Motion capture data processing method and device

Abstract

The invention provides a motion capture data processing method and device, and the method comprises the steps: obtaining at least two initial motion capture video frames, and determining a first part length corresponding to a target object and a target motion capture video frame corresponding to the first part length in each initial motion capture video frame; collecting a second part length in each initial motion capture video frame, and determining a motion state corresponding to the target object in each initial motion capture video frame according to the second part length and the first part length corresponding to each initial motion capture video frame; based on the motion state corresponding to each initial motion capture video frame, determining a motion capture video frame to be processed in each initial motion capture video frame, and collecting initial motion capture parameter information of each motion capture video frame to be processed; and adjusting each initial motion capture parameter information according to the target motion capture video frame, and obtaining target motion capture parameter information corresponding to each to-be-processed motion capture video frame. And performing targeted adjustment on the motion capture data by determining the motion state of the target object in the initial motion capture video frame.

Description

Technical Field

[0001] This application relates to the field of computer technology, and particularly to a method for processing motion capture data. Background Art

[0002] With the wide application of video motion capture technology, it plays an important role in fields such as film and television production, game development, virtual reality, etc.

[0003] However, currently when capturing the actions of an object, the problem of the object's sole slipping easily occurs. This is because during the forward and backward movement of the object, the position is not fixed, and the directly inferred depth information of the object is unstable. According to the visual effect of objects being larger when closer and smaller when farther away, when restoring to the 3D space, the soles of the object are prone to deviate from the ground, seriously affecting the accuracy and realism of motion capture.

[0004] Therefore, how to stably correct the sole slipping of the object in video motion capture has become a technical problem that needs to be urgently solved by those skilled in the art. Summary of the Invention

[0005] In view of this, the embodiments of this application provide a method for processing motion capture data to solve the technical defects existing in the prior art. The embodiments of this application also provide a device for processing motion capture data, a computing device, a computer-readable storage medium, and a computer program product.

[0006] According to the first aspect of the embodiments of this application, a method for processing motion capture data is provided, including: Obtaining at least two initial motion capture video frames, and determining the length of the first part corresponding to the target object and the target motion capture video frame corresponding to the length of the first part in each initial motion capture video frame; Collecting the length of the second part in each initial motion capture video frame, and determining the motion state of the target object in each initial motion capture video frame according to the length of the second part corresponding to each initial motion capture video frame and the length of the first part; Based on the motion state corresponding to each initial motion capture video frame, determining the motion capture video frames to be processed in each initial motion capture video frame, and collecting the initial motion capture parameter information of each motion capture video frame to be processed; Adjusting each initial motion capture parameter information according to the target motion capture video frame to obtain the target motion capture parameter information corresponding to each motion capture video frame to be processed.

[0007] According to the second aspect of the embodiments of this application, a device for processing motion capture data is provided, including: An obtaining module, configured to obtain at least two initial motion capture video frames, and determine the length of the first part corresponding to the target object and the target motion capture video frame corresponding to the length of the first part in each initial motion capture video frame; An acquisition module, configured to acquire the length of the second part in each initial motion capture video frame, and determine the motion state of the target object in each initial motion capture video frame according to the length of the second part corresponding to each initial motion capture video frame and the length of the first part; A determination module, configured to determine a to-be-processed motion capture video frame in each initial motion capture video frame based on the motion state corresponding to each initial motion capture video frame, and acquire the initial motion capture parameter information of each to-be-processed motion capture video frame; An adjustment module, configured to adjust the initial motion capture parameter information according to the target motion capture video frame to obtain the target motion capture parameter information corresponding to each to-be-processed motion capture video frame.

[0008] According to the third aspect of the embodiments of the present application, a computing device is provided, including: A memory and a processor; The memory is used to store computer-executable instructions, and when the processor executes the computer-executable instructions, the steps of the method for processing motion capture data are implemented.

[0009] According to the fourth aspect of the embodiments of the present application, a computer-readable storage medium is provided, which stores computer-executable instructions, and when the instructions are executed by a processor, the steps of the method for processing motion capture data are implemented.

[0010] According to the fifth aspect of the embodiments of the present application, a chip is provided, which stores a computer program, and when the computer program is executed by the chip, the steps of the method for processing motion capture data are implemented.

[0011] According to the sixth aspect of the embodiments of the present specification, a computer program product is provided, including a computer program or instructions, and when the computer program or instructions are executed by a processor, the steps of the above-mentioned method for processing motion capture data are implemented.

[0012] Method for processing motion capture data of this application. Obtain at least two initial motion capture video frames, determine the length of the first part corresponding to the target object and the target motion capture video frame corresponding to the length of the first part in each initial motion capture video frame; collect the length of the second part in each initial motion capture video frame, and determine the motion state of the target object corresponding to each initial motion capture video frame according to the length of the second part corresponding to each initial motion capture video frame and the length of the first part; based on the motion state corresponding to each initial motion capture video frame, determine the motion capture video frames to be processed in each initial motion capture video frame, and collect the initial motion capture parameter information of each motion capture video frame to be processed; adjust the initial motion capture parameter information according to the target motion capture video frame to obtain the target motion capture parameter information corresponding to each motion capture video frame to be processed. Determine the motion state of the target object through the length of the first part and the length of the second part of each initial motion capture video frame, so as to select the motion capture video frames to be processed that need to be adjusted to avoid sole slippage based on the motion state, and then adjust the initial motion capture parameter information of the motion capture video frames to be processed, so as to obtain the target motion capture parameter information that can avoid the problem of sole slippage during the generation of the three-dimensional video, improve the quality of the motion capture data, reduce the workload and cost of video repair, and improve the efficiency of video production. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] Figure 1 is a schematic diagram of a scenario of a method for processing motion capture data provided by an embodiment of this application; Figure 2 is a flowchart of a method for processing motion capture data provided by an embodiment of this application; Figure 3 is a processing flowchart of a method for processing motion capture data provided by an embodiment of this application; Figure 4 is a schematic structural diagram of a device for processing motion capture data provided by an embodiment of this application; Figure 5 is a structural block diagram of a computing device provided by an embodiment of this application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0014] Many specific details are set forth in the following description in order to provide a thorough understanding of this application. However, this application can be implemented in many other ways different from those described herein, and those skilled in the art can make similar generalizations without departing from the connotation of this application. Therefore, this application is not limited by the specific implementations disclosed below.

