Action redirection method and device and electronic equipment cluster

Abstract

The invention discloses an action redirection method and device and an electronic equipment cluster, which are applied to the technical field of redirection and solve the problem of action redirection efficiency of a current redirection system. The method comprises the following steps: acquiring first motion data generated by first body shape data of a target image, second motion data of a source image and second body shape data of the source image according to a redirection algorithm; and displaying a first preview picture including an action corresponding to the first action data executed by the target image. And receiving a correction instruction sent by the user and used for correcting the action corresponding to the first action data executed by the target image. And determining a correction parameter of the redirection algorithm according to the correction instruction. And using a redirection algorithm including correction parameters to determine corrected first action data according to the first body shape data of the target image and the second action data and the second body shape data of the source image. And displaying a second preview picture comprising the action corresponding to the first action data after the target image executes the correction.

Description

Technical Field

[0001] The present application relates to the field of redirection technology, and in particular to an action redirection method and device, and an electronic device cluster. Background Art

[0002] Motion redirection, also known as motion capture redirection, refers to the use of motion capture equipment to collect the motion source data of a source image (such as a motion capture actor), such as video data that can reflect the motion information of the source image, and then detect the motion data and body shape data of the source image from the collected motion source data. Then, using the motion redirection system, based on the body shape difference between the source image and the target image, the motion of the source image is redirected to the target image.

[0003] At present, in the process of motion redirection, after receiving the body shape data of the target image and the motion data and body shape data of the source image uploaded by the motion capture device, the motion redirection system performs motion redirection on the source image according to the body shape data of the target image and the motion data and body shape data of the source image to obtain the motion data of the target image, so that the target image performs the action corresponding to the action data.

[0004] However, the algorithm rules in the current action redirection system are single, with poor versatility and low action redirection efficiency. For example, the action redirection system can usually redirect the action of a specific source image, but when the redirection effect is not good or the target image is replaced, it is necessary to manually adjust the target image frame by frame to perform the action corresponding to the action data so that the target image can perform the correct action. Or after manually adjusting the body shape data of the source image, the body shape data of the target image, the action data of the source image and the manually adjusted body shape data of the source image are input into the action redirection system to regenerate the action data of the target image so that the target image performs the action corresponding to the regenerated action data. Summary of the invention

[0005] The embodiments of the present application provide an action redirection method and device, and an electronic device cluster to solve the problem of low action redirection efficiency of the current redirection system.

[0006] To achieve the above objectives, the embodiments of the present application adopt the following technical solutions:

[0007] In a first aspect, a method for redirecting an action is provided, the method comprising: obtaining first action data, the first action data being generated by first body shape data of a target image, second action data of a source image and second body shape data of the source image according to a redirection algorithm, the target image comprising at least one body part, and the first action data comprising kinematic parameters of the at least one body part. Displaying a first preview screen, the first preview screen comprising a screen of the target image performing an action corresponding to the first action data. Receive a correction instruction sent by a user, the correction instruction being used to correct an action corresponding to the first action data performed by the target image, the correction instruction comprising a correction instruction for kinematic parameters of at least one body part. Determining correction parameters of the redirection algorithm according to the correction instruction. Using the redirection algorithm including the correction parameters, determining the corrected first action data according to the first body shape data of the target image, the second action data of the source image and the second body shape data of the source image. Displaying a second preview screen, the second preview screen comprising a screen of the target image performing an action corresponding to the corrected first action data.

[0008] The action redirection method provided in the embodiment of the present application generates the first action data of the target image according to the redirection algorithm, the first body shape data of the target image, the second action data of the source image and the second body shape data of the source image, and then receives a correction instruction sent by the user. According to the correction instruction, a correction parameter of the redirection algorithm can be determined, and the redirection algorithm can be automatically corrected using the correction parameter, thereby improving the efficiency of action redirection.

[0009] In a possible implementation, the first preview screen also includes a screen of the source image performing the action corresponding to the second action data, and the second preview screen also includes a screen of the source image performing the action corresponding to the second action data.

[0010] In this possible implementation, the preview screen provided by the embodiment of the present application may include a screen of the source image executing the action corresponding to the action data, which can allow the user to view the screen of the source image executing the action corresponding to the action data in real time, so that the user can directly correct the action of the target image based on the screen indicated by the preview screen, without adjusting the internal algorithm of the action redirection system, making the action redirection method more flexible and saving the action redirection adjustment time.

[0011] In a possible implementation, the first preview screen also indicates the comparison effect between the action corresponding to the first action data of the target image and the action corresponding to the second action data of the source image. The second preview screen also indicates the comparison effect between the action corresponding to the first action data after the target image performs the correction and the action corresponding to the second action data of the source image.

[0012] In this possible implementation, the preview screen provided by the embodiment of the present application can indicate the comparison effect between the action corresponding to the target image's action data and the action corresponding to the source image's action data, so that the user can more intuitively see the comparison effect between the action corresponding to the target image's action data and the action corresponding to the source image's action gear, and then correct the action of the target image based on the screen of the source image's action data.

[0013] In a possible implementation, the action redirection method provided in the embodiment of the present application further includes: using a redirection algorithm including a correction parameter to determine the third action data of the other image according to the third body shape data of the other image, the second action data of the source image and the second body shape data of the source image.

[0014] In this possible implementation, the action redirection method provided in the embodiment of the present application can input the correction parameters as input parameters into the action redirection module for action redirection, without adjusting the internal algorithm of the action redirection module, making the action redirection method more flexible and saving the action redirection adjustment time.

[0015] In a possible implementation, determining the correction parameters of the redirection algorithm according to the correction instruction includes: obtaining an adjustment value of the kinematic parameter of the at least one body part and / or the kinematic parameter of the at least one body part after adjustment according to the correction instruction for the kinematic parameter of the at least one body part. Determining the correction parameters of the redirection algorithm according to the adjustment value of the kinematic parameter of the at least one body part and / or the kinematic parameter of the at least one body part after adjustment.

[0016] In this possible implementation, the motion redirection method provided in the embodiment of the present application can obtain the adjustment value of the kinematic parameters of at least one body part and / or the kinematic parameters of at least one body part after adjustment according to the correction instruction of the kinematic parameters of at least one body part, determine the correction parameters using the adjustment value of the kinematic parameters and / or the adjusted kinematic parameters, and input the correction parameters as input parameters into the motion redirection module for motion redirection. There is no need to adjust the internal algorithm of the motion redirection module, which makes the motion redirection method more flexible and saves the motion redirection adjustment time.

[0017] In a possible implementation, the correction instruction further includes an automatic correction instruction, and determining the correction parameters of the redirection algorithm according to the correction instruction includes: in response to the correction instruction, determining the adjustment value of the kinematic parameter of at least one body part and / or the kinematic parameter of at least one body part after adjustment according to the difference between the first motion data and the second motion data of the source image. Determine the correction parameters of the redirection algorithm according to the adjustment value of the kinematic parameter of at least one body part and / or the kinematic parameter of at least one body part after adjustment.

[0018] In this possible implementation, the motion redirection method provided in the embodiment of the present application can respond to the automatic correction instruction after receiving the automatic correction instruction, automatically determine the kinematic parameters and adjustment values ​​of at least one body part and / or the kinematic parameters of at least one body part after adjustment according to the difference between the first motion data and the second motion data of the source image, determine the correction parameters using the adjustment values ​​of the kinematic parameters and / or the adjusted kinematic parameters, and input the correction parameters as input parameters into the motion redirection module for motion redirection. There is no need to adjust the internal algorithm of the motion redirection module, which makes the motion redirection method more flexible and saves the motion redirection adjustment time.

