coordinate system. The technical solution provided by this application utilizes some or all of the multiple binary square fiducial markers to calibrate the first physical space coordinate system corresponding to the display screen and the second physical space coordinate system corresponding to the tracking device in virtual production. The resulting target calibration results are accurate, stable, and highly efficient. During the virtual production process, regardless of the camera's position or angle, the precise and stable target calibration results ensure that the virtual scene and the real scene are accurately matched.

[0116] In one embodiment of the present application, the method may further include:

[0117] S310: Acquire a real-time two-dimensional image captured by the camera with the display screen as the background and first real-time position information of the device tracked by the camera in a second physical space coordinate system during the capture.

[0118] S320: Determine first real-time relative posture information between the display screen and the camera according to the first real-time position information and the target space calibration result.

[0119] S330: According to the first real-time relative posture information, the three-dimensional virtual model corresponding to the display screen is projected onto a two-dimensional simulation plane to obtain a projected two-dimensional image.

[0120] Alternatively, the projectPoints function in OpenCV (a cross-platform computer vision and machine learning software library) is used to project the three-dimensional model corresponding to the display screen onto a two-dimensional simulation plane to obtain a projected two-dimensional image. Alternatively, the first real-time relative posture information and the target parameter information of the camera are transmitted to the virtual engine, so that the parameter information of the virtual camera in the virtual engine is consistent with the target parameter, and the virtual camera and the three-dimensional model corresponding to the display screen maintain the posture corresponding to the first real-time relative posture information. The three-dimensional virtual model corresponding to the display screen is then projected onto the two-dimensional simulation plane where the image coordinate system corresponding to the virtual camera is located to obtain a projected two-dimensional image.

[0121] S340: performing position comparison on the corner points of the display screen according to the projected two-dimensional image and the real-time two-dimensional image to obtain a comparison result, which is used to indicate whether to retain the target calibration result.

[0122] The first pixel coordinates corresponding to the corner points of each display unit in the display screen can be determined based on the projected two-dimensional image, and the first pixel coordinates corresponding to the corner points of each display unit in the display screen can be determined based on the real-time two-dimensional image. A comparison result is determined by comparing the difference between the first pixel coordinates and the second pixel coordinates corresponding to each corner point. For example, if the maximum difference is within an acceptable range, the comparison result indicates that the target calibration result can be retained; if the maximum difference is outside the acceptable range, the comparison result indicates that recalibration is required.

[0123] In the above embodiment, during the calibration phase, the target calibration result is verified using the projected two-dimensional image output by the three-dimensional model corresponding to the display screen and the real-time two-dimensional image captured by the camera, which can further improve the accuracy of the target calibration result.

[0124] Furthermore, the method may further include:

[0125] S410: Obtain second real-time position information of the tracking device in a second physical space coordinate system when the camera is shooting.

[0126] It can be understood that the second real-time position information in the second physical space coordinate system is the relative position information of the camera during actual shooting in virtual production.

[0127] S420: Determine second real-time relative posture information between the display screen and the camera according to the second real-time position information and the target space calibration result.

[0128] Based on the spatial transformation relationship represented by the target space calibration result, the second real-time relative posture information of the display screen and the camera can be obtained.

[0129] S430: Projecting the three-dimensional virtual scene model according to the second real-time relative posture information to obtain a two-dimensional virtual scene image.

[0130] It is feasible to transmit the second real-time relative posture information to the virtual engine so that the virtual camera in the virtual engine and the designed three-dimensional virtual scene model maintain the posture corresponding to the second real-time relative posture information. During the simulation shooting, a two-dimensional virtual scene image is output.

[0131] S440: Displaying a two-dimensional virtual scene image on a display screen, and acquiring a target image captured by a camera with the display screen as a background.

[0132] In the above embodiment, the virtual camera in the virtual engine and the real camera are bound to each other in position, and the two-dimensional virtual scene image presented on the display screen can automatically adjust the displayed scene and the perspective and parallax of the scene according to the movement of the camera, providing the performer with a more realistic performance scene.