[0015] The terms used in one or more embodiments of the present application are for the purpose of describing specific embodiments only and are not intended to limit one or more embodiments of the present application. The singular forms "a", "the", and "said" used in one or more embodiments of the present application and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term "and / or" used in one or more embodiments of the present application refers to and includes any or all possible combinations of one or more of the associated listed items.

[0016] It should be understood that although the terms first, second, etc. may be used in one or more embodiments of the present application to describe various information, such information should not be limited to these terms. These terms are only used to distinguish information of the same type from each other. For example, without departing from the scope of one or more embodiments of the present application, the first may also be referred to as the second, and similarly, the second may also be referred to as the first.

[0017] First, the noun terms related to one or more embodiments of the present application are explained.

[0018] Median filtering algorithm: It is a non-linear smoothing filtering algorithm mainly used to remove salt-and-pepper noise and impulse noise in images or signals.

[0019] In the present application, a method for processing motion capture data is provided. The present application also relates to a device for processing motion capture data, a computing device, a computer-readable storage medium, and a computer program product, which will be described in detail one by one in the following embodiments.

[0020] Figure 1 A schematic diagram of a scenario of a method for processing motion capture data according to an embodiment of the present application is shown, which specifically includes: using video frames in a two-dimensional action video as initial motion capture video frames, where the two-dimensional action video contains a target object; scanning each initial motion capture video frame to obtain the corresponding original first part length of each initial motion capture video frame, that is, the distance from the hip to the heel of the target object, and obtaining the original first part lengths L1, L2... Ln corresponding to each initial action video frame; sorting the original first part lengths from largest to smallest, selecting the original first part length at the head of the queue as the first part length L, and determining the initial motion capture video frame corresponding to the first part length L as the target motion capture video frame; determining the distance d from the knee to the heel of the target object in the target motion capture video frame as the standard second part length D.

[0021] Further, scan each initial motion capture video frame to determine the length of the second body part corresponding to each initial motion capture video, that is, the distance from the target object's knee to the heel, and obtain the lengths of the second body part d1, d2... dn corresponding to each initial motion capture video frame; calculate the ratio of each second body part length to the standard second body part length D to obtain the ratios d1 / D, d2 / D... dn / D corresponding to each initial motion capture video frame. Determine that the target object in the initial motion capture video frame with a ratio less than the preset length ratio is in a leg-lifting state, and the ratio greater than or equal to the preset length ratio is in a leg-landing state. To improve accuracy, the distance from the left knee of the target object to the sole of the foot and the distance from the right knee of the target object to the sole of the foot can be collected respectively, so as to judge the motion states of the left and right legs respectively. Select the initial motion capture video frames in which the target object is in a leg-landing state as the to-be-processed motion capture video frames for subsequent adjustment.

[0022] Collect the standard motion capture parameter information in the target motion capture video frame and the initial motion capture parameter information in each to-be-processed motion capture video frame, and adjust each initial motion capture parameter information based on the standard motion capture parameter information. Specifically, obtain the longitudinal standard motion capture parameter information in the standard motion capture parameter information and the longitudinal initial motion capture parameter information in each initial motion capture parameter information, and adjust each longitudinal initial motion capture parameter information to be consistent with the longitudinal standard motion capture parameter information to obtain the target motion capture parameter information corresponding to each to-be-processed motion capture video frame. Preferably, to avoid abnormal key point recognition caused by large-amplitude movements of the person in the video, the horizontal initial motion capture parameter information and the predicted vertical initial motion capture parameter information in each initial motion capture parameter information can also be obtained, and the median filtering algorithm is used to filter and denoise the horizontal initial motion capture parameter information and the vertical initial motion capture parameter information to obtain the corrected target motion capture parameter information. The corrected target motion capture parameter information can be used to generate a three-dimensional action video.

[0023] Method for processing motion capture data of the present application, obtaining at least two initial motion capture video frames, determining a first part length corresponding to a target object and a target motion capture video frame corresponding to the first part length in each initial motion capture video frame; collecting a second part length in each initial motion capture video frame, and determining a motion state corresponding to the target object in each initial motion capture video frame according to the second part length and the first part length corresponding to each initial motion capture video frame; based on the motion state corresponding to each initial motion capture video frame, determining a to-be-processed motion capture video frame in each initial motion capture video frame, and collecting initial motion capture parameter information of each to-be-processed motion capture video frame; adjusting the initial motion capture parameter information according to the target motion capture video frame to obtain target motion capture parameter information corresponding to each to-be-processed motion capture video frame. The motion state corresponding to the target object is determined by the first part length and the second part length of each initial motion capture video frame, so as to select, based on the motion state, a to-be-processed motion capture video frame that needs to be adjusted to avoid sole slippage, and then adjust the initial motion capture parameter information of the to-be-processed motion capture video frame, so as to obtain target motion capture parameter information that can avoid the problem of sole slippage during the generation of a three-dimensional video.

[0024] Figure 2 The flowchart shows a method for processing motion capture data provided by an embodiment of the present application, which specifically includes the following steps: Step 202: Obtain at least two initial motion capture video frames, and determine a first part length corresponding to a target object and a target motion capture video frame corresponding to the first part length in each initial motion capture video frame.

[0025] Among them, the initial motion capture video frame refers to a video frame parsed from a two-dimensional video containing motion capture data; the target object refers to an object shown in the initial motion capture video frame; the first part length refers to the length of the first part of the target object in each initial motion capture video frame, and the first part refers to a part of the target object; the target motion capture video frame refers to the initial motion capture video frame corresponding to the first part length.

[0026] Specifically, parse a two-dimensional video containing motion capture data of the target object to obtain at least two initial motion capture video frames; screen the first part length corresponding to the target object according to each initial motion capture video frame, and use the initial motion capture video frame containing the first part length as the target motion capture video frame.

[0027] In practical applications, determining a first part length corresponding to a target object and a target motion capture video frame corresponding to the first part length in each initial motion capture video frame includes: Collect the original first part length corresponding to the target object in each initial motion capture video frame; Sort the original first part lengths according to the length, and determine the first part length based on the sorting result; Use the initial motion capture video frame corresponding to the length of the first part as the target motion capture video frame.

[0028] Among them, the original length of the first part refers to the distance from the hip to the heel of the target object in each initial motion capture video frame; the sorting result refers to the queue obtained by sorting the original lengths of the first part according to the length.