[0019] In a possible implementation, displaying the first preview image includes: displaying the target image and the source image in an overlapping manner, or displaying the target image and the source image in a partitioned manner, or generating a point cloud of the target image and displaying the point cloud and the source image in an overlapping manner.

[0020] In this possible implementation, the target image and the source image may be superimposed and displayed in the first preview screen, or the target image and the source image may be partitioned and displayed, or a point cloud of the target image may be generated and the point cloud and the source image may be superimposed and displayed, so that the user can more intuitively view the contrast effect of the target image and the source image from the first preview screen.

[0021] In a possible implementation, the source image includes an image of a motion capture target.

[0022] In a second aspect, an embodiment of the present application provides an action redirection device, which includes: an acquisition module, a display module, a receiving module and a determination module.

[0023] Among them, the acquisition module is used to obtain first motion data, the first motion data is generated by first body shape data of the target image, second motion data of the source image and second body shape data of the source image according to the redirection algorithm, the target image includes at least one body part, and the first motion data includes kinematic parameters of at least one body part.

[0024] The display module is used to display a first preview picture, wherein the first preview picture includes a picture of a target image performing an action corresponding to the first action data.

[0025] The receiving module is used to receive a correction instruction sent by a user, the correction instruction is used to correct the action corresponding to the first action data performed by the target image, and the correction instruction includes a correction instruction for the kinematic parameters of at least one body part.

[0026] The determination module is used to determine the correction parameters of the redirection algorithm according to the correction instruction. The redirection algorithm including the correction parameters is used to determine the corrected first action data according to the first body shape data of the target image, the second action data of the source image and the second body shape data of the source image.

[0027] The display module is further used to display a second preview screen, wherein the second preview screen includes a screen in which the target image performs an action corresponding to the modified first action data.

[0028] In a possible implementation, the first preview screen also includes a screen of the source image performing the action corresponding to the second action data, and the second preview screen also includes a screen of the source image performing the action corresponding to the second action data.

[0029] In a possible implementation, the first preview screen also indicates the comparison effect between the action corresponding to the first action data of the target image and the action corresponding to the second action data of the source image. The second preview screen also indicates the comparison effect between the action corresponding to the first action data after the target image performs the correction and the action corresponding to the second action data of the source image.

[0030] In a possible implementation, the determination module is further configured to use a redirection algorithm including a correction parameter to determine the third action data of the other image according to the third body shape data of the other image, the second action data of the source image and the second body shape data of the source image.

[0031] In a possible implementation, the acquisition module is further used to obtain the adjustment value of the kinematic parameter of at least one body part and / or the adjusted kinematic parameter of at least one body part according to the correction instruction of the kinematic parameter of at least one body part.

[0032] The determination module is specifically used to determine the correction parameters of the redirection algorithm according to the adjustment value of the kinematic parameter of at least one body part and / or the adjusted kinematic parameter of at least one body part.

[0033] In a possible implementation, the determination module is specifically configured to determine, in response to the correction instruction, an adjustment value of a kinematic parameter of at least one body part and / or the kinematic parameter of at least one body part after adjustment according to a difference between the first motion data and the second motion data of the source image, and to determine a correction parameter of the redirection algorithm according to the adjustment value of the kinematic parameter of at least one body part and / or the kinematic parameter of at least one body part after adjustment.

[0034] In a possible implementation, the display module is specifically used to display the target image and the source image in a superimposed manner, or to display the target image and the source image in partitions, or to generate a point cloud of the target image and to display the point cloud in a superimposed manner with the source image.

[0035] In a possible implementation, the source image includes an image of a motion capture target.

[0036] In a third aspect, an embodiment of the present application provides an electronic device cluster, the electronic device cluster includes at least one electronic device, each electronic device includes a processor and a memory. The processor of at least one electronic device is used to execute instructions stored in the memory of at least one electronic device, so that the electronic device cluster executes the action redirection method described in any one of the first aspects and the first aspect.

[0037] In a fourth aspect, a computer program product comprising instructions is provided. When the instructions are executed by an electronic device cluster, the electronic device cluster executes the above-mentioned first aspect and the action redirection method described in any one of the first aspects.

[0038] In a fifth aspect, a computer-readable storage medium is provided, wherein computer program instructions are stored in the computer-readable storage medium. When the computer-readable storage medium is executed in an electronic device cluster, the electronic device cluster can execute the above-mentioned first aspect and the action redirection method described in any one of the first aspects.

[0039] Among them, the technical effects brought about by any design method in the second to fifth aspects can refer to the technical effects brought about by different design methods in the first aspect, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 A structural diagram of an action redirection system provided in an embodiment of the present application;

[0041] Figure 2 Another structural diagram of an action redirection system provided in an embodiment of the present application;

[0042] Figure 3 A schematic diagram of a motion capture device according to an embodiment of the present application collecting motion source data of a motion capture target;

[0043] Figure 4 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application;

[0044] Figure 5 A specific flow chart of an action redirection method provided in an embodiment of the present application;

[0045] Figure 6 An effect diagram of the target image and the source image superimposed and displayed in an embodiment of the present application;

[0046] Figure 7 An effect diagram of the target image and the source image provided in the embodiment of the present application, showing the partitioned display;

[0047] Figure 8 An effect diagram of displaying a point cloud on top of a source image provided by an embodiment of the present application;

[0048] Fig. 9 A specific example diagram of an action redirection method provided in an embodiment of the present application;

[0049] Fig.10 An effect diagram of a second preview screen provided in an embodiment of the present application;

[0050] Fig.11 Another effect diagram of the second preview screen provided in the embodiment of the present application;

[0051] Fig.12 Another specific flow chart of an action redirection method provided in an embodiment of the present application;

[0052] Fig.13 A schematic diagram of the structure of an action redirection device provided in an embodiment of the present application;

[0053] Fig.14 Another structural schematic diagram of an action redirection device provided in an embodiment of the present application;

[0054] Fig.15 Another structural schematic diagram of an electronic device provided in an embodiment of the present application;

[0055] Fig.16 A schematic diagram of the structure of an electronic device cluster provided in an embodiment of the present application;

[0056] Fig.17 Another structural schematic diagram of an electronic device cluster provided in an embodiment of the present application. DETAILED DESCRIPTION

[0057] The technical solutions in the embodiments of the present application will be described below in conjunction with the drawings in the embodiments of the present application. Among them, in the description of the present application, unless otherwise specified, " / " indicates that the objects associated before and after are in an "or" relationship, for example, A / B can represent A or B; "and / or" in the present application is only a description of the association relationship of the associated objects, indicating that there can be three relationships, for example, A and / or B, which can represent: A exists alone, A and B exist at the same time, and B exists alone, where A and B can be singular or plural. And, in the description of the present application, unless otherwise specified, "multiple" refers to two or more than two. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b, or c can represent: a, b, c, ab, ac, bc, or abc, where a, b, c can be single or multiple. In addition, in order to facilitate the clear description of the technical solutions of the embodiments of the present application, in the embodiments of the present application, the words "first", "second" and the like are used to distinguish the same items or similar items with substantially the same functions and effects. Those skilled in the art will understand that the words "first", "second" and the like do not limit the quantity and execution order, and the words "first", "second" and the like do not necessarily limit the differences. At the same time, in the embodiments of the present application, the words "exemplary" or "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "exemplary" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or design solutions. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a concrete manner for ease of understanding.

