Visual motion capture and 3D digital human skeleton initial posture automatic matching method, system and device, medium and product

Abstract

The invention discloses a visual motion capture and 3D digital human skeleton initial posture automatic matching method, system and device, a medium and a product, and relates to the technical field of visual rendering. The method comprises the following steps: firstly, in a rendering environment, obtaining photos of a 3D digital person under different views, attitude data of each skeleton of the 3D digital person under a rendering end world coordinate system and external parameters of a virtual camera for shooting the photos under each view; in the motion capture environment, capturing attitude data of each skeleton in the picture under each view under the corresponding motion capture end skeleton coordinate system; then calculating an initial attitude error of the motion capture end relative to the rendering end, and attitude data of each skeleton in a motion capture end world coordinate system; according to the method and the device, the vision-based multi-view motion capture and the rendering end are combined, and automatic matching of the vision motion capture and the initial posture of the 3D digital human skeleton is realized.

Description

Technical Field

[0001] The present application relates to the field of visual rendering technology, and in particular to a method, system, device, medium and product for automatic matching of visual motion capture and initial posture of 3D digital human skeleton. Background Art

[0002] Currently, most 3D digital humans are driven by real-time rendering in environments such as Unreal Engine (UE) or Blender. The input is the rotation data of each bone relative to the initial pose. However, due to the different methods of generating digital humans, the default initial pose when they are produced is not the standard T_pose (T-shaped pose) or A_pose (A-shaped pose). Most motion capture terminals use wearable or non-wearable visual capture, and their coordinate systems and initial poses of bones also vary due to different algorithms. In order to match the two, some plug-ins or algorithms are needed to identify the coordinate system and pose of the digital human skeleton in the rendering terminal such as UE and Blender, and then manually adjust them to ensure that the coordinate system and initial pose are consistent with those of the motion capture terminal so that the two can work normally.

[0003] Most of the existing skeleton recognition algorithms on the rendering side are integrated with the rendering environment in the form of plug-ins, such as Mixamo of UnrealEngine and Autorig of Blender. The shortcomings of the existing technology are:

[0004] 1. To ensure the consistency of the initial postures of the rendering end and the motion capture end, the initial posture of each bone on the rendering end is generally adjusted manually one by one to make it consistent with the initial posture of the motion capture end. This method is time-consuming and labor-intensive and may result in errors that cannot be distinguished by the naked eye.

[0005] 2. The skeleton posture recognized by the plug-in is based on the rendering environment coordinate system, which is inconsistent with the coordinate system definition of the motion capture end. It is also necessary to calculate the coordinate system conversion of the two bones one by one. This method is time-consuming and labor-intensive and will have errors that cannot be distinguished by the naked eye. Summary of the invention

[0006] The purpose of this application is to provide a method, system, device, medium and product for automatic matching of visual motion capture and the initial posture of 3D digital human skeleton, so as to realize automatic identification of the initial posture error of the motion capture end relative to the rendering end and the conversion relationship between the skeleton coordinate system of the motion capture end and the skeleton coordinate system of the rendering end, thereby realizing automatic matching of visual motion capture and the initial posture of 3D digital human skeleton.

[0007] To achieve the above objectives, this application provides the following solutions.

[0008] In a first aspect, the present application provides a method for automatic matching of visual motion capture and 3D digital human skeleton initial posture, comprising:

[0009] In the rendering environment, obtain photos of the 3D digital human in different views, the posture data of each skeleton of the 3D digital human in the world coordinate system of the rendering end, and the external parameters of the virtual camera that takes the photos in each view;

[0010] In the motion capture environment, the posture data of each skeleton in the photo of each view in the corresponding motion capture end skeleton coordinate system is captured according to the external parameters of the virtual camera that takes the photo of each view;

[0011] According to the posture data of each bone in the corresponding motion capture end bone coordinate system, the initial posture error of the motion capture end relative to the rendering end is calculated;

[0012] According to the posture data of each bone in the corresponding motion capture end bone coordinate system, the posture data of each bone in the motion capture end world coordinate system is calculated;

[0013] According to the posture data of each bone in the world coordinate system of the motion capture end and the posture data of each bone in the world coordinate system of the rendering end, as well as the conversion relationship between the world coordinate system of the motion capture end and the world coordinate system of the rendering end, the conversion relationship between the motion capture end bone coordinate system and the rendering end bone coordinate system corresponding to each bone is determined.