[0133] Figure 4 This is a specific flow chart of a spatial calibration method for virtual film production provided by an embodiment of the present application. Figure 4 As shown, according to the working sequence, first build a three-dimensional model of the display screen and set the Aruco mark corresponding to the display screen, such as Figure 3 The LED curtain wall shown has eight large blocks, each containing 10x12 smaller blocks. An Aruco marker is added to each block according to the settings, and the 3D vertex position of each block in the 3D model is obtained in UE4. Next, images are taken at different positions and angles to obtain eight calibrated 2D images, along with the third position information of the tracking device during imaging for each calibrated 2D image. Calibration is then performed using the method provided in the above embodiment to obtain a target calibration result. During this process, the camera's intrinsic parameters can also be calibrated to adjust the camera's intrinsic parameters. Finally, a pixel comparison is performed between the real-time image captured by the camera and the 2D image projected from the 3D model. If the pixel difference is significant, a new calibrated 2D image is obtained and the corresponding third position information is recorded. If the pixel offset of a corner point at a certain angle is large, such as exceeding 10 pixels, the corresponding source data can be deleted and recalculated to obtain a new target calibration result.

[0134] The embodiment of the present application also provides a schematic diagram of a graphical interface of computer software, and a user can set, obtain and calculate relevant data based on the graphical interface. Figure 5 It shows how to use the graphical interface to set the 3D model parameters and camera initial parameters corresponding to the LED curtain wall, and generate the Aruco mark to be displayed; Figure 6 It shows how to use a graphical interface to obtain images of the LED curtain wall taken by four cameras at different positions and angles; Figure 7 The use of a graphical interface to calculate the relative postures between the camera, tracking device, and LED curtain wall is shown; Figure 8 It shows that when checking the calibration results in real time, data with large pixel offsets are detected and deleted; Figure 9 The figure shows the corner point matching effect of the projected 2D image of the 3D model (bottom right view) and the real-time 2D image captured by the camera (bottom left view) after recalculation. The above is an exemplary graphical interface diagram provided in an embodiment of the present application. In actual application, the design can be adapted according to application requirements and graphical interface style, and is not limited here.

[0135] The embodiment of the present application also provides a space calibration device 1000 for virtual film production, such as Figure 10 As shown, the device may include:

[0136] A first acquisition module 1010 is configured to acquire first position information of at least one target mark in a pixel coordinate system and second position information of the at least one target mark in a first physical space coordinate system corresponding to a display screen, wherein the display screen displays a plurality of binary square reference marks; the plurality of binary square reference marks includes the at least one target mark;

[0137] A first calibration module 1020 is configured to determine a first spatial calibration result based on the first position information and the second position information, where the first spatial calibration result represents a conversion relationship between the first physical space coordinate system and a camera coordinate system corresponding to the camera;

[0138] A second acquisition module 1030 is configured to acquire third position information of the tracking device in a second physical space coordinate system corresponding to the tracking device when the camera is photographing the display screen; the tracking device is configured to track the camera in virtual production; and the camera is configured to photograph a real scene with the display screen as a background in virtual production;

[0139] A second calibration module 1040 is configured to determine a second space calibration result based on the third position information, where the second space calibration result represents a conversion relationship between the second physical space coordinate system and the camera coordinate system;

[0140] The target calibration module 1050 is configured to determine a target space calibration result based on the first space calibration result and the second space calibration result, where the target space calibration result represents a conversion relationship between the first physical space coordinate system and the second physical space coordinate system.

[0141] In one embodiment of the present application, the first acquisition module 1010 may include:

[0142] an image acquisition unit, configured to acquire at least one calibrated two-dimensional image obtained by photographing the display screen with the camera;

[0143] a target marker acquiring unit, configured to determine the at least one target marker included in the at least one calibration two-dimensional image;

[0144] The first position determination unit is used to determine the first position information of the at least one target mark in the pixel coordinate system according to the image area corresponding to the at least one target mark, where the first position information includes the pixel coordinate data of the corner point corresponding to the at least one target mark.

[0145] In one embodiment of the present application, the first acquisition module 1010 may further include:

[0146] A model acquisition unit, configured to acquire three-dimensional model information corresponding to the display screen in a virtual space coordinate system;

[0147] a unit position determining unit, configured to determine, based on the three-dimensional model information, unit position information corresponding to each of the plurality of display units of the display screen; the plurality of display units corresponding one-to-one to the plurality of binary square reference marks;

[0148] a second position determination unit, configured to obtain the second position information of the at least one target mark according to the unit position information corresponding to each of the display units; the second position information includes spatial coordinate data of a corner point corresponding to the at least one target mark;

[0149] The virtual space coordinate system corresponds to the first physical space coordinate system.