[0029] Specifically, scan the original length of the first part corresponding to the target object in each initial motion capture video frame, that is, collect the distance from the hip to the heel of the target object in each initial motion capture video frame; sort the original lengths of the first part from largest to smallest according to the length to obtain the sorted queue, and use the original length of the first part at the head of the queue as the length of the first part; use the initial motion capture video frame corresponding to the length of the first part as the target motion capture video frame.

[0030] In a specific embodiment of the present application, scan the initial motion capture video frames 1, 2, and 3; respectively collect the distances from the hip to the heel of the target object in each initial motion capture video frame, and obtain the original lengths of the first part as 5, 6, and 7 respectively; sort the original lengths of the first part from largest to smallest according to the length, and select the original length of the first part 7 at the head of the queue as the length of the first part; use the initial motion video frame 3 corresponding to the length of the first part 7 as the target motion capture video frame.

[0031] By selecting the original length of the first part at the head of the queue as the length of the first part, the length of the first part is used as the benchmark for the standing state of the target object, so as to subsequently judge the motion state of the target object based on the length of the first part.

[0032] Furthermore, collecting the original length of the first part corresponding to the target object in each initial motion capture video frame includes: Determine the initial target motion capture video frame in each initial motion capture video frame; Collect the hip coordinates and heel coordinates of the target object in the initial target motion capture video frame; Calculate the original length of the first part corresponding to the initial target motion capture video frame according to the hip coordinates and the heel coordinates.

[0033] Among them, the initial target motion capture video frame refers to any one of the initial motion capture video frames; the hip coordinates refer to the coordinates of the center point of the target object's hip in the initial target motion capture video frame; the heel coordinates refer to the coordinates of the target object's heel in the initial target motion capture video frame.

[0034] Specifically, an initial motion capture video frame is arbitrarily selected from each of the initial motion capture video frames as the initial target motion capture video frame; the hip coordinates and heel coordinates of the target object in this initial target motion capture video frame are collected; based on the distance calculation formula, the hip coordinates, and the heel coordinates, a distance value is calculated as the original first part length corresponding to this initial target motion capture video frame. In practical applications, to improve the calculation efficiency, the difference between the hip coordinates and the heel coordinates on the y-axis can also be calculated as the original first part length. The remaining initial motion capture video frames are all processed according to the above operations for the initial target motion capture video frame, so as to obtain the original first part lengths corresponding to each initial motion capture video frame.

[0035] In a specific embodiment of the present application, video frame 1 is selected as the initial target motion capture video frame from each of the initial motion capture video frames; the hip y-axis coordinate and the heel y-axis coordinate of the target object in video frame 1 are collected; the distance between the hip y-axis coordinate and the heel y-axis coordinate is calculated as the original first part length corresponding to video frame 1.

[0036] By calculating the distance between the hip and the heel of the target object on the y-axis, the calculation efficiency of the distance is improved, and further the efficiency of obtaining each original first part length is improved.

[0037] Step 204: Collect the second part lengths in each of the initial motion capture video frames, and determine the motion state of the target object corresponding to each of the initial motion capture video frames according to the second part lengths and the first part lengths corresponding to each of the initial motion capture video frames.

[0038] Among them, the second part length refers to the part length of the part other than the first part on the target object; the second part refers to the part other than the first part on the target object; the motion state refers to the motion state of the legs of the target object, including the leg-lifting state and the leg-lowering state.

[0039] In practical applications, collecting the second part lengths in each of the initial motion capture video frames includes: Determine the initial target motion capture video frame in each of the initial motion capture video frames; Collect the knee coordinates and heel coordinates of the target object in the initial target motion capture video frame; Calculate the second part length corresponding to the initial target motion capture video frame according to the knee coordinates and the heel coordinates.

[0040] Among them, the initial target motion capture video frame refers to any one of the initial motion capture video frames; the knee coordinates refer to the coordinates of the target object's knee in the initial target motion capture video frame; the heel coordinates refer to the coordinates of the target object's heel in the initial target motion capture video frame.

[0041] Specifically, randomly select an initial motion capture video frame from each of the initial motion capture video frames as the initial target motion capture video frame; collect the knee coordinates and heel coordinates of the target object in this initial target motion capture video frame; calculate a distance value based on the distance calculation formula, the knee coordinates, and the heel coordinates as the length of the second part corresponding to this initial target motion capture video frame; process the remaining initial motion capture video frames according to the above operations for the initial target motion capture video frame, so as to obtain the length of the second part corresponding to each initial motion capture video frame.

[0042] In a specific embodiment of the present application, select video frame 1 as the initial target motion capture video frame from each of the initial motion capture video frames; collect the knee coordinates and heel coordinates of the target object in video frame 1; calculate the distance between the knee coordinates and the heel coordinates as the length of the second part corresponding to video frame 1.

[0043] Use the distance between the knee coordinates and the heel coordinates as the length of the second part to determine the motion data of the target object, for subsequent determination of the motion state of each initial motion capture video frame based on the lengths of each second part.

[0044] Preferably, since the target object will include two or more legs and thus correspond to two or more heels, at this time, it is necessary to determine the length of the second part corresponding to each leg separately. That is, the heel coordinates may include the left heel coordinates and the right heel coordinates. Calculating the length of the second part corresponding to the initial target motion capture video frame according to the knee coordinates and the heel coordinates includes: Calculate the left part length according to the knee coordinates and the left heel coordinates, and calculate the right part length according to the knee coordinates and the right heel coordinates; Use the left part length and the right part length as the length of the second part corresponding to the initial target motion capture video frame.

[0045] Among them, the left heel coordinates refer to the coordinates of the left heel of the target object in the initial target motion capture video frame; the right heel coordinates refer to the coordinates of the right heel of the target object in the initial target motion capture video frame; the left part length refers to the distance between the left knee coordinates and the left heel, and the right part length refers to the distance between the right knee coordinates and the right heel.

[0046] Specifically, calculate the left part length according to the left knee coordinates, the left heel coordinates in the knee coordinates, and the distance calculation formula; calculate the right part length according to the right knee coordinates, the right heel coordinates in the knee coordinates, and the distance calculation formula; use both the left part length and the right part length as the length of the second part corresponding to the initial target motion capture video frame, so as to realize the independent processing of the left foot or the right foot subsequently.