[0058] In addition, the network architecture and business scenarios described in the embodiments of the present application are intended to more clearly illustrate the technical solutions of the embodiments of the present application, and do not constitute a limitation on the technical solutions provided in the embodiments of the present application. Ordinary technicians in this field can know that with the evolution of network architecture and the emergence of new business scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.

[0059] First, the application scenarios of the embodiments of the present application are exemplarily introduced.

[0060] Virtual digital space products such as animation, film, television, games, and the metaverse construct virtual images in virtual space as digital clones of objects in real space (hereinafter referred to as real objects), and map the action process of the real object in real space to the virtual image in virtual space for animation video display. In this way, the action process of the virtual image can replicate the action process of the real object in real space, and even surpass the realism and beauty of the action process of the real object in real space.

[0061] Generally, the body movements of real objects in real space can be obtained through motion capture technology. The data that carries the body movements of real objects can be called motion source data. Specifically, motion capture technology can be to collect the motion source data of real objects in real space through motion capture devices such as optical sensors, inertial sensors and cameras. Skeletal animation data can be generated through the collected motion source data of real objects to restore the movements of real objects in virtual space for display. The skeleton of the virtual image can be a data structure composed of virtual joint rotation and position information that is not displayed inside the three-dimensional model of the virtual image, such as skeleton points, mesh structures, etc.

[0062] After obtaining the action source data of the real object in the real space through the motion capture technology, the action redirection system is used to redirect the action of the virtual image in the virtual space according to the action data in the action source data, so that the virtual image performs the action. Although this can accurately restore the action of the real object in the real space, the algorithm rules in the current action redirection system are single, the versatility is poor, and the action redirection efficiency is low. For example, the action redirection system can usually redirect the action of a specific source image, but when the redirection effect is not good or the target image is replaced, it is necessary to manually adjust the target image frame by frame to perform the action corresponding to the action data so that the target image makes the correct action. Or after manually adjusting the body shape data of the source image, the body shape data of the target image, the action data of the source image and the body shape data of the manually adjusted source image are input into the action redirection system, and the action data of the target image is regenerated, so that the target image performs the action corresponding to the regenerated action data. Or the user uploads a new redirection algorithm to the redirection system again, so as to use the body shape data of the target image, the action data of the source image and the body shape data of the source image to input them into the redirection system configured with the new redirection algorithm, and regenerate the action data of the target image.

[0063] The source image may be any object of any action in the real space, for example, a person, an animal, etc.

[0064] As another example, the source image may also be a virtual image, and the motion data may be an animation video of the virtual image, such as an animation video obtained by redirecting the motion of a virtual image by a previous redirection system.

[0065] The current redirection system uses the action data d to drive the target image to complete the action redirection of the target image. Since the algorithm and rule F0 inside the current redirection system remain unchanged, when a, b, and c remain unchanged, d remains unchanged, that is, the action redirection result remains unchanged at this time.

[0066] If the current action redirection result is not good, the user needs to adjust the redirection algorithm. The redirection correction process is not flexible enough and the algorithm adjustment takes a long time. For example, the algorithm is adjusted to F1 = {F0 U (c < 50, d-1)}.

[0067] However, the current redirection system has a single rule and poor versatility. When the redirection effect is not good, the entire redirection algorithm needs to be adjusted. The redirection correction process is not flexible enough and the algorithm adjustment takes a long time. For example, the current redirection system can only redirect specific virtual images. If the redirection effect is not good or the virtual image is replaced, the internal algorithm of the redirection system needs to be adjusted.

[0068] Based on this, an embodiment of the present application provides an action redirection method, which can be applied to an action redirection system. In the embodiment of the present application, during the process of the action redirection system executing action redirection for a target image, a preview screen can be displayed, and the preview screen is used to indicate the screen of the target image executing the action corresponding to the action data of the target image (i.e., the action redirection result of the target image), so that the user can directly correct the action of the target image based on the screen indicated by the preview screen, without adjusting the internal algorithm of the action redirection system, making the action redirection method more flexible and saving the action redirection adjustment time.

[0069] like Figure 1 As shown, the action redirection system 100 provided in the embodiment of the present application may include a redirection module 101 , a display module 102 and a correction module 103 .

[0070] The redirection module 101 may establish a communication connection with the display module 102 , the redirection module 101 may establish a communication connection with the correction module 103 , and the display module 102 may establish a communication connection with the correction module 103 .

[0071] The redirection module 101 is used to redirect the target virtual image based on the action data of the source image, the body shape data of the source image and the body shape data of the target image, and generate a first preview screen, and send the first preview screen to the display module 102. The first preview screen can at least indicate the screen of the target image performing the action corresponding to the action data of the source image (such as the action redirection result obtained by redirecting the action of the target image for the first time), and can also indicate the action description information of the target image. For example, the action description information may include the bending direction, height, angle, etc. of each joint of the target image.

[0072] In a possible implementation, the redirection module 101 may be configured with a redirection model built by a neural network model and some redirection rules. The redirection model is a model trained based on deep learning technology, and the redirection rules are rules designed based on action redirection requirements. The redirection module 101 implements action redirection of the target image based on the redirection model and the redirection rules. The input parameters of the redirection module 101 include but are not limited to the action data and body shape data of the source image and the body shape data of the target image.

[0073] The display module 102 is used to display a user interface. The user interface may include various images, prompt information, and interactive controls. For example, the display module 102 may receive a first preview image sent by the redirection module 101 and display the first preview image to the user. The display module 102 also has a human-computer interaction function. In this way, the user may interact with the display module 102 based on the displayed first preview image to input a first correction instruction for correcting the result of the action redirection of the target image.

[0074] In a possible implementation, the display module 102 may be a display screen, and the display module may include 1 or N display screens, where N is a positive integer greater than 1. The display screen may be a touch-sensitive display screen, or a non-touch-sensitive display screen connected to an external input device. For example, when the display module 102 is a touch-sensitive display screen, a touch sensor may be provided below the display screen. The touch sensor is also referred to as a "touch panel". A touch screen may be formed by a touch sensor and a display screen, and the touch screen is also referred to as a "touch screen". The touch sensor is used to detect touch operations acting on or near it. The touch sensor may transmit the detected touch operation to a redirection system to determine the type of touch event corresponding to the touch operation. In addition, a pressure sensor may be provided below the display screen, and the pressure sensor is used to sense a pressure signal and convert the sensed pressure signal into an electrical signal. When a touch operation acts on the display screen, the display screen detects the intensity corresponding to the touch operation according to the pressure sensor. The display screen may also calculate the operation position corresponding to the touch operation according to the detection signal of the pressure sensor.

[0075] It should be understood that when the display module 102 is a touch screen, the display module 102 also serves as an input device to receive user input. When the display module 102 is a non-touch screen, it can be used to interact with the display module 102 based on an external input device. The present application does not limit the type of the display module 102.

[0076] The correction module 103 is used to obtain a first correction instruction and send the first correction instruction to the redirection module 101. As an example, the correction module 103 can generate a first correction parameter based on a user input (such as an instruction to adjust the current action redirection result or a parameter for adjusting the current action redirection result). In addition, the correction module 103 can also calculate and obtain the first correction parameter based on the difference or comparison effect between the action redirection effect of the target image and the action of the motion capture target.