[0014] Optionally, the formula for calculating the initial posture error of the motion capture end relative to the rendering end is:

[0015] T i,PoseError = inverse(T i,lm );

[0016] Among them, T i,PoseError is the initial posture error of the motion capture end relative to the rendering end of the skeleton i, T i,lm is the posture data of bone i in the corresponding motion capture end bone coordinate system, and inverse() is the inverse function.

[0017] Optionally, the conversion relationship between the motion capture end skeleton coordinate system and the rendering end skeleton coordinate system is:

[0018] T i,Coordinate = inverse(T i,wr )×T rm ×T i,wm ;

[0019] Among them, T i,Coordinate is the conversion relationship between the motion capture end bone coordinate system and the rendering end bone coordinate system corresponding to bone i, T i,wr is the posture data of bone i in the world coordinate system of the rendering end, T rm is the conversion relationship between the world coordinate system of the rendering end and the world coordinate system of the motion capture end, T i,wmis the posture data of bone i in the world coordinate system of the motion capture end.

[0020] Optionally, in the motion capture environment, the posture data of each skeleton in the photo of each view in the corresponding motion capture end skeleton coordinate system is captured according to the external parameters of the virtual camera that takes the photo of each view, specifically including:

[0021] In the motion capture environment, the external parameters of the multi-view visual motion capture module in the motion capture environment are set according to the external parameters of the virtual camera of the photo in each view, and the posture data of each bone in the photo in each view in the corresponding motion capture end bone coordinate system is captured.

[0022] In a second aspect, the present application provides a visual motion capture and 3D digital human skeleton initial posture automatic matching system, the visual motion capture and 3D digital human skeleton initial posture automatic matching system is used to perform the above-mentioned visual motion capture and 3D digital human skeleton initial posture automatic matching method, the visual motion capture and 3D digital human skeleton initial posture automatic matching system includes: a rendering module and a motion capture module;

[0023] The rendering module includes: a virtual camera submodule, a first posture acquisition submodule and a data transmission submodule; the motion capture module includes: a second posture acquisition submodule and a data processing submodule;

[0024] The virtual camera submodule is used to obtain photos of the 3D digital human in different views in the rendering environment;

[0025] The first posture acquisition submodule is used to acquire the posture data of each skeleton of the 3D digital human in the world coordinate system of the rendering end in the rendering environment;

[0026] The data transmission submodule is used to transmit the photos of the 3D digital human in different views in the rendering environment, the posture data of each skeleton of the 3D digital human in the world coordinate system of the rendering end, and the external parameters of the virtual camera that takes the photos in each view to the motion capture module;

[0027] The second posture acquisition submodule is used to capture the posture data of each skeleton in the photo under each view in the corresponding motion capture end skeleton coordinate system according to the external parameters of the virtual camera that takes the photo under each view in the motion capture environment;

[0028] The data processing submodule is used to calculate the initial posture error of the motion capture end relative to the rendering end according to the posture data of each bone in the corresponding motion capture end skeleton coordinate system; calculate the posture data of each bone in the world coordinate system of the motion capture end according to the posture data of each bone in the corresponding motion capture end skeleton coordinate system; determine the conversion relationship between the motion capture end skeleton coordinate system and the rendering end skeleton coordinate system corresponding to each bone according to the posture data of each bone in the world coordinate system of the motion capture end and the posture data of each bone in the world coordinate system of the rendering end, as well as the conversion relationship between the world coordinate system of the motion capture end and the world coordinate system of the rendering end.

[0029] Optionally, the virtual camera submodule includes a plurality of virtual cameras;

[0030] In the rendering environment, a plurality of virtual cameras are arranged around the 3D digital human.

[0031] Optionally, in the motion capture environment, a multi-view visual motion capture module is provided. During motion capture, external parameters of the multi-view visual motion capture module are respectively set to be consistent with external parameters of each virtual camera.

[0032] In a third aspect, the present application provides a computer device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the above-mentioned visual motion capture and 3D digital human skeleton initial posture automatic matching method.

[0033] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the above-mentioned method for automatic matching of visual motion capture and 3D digital human skeleton initial posture.