[0047] In a specific embodiment of the present application, video frame 1 is selected as the initial target motion capture video frame from each initial motion capture video frame. Among them, the object included in the initial target motion capture video is a human object; the left knee coordinate and left heel coordinate of the target object in video frame 1 are respectively collected, as well as the right knee coordinate and right heel coordinate; the left part length is calculated according to the left knee coordinate and left heel coordinate, and the right part length is calculated according to the right knee coordinate and right heel coordinate; the left part length and the right part length are used as the second part length corresponding to video frame 1.

[0048] By respectively obtaining the left part length and the right part length corresponding to the left and right feet as the second part length, so as to subsequently judge the motion state of each leg respectively, thereby realizing the separate control of each leg and improving the accuracy of correction.

[0049] Furthermore, determining the motion state corresponding to the target object in each initial motion capture video frame according to the second part length and the first part length corresponding to each initial motion capture video frame includes: Determining the standard second part length in the target motion capture video frame corresponding to the first part length; Respectively calculating the ratio of the second part length corresponding to each initial motion capture video frame to the standard second part length to obtain the length ratio corresponding to each initial motion capture video frame; Comparing each length ratio with a preset length ratio respectively; In the case where the length ratio is greater than or equal to the preset length ratio, determining the motion state of the initial motion capture video frame as the leg landing state; In the case where the length ratio is less than the preset length ratio, determining the motion state of the initial motion capture video frame as the leg lifting state.

[0050] Among them, the standard second part length refers to the second part length of the target motion capture video frame. In the case where the target object has left and right legs, the standard left part length and the standard right part length can be set to judge the motion states of the left and right legs respectively; the length ratio refers to the ratio of the second part length of each initial motion capture video frame to the standard second part length; the preset length ratio refers to the preset length ratio. In practical applications, the preset length ratio is determined by statistically analyzing a certain number of video motion capture data. Preferably, the preset length ratio is 0.5; the leg landing state refers to the state where the heel of the target object touches the ground; the leg lifting state refers to the state where the target object lifts any one leg or all legs.

[0051] Specifically, determine the knee coordinates and heel coordinates in the target motion capture video frame, and calculate the length of the second part corresponding to the target motion capture video frame based on the knee coordinates and heel coordinates as the standard second part length; when the target person has left and right feet, calculate the standard left part length corresponding to the target motion capture video frame based on the left knee coordinates and left heel coordinates, and calculate the standard right part length corresponding to the target motion capture video frame based on the right knee coordinates and right heel coordinates; calculate the ratio of the length of the second part of each initial motion capture video frame to the standard second part length respectively, and determine the length ratio corresponding to each initial motion capture video frame; compare the length ratios with the preset length ratios respectively, and determine the target object with the length ratio greater than or equal to the preset length ratio as the leg landing state, and determine the target object with the length ratio less than the preset length ratio as the leg lifting state.

[0052] In a specific embodiment of the present application, obtain the knee coordinates and heel coordinates of the target object in the target motion capture video frame, and calculate and obtain the standard second part length D based on the knee coordinates and heel coordinates; calculate the ratios of the initial motion capture video frames 1, 2, and 3 to the standard second part length D respectively, and obtain the length ratios corresponding to the initial motion capture video frames 1, 2, and 3 as 0.8, 0.9, and 0.4 respectively; the preset length ratio is 0.5, compare the length ratio with the preset length ratio, and determine that the motion states of the initial motion capture video frames 1 and 2 are the leg landing state, and the motion state of the initial motion capture video frame 3 is the leg lifting state.

[0053] By calculating the ratio of the length of the second part in each initial motion capture video frame to the standard second part length corresponding to the target object in the standing state determined in advance, and comparing it with the preset length ratio, determine the motion state of the target object in each initial motion capture video frame, which is convenient for subsequent correction of the initial motion capture video frames corresponding to the target object in a specific motion state.

[0054] Step 206: Based on the motion state corresponding to each initial motion capture video frame, determine the to-be-processed motion capture video frames in each initial motion capture video frame, and collect the initial motion capture parameter information of each to-be-processed motion capture video frame.

[0055] Among them, the to-be-processed motion capture video frame refers to the video frame that needs to be corrected in each initial motion capture video frame; the initial motion capture parameter information refers to the action parameter information of the target object in the to-be-processed motion capture video frame, such as the coordinate information of the target object, the direction information of parts such as legs and feet, and so on.

[0056] In practical applications, based on the motion state corresponding to each initial motion capture video frame, determining the to-be-processed motion capture video frames in each initial motion capture video frame includes: Determine the initial motion capture video frames with the motion state of the leg landing state as the to-be-processed motion capture video frames.

[0057] Specifically, the problem to be solved in this application is that there will be a problem of foot sliding when the target object is mapped from two dimensions to three dimensions. Therefore, it is necessary to correct the deviated feet to solve this problem. Therefore, this application selects the initial motion capture video frame with the leg landing state as the motion capture video frame to be processed, so as to eliminate the offsets existing in the motion capture video frame to be processed in the subsequent process. In a specific embodiment of this application, following the above example, if the motion state of the initial motion capture video frame 3 is determined to be the leg lifting state, then the initial motion capture video frame 3 is used as the motion capture video frame to be processed.

[0058] By using the initial motion capture video frame with the leg landing state as the motion capture video frame to be processed, it is only necessary to correct the motion capture video frame to be processed in the subsequent process, thereby improving the efficiency of correcting the foot sliding problem in the subsequent process.

[0059] Step 208: Adjust each initial motion capture parameter information according to the target motion capture video frame to obtain the target motion capture parameter information corresponding to each motion capture video frame to be processed.

[0060] Among them, the target motion capture parameter information refers to the motion capture parameter information obtained by adjusting each initial motion capture parameter information according to the target motion capture video frame.

[0061] In practical applications, adjusting each initial motion capture parameter information according to the target motion capture video frame to obtain the target motion capture parameter information corresponding to each motion capture video frame to be processed includes: Obtain the standard motion capture parameter information corresponding to the target motion capture video frame; Based on the standard motion capture parameter information, adjust each initial motion capture parameter information to obtain the target motion capture parameter information corresponding to each motion capture video frame to be processed.

[0062] Among them, the standard motion capture parameter information refers to the motion capture parameter information corresponding to the target motion capture video frame, such as the coordinate information of the target object in the target motion capture video frame, the direction information of parts such as legs and feet, and so on.