[0077] The redirection module 101 is also used to redirect the target image's action using the redirection algorithm including the first correction parameter, the action data of the source image, the body shape data of the source image, and the body shape data of the target image after receiving the first correction parameter sent by the correction module 103, generate a second preview screen, and send the second preview screen to the display module 102. The second preview screen can at least indicate a screen including the action corresponding to the first action data after correction performed by the target image (such as the action redirection result obtained by redirecting the action of the target image again), and can also indicate the difference or comparison effect between the second action of the target image and the action of the source image, and can also indicate the action description information of the target virtual image and / or the action capture target.

[0078] The display module 102 is further configured to display the second preview picture to the user through an interactive interface with the user after receiving the second preview picture sent by the redirection module 101 .

[0079] Further, if Figure 2 As shown, the action redirection system 100 provided in the embodiment of the present application may further include a data detection module 104. The data detection module 104 is in communication connection with the redirection module 101.

[0080] The data detection module 104 is configured with a motion detection algorithm and a body shape detection algorithm, which are respectively used to detect motion data and body shape data from the motion source data and transmit them to the redirection module.

[0081] The redirection system in the embodiment of the present application can be specifically implemented as an electronic device, which can have data processing, data communication and data display functions, such as a server, a computer device or a terminal. In this implementation, the redirection module 101, the display module 102, the correction module 103 and the data detection module 104 are integrated into one device. Of course, in other embodiments of the present application, the redirection module 101, the display module 102, the correction module 103 and the data detection module 104 can also be integrated into different devices respectively. This application is not limited to this.

[0082] As an example, the electronic device can establish a communication connection with the motion capture device, and the motion capture device can transmit data to the electronic device. For example, the motion capture device collects motion source data of the motion capture target and transmits the collected motion source data to the electronic device, so that the electronic device redirects the motion of the target virtual image based on the motion source data of the motion capture target. The motion capture device can be an optical motion capture device, such as a camera. The motion capture device can also be an inertial motion capture device, a sound motion capture device, or a sensor set, etc. The present application does not limit the type of motion capture device.

[0083] For example, Figure 3 Schematic diagram of a motion capture device collecting motion source data of a motion capture target according to an embodiment of the present application. Figure 3 As shown, the motion capture device collects the motion of the motion capture target and converts it into motion data.

[0084] like Figure 4 As shown, the electronic device may be a computer device 400. The computer device 400 is connected to a motion capture device 401 for communication. The computer device 400 includes a processor 402 and a memory 403.

[0085] Among them, the processor 402 can be a central processing unit (CPU), and the processor 402 can also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components and other chips, or a combination of the above-mentioned types of chips.

[0086] The memory 403 may be a volatile memory, such as a random-access memory (RAM); or a non-volatile memory, such as a read-only memory (ROM), a flash memory, a hard disk drive (HDD) or a solid-state drive (SSD); or a combination of the above types of memories, used to store applications, configuration files, data information or other content that can implement the method of the present application.

[0087] The memory 403 is used to store the motion source data collected by the motion capture device 401 and uploaded to the computer device 400 .

[0088] The processor 402 performs the following functions by running or executing the software programs and / or modules stored in the memory 403 and calling the data stored in the memory 403:

[0089] The processor 402 performs action redirection on the target image based on the action source data.

[0090] It should be noted that the application scenarios and system architectures described in the embodiments of the present application are intended to more clearly illustrate the technical solutions of the embodiments of the present application, and do not constitute a limitation on the technical solutions provided in the embodiments of the present application. Ordinary technicians in this field can know that with the evolution of the system architecture and the emergence of new business scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.

[0091] For ease of understanding, the following is an exemplary introduction to the action redirection method provided by the present application in conjunction with the accompanying drawings. The method is applicable to the above-mentioned action redirection system, such as the computer device 400. Figure 5 As shown, the method may include the following steps:

[0092] S501: The redirection module obtains first action data.

[0093] The first motion data is generated by the first body shape data of the target image, the second motion data of the source image and the second body shape data of the source image according to the redirection algorithm. The target image includes at least one body part, and the first motion data includes kinematic parameters of at least one body part.

[0094] The second motion data can characterize the motion and / or posture of the source image. The posture of the source image can be a posture of the body of the source image. For example, if the source image is a person, the posture of the source image can include the posture when standing, walking or sitting. The motion of the source image can be a motion belonging to a certain motion category performed by a certain body part of the source image during the movement. For example, if the source image is a person, the body parts of the source image can include limbs, trunk, and shoulders, neck and head. Each body part includes multiple joints. Different body parts can perform different actions. For example, the actions that can be performed by the upper limbs include waving, swinging, punching, elbowing, etc.; the actions that can be performed by the lower limbs include walking, running, jumping, squatting, sitting, dancing, etc.; the actions that can be performed by the shoulders, neck and head can include shaking heads, nodding, etc.; the actions that can be performed by the trunk can include bowing, twisting the waist, etc.

[0095] In this embodiment, the second motion data and the second body shape data are inputted into the redirection module from outside the redirection module. For example, the second motion data and the second body shape data are detected by the data detection module of the electronic device from the motion source data captured by the motion capture device, and transmitted to the redirection module. In another embodiment, the process of the redirection module receiving the second motion data and the second body shape data may specifically include: receiving the motion source data, and detecting the second motion data and the second body shape data from the motion source data. That is to say, the motion detection algorithm and the body shape detection algorithm may be configured inside the redirection module, which are used to detect the motion data and the body shape data from the motion source data, respectively.

[0096] It can be seen that the movement process of the source image can be recorded by a motion capture device in a way including but not limited to video to obtain motion source data, and the motion data and body shape data of the motion capture target performing the action in the video can be obtained through the motion detection algorithm and body shape detection algorithm.

[0097] The process of the source image performing an action can be realized in the real space, and the action data of the source image can include the position information of the reference point in each video frame when the action capture target performs an action in the real space, the rotation angle of the reference point, the motion acceleration, the force condition of the reference point, and the Euler angle of the reference point. The reference point can be any point on the skeleton when performing an action, and the reference point can include the joint point of the skeleton. The action data of the source image can also include a variety of data formats such as quaternions and vectors as standardized target data formats. In other words, the motion capture device can capture the motion data of each joint point, and through the changes in the timing of each motion data, it can be determined that each joint point participates in the execution of the action within a certain time period.

[0098] The body shape data of the source image may represent the height, chest circumference, waist circumference, hip circumference, driving skeleton, etc. of the source image. The body shape data of the source image may be in various data formats such as quaternion and vector as a standardized target data format.

[0099] In another possible implementation, the second motion data and the second body shape data may be the motion data and body shape data of the source image manually input by the user.

[0100] In another possible implementation, the second motion data and the second body shape data may be the motion data and body shape data of the source image history stored in the redirection module.

[0101] Specifically, the redirection module may utilize a redirection algorithm in the redirection module to determine the first action data according to the first body shape data, the second body shape data and the second action data. The redirection algorithm may be represented by F(a, b, c, d)=e.

[0102] Wherein, a represents the first body shape data, b represents the second body shape data, c represents the second motion data, d represents the correction parameter, and e represents the first motion data. The correction parameter d may be a correction parameter generated according to the difference between the first body shape data and the second body shape data, or the correction parameter d may also be normalized data generated by the correction module according to the adjustment parameter. The present application does not limit the type of d. The correction parameter d of the redirection module is a null value during the first redirection process.

[0103] In a possible implementation, the redirection module may modify the second motion data according to the first body shape data, the second body shape data, the collision rule or the penetration rule parameter and the correction parameter to generate the first motion data.