[0150] In one embodiment of the present application, the target mark acquisition unit may include:

[0151] a marker detection subunit, configured to perform marker detection on the at least one calibrated two-dimensional image to determine at least one candidate marker;

[0152] The recognition and matching subunit is used to perform point recognition and matching on the at least one candidate marker to determine the at least one target marker.

[0153] In one embodiment of the present application, the first calibration module 1020 may include:

[0154] a coordinate corresponding unit, configured to determine a coordinate corresponding relationship between each target marker based on the pixel coordinate data of the corner point corresponding to each target marker in the first position information and the spatial coordinate data of the corner point corresponding to each target marker in the second position information;

[0155] A coordinate conversion unit, configured to determine at least one coordinate conversion matrix according to the coordinate correspondence between the target markers;

[0156] A camera parameter calibration unit, configured to determine target parameter information of the camera according to the at least one coordinate transformation matrix; the target parameter information represents a transformation relationship between the camera coordinate system and the pixel coordinate system;

[0157] The first calibration unit is configured to determine the first space calibration result based on the first position information, the second position information, and the target parameter information.

[0158] In one embodiment of the present application, the apparatus 1000 may further include:

[0159] a real-time information acquisition unit, configured to acquire a real-time two-dimensional image captured by the camera with the display screen as the background and first real-time position information of the tracking device in the second physical space coordinate system when the camera captures the image;

[0160] a first real-time relative posture determining unit, configured to determine first real-time relative posture information between the display screen and the camera according to the first real-time position information and the target space calibration result;

[0161] a first three-dimensional projection unit, configured to project the three-dimensional virtual model corresponding to the display screen onto a two-dimensional simulation plane to obtain a projected two-dimensional image according to the first real-time relative posture information;

[0162] A comparison unit is used to perform position comparison on the corner points of the display screen according to the projected two-dimensional image and the real-time two-dimensional image to obtain a comparison result, wherein the comparison result is used to indicate whether to retain the target calibration result.

[0163] In one embodiment of the present application, the apparatus 1000 may further include:

[0164] a real-time position acquisition unit, configured to acquire second real-time position information of the tracking device in the second physical space coordinate system when the camera is shooting;

[0165] a second real-time relative posture determining unit, configured to determine second real-time relative posture information between the display screen and the camera according to the second real-time position information and the target space calibration result;

[0166] a second three-dimensional projection unit, configured to project the three-dimensional virtual scene model according to the second real-time relative posture information to obtain a two-dimensional virtual scene image;

[0167] The target image acquisition unit is used to display the two-dimensional virtual scene image on the display screen and acquire the target image shot by the camera with the display screen as the background.

[0168] It should be noted that the apparatus provided in the above embodiments, when implementing its functions, is only illustrated by the division of the above functional modules. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. In addition, the apparatus and method embodiments provided in the above embodiments are based on the same concept. The specific implementation process is detailed in the method embodiment and will not be repeated here.

[0169] An embodiment of the present application provides a computer device, which includes a processor and a memory, wherein the memory stores at least one instruction or at least one program, and the at least one instruction or the at least one program is loaded and executed by the processor to implement a spatial calibration method for virtual production as provided in the above-mentioned method embodiment.

[0170] Figure 11 A schematic diagram of the hardware structure of a device for implementing a spatial calibration method for virtual filming provided in an embodiment of the present application is shown. The device may participate in or include the apparatus or system provided in an embodiment of the present application. Figure 11 As shown, the device 10 may include one or more (illustrated as 1002a, 1002b, ..., 1002n in the figure) processors 1002 (the processor 1002 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA), a memory 1004 for storing data, and a transmission device 1006 for communication functions. In addition, it may also include: a display, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports of the I / O interface), a network interface, a power supply and / or a camera. It will be understood by those skilled in the art that Figure 11 The structure shown is only for illustration and does not limit the structure of the above electronic device. Figure 11 More or fewer components than shown, or with Figure 11 Different configurations shown.

[0171] It should be noted that the one or more processors 1002 and / or other data processing circuits described above may generally be referred to herein as "data processing circuitry". The data processing circuitry may be embodied in whole or in part as software, hardware, firmware, or any other combination thereof. In addition, the data processing circuitry may be a single independent processing module, or may be incorporated in whole or in part into any of the other components of the device 10 (or mobile device). As described in the embodiments of the present application, the data processing circuitry serves as a processor control (e.g., selection of a variable resistor terminal path connected to an interface).