[0063] Specifically, the target object in the target motion capture video frame is selected as the standing standard through screening. Therefore, the standard motion capture parameter information corresponding to the target motion capture video frame is the standard value in the state where the target object's feet land. Each initial motion capture parameter information can be adjusted based on the standard motion capture parameter information of the target motion capture video frame, that is, adjust the initial motion capture parameter information in the direction without offset.

[0064] Further, adjusting each initial motion capture parameter information based on the standard motion capture parameter information to obtain the target motion capture parameter information corresponding to each motion capture video frame to be processed includes: Obtain the longitudinal standard motion capture parameter information in the standard motion capture parameter information, and the longitudinal initial motion capture parameter information in each initial motion capture parameter information; Adjust each longitudinal initial motion capture parameter information to be consistent with the longitudinal standard motion capture parameter information, and obtain the target motion capture parameter information corresponding to each to-be-processed motion capture video frame.

[0065] Among them, the longitudinal standard motion capture parameter information refers to the motion parameter information of the target object in the y-axis direction in the target motion capture video frame; the longitudinal initial motion capture parameter information refers to the motion parameter information of the target object in the y-axis direction in the initial motion capture parameter information.

[0066] Specifically, the standard motion capture parameter information includes longitudinal standard motion capture parameter information, lateral standard motion capture parameter information, and predicted vertical standard motion capture parameter information; the initial motion capture parameter information includes longitudinal initial motion capture parameter information, lateral initial motion capture parameter information, and predicted vertical initial motion capture parameter information; in order to adjust the sole sliding offset, it is necessary to eliminate the longitudinal offset, that is, eliminate the direction offset of the y-axis; therefore, the longitudinal initial motion capture parameter information is adjusted to be consistent with the longitudinal standard motion capture parameter information, so as to eliminate the offset in the y-axis direction and obtain the target motion capture parameter information.

[0067] In a specific embodiment of the present application, obtain the standard y-axis offset direction information in the standard motion capture parameter information corresponding to the target motion capture video frame, and obtain the y-axis offset direction information in the initial motion capture parameter information corresponding to each to-be-processed motion capture video frame; compare each y-axis offset direction information with the standard y-axis offset direction information, if there is a difference between the y-axis offset direction information and the standard y-axis offset direction information, then adjust the y-axis offset direction information until it is consistent with the standard y-axis offset direction information, and after the adjustment is completed, obtain the target motion capture parameter information corresponding to each to-be-processed motion capture video frame.

[0068] Preferably, the lateral initial motion capture parameter information and the predicted vertical initial motion capture parameter information included in the initial motion capture parameter information can also be filtered and denoised by a filtering algorithm (such as a median filtering algorithm) to avoid abnormal key point recognition caused by large-scale movement of the object in the video.

[0069] By adjusting the longitudinal initial motion capture parameter information to be consistent with the longitudinal standard motion capture parameter information, the offset in the longitudinal direction of the target object in the leg landing state is eliminated, so that a three-dimensional video in which the object action does not have sole sliding can be generated based on the target motion capture parameter information later.

[0070] In practical applications, after adjusting each initial motion capture parameter information according to the target motion capture video frame and obtaining the target motion capture parameter information corresponding to each to-be-processed motion capture video frame, it further includes: Generate a three-dimensional video corresponding to the target object based on the target motion capture parameter information corresponding to each to-be-processed motion capture video frame.

[0071] Specifically, based on the target motion capture parameter information corresponding to the motion capture video frame to be processed, and the initial motion capture parameter information corresponding to the non-target motion capture video frames in each initial motion capture video frame, a three-dimensional video corresponding to the target object is generated.

[0072] By generating a three-dimensional video based on the corrected target motion capture parameter information, it is possible to avoid the problem that the target object in the generated three-dimensional video has a sole slip that affects authenticity, improve the data quality of the video motion capture data, and reduce the repair workload and cost in the later video production.

[0073] The method for processing motion capture data of this application obtains at least two initial motion capture video frames, determines the length of the first part corresponding to the target object and the target motion capture video frame corresponding to the length of the first part in each initial motion capture video frame; collects the length of the second part in each initial motion capture video frame, and determines the motion state of the target object in each initial motion capture video frame according to the length of the second part and the length of the first part corresponding to each initial motion capture video frame; based on the motion state corresponding to each initial motion capture video frame, determines the motion capture video frame to be processed in each initial motion capture video frame, and collects the initial motion capture parameter information of each motion capture video frame to be processed; adjusts the initial motion capture parameter information according to the target motion capture video frame to obtain the target motion capture parameter information corresponding to each motion capture video frame to be processed. By determining the motion state of the target object through the length of the first part and the length of the second part of each initial motion capture video frame, the motion capture video frame to be processed that needs to be adjusted to avoid sole slip is selected based on the motion state, and then the initial motion capture parameter information of the motion capture video frame to be processed is adjusted, so as to obtain the target motion capture parameter information that can avoid the generation of sole slip problems when generating a three-dimensional video, improve the quality of the motion capture data, reduce the workload and cost of video repair, and improve the efficiency of video production.

[0074] The following combines the attached Figure 3 Taking the application of the method for processing motion capture data provided by this application in a human action video as an example, the method for processing motion capture data is further described. Among them, Figure 3 The processing flow chart of a method for processing motion capture data provided by an embodiment of this application is shown, specifically including the following steps: Step 302: Parse the human action video to obtain at least two initial motion capture video frames, and determine the initial target motion capture video frame in each initial motion capture video frame.

[0075] Step 304: Collect the hip coordinates and heel coordinates of the human object in the initial target motion capture video frame, and calculate the original first part length corresponding to the initial target motion capture video frame according to the hip coordinates and heel coordinates.

[0076] Step 306: Obtain the original first part lengths corresponding to each initial motion capture video frame, sort the original first part lengths from largest to smallest, select the original first part length at the head of the queue as the first part length, and use the initial motion capture video frame corresponding to the first part length as the target motion capture video frame.

[0077] Step 308: Collect the knee coordinates and heel coordinates of the human object in the initial target motion capture video frame, calculate the left part length based on the left knee coordinate and left heel coordinate, and calculate the right part length based on the right knee coordinate and right heel coordinate; use the left part length and the right part length as the second part lengths corresponding to the initial target motion capture video frame.