[0104] The collision rule detects collisions between the target avatar and the environment or other avatars to avoid abnormal or unnatural movement of the target avatar. The penetration rule detects obstacles to avoid mutual penetration and superposition between the target avatar and the environment or other avatars due to collisions.

[0105] Exemplarily, the redirection module can utilize a redirection algorithm in the redirection module to determine the first motion data based on the first body shape data, the second body shape data and the second motion data. The redirection algorithm can be represented by F(a, b, c, d, f)=e.

[0106] Among them, f represents the collision rule or penetration rule parameter.

[0107] In another possible implementation, the redirection module may correct the second motion data according to the first body shape data, the second body shape data, and the collision rule or the penetration rule parameters to obtain a preliminary correction result of the second motion data, and then correct the preliminary correction result in combination with the correction parameters to obtain the first motion data.

[0108] S502: The redirection module generates a first preview picture based on the first action data.

[0109] The first preview screen includes a screen of the target image performing the action corresponding to the first action data. The first preview screen also includes a screen of the source image performing the action corresponding to the second action data. The first preview screen also includes a comparison effect of the action corresponding to the first action data of the target image and the action corresponding to the second action data of the source image. The first preview screen can be an image, a frame in a video file, etc. The first preview screen can be a depth map, and the present application does not limit the type of the first preview screen.

[0110] S503: The redirection module sends the first preview image to the display module.

[0111] S504: The display module displays a first preview picture.

[0112] In a possible implementation, the target image and the source image are displayed superimposed on each other in the first preview screen to show the comparison effect between the action corresponding to the first action data of the target image and the action corresponding to the second action data of the source image.

[0113] For example, Figure 6 An effect diagram of superimposed display of a target image and a source image is shown, a is an action of the source image, b is a first action of the target image, and a and b are superimposed to obtain a first preview image.

[0114] Another possible implementation is to display the target image and the source image in separate areas in the first preview screen to show the comparison effect between the action corresponding to the first action data of the target image and the action corresponding to the second action data of the source image.

[0115] For example, Figure 7 An effect diagram of the target image and the source image being displayed in partitions is shown, and the first preview image is obtained by displaying partitions a and b.

[0116] In another possible implementation, a point cloud of the target image is generated in the first preview screen, and the point cloud is displayed on top of the source image to show a comparison effect between the action corresponding to the first action data of the target image and the action corresponding to the second data of the source image.

[0117] For example, Figure 8 An effect diagram of displaying a point cloud on an upper layer of a source image is shown. c is a point cloud of an action of a target image. A first preview image is obtained by displaying c on an upper layer of a.

[0118] Specifically, the process of the display module displaying the first preview picture may be that the display module displays the first preview picture to the user through an interactive interface with the user.

[0119] S505: The correction module receives a correction instruction sent by the user.

[0120] The correction instruction is used to correct the action corresponding to the first action data performed by the target image, and the correction instruction includes a correction instruction for the kinematic parameters of at least one body part.

[0121] S506: The correction module determines correction parameters of the redirection algorithm according to the correction instruction.

[0122] In one possible implementation, according to the correction instruction of the kinematic parameters of at least one body part, an adjustment value of the kinematic parameters of at least one body part and / or the kinematic parameters of at least one body part after adjustment is obtained. According to the adjustment value of the kinematic parameters of at least one body part and / or the kinematic parameters of at least one body part after adjustment, a correction parameter of the redirection algorithm is determined.

[0123] Specifically, the kinematic parameter of at least one body part of the target image may include distribution information of the skeleton points of the target image. The adjustment value of the kinematic parameter of at least one body part may include an adjustment value for moving at least one skeleton point of the target image.

[0124] For example, Fig. 9 As shown, m is the original position of a skeleton point of the target image, and n is the target position corresponding to the skeleton point of the target image. The user can view the contrast effect of the action corresponding to the first action data of the target image in the first preview screen and the action corresponding to the second action data of the source image through the display module, and move a skeleton point of the target image according to the contrast effect. The moving process can be that the user first clicks the original position m of a skeleton point of the target image through the interactive interface, and then clicks the target position n of the skeleton point to move a skeleton point of the target image from the original position m to the target position n, or the user directly drags a skeleton point of the target image from the original position m to the target position n of the skeleton point through the interactive interface. After receiving the adjustment instruction, the correction module implicitly calculates the correction angle according to the adjustment instruction to obtain the action of the target image. The correction module generates correction parameters based on the original position and target position of the skeleton point.

[0125] Furthermore, the correction module can detect whether an adjustment instruction input by the user is received within a preset time. If the adjustment instruction input by the user is received within the preset time, the second action of the target virtual image is obtained according to the adjustment instruction, and the second action is the action after the first action is adjusted. The correction module generates a correction parameter according to the second action of the target virtual image. If the adjustment instruction input by the user is not received within the preset time, the detection is stopped after the preset time.

[0126] Specifically, the kinematic parameters of at least one body part after adjustment can also be used for the display module to display to the user the contrast effect between the action corresponding to the first action data of the target image in the first preview screen and the action corresponding to the second action data of the source image. The user can manually select a position with a poor contrast effect through the display module, and manually input adjustment parameters such as an adjustment angle or adjustment length corresponding to the position with a poor contrast effect through the interactive interface. After receiving the adjustment parameters, the correction module determines the correction parameters of the redirection algorithm.

[0127] The process in which the display module displays the action corresponding to the first action data of the target image in the first preview screen and the action corresponding to the second action data of the source image to the user can be that the display module displays the parameters, number of joints, bending conditions, angles, etc. of the action corresponding to the first action data of the target image and the action corresponding to the second action data of the source image to the user in the form of a list, or compares the parameters, number of joints, bending conditions, and angles of the action corresponding to the first action data of the target image and the action corresponding to the second action data of the source image, and displays the comparison results to the user in a list. The user can manually select a position with poor contrast effect by combining the list displayed by the display module, and manually input adjustment parameters such as adjustment angle or adjustment length corresponding to the position with poor contrast effect through the interactive interface, and the correction module generates correction parameters after receiving the adjustment parameters.

[0128] For example, the user interface may display a first preview screen and adjustment parameters corresponding to various positions of the action corresponding to the first action data of the target image in the first preview screen, and the user may modify the corresponding adjustment parameters by clicking a certain position of the target virtual image.

[0129] In the process of displaying the contrast effect of the action corresponding to the first action data of the target image in the first preview screen and the action corresponding to the second action data of the source image to the user, the display module can also generate recommended adjustment parameters for the correction module directly according to the difference between the action corresponding to the first action data of the target image in the first preview screen and the action corresponding to the second action data of the source image, and display the recommended adjustment parameters and the first preview screen to the user at the same time, so as to recommend optional recommended adjustment parameters to the user. The user can directly select the adjustment parameters as the adjustment parameters to be input into the correction module, or determine the adjustment parameters based on the recommended adjustment parameters, and manually input the adjustment parameters into the correction module through the interactive interface. After receiving the adjustment parameters, the correction module generates the correction parameters of the redirection algorithm.

[0130] Furthermore, the correction module can detect whether the adjustment parameter input by the user is received within a preset time, and if the adjustment parameter input by the user is received within the preset time, the correction parameter of the redirection algorithm is determined according to the adjustment parameter. If the adjustment parameter input by the user is not received within the preset time, the detection is stopped after the preset time.