[0172] The memory 1004 can be used to store software programs and modules of application software, such as program instructions / data storage devices corresponding to the methods described in the embodiments of the present application. The processor 1002 executes various functional applications and data processing by running the software programs and modules stored in the memory 1004, thereby implementing the above-mentioned spatial calibration method for virtual production. The memory 1004 may include a high-speed random access memory and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 1004 may further include a memory remotely located relative to the processor 1002, and these remote memories may be connected to the device 10 via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0173] Transmission device 1006 is configured to receive or transmit data via a network. A specific example of the aforementioned network may include a wireless network provided by the communications provider of device 10. In one embodiment, transmission device 1006 includes a network interface controller (NIC), which can be connected to other network devices via a base station to enable communication with the Internet. In another embodiment, transmission device 1006 may be a radio frequency (RF) module, which is configured to communicate with the Internet wirelessly.

[0174] The display may be, for example, a touch screen liquid crystal display (LCD) that enables a user to interact with a user interface of device 10 (or mobile device).

[0175] An embodiment of the present application also provides a computer-readable storage medium, which can be set in a server to store at least one instruction or at least one program related to a spatial calibration method applied to virtual production in a method embodiment. The at least one instruction or the at least one program is loaded and executed by the processor to implement a spatial calibration method applied to virtual production provided by the above method embodiment.

[0176] Optionally, in this embodiment, the storage medium may be located in at least one of a plurality of network servers in a computer network. Optionally, in this embodiment, the storage medium may include, but is not limited to, various media capable of storing program code, such as a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk, or an optical disk.

[0177] An embodiment of the present invention further provides a computer program product or computer program, comprising computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform a spatial calibration method for virtual production provided in any of the aforementioned optional embodiments.

[0178] It should be noted that the order of the embodiments of the present application described above is for descriptive purposes only and does not represent the superiority or inferiority of the embodiments. The above description is of specific embodiments of the present application. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps described in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0179] The various embodiments in this application are described in a progressive manner. Similar portions between the various embodiments can be referred to in conjunction with each other. Each embodiment focuses on the differences between the other embodiments. In particular, the device, equipment, and storage medium embodiments are generally similar to the method embodiments, so their descriptions are relatively simple. For relevant portions, refer to the descriptions of the method embodiments.

[0180] Those skilled in the art will understand that all or part of the steps to implement the above embodiments may be accomplished by hardware, or by a program to instruct the relevant hardware, and the program may be stored in a computer-readable storage medium, which may be a read-only memory, a disk, or an optical disk, etc.

[0181] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application should be included in the scope of protection of the present application.

Claims

1. A spatial calibration method for virtual film production, characterized in that: The method comprises: Obtaining first position information of at least one target mark in a pixel coordinate system and second position information of the at least one target mark in a first physical space coordinate system corresponding to a display screen, wherein the display screen displays a plurality of binary square reference marks; the plurality of binary square reference marks includes the at least one target mark; Determining a first spatial calibration result based on the first position information and the second position information, where the first spatial calibration result represents a conversion relationship between the first physical space coordinate system and a camera coordinate system corresponding to the camera; obtaining third position information of the tracking device in a second physical space coordinate system corresponding to the tracking device when the camera photographs the display screen; the tracking device is used to track the camera in virtual production; the camera is used to photograph a real scene with the display screen as a background in virtual production; determining a second space calibration result based on the third position information, where the second space calibration result represents a conversion relationship between the second physical space coordinate system and the camera coordinate system; A target space calibration result is determined based on the first space calibration result and the second space calibration result, where the target space calibration result represents a conversion relationship between the first physical space coordinate system and the second physical space coordinate system.

2. The method according to claim 1, characterized in that The acquiring first position information of at least one target mark in a pixel coordinate system and second position information of the at least one target mark in a first physical space coordinate system corresponding to the display screen includes: Acquire at least one calibrated two-dimensional image obtained by photographing the display screen with the camera; determining the at least one target marker included in the at least one calibration two-dimensional image; The first position information of the at least one target mark in the pixel coordinate system is determined according to the image area corresponding to the at least one target mark, where the first position information includes pixel coordinate data of a corner point corresponding to the at least one target mark.