[0078] Step 310: Determine the standard second part length that includes the standard left part length and the standard right part length in the target motion capture video frame, and determine the motion state of the human object in each initial motion capture video frame according to the lengths of the second part lengths corresponding to each initial motion capture video frame and the standard second part length, as well as a preset length ratio.

[0079] Specifically, calculate the ratios of the second part lengths corresponding to each initial motion capture video frame to the standard second part length respectively to obtain the length ratios corresponding to each initial motion capture video frame; compare each length ratio with the preset length ratio respectively; when the length ratio is greater than or equal to the preset length ratio, determine that the motion state of the initial motion capture video frame is the leg landing state; when the length ratio is less than the preset length ratio, determine that the motion state of the initial motion capture video frame is the leg raising state.

[0080] Step 312: Determine the initial motion capture video frames with the motion state of the leg landing state as the motion capture video frames to be processed, and collect the initial motion capture parameter information of each motion capture video frame to be processed.

[0081] Step 314: Obtain the longitudinal standard motion capture parameter information in the standard motion capture parameter information, and the longitudinal initial motion capture parameter information in each initial motion capture parameter information.

[0082] Step 316: Adjust each longitudinal initial motion capture parameter information to be consistent with the longitudinal standard motion capture parameter information, and perform filtering and noise reduction on the lateral initial motion capture parameter information and the predicted vertical initial motion capture parameter information in the initial motion capture parameter information based on a filtering algorithm to obtain the target motion capture parameter information corresponding to each motion capture video frame to be processed.

[0083] Step 318: Generate a three-dimensional video corresponding to the human object based on the target motion capture parameter information corresponding to each motion capture video frame to be processed.

[0084] Method for processing motion capture data of this application, obtaining at least two initial motion capture video frames, determining the length of the first part corresponding to the target object and the target motion capture video frame corresponding to the length of the first part in each initial motion capture video frame; collecting the length of the second part in each initial motion capture video frame, and determining the motion state of the target object corresponding to each initial motion capture video frame according to the length of the second part corresponding to each initial motion capture video frame and the length of the first part; based on the motion state corresponding to each initial motion capture video frame, determining the motion capture video frames to be processed in each initial motion capture video frame, and collecting the initial motion capture parameter information of each motion capture video frame to be processed; adjusting the initial motion capture parameter information according to the target motion capture video frame to obtain the target motion capture parameter information corresponding to each motion capture video frame to be processed. Determine the motion state of the target object through the length of the first part and the length of the second part of each initial motion capture video frame, so as to select the motion capture video frames to be processed that need to be adjusted to avoid slipping of the soles of the feet based on the motion state, and then adjust the initial motion capture parameter information of the motion capture video frames to be processed, so as to obtain the target motion capture parameter information that can avoid the problem of slipping of the soles of the feet when generating a three-dimensional video.

[0085] Corresponding to the above method embodiment, this application also provides an embodiment of a device for processing motion capture data. Figure 4 The structural schematic diagram of a device for processing motion capture data provided by an embodiment of this application is shown. As Figure 4 shown, the device includes: An acquisition module 402, configured to acquire at least two initial motion capture video frames, and determine the length of the first part corresponding to the target object and the target motion capture video frame corresponding to the length of the first part in each initial motion capture video frame; A collection module 404, configured to collect the length of the second part in each initial motion capture video frame, and determine the motion state of the target object corresponding to each initial motion capture video frame according to the length of the second part corresponding to each initial motion capture video frame and the length of the first part; A determination module 406, configured to determine the motion capture video frames to be processed in each initial motion capture video frame based on the motion state corresponding to each initial motion capture video frame, and collect the initial motion capture parameter information of each motion capture video frame to be processed; An adjustment module 408, configured to adjust the initial motion capture parameter information according to the target motion capture video frame to obtain the target motion capture parameter information corresponding to each motion capture video frame to be processed.

[0086] In a specific embodiment of this application, the acquisition module 402 is further configured to: Collect the original length of the first part corresponding to the target object in each initial motion capture video frame; Sort the original lengths of the first part according to the length, and determine the length of the first part based on the sorting result; Use the initial motion capture video frame corresponding to the length of the first part as the target motion capture video frame.

[0087] In a specific embodiment of the present application, the acquisition module 402 is further configured to: Determine the initial target motion capture video frame in each initial motion capture video frame; Collect the hip coordinates and heel coordinates of the target object in the initial target motion capture video frame; Calculate the original length of the first part corresponding to the initial target motion capture video frame according to the hip coordinates and the heel coordinates.

[0088] In a specific embodiment of the present application, the acquisition module 404 is further configured to: Determine the initial target motion capture video frame in each initial motion capture video frame; Collect the knee coordinates and heel coordinates of the target object in the initial target motion capture video frame; Calculate the length of the second part corresponding to the initial target motion capture video frame according to the knee coordinates and the heel coordinates.

[0089] In a specific embodiment of the present application, the acquisition module 404 is further configured to: Calculate the length of the left part according to the knee coordinates and the left heel coordinates, and calculate the length of the right part according to the knee coordinates and the right heel coordinates; Use the length of the left part and the length of the right part as the length of the second part corresponding to the initial target motion capture video frame.

[0090] In a specific embodiment of the present application, the acquisition module 404 is further configured to: Determine the standard length of the second part in the target motion capture video frame corresponding to the length of the first part; Calculate the ratio of the length of the second part corresponding to each initial motion capture video frame to the standard length of the second part respectively, and obtain the length ratio corresponding to each initial motion capture video frame; Compare each length ratio with a preset length ratio respectively; When the length ratio is greater than or equal to the preset length ratio, determine that the motion state of the initial motion capture video frame is the leg landing state; When the length ratio is less than the preset length ratio, determine that the motion state of the initial motion capture video frame is the leg lifting state.

[0091] In a specific embodiment of the present application, the determination module 406 is further configured to: Determine that the initial motion capture video frame with the motion state of the leg landing state is the motion capture video frame to be processed.

[0092] In a specific embodiment of the present application, the adjustment module 408 is further configured to: Obtain the standard motion capture parameter information corresponding to the target motion capture video frame; Adjust each initial motion capture parameter information based on the standard motion capture parameter information to obtain the target motion capture parameter information corresponding to each to-be-processed motion capture video frame.