[0131] In another possible implementation, the correction instruction further includes an automatic correction instruction, and the correction module determines, in response to the correction instruction, an adjustment value of a kinematic parameter of at least one body part and / or an adjusted kinematic parameter of at least one body part according to a difference between the first motion data and the second motion data of the source image, and determines a correction parameter of the redirection algorithm according to the adjustment value of the kinematic parameter of at least one body part and / or the adjusted kinematic parameter of at least one body part.

[0132] Exemplarily, the user can select the automatic correction instruction by clicking on the display module, and the correction module responds to the automatic correction instruction and automatically determines the adjustment value of the kinematic parameter of at least one body part and / or the kinematic parameter of at least one body part after adjustment according to the difference between the first motion data of the target image and the second motion data of the source image. According to the adjustment value of the kinematic parameter of at least one body part and / or the kinematic parameter of at least one body part after adjustment, the correction parameter of the redirection algorithm is determined.

[0133] It should be noted that the process may also be that if no correction instruction input by the user is received within a preset time, the redirection system automatically determines the correction parameters of the redirection algorithm according to the difference between the first action data of the target image and the second action data of the source image.

[0134] S507: The correction module sends the correction parameters to the redirection module.

[0135] S508, the redirection module uses a redirection algorithm including a correction parameter to determine the corrected first motion data according to the first body shape data of the target image, the second motion data of the source image and the second body shape data of the source image.

[0136] In a possible implementation, the redirection module may correct the second motion data according to the first body shape data, the second body shape data and the correction parameter to generate the first motion data.

[0137] Specifically, the redirection module can utilize the redirection algorithm in the redirection module to determine the first action data based on the first body shape data, the second body shape data and the second action data. The redirection algorithm can be represented by F(a, b, c, d)=e, where d is not a null value and d is a correction parameter.

[0138] In another possible implementation, the redirection module may correct the second action data according to the first body shape data and the second body shape data to obtain a preliminary correction result of the action corresponding to the first action data, and then correct the preliminary correction result in combination with the correction parameter to obtain the first action data.

[0139] In another possible implementation, a smoothing module may be deployed in the redirection system. After the redirection module determines the corrected first motion data according to the first body shape data of the target information, the second motion data of the source image, and the second body shape data of the source image, the redirection module sends the first motion data and the corrected first motion data to the smoothing module. After receiving the first motion data and the corrected first motion data, the smoothing module uses the first motion data to smooth the corrected first motion data to obtain the corrected first motion data after smoothing.

[0140] S509: The redirection module sends the corrected first action data to the display module.

[0141] S510: The display module displays a second preview picture based on the corrected first action data.

[0142] Specifically, the display module displays the second preview image to the user through the interactive interface.

[0143] In a possible implementation, the second preview screen includes a screen of the target image performing an action corresponding to the modified first action data.

[0144] For example, Fig.10 An effect diagram of the second preview screen is shown, and d is the action corresponding to the first action data after the target image performs the correction.

[0145] In another possible implementation, the second preview image also includes a picture of the source image performing the action corresponding to the second action data.

[0146] In another possible implementation, the second preview screen also includes the target image executing the action corresponding to the modified first action data, and also indicates the comparison effect between the target image executing the action corresponding to the modified first action data and the action of the source image.

[0147] For example, Fig.11 Another effect diagram of the second preview screen is shown. The second preview screen is obtained by superimposing a and d.

[0148] The action redirection method provided by the present application can display a preview screen during the process of executing action redirection for the target image. The preview screen is used to indicate the contrast effect between the action of the source image and the action of the target image (i.e., the action redirection result of the target image), so that the user can directly correct the action of the target image based on the contrast effect indicated by the preview screen, and then obtain the correction parameters according to the correction, and input the correction parameters as input parameters into the action redirection module for action redirection. There is no need to adjust the internal algorithm of the action redirection module, making the action redirection method more flexible and saving the action redirection adjustment time. At the same time, the action redirection method provided by the present application is not only applicable to the scene where the action of the target image is close to the body shape of the source image. It is also applicable to the scene where the body shape of the target image and the source image is quite different. For example, after displaying the preview screen, the user can adjust the first action of the target image in the preview screen to a more exaggerated action by inputting adjustment instructions or adjustment parameters.

[0149] In some embodiments, Fig.12As shown, the action redirection method provided by the present application may further include S511-S516. Exemplarily, S511-S516 may be executed after S510. The present application does not limit the number of executions of S511-S516, which may be determined by the user according to the third preview screen.

[0150] S511, the correction module receives a second correction instruction sent by the user.

[0151] Specifically, the process of receiving the second correction instruction sent by the user is the same as the process of receiving the correction instruction sent by the user in the above S505, and this application will not elaborate on this.

[0152] S512: The correction module determines a second correction parameter of the redirection algorithm according to the second correction instruction.

[0153] Specifically, the process in which the correction module determines the second correction parameter of the redirection algorithm according to the second correction instruction is the same as the process in which the correction module determines the correction parameter of the redirection algorithm according to the correction instruction in S506 above, and this application will not elaborate on this.

[0154] S513: The correction module sends the second correction parameter to the redirection module.

[0155] S514, the redirection module uses a redirection algorithm including a second correction parameter to determine the first action data after further correction according to the first body shape data of the target image, the corrected first action data of the source image and the second body shape data of the source image.

[0156] S515: The redirection module sends the revised first action data to the display module.

[0157] S516: The display module displays a third preview image based on the revised first action data.

[0158] Specifically, the process of the display module displaying the third preview picture is the same as the process of the display module displaying the second preview picture in the above S510, which is not described in detail in this application.

[0159] The embodiment of the present application can divide the functional modules of the electronic device according to the above method example. For example, each functional module can be divided according to each function, or two or more functions can be integrated into one processing module. The above integrated module can be implemented in the form of hardware or in the form of software functional modules. It should be noted that the division of modules in the embodiment of the present application is schematic and is only a logical function division. There may be other division methods in actual implementation.

[0160] In the case of dividing each functional module into corresponding functional modules, Fig.13 A possible schematic diagram of the composition of the action redirection device involved in the above-mentioned embodiment is shown. The action redirection device 1300 is deployed in an electronic device. Fig.13 As shown, the action redirection device 1300 may include: an acquisition module 131 , a display module 132 , a receiving module 133 and a determination module 134 .

[0161] The acquisition module 131 is used to support the action redirection device 1300 to execute Figure 5 S501 in the action redirection method shown.

[0162] The display module 132 is used to support the action redirection device 1300 to execute Figure 5 S504 or S510 or Figure 6 S517 in the action redirection method shown.

[0163] The receiving module 133 is used to support the action redirection device 1300 to execute Figure 5 S505 or Figure 6 S511 in the action redirection method shown.

[0164] The determination module 134 is used to support the action redirection device 1300 to execute Figure 5 S506 or S508 or Figure 6 S513 or S515 in the action redirection method shown.

[0165] Further, such as Fig.14 As shown, the action redirection device 1300 provided by the embodiment of the present application may also include: a generating module 135 and a sending module 136.

[0166] The generating module 135 is used to support the action redirection device 1200 to execute Figure 5 S502 in the action redirection method shown.

[0167] The sending module 136 is used to support the action redirection device 1300 to execute Figure 5 S503 or S507 or S509 or Figure 6 S512 or S514 or S516 in the action redirection method shown.

[0168] It should be noted that all relevant contents of each step involved in the above method embodiment can be referred to the functional description of the corresponding functional module and will not be repeated here.