[0034] In a fifth aspect, the present application provides a computer program product, including a computer program, characterized in that when the computer program is executed by a processor, the above-mentioned visual motion capture and 3D digital human skeleton initial posture automatic matching method is implemented.

[0035] According to the specific embodiments provided in this application, this application has the following technical effects.

[0036] The present application provides a method, system, device, medium and product for automatic matching of visual motion capture and the initial posture of 3D digital human skeleton. The present application combines visual-based multi-view motion capture and the rendering end, and automatically identifies the initial posture and coordinate system conversion of the 3D digital image on the rendering end in the motion capture environment through an algorithm, effectively solving the problem of inconsistency between the coordinate systems and initial postures of the two, thereby achieving automatic matching of visual motion capture and the initial posture of 3D digital human skeleton. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. 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 paying creative work.

[0038] Figure 1 A flowchart of a method for automatic matching of visual motion capture and 3D digital human skeleton initial posture provided in one embodiment of the present application.

[0039] Figure 2 These are example pictures of a 3D digital human in different views provided by an embodiment of the present application.

[0040] Figure 3 A schematic diagram of the structure of a computer device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0041] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions 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.

[0042] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below with reference to the accompanying drawings and specific implementation methods.

[0043] In an exemplary embodiment, Figure 1 As shown, a method for automatic matching of visual motion capture and 3D digital human skeleton initial posture is provided, including the following steps 101 to 105.

[0044] Step 101, in a rendering environment, obtain photos of a 3D digital human in different views, posture data of each skeleton of the 3D digital human in a world coordinate system of a rendering end, and external parameters of a virtual camera for taking photos in each view.

[0045] Step 102 , in a motion capture environment, capturing the posture data of each skeleton in the photo of each view in the corresponding motion capture end skeleton coordinate system according to the external parameters of the virtual camera that takes the photo of each view.

[0046] Step 103, calculating the initial posture error of the motion capture end relative to the rendering end according to the posture data of each skeleton in the corresponding motion capture end skeleton coordinate system.

[0047] Step 104, calculating the posture data of each skeleton in the world coordinate system of the motion capture end according to the posture data of each skeleton in the corresponding skeleton coordinate system of the motion capture end.

[0048] Step 105, based on the posture data of each skeleton in the world coordinate system of the motion capture end and the posture data of each skeleton in the world coordinate system of the rendering end, as well as the conversion relationship between the world coordinate system of the motion capture end and the world coordinate system of the rendering end, determine the conversion relationship between the skeleton coordinate system of the motion capture end and the skeleton coordinate system of the rendering end corresponding to each skeleton.

[0049] By implementing the above steps 101 to 105, the initial posture error of the motion capture end relative to the rendering end and the conversion relationship between the motion capture end skeleton coordinate system and the rendering end skeleton coordinate system are automatically identified, thereby achieving automatic matching of visual motion capture and the initial posture of the 3D digital human skeleton.

[0050] In the embodiment of the present application, the representation form of the posture data is a rotation matrix or a quaternion.

[0051] In another exemplary embodiment of the present application, a circle of multiple virtual cameras in different directions are set around the 3D digital human in the rendering environment to obtain photos of the 3D digital human in different views, such as Figure 2 As shown, in the embodiment of the present application, photos of the 3D digital human in 6 different views are obtained, marked as P1 to P6, and the corresponding external parameters of the virtual camera that takes the photos in each view are marked as E1 to E6. Further, the posture of each skeleton of the 3D digital human in the world coordinate system of the rendering end is obtained, that is, the posture data of each skeleton of the 3D digital human in the world coordinate system of the rendering end is marked as T i,wr , where the subscript i represents the bone sequence number, the subscript r represents the render end, and the subscript w represents the world coordinate system.

[0052] In order to realize the combination of rendering environment and motion capture environment, in the embodiment of the present application, a data transmission submodule can be set to transmit photos P1-P6 and external references E1-E6, T i,wr The parameter file is transferred to the motion capture environment.