3. The method according to claim 1, characterized in that The acquiring of first position information of at least one target mark in a pixel coordinate system and second position information of the at least one target mark in a first physical space coordinate system corresponding to the display screen further includes: Acquiring three-dimensional model information corresponding to the display screen in a virtual space coordinate system; Determining unit position information corresponding to each of the plurality of display units of the display screen according to the three-dimensional model information; wherein the plurality of display units correspond one-to-one to the plurality of binary square reference marks; Obtaining the second position information of the at least one target mark according to the unit position information corresponding to each of the display units; the second position information includes spatial coordinate data of a corner point corresponding to the at least one target mark; The virtual space coordinate system corresponds to the first physical space coordinate system.

4. The method according to claim 2, characterized in that The determining the at least one target marker included in the at least one calibration two-dimensional image includes: performing marker detection on the at least one calibrated two-dimensional image to determine at least one candidate marker; Perform point recognition and matching on the at least one candidate marker to determine the at least one target marker.

5. The method according to claim 1, wherein The determining a first spatial calibration result based on the first position information and the second position information includes: Determining a coordinate correspondence between the target markers based on the pixel coordinate data of the corner points corresponding to the target markers in the first position information and the spatial coordinate data of the corner points corresponding to the target markers in the second position information; Determining at least one coordinate transformation matrix according to the coordinate correspondence of each target marker; Determining target parameter information of the camera according to the at least one coordinate transformation matrix; the target parameter information represents a transformation relationship between the camera coordinate system and the pixel coordinate system; The first spatial calibration result is determined based on the first position information, the second position information, and the target parameter information.

6. The method according to claim 1, characterized in that The method further comprises: Acquire a real-time two-dimensional image captured by the camera with the display screen as the background and first real-time position information of the tracking device in the second physical space coordinate system when the camera captures the image; determining first real-time relative posture information between the display screen and the camera according to the first real-time position information and the target space calibration result; projecting the three-dimensional virtual model corresponding to the display screen onto a two-dimensional simulation plane to obtain a projected two-dimensional image according to the first real-time relative posture information; According to the projected two-dimensional image and the real-time two-dimensional image, a position comparison is performed on the corner points of the display screen to obtain a comparison result, and the comparison result is used to indicate whether to retain the target calibration result.

7. The method according to claim 1, characterized in that The method further comprises: Acquire second real-time position information of the tracking device in the second physical space coordinate system when the camera is shooting; determining second real-time relative posture information between the display screen and the camera according to the second real-time position information and the target space calibration result; projecting the three-dimensional virtual scene model according to the second real-time relative posture information to obtain a two-dimensional virtual scene image; The two-dimensional virtual scene image is displayed on the display screen, and a target image captured by the camera with the display screen as the background is acquired.

8. A spatial calibration device for virtual film production, characterized in that: The device comprises: a first acquisition module, configured to acquire first position information of at least one target mark in a pixel coordinate system and second position information of the at least one target mark in a first physical space coordinate system corresponding to a display screen, wherein the display screen displays a plurality of binary square reference marks; the plurality of binary square reference marks includes the at least one target mark; a first calibration module, configured to determine a first spatial calibration result based on the first position information and the second position information, wherein the first spatial calibration result represents a conversion relationship between the first physical space coordinate system and a camera coordinate system corresponding to the camera; a second acquisition module, configured to acquire third position information of the tracking device in a second physical space coordinate system corresponding to the tracking device when the camera is photographing the display screen; the tracking device is configured to track the camera in virtual production; and the camera is configured to photograph a real scene with the display screen as a background in virtual production; a second calibration module, configured to determine a second space calibration result based on the third position information, where the second space calibration result represents a conversion relationship between the second physical space coordinate system and the camera coordinate system; The target calibration module is used to determine a target space calibration result based on the first space calibration result and the second space calibration result, where the target space calibration result represents a conversion relationship between the first physical space coordinate system and the second physical space coordinate system.

9. A computer-readable storage medium, characterized in that The computer-readable storage medium stores at least one instruction or at least one program, and the at least one instruction or the at least one program is loaded and executed by the processor to implement the spatial calibration method for virtual production according to any one of claims 1 to 7.

10. A computer device, characterized in that: The computer device includes a processor and a memory, wherein the memory stores at least one instruction or at least one program, and the at least one instruction or at least one program is loaded and executed by the processor to implement the spatial calibration method for virtual production as described in any one of claims 1 to 7.

Images