[0169] Among them, the acquisition module 131, the display module 132, the receiving module 133, the determination module 134, the generation module 135 and the sending module 136 can all be implemented by software, or can be implemented by hardware. Exemplarily, the implementation of the acquisition module 131 is described below by taking the acquisition module 131 as an example. Similarly, the implementation of the display module 132, the receiving module 133, the determination module 134, the generation module 135 and the sending module 136 can refer to the implementation of the acquisition module 131.

[0170] As an example of a software functional unit, the acquisition module 131 may include code running on a computing instance. Among them, the computing instance may include at least one of a physical host (electronic device), a virtual machine, and a container. Further, the above-mentioned computing instance may be one or more. For example, the acquisition module 131 may include code running on multiple hosts / virtual machines / containers. It should be noted that the multiple hosts / virtual machines / containers used to run the code may be distributed in the same region (region) or in different regions. Furthermore, the multiple hosts / virtual machines / containers used to run the code may be distributed in the same availability zone (AZ) or in different AZs, each AZ including a data center or multiple data centers with close geographical locations. Among them, usually a region may include multiple AZs.

[0171] Similarly, multiple hosts / virtual machines / containers used to run the code can be distributed in the same virtual private cloud (VPC) or in multiple VPCs. Usually, a VPC is set up in a region. For cross-region communication between two VPCs in the same region and between VPCs in different regions, a communication gateway needs to be set up in each VPC to achieve interconnection between VPCs through the communication gateway.

[0172] As an example of a hardware functional unit, the acquisition module 131 may include at least one electronic device, such as a server, etc. Alternatively, the acquisition module 131 may also be a device implemented using an application-specific integrated circuit (ASIC) or a programmable logic device (PLD). The PLD may be a complex programmable logical device (CPLD), a field-programmable gate array (FPGA), a generic array logic (GAL) or any combination thereof.

[0173] The multiple electronic devices included in the acquisition module 131 can be distributed in the same region or in different regions. The multiple electronic devices included in the acquisition module 131 can be distributed in the same AZ or in different AZs. Similarly, the multiple electronic devices included in the acquisition module 131 can be distributed in the same VPC or in multiple VPCs. The multiple electronic devices can be any combination of electronic devices such as servers, ASICs, PLDs, CPLDs, FPGAs, and GALs.

[0174] It should be noted that, in other embodiments, the acquisition module 131 can be used to execute any step in the action redirection method, the display module 132 can be used to execute any step in the action redirection method, the receiving module 133 can be used to execute any step in the action redirection method, the determination module 134 can be used to execute any step in the action redirection method, the generation module 135 can be used to execute any step in the action redirection method, and the sending module 136 can be used to execute any step in the action redirection method. The steps that the acquisition module 131, the display module 132, the receiving module 133, the determination module 134, the generation module 135 and the sending module 136 are responsible for implementing can be specified as needed. The full functions of the action redirection device are realized by respectively implementing different steps in the action redirection method through the acquisition module 131, the display module 132, the receiving module 133, the determination module 134, the generation module 135 and the sending module 136.

[0175] The action redirection device 1300 provided in the embodiment of the present application is used to execute the above-mentioned action redirection method, and thus can achieve the same effect as the above-mentioned action redirection method.

[0176] The present application also provides an electronic device 1500. Fig.15 As shown, the electronic device 1500 includes: a bus 1501, a processor 1502, a memory 1503 and a communication interface 1504. The processor 1502, the memory 1503 and the communication interface 1504 communicate with each other through the bus 1501. The electronic device 100 can be a server or a terminal device. It should be understood that the present application does not limit the number of processors and memories in the electronic device 100.

[0177] The bus 1501 may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Fig.15 The bus 1502 is represented by only one line, but it does not mean that there is only one bus or one type of bus. The bus 1502 may include a path for transmitting information between various components of the electronic device 1500 (for example, the memory 1503, the processor 1502, and the communication interface 1504).

[0178] The processor 1502 may include any one or more of a central processing unit (CPU), a graphics processing unit (GPU), a microprocessor (MP), or a digital signal processor (DSP).

[0179] The memory 1503 may include a volatile memory, such as a random access memory (RAM). The processor 1502 may also include a non-volatile memory, such as a read-only memory (ROM), a flash memory, a hard disk drive (HDD), or a solid state drive (SSD).

[0180] The memory 1503 stores executable program codes, and the processor 1502 executes the executable program codes to respectively implement the functions of the aforementioned acquisition module 131, display module 132, receiving module 133, determination module 134, generation module 135, and sending module 136, thereby implementing the action re-definition method. That is, the memory 1503 stores instructions for executing the action redirection method.

[0181] Alternatively, the memory 1503 stores executable codes, and the processor 1502 executes the executable codes to respectively implement the functions of the aforementioned action redirection device, thereby implementing the action redirection method. That is, the memory 1503 stores instructions for executing the action redirection method.

[0182] The communication interface 1504 uses a transceiver module such as, but not limited to, a network interface card or a transceiver to implement communication between the electronic device 1500 and other devices or a communication network. An embodiment of the present application also provides an electronic device cluster. The electronic device cluster includes at least one electronic device. The electronic device can be a server, such as a central server, an edge server, or a local server in a local data center. In some embodiments, the electronic device can also be a terminal device such as a desktop computer, a laptop computer, or a smart phone.

[0183] like Fig.16 As shown, the electronic device cluster includes at least one electronic device 1500. The memory 1503 in one or more electronic devices 1500 in the electronic device cluster may store the same instructions for executing the action redirection method.

[0184] In some possible implementations, the memory 1503 of one or more electronic devices 1500 in the electronic device cluster may also store partial instructions for executing the action redirection method. In other words, the combination of one or more electronic devices 1500 may jointly execute instructions for executing the action redirection method.

[0185] It should be noted that the memory 1503 in different electronic devices 1500 in the electronic device cluster can store different instructions, which are respectively used to execute part of the functions of the action redirection device. That is, the instructions stored in the memory 1503 in different electronic devices 1500 can implement the functions of one or more modules of the acquisition module 131, the display module 132, the receiving module 133, the determination module 134, the generation module 135 and the sending module 136.

[0186] In some possible implementations, one or more electronic devices in the electronic device cluster may be connected via a network, which may be a wide area network or a local area network. Fig.17 A possible implementation is shown. Fig.17As shown, two electronic devices 1500A and 1500B are connected via a network. Specifically, the network is connected via a communication interface in each electronic device. In this type of possible implementation, the memory 1503 in the electronic device 1500A stores instructions for executing the functions of the acquisition module 131. At the same time, the memory 1503 in the electronic device 1500B stores instructions for executing the functions of the display module 132, the receiving module 133, the determining module 134, the generating module 135, and the sending module 136.

[0187] Fig.17 The connection mode between the electronic device clusters shown can be considered that the action redirection method provided by the present application needs to display a first preview screen, receive a correction instruction sent by a user, determine the correction parameters of the redirection algorithm according to the correction instruction, and use the redirection algorithm including the correction parameters to determine the corrected first action data and display the second preview screen according to the first body shape data of the target image, the second action data of the source image and the second body shape data of the source image. Therefore, it is considered that the functions implemented by the display module 132, the receiving module 133, the determining module 134, the generating module 135 and the sending module 136 are handed over to the electronic device 1500B for execution.

[0188] It should be understood that Fig.17 The functions of the electronic device 1500A shown in FIG. 1 may also be completed by a plurality of electronic devices 1500. Similarly, the functions of the electronic device 1500B may also be completed by a plurality of electronic devices 1500.