[0053] In another exemplary embodiment of the present application, in a motion capture environment, the external parameters of the visual motion capture modules at different viewing angles in the motion capture environment are replaced with the external parameters E1 to E6 of the virtual camera, and each visual motion capture module is started to capture the posture data T of each skeleton of the 3D digital human in the images P1 to P6 in the corresponding motion capture end skeleton coordinate system. i,lm, wherein the subscript m represents the motioncapture end, and the subscript l represents the local skeletal coordinate system. In an embodiment of the present application, each skeleton has a skeletal coordinate system, wherein the skeletal coordinate system in the rendering environment is called the rendering end skeletal coordinate system, and the skeletal coordinate system in the motion capture environment is called the motion capture end skeletal coordinate system. The origin of the skeletal coordinate system can be the starting point of the skeleton, that is, the connection between the skeleton and its previous skeleton (the previous skeleton connected to the skeleton is called the parent skeleton). The origin of the skeletal coordinate system can also be the midpoint of the skeleton, which is not limited here. In some embodiments, the center point position of the hip bone can be set to be determined as the origin of the skeletal coordinate system of the root skeleton. As a preferred solution, the skeletal coordinate system of the root skeleton may or may not coincide with the world coordinate system of its environment. It is only necessary to clarify its conversion relationship with the world coordinate system, which is not limited here.

[0054] In another exemplary embodiment of the present application, the posture data of each bone in the photo under each view in the corresponding motion capture end bone coordinate system is captured, and it can be obtained by setting specific parameters. The specific process can be found in the paper "Graph-Based 3D Multi-Person Pose Estimation Using Multi-ViewImages".

[0055] In another exemplary embodiment of the present application, after determining the posture data of each skeleton of the 3D digital human in the world coordinate system of the rendering end and the posture data of each skeleton in the corresponding skeleton coordinate system of the motion capture end, the steps 103 to 105 of the present application are executed to automatically identify the initial posture error and the conversion relationship, as follows:

[0056] Use the following formula to calculate the initial posture error of the motion capture end relative to the rendering end.

[0057] T i,PoseError =inveerse(T i,ln )

[0058] Among them, T i,PoseError is the initial posture error of the motion capture end relative to the rendering end of the skeleton i, T i,lm is the posture data of bone i in the corresponding motion capture end bone coordinate system, and inverse() is the inverse function.

[0059] Calculate the posture T of each bone in the motion capture end in the world coordinate system i,wm , where the subscript w represents the world coordinate system, such as T of bone 1 1,wm =T 3,lm ×T 2,lm ×T 1,lm, bone 2 is the previous bone of bone 1, bone 3 is the previous bone of bone 2, and bone 3 is the root bone. In this example, bone 2 is the parent bone of bone 1, bone 3 is the parent bone of bone 2, and so on for other bones. I will not give examples one by one here.

[0060] Since the definitions of the world coordinate system of the motion capture end and the world coordinate system of the rendering end are known (assuming that the transformation relationship between the two is T rm ), the posture of the motion capture end skeleton in the rendering world coordinate system can be calculated: T rm ×T i,wm , and then the conversion relationship between the motion capture end skeleton coordinate system and the rendering end skeleton coordinate system can be calculated as:

[0061] T i,Coordinate = inverse(T i,wr )×T rm ×T i,wm

[0062] Among them, T i,Coordinate is the conversion relationship between the motion capture end bone coordinate system and the rendering end bone coordinate system corresponding to bone i, T i,wr is the posture data of bone i in the world coordinate system of the rendering end, T i,rn is the conversion relationship between the world coordinate system of the rendering end and the world coordinate system of the motion capture end, T i,wm is the posture data of bone i in the world coordinate system of the motion capture end.

[0063] At this point, the automatic matching of visual motion capture and the initial posture of the 3D digital human skeleton is completed.

[0064] Based on the same inventive concept, the embodiment of the present application also provides a visual motion capture and 3D digital human skeleton initial posture automatic matching system for realizing the above-mentioned visual motion capture and 3D digital human skeleton initial posture automatic matching method. The implementation scheme for solving the problem provided by the system is similar to the implementation scheme recorded in the above-mentioned method, so the specific limitations in one or more visual motion capture and 3D digital human skeleton initial posture automatic matching system embodiments provided below can refer to the limitations of the visual motion capture and 3D digital human skeleton initial posture automatic matching method above, and will not be repeated here.