[0093] In a specific embodiment of the present application, the adjustment module 408 is further configured to: Obtain the longitudinal standard motion capture parameter information in the standard motion capture parameter information, and the longitudinal initial motion capture parameter information in each initial motion capture parameter information; Adjust each longitudinal initial motion capture parameter information to be consistent with the longitudinal standard motion capture parameter information to obtain the target motion capture parameter information corresponding to each to-be-processed motion capture video frame.

[0094] In a specific embodiment of the present application, the device further includes a generation module, and the generation module is configured to: Generate a three-dimensional video corresponding to the target object based on the target motion capture parameter information corresponding to each to-be-processed motion capture video frame.

[0095] The motion capture data processing device of the present application realizes an acquisition module configured to acquire at least two initial motion capture video frames, determine the length of the first part corresponding to the target object and the target motion capture video frame corresponding to the length of the first part in each initial motion capture video frame; a collection module configured to collect the length of the second part in each initial motion capture video frame, and determine the motion state of the target object corresponding to each initial motion capture video frame according to the length of the second part corresponding to each initial motion capture video frame and the length of the first part; a determination module configured to determine the to-be-processed motion capture video frames in each initial motion capture video frame based on the motion state corresponding to each initial motion capture video frame, and collect the initial motion capture parameter information of each to-be-processed motion capture video frame; an adjustment module configured to adjust each initial motion capture parameter information according to the target motion capture video frame to obtain the target motion capture parameter information corresponding to each to-be-processed motion capture video frame. The motion state of the target object is determined by the length of the first part and the length of the second part of each initial motion capture video frame, so as to select the to-be-processed motion capture video frames that need to be adjusted to avoid sole sliding based on the motion state, and then adjust the initial motion capture parameter information of the to-be-processed motion capture video frames, so as to obtain the target motion capture parameter information that can avoid the problem of sole sliding during the generation of the three-dimensional video.

[0096] The above is a schematic solution of a motion capture data processing device according to this embodiment. It should be noted that the technical solution of the motion capture data processing device and the technical solution of the above-mentioned motion capture data processing method belong to the same concept. For the details not described in detail in the technical solution of the motion capture data processing device, reference can be made to the description of the technical solution of the above-mentioned motion capture data processing method. In addition, each component in the device embodiment should be understood as a functional module that must be established to implement each step of the program flow or each step of the method. Each functional module is not an actual functional division or separation limitation. The device claim defined by such a set of functional modules should be understood as a functional module architecture that mainly implements the solution through the computer program recorded in the specification, rather than an entity device that mainly implements the solution through hardware.

[0097] Figure 5 FIG. shows a block diagram of a computing device 500 according to an embodiment of the present application. The components of the computing device 500 include, but are not limited to, a memory 510 and a processor 520. The processor 520 is connected to the memory 510 through a bus 530, and a database 550 is used to store data.

[0098] The computing device 500 further includes an access device 540, and the access device 540 enables the computing device 500 to communicate via one or more networks 560. Examples of these networks include the Public Switched Telephone Network (PSTN), Local Area Network (LAN), Wide Area Network (WAN), Personal Area Network (PAN), or a combination of communication networks such as the Internet. The access device 540 may include one or more of any type of wired or wireless network interfaces (e.g., Network Interface Card (NIC)), such as IEEE802.11 Wireless Local Area Network (WLAN) wireless interface, Worldwide Interoperability for Microwave Access (Wi-MAX) interface, Ethernet interface, Universal Serial Bus (USB) interface, cellular network interface, Bluetooth interface, Near Field Communication (NFC) interface, and so on.

[0099] In an embodiment of the present application, the above components of the computing device 500 and Figure 5 other components not shown in the figure may also be connected to each other, for example, through a bus. It should be understood that Figure 5 the block diagram of the computing device shown is only for illustrative purposes and is not a limitation on the scope of the present application. Those skilled in the art can add or replace other components as needed.

[0100] The computing device 500 can be any type of stationary or mobile computing device, including mobile computers or mobile computing devices (e.g., tablet computers, personal digital assistants, laptop computers, notebook computers, netbooks, etc.), mobile phones (e.g., smart phones), wearable computing devices (e.g., smart watches, smart glasses, etc.) or other types of mobile devices, or stationary computing devices such as desktop computers or PCs. The computing device 500 can also be a mobile or stationary server.

[0101] Wherein, the processor 520 is used to execute the computer-executable instructions of the method for processing the motion capture data.

[0102] The above is a schematic solution of a computing device according to this embodiment. It should be noted that the technical solution of this computing device and the technical solution of the above method for processing motion capture data belong to the same concept. For the details not described in detail in the technical solution of the computing device, reference can be made to the description of the technical solution of the above method for processing motion capture data.

[0103] An embodiment of the present application further provides a computer-readable storage medium, which stores computer instructions, and when the instructions are executed by a processor, they are used for the method for processing motion capture data.

[0104] The above is a schematic solution of a computer-readable storage medium according to this embodiment. It should be noted that the technical solution of this storage medium and the technical solution of the above method for processing motion capture data belong to the same concept. For the details not described in detail in the technical solution of the storage medium, reference can be made to the description of the technical solution of the above method for processing motion capture data.

[0105] An embodiment of the present application further provides a chip, which stores a computer program, and when the computer program is executed by the chip, the steps of the method for processing the motion capture data are implemented.

[0106] An embodiment of this specification further provides a computer program product, including a computer program or instructions, and when the computer program or instructions are executed by a processor, the steps of the above method for processing motion capture data are implemented.

[0107] The above is a schematic solution of a computer program product according to this embodiment. It should be noted that the technical solution of this computer program product and the technical solution of the above method for processing motion capture data belong to the same concept. For the details not described in detail in the technical solution of the computer program product, reference can be made to the description of the technical solution of the above method for processing motion capture data.

[0108] The above describes specific embodiments of the present application. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve the desired results. Additionally, the processes depicted in the drawings do not necessarily require the particular order or sequential order shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0109] The computer instructions include computer program code, which may be in source code form, object code form, executable file, or some intermediate form, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, removable hard disk, magnetic disk, optical disc, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal, and software distribution medium, etc. It should be noted that the content included in the computer-readable medium may be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, the computer-readable medium does not include electrical carrier signals and telecommunication signals.

[0110] It should be noted that for the foregoing method embodiments, for the sake of simplicity of description, they are all expressed as a series of action combinations. However, those skilled in the art should know that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily all essential to the present application.