[0189] The present application embodiment also provides another electronic device cluster. The connection relationship between the electronic devices in the electronic device cluster can be similar to that of Fig.16 and Fig.17 The connection mode of the electronic device cluster is different in that the memory 1503 in one or more electronic devices in the electronic device cluster may store the same instruction for executing the action redirection method.

[0190] In some possible implementations, the memory 1503 of one or more electronic devices 1500 in the electronic device cluster may also store partial instructions for executing the action redirection method. In other words, the combination of one or more electronic devices 1500 may jointly execute instructions for executing the action redirection method.

[0191] It should be noted that the memory 1503 in different electronic devices 1500 in the electronic device cluster can store different instructions for executing part of the functions of the action redirection system. That is, the instructions stored in the memory 1503 in different electronic devices 1500 can implement the functions of the action redirection device.

Claims

1. An action redirection method, characterized in that: The method comprises: Acquire first motion data, wherein the first motion data is generated by first body shape data of a target image, second motion data of a source image, and second body shape data of the source image according to a redirection algorithm, wherein the target image includes at least one body part, and the first motion data includes kinematic parameters of the at least one body part; displaying a first preview screen, wherein the first preview screen includes a screen in which the target image performs the action corresponding to the first action data; receiving a correction instruction sent by a user, wherein the correction instruction is used to correct the action corresponding to the first action data performed by the target image, and the correction instruction includes a correction instruction for the kinematic parameters of the at least one body part; Determining correction parameters of the redirection algorithm according to the correction instruction; Determine the corrected first motion data based on the first body shape data of the target image, the second motion data of the source image, and the second body shape data of the source image using the redirection algorithm including the correction parameter; A second preview screen is displayed, wherein the second preview screen includes a screen in which the target image performs an action corresponding to the modified first action data.

2. The method according to claim 1, characterized in that The first preview screen also includes a screen in which the source image performs an action corresponding to the second action data, and the second preview screen also includes a screen in which the source image performs an action corresponding to the second action data.

3. The method according to claim 1 or 2, characterized in that: The first preview screen also indicates the comparison effect between the action corresponding to the first action data of the target image and the action corresponding to the second action data of the source image; the second preview screen also indicates the comparison effect between the action corresponding to the modified first action data executed by the target image and the action corresponding to the second action data of the source image.

4. The method according to any one of claims 1 to 3, characterized in that The method further comprises: The redirection algorithm including the correction parameter is used to determine the third motion data of the other image according to the third body shape data of the other image, the second motion data of the source image and the second body shape data of the source image.

5. The method according to any one of claims 1 to 4, characterized in that Determining the correction parameters of the redirection algorithm according to the correction instruction includes: According to the correction instruction for the kinematic parameter of the at least one body part, obtaining an adjustment value of the kinematic parameter of the at least one body part and / or the kinematic parameter of the at least one body part after adjustment; Correction parameters of the redirection algorithm are determined based on the adjusted values ​​of the kinematic parameters of the at least one body part and / or the adjusted kinematic parameters of the at least one body part.

6. The method according to any one of claims 1 to 4, characterized in that The correction instruction further includes an automatic correction instruction, and determining the correction parameter of the redirection algorithm according to the correction instruction includes: In response to the correction instruction, determining an adjustment value of the kinematic parameter of the at least one body part and / or the adjusted kinematic parameter of the at least one body part according to a difference between the first motion data and the second motion data of the source image; Correction parameters of the redirection algorithm are determined based on the adjusted values ​​of the kinematic parameters of the at least one body part and / or the adjusted kinematic parameters of the at least one body part.

7. The method according to any one of claims 1 to 6, characterized in that The displaying of the first preview picture includes: Overlaying and displaying the target image and the source image; or, displaying the target image and the source image in partitions; Or, generate a point cloud of the target image, and display the point cloud superimposed on the source image.

8. The method according to any one of claims 1 to 7, characterized in that The source image includes an image of a motion capture target.

9. An action redirection device, characterized in that: The device comprises: an acquisition module, configured to acquire first motion data, wherein the first motion data is generated by first body shape data of a target image, second motion data of a source image, and second body shape data of the source image according to a redirection algorithm, wherein the target image includes at least one body part, and the first motion data includes kinematic parameters of the at least one body part; A display module, configured to display a first preview screen, wherein the first preview screen includes a screen in which the target image performs an action corresponding to the first action data; A receiving module, configured to receive a correction instruction sent by a user, wherein the correction instruction is used to correct the action corresponding to the first action data performed by the target image, and the correction instruction includes a correction instruction for the kinematic parameters of the at least one body part; a determination module, configured to determine a correction parameter of the redirection algorithm according to the correction instruction; and determine the corrected first motion data according to the first body shape data of the target image, the second motion data of the source image and the second body shape data of the source image using the redirection algorithm including the correction parameter; The display module is further used to display a second preview screen, wherein the second preview screen includes a screen in which the target image performs an action corresponding to the modified first action data.

10. The device according to claim 9, characterized in that The first preview screen also includes a screen in which the source image performs an action corresponding to the second action data, and the second preview screen also includes a screen in which the source image performs an action corresponding to the second action data.

11. The device according to claim 9 or 10, characterized in that The first preview screen also indicates the comparison effect between the action corresponding to the first action data of the target image and the action corresponding to the second action data of the source image; the second preview screen also indicates the comparison effect between the action corresponding to the modified first action data executed by the target image and the action corresponding to the second action data of the source image.

12. The device according to any one of claims 9 to 11, characterized in that The determination module is further configured to use the redirection algorithm including the correction parameter to determine the third action data of the other image according to the third body shape data of the other image, the second action data of the source image and the second body shape data of the source image.

13. The device according to any one of claims 9 to 12, characterized in that The acquisition module is further configured to obtain, according to the correction instruction for the kinematic parameters of the at least one body part, an adjustment value of the kinematic parameters of the at least one body part and / or the adjusted kinematic parameters of the at least one body part; The determination module is specifically configured to determine correction parameters of the redirection algorithm according to the adjustment value of the kinematic parameter of the at least one body part and / or the adjusted kinematic parameter of the at least one body part.

14. The device according to any one of claims 9 to 12, characterized in that The determination module is specifically used to respond to the correction instruction and determine the adjustment value of the kinematic parameters of the at least one body part and / or the kinematic parameters of the at least one body part after adjustment according to the difference between the first motion data and the second motion data of the source image; and determine the correction parameters of the redirection algorithm according to the adjustment value of the kinematic parameters of the at least one body part and / or the kinematic parameters of the at least one body part after adjustment.

15. The device according to any one of claims 9 to 14, characterized in that The display module is specifically used to display the target image and the source image in a superimposed manner; or, to display the target image and the source image in partitions; or, to generate a point cloud of the target image and to display the point cloud in a superimposed manner with the source image.

16. The device according to any one of claims 9 to 15, characterized in that The source image includes an image of a motion capture target.

17. An electronic equipment cluster, characterized in that: comprising at least one electronic device, each electronic device comprising a processor and a memory; The processor of the at least one electronic device is used to execute instructions stored in the memory of the at least one electronic device, so that the electronic device cluster executes the action redirection method as described in any one of claims 1-8.

18. A computer program product comprising instructions, characterized in that When the instruction is executed by the electronic device cluster, the electronic device cluster executes the action redirection method as described in any one of claims 1-8.

19. A computer-readable storage medium, characterized in that: The method comprises computer program instructions. When the computer program instructions are executed by an electronic device cluster, the electronic device cluster executes the action redirection method as described in any one of claims 1 to 8.

Images