[0065] In an exemplary embodiment, a visual motion capture and 3D digital human skeleton initial posture automatic matching system is provided, comprising: a rendering module and a motion capture module; the rendering module comprises: a virtual camera submodule, a first posture acquisition submodule and a data transmission submodule; the motion capture module comprises: a second posture acquisition submodule and a data processing submodule; the virtual camera submodule and the first posture acquisition submodule are connected to the data transmission submodule, and the data transmission submodule and the second posture acquisition submodule are both connected to the data processing submodule.

[0066] The virtual camera submodule is used to obtain photos of the 3D digital human in different views in the rendering environment.

[0067] The first posture acquisition submodule is used to acquire the posture data of each skeleton of the 3D digital human in the world coordinate system of the rendering end in the rendering environment.

[0068] The data transmission submodule is used to transmit photos of 3D digital humans in different views in the rendering environment, posture data of each skeleton of the 3D digital humans in the world coordinate system of the rendering end, and external parameters of the virtual camera that takes photos in each view to the motion capture module.

[0069] The second posture acquisition submodule is used to capture the posture data of each skeleton in the photo of each view in the corresponding motion capture end skeleton coordinate system in the motion capture environment according to the external parameters of the virtual camera that takes the photo of each view.

[0070] The data processing submodule is used to calculate the initial posture error of the motion capture end relative to the rendering end according to the posture data of each bone in the corresponding motion capture end skeleton coordinate system; calculate the posture data of each bone in the world coordinate system of the motion capture end according to the posture data of each bone in the corresponding motion capture end skeleton coordinate system; determine the conversion relationship between the motion capture end skeleton coordinate system and the rendering end skeleton coordinate system corresponding to each bone according to the posture data of each bone in the world coordinate system of the motion capture end and the posture data of each bone in the world coordinate system of the rendering end, as well as the conversion relationship between the world coordinate system of the motion capture end and the world coordinate system of the rendering end.

[0071] In another exemplary embodiment, the virtual camera submodule includes multiple virtual cameras. In the embodiment of the present application, it includes 6 virtual cameras.

[0072] The above-mentioned motion capture module is a multi-view visual motion capture module.

[0073] In an exemplary embodiment, a computer device is provided. The computer device may be a server or a terminal. The internal structure diagram thereof may be as follows: Figure 3As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. 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 input / output interface of the computer device is used to exchange information between the processor and an external device. The communication 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 method for automatic matching of visual motion capture and initial posture of 3D digital human skeleton is implemented.

[0074] Those skilled in the art will understand that Figure 3 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components. In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above-mentioned method embodiments when executing the computer program.

[0075] In an exemplary embodiment, a computer-readable storage medium is provided, storing a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0076] In an exemplary embodiment, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0077] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.

[0078] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM may be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0079] The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. The non-relational database may include a distributed database based on blockchain, etc., but is not limited thereto. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but is not limited thereto.

[0080] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0081] This article uses specific examples to illustrate the principles and implementation methods of this application. The description of the above embodiments is only used to help understand the method and core ideas of this application. At the same time, for those skilled in the art, according to the ideas of this application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.

Claims

1. A method for automatically matching visual motion capture and 3D digital human skeleton initial posture, characterized in that: include: In the rendering environment, obtain photos of the 3D digital human in different views, the posture data of each skeleton of the 3D digital human in the world coordinate system of the rendering end, and the external parameters of the virtual camera that takes the photos in each view; In the motion capture environment, the posture data of each skeleton in the photo of each view in the corresponding motion capture end skeleton coordinate system is captured according to the external parameters of the virtual camera that takes the photo of each view; According to the posture data of each bone in the corresponding motion capture end bone coordinate system, the initial posture error of the motion capture end relative to the rendering end is calculated; According to the posture data of each bone in the corresponding motion capture end bone coordinate system, the posture data of each bone in the motion capture end world coordinate system is calculated; According to the posture data of each bone in the world coordinate system of the motion capture end and the posture data of each bone in the world coordinate system of the rendering end, as well as the conversion relationship between the world coordinate system of the motion capture end and the world coordinate system of the rendering end, the conversion relationship between the motion capture end bone coordinate system and the rendering end bone coordinate system corresponding to each bone is determined.

2. The method for automatic matching of visual motion capture and 3D digital human skeleton initial posture according to claim 1, characterized in that: The formula for calculating the initial posture error of the motion capture end relative to the rendering end is: T i,PoseError =inverse(T i,lm ); Among them, T i,PoseError is the initial posture error of the motion capture end relative to the rendering end of the skeleton i, T i,lm is the posture data of bone i in the corresponding motion capture end bone coordinate system, and inverse() is the inverse function.