[0111] In the above embodiments, the descriptions of the respective embodiments have their own emphases. For the parts not detailed in a certain embodiment, reference may be made to the relevant descriptions of other embodiments.

[0112] The preferred embodiments of the present application disclosed above are only used to help explain the present application. The alternative embodiments do not elaborate on all the details and do not limit the invention to the specific embodiments described. Obviously, many modifications and variations can be made according to the content of the present application. The present application selects and specifically describes these embodiments to better explain the principles and practical applications of the present application, so that those skilled in the art can well understand and utilize the present application. The present application is only limited by the claims and their full scope and equivalents.

Claims

1. A method for processing motion capture data, characterized in that: include: Acquire at least two initial motion capture video frames, and determine, in each initial motion capture video frame, a first part length corresponding to the target object and a target motion capture video frame corresponding to the first part length; Collecting the second part length in each initial motion capture video frame, and determining the motion state corresponding to the target object in each initial motion capture video frame according to the second part length corresponding to each initial motion capture video frame and the first part length; Based on the motion states corresponding to the initial motion capture video frames, determining the motion capture video frames to be processed in the initial motion capture video frames, and collecting the initial motion capture parameter information of the motion capture video frames to be processed; The initial motion capture parameter information is adjusted according to the target motion capture video frame to obtain the target motion capture parameter information corresponding to each motion capture video frame to be processed.

2. The method according to claim 1, characterized in that Determining a first part length corresponding to the target object and a target motion capture video frame corresponding to the first part length in each initial motion capture video frame includes: Collecting the original first part length corresponding to the target object in each initial motion capture video frame; Sorting the lengths of the original first parts by length, and determining the length of the first part based on the sorting result; An initial motion capture video frame corresponding to the first part length is used as a target motion capture video frame.

3. The method according to claim 2, characterized in that Collecting the original first part length corresponding to the target object in each initial motion capture video frame includes: Determining an initial target motion capture video frame among the initial motion capture video frames; Collecting the hip coordinates and heel coordinates of the target object in the initial target motion capture video frame; The original first part length corresponding to the initial target motion capture video frame is calculated according to the hip coordinates and the heel coordinates.

4. The method according to claim 1, characterized in that The length of the second part in each initial motion capture video frame is collected, including: Determining an initial target motion capture video frame among the initial motion capture video frames; Acquire knee coordinates and heel coordinates of the target object in the initial target motion capture video frame; The second part length corresponding to the initial target motion capture video frame is calculated according to the knee coordinates and the heel coordinates.

5. The method according to claim 4, characterized in that The heel coordinates include left heel coordinates and right heel coordinates, and calculating and obtaining the second part length corresponding to the initial target motion capture video frame according to the knee coordinates and the heel coordinates includes: Calculate the length of the left part according to the knee coordinates and the left heel coordinates, and calculate the length of the right part according to the knee coordinates and the right heel coordinates; The left part length and the right part length are used as the second part length corresponding to the initial target motion capture video frame.

6. The method according to claim 1, characterized in that Determining the motion state corresponding to the target object in each initial motion capture video frame according to the second part length corresponding to each initial motion capture video frame and the first part length, comprising: Determining a standard second part length in a target motion capture video frame corresponding to the first part length; Calculating the ratio of the second part length corresponding to each initial motion capture video frame to the standard second part length respectively, to obtain the length ratio corresponding to each initial motion capture video frame; Compare each length ratio with a preset length ratio; When the length ratio is greater than or equal to the preset length ratio, determining that the motion state of the initial motion capture video frame is a leg landing state; When the length ratio is less than the preset length ratio, it is determined that the motion state of the initial motion capture video frame is a leg-lifting state.

7. The method according to claim 6, characterized in that Based on the motion states corresponding to the initial motion capture video frames, determining the motion capture video frames to be processed in the initial motion capture video frames includes: It is determined that the initial motion capture video frame in which the motion state is the leg landing state is the motion capture video frame to be processed.

8. The method according to claim 1, characterized in that Adjusting each initial motion capture parameter information according to the target motion capture video frame to obtain target motion capture parameter information corresponding to each motion capture video frame to be processed includes: Obtain standard motion capture parameter information corresponding to the target motion capture video frame; Each initial motion capture parameter information is adjusted based on the standard motion capture parameter information to obtain target motion capture parameter information corresponding to each motion capture video frame to be processed.

9. The method according to claim 8, characterized in that Adjusting each initial motion capture parameter information based on the standard motion capture parameter information to obtain target motion capture parameter information corresponding to each motion capture video frame to be processed includes: Acquire longitudinal standard motion capture parameter information in the standard motion capture parameter information and longitudinal initial motion capture parameter information in each initial motion capture parameter information; Each longitudinal initial motion capture parameter information is adjusted to be consistent with the longitudinal standard motion capture parameter information, and the target motion capture parameter information corresponding to each motion capture video frame to be processed is obtained.

10. The method according to claim 1, characterized in that After adjusting each initial motion capture parameter information according to the target motion capture video frame and obtaining the target motion capture parameter information corresponding to each motion capture video frame to be processed, the method further includes: Based on the target motion capture parameter information corresponding to each motion capture video frame to be processed, a three-dimensional video corresponding to the target object is generated.

11. A motion capture data processing device, characterized in that: include: An acquisition module is configured to acquire at least two initial motion capture video frames, and determine a first part length corresponding to the target object and a target motion capture video frame corresponding to the first part length in each initial motion capture video frame; A collection module is configured to collect the length of the second part in each initial motion capture video frame, and determine the motion state corresponding to the target object in each initial motion capture video frame according to the length of the second part corresponding to each initial motion capture video frame and the length of the first part; A determination module is configured to determine the motion capture video frames to be processed in each initial motion capture video frame based on the motion state corresponding to each initial motion capture video frame, and collect initial motion capture parameter information of each motion capture video frame to be processed; The adjustment module is configured to adjust each initial motion capture parameter information according to the target motion capture video frame to obtain the target motion capture parameter information corresponding to each motion capture video frame to be processed.

12. A computing device, characterized in that: include: Memory and processor; The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions to implement the steps of the method according to claims 1-10.

13. A computer-readable storage medium storing computer instructions, characterized in that: When the instruction is executed by a processor, the steps of the method described in claims 1-10 are implemented.

14. A computer program product comprising a computer program or instructions, characterized in that When the computer program or instruction is executed by a processor, the steps of the method according to claims 1 to 10 are implemented.

Images