3. The method for automatic matching of visual motion capture and 3D digital human skeleton initial posture according to claim 1, characterized in that: The conversion relationship between the motion capture end skeleton coordinate system and the rendering end skeleton coordinate system is: T i,Coordinate =inverse(T i,wr )×T rm ×T i,wm ; Among them, T i,Corrdinate is the conversion relationship between the motion capture end bone coordinate system and the rendering end bone coordinate system corresponding to bone i, T i,wr is the posture data of bone i in the world coordinate system of the rendering end, T rm is the conversion relationship between the world coordinate system of the rendering end and the world coordinate system of the motion capture end, T i,wm is the posture data of bone i in the world coordinate system of the motion capture end, and inverse() is the inverse function.

4. The method for automatic matching of visual motion capture and 3D digital human skeleton initial posture according to claim 1, characterized in that: In the motion capture environment, the posture data of each skeleton in the photo of each view in the corresponding motion capture end skeleton coordinate system is captured according to the external parameters of the virtual camera that takes the photo of each view, including: In the motion capture environment, the external parameters of the multi-view visual motion capture module in the motion capture environment are set according to the external parameters of the virtual camera of the photo in each view, and the posture data of each bone in the photo in each view in the corresponding motion capture end bone coordinate system is captured.

5. A visual motion capture and 3D digital human skeleton initial posture automatic matching system, characterized in that: The visual motion capture and 3D digital human skeleton initial posture automatic matching system is used to execute the visual motion capture and 3D digital human skeleton initial posture automatic matching method according to any one of claims 1 to 4, and the visual motion capture and 3D digital human skeleton initial posture automatic matching system comprises: a rendering module and a motion capture module; The rendering module includes: a virtual camera submodule, a first posture acquisition submodule and a data transmission submodule; the motion capture module includes: a second posture acquisition submodule and a data processing submodule; The virtual camera submodule is used to obtain photos of the 3D digital human in different views in the rendering environment; The first posture acquisition submodule is used to acquire the posture data of each skeleton of the 3D digital human in the world coordinate system of the rendering end in the rendering environment; The data transmission submodule is used to transmit the photos of the 3D digital human in different views in the rendering environment, the posture data of each skeleton of the 3D digital human in the world coordinate system of the rendering end, and the external parameters of the virtual camera that takes the photos in each view to the motion capture module; The second posture acquisition submodule is used to capture the posture data of each skeleton in the photo under each view in the corresponding motion capture end skeleton coordinate system according to the external parameters of the virtual camera that takes the photo under each view in the motion capture environment; The data processing submodule is used to calculate the initial posture error of the motion capture end relative to the rendering end according to the posture data of each bone in the corresponding motion capture end skeleton coordinate system; calculate the posture data of each bone in the world coordinate system of the motion capture end according to the posture data of each bone in the corresponding motion capture end skeleton coordinate system; determine the conversion relationship between the motion capture end skeleton coordinate system and the rendering end skeleton coordinate system corresponding to each bone according to the posture data of each bone in the world coordinate system of the motion capture end and the posture data of each bone in the world coordinate system of the rendering end, as well as the conversion relationship between the world coordinate system of the motion capture end and the world coordinate system of the rendering end.

6. The visual motion capture and 3D digital human skeleton initial posture automatic matching system according to claim 5, characterized in that: The virtual camera submodule includes a plurality of virtual cameras; In the rendering environment, a plurality of virtual cameras are arranged around the 3D digital human.

7. The visual motion capture and 3D digital human skeleton initial posture automatic matching system according to claim 6, characterized in that: In the motion capture environment, a multi-view visual motion capture module is provided. During motion capture, the external parameters of the multi-view visual motion capture module are respectively set to be consistent with the external parameters of each virtual camera.

8. A computer device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the method for automatic matching of visual motion capture and 3D digital human skeleton initial posture according to any one of claims 1 to 4.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for automatic matching of visual motion capture and 3D digital human skeleton initial posture described in any one of claims 1 to 4 is implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the method for automatic matching of visual motion capture and 3D digital human skeleton initial posture described in any one of claims 1 to 4 is implemented.

Images