Three-dimensional animation-oriented ethnic dance movement data synthesis method

Abstract

A national dance sports data synthesis method for three-dimensional cartoons belongs to the technical field of sports data synthesis, collects previous communication time points and information frames, instantly evaluates the communication time, evaluates the correct communication time, and can calibrate an audio and video data set of a synthesis terminal according to the communication time. The accuracy of the state of the synthesis terminal is improved, the audio and video data set of the synthesis terminal can be evaluated under the condition that the synthesis terminal has continuous audio and video data loss (the continuous audio and video data loss duration or frequency is not higher than the safe communication critical quantity), and the stability of communication connection of the synthesis terminal is improved.

Description

Technical Field

[0001] The invention belongs to the technical field of motion data synthesis, and in particular relates to a method for synthesizing folk dance motion data for three-dimensional animation. Background Art

[0002] The synthesis of folk dance motion data is to use motion capture technology and artificial intelligence technology to digitally store and display high-quality dance movements, protect and promote folk dance culture, and store and display dance movements in a three-dimensional digital way.

[0003] As for the synthesis of folk dance motion data for three-dimensional animation, currently, the scheme mentioned in the patent publication number "CN117077084A" is often used to perform the synthesis of folk dance motion data for three-dimensional animation, which specifically includes a sensor and a synthesis terminal connected to it for communication (the synthesis terminal can be a computer, and the synthesis terminals are also connected for communication, just as the synthesis terminals are connected to each other in a WLAN), the sensor is used to obtain the audio and video data set of professional dancers and transmit it to the synthesis terminal; the synthesis terminal is used to perform data fusion on the audio and video data set, so as to achieve the purpose of synthesizing folk dance motion data for three-dimensional animation.

[0004] In the sharing era, a synthetic terminal often transmits the audio and video data set of a professional dancer to another synthetic terminal connected to it for communication. However, during the period when a synthetic terminal transmits the audio and video data set of a professional dancer to another synthetic terminal connected to it for communication, communication delays and audio and video data loss often occur during the period when several synthetic terminals transmit the audio and video data set of the professional dancer to each other under the interference of external noise sensors. Communication delays will cause errors between the audio and video data set of the professional dancer received by the synthetic terminal and the actual audio and video data set of the professional dancer. Information frame loss will make the synthetic terminal unable to receive the audio and video data set of another synthetic terminal at a certain point in time. The current common method of transmitting the audio and video data set of the professional dancer to each other is to control the changing address of the synthetic terminal under the condition that there is no communication delay and audio and video data loss to allow the synthetic terminals to execute the transmission of the audio and video data set of the professional dancer to each other, which is obviously not suitable for current communication rules. Summary of the invention

[0005] In order to solve the defects in the prior art, the present invention provides a method for synthesizing folk dance motion data for three-dimensional animation, which collects past communication time points and information frames, and instantly evaluates the communication time. The evaluated communication time is correct, and the audio and video data set of the synthesized terminal can be calibrated according to the communication time, thereby improving the accuracy of the synthesized terminal state. When the synthesized terminal has continuous audio and video data loss (the duration or frequency of continuous audio and video data loss is not higher than the critical amount of safe communication), the audio and video data set of the synthesized terminal can be evaluated, thereby improving the stability of the communication connection of the synthesized terminal.

[0006] The present invention uses the following technical solutions.

[0007] A method for synthesizing folk dance motion data for three-dimensional animation, comprising:

[0008] The sensor obtains the audio and video data set, process noise, and observation noise of professional dancers and transmits them to the synthesis terminal; the synthesis terminal performs data fusion on the audio and video data set to achieve the purpose of synthesizing folk dance movement data for three-dimensional animation;

[0009] In addition, during the period when the synthesis terminal transmits the audio and video data set of the professional dancer to another synthesis terminal connected to the synthesis terminal for communication, the method further includes:

[0010] Step 1: Obtain communication messages, audio and video data sets of the synthetic terminal via the network element and other synthetic terminals;

[0011] Step 2: Based on the communication time points of other synthetic terminals to network elements in the previous 6S, construct the average communication time of other synthetic terminals to network elements v w , the average communication time from the network element to the local synthetic terminal v d , the mode of the average total communication time v from another synthetic terminal to the network element and then to the local synthetic terminal;

[0012] Step 3: Construct a synthetic terminal status evaluation model involving communication time through the average communication time v;

[0013] Step 4: construct an audio and video data set evaluation model involving both communication time and audio and video data loss through a synthetic terminal status evaluation model involving communication time;

[0014] Step 5: Construct an audio and video dataset evaluation method based on the audio and video dataset evaluation model.

[0015] Further, before step 1, the method includes:

[0016] First, construct a real communication time pattern, which is a probability distribution; the equation for the probability distribution of communication time is:

[0017]

[0018] In the equation, υ is the communication time, ν is the mean of the communication time, ε is the variance of the communication time, and e is the Euler number.

[0019] Furthermore, in step 1, the communication message between the synthetic terminal via the network element and another synthetic terminal is the process noise and observation noise transmitted to the synthetic terminal by another synthetic terminal; the audio and video data set of the synthetic terminal via the network element and another synthetic terminal is the audio and video data set transmitted to the synthetic terminal by another synthetic terminal.

[0020] Furthermore, in step 1, the communication messages and the transmission of audio and video data sets between the composite terminal and another composite terminal via the network element are transmitted in the structure of information frames.

[0021] Furthermore, step 2 specifically includes:

[0022] Step 2-1: Calculate the average communication time from another synthetic terminal to the network element v w ;

[0023] Step 2-2: Calculate the average communication time from the network element to the local synthetic terminal v d ;

[0024] Step 2-3: Calculate the average total communication time v from another synthetic terminal to the network element and then to the local synthetic terminal.

[0025] Further, in step 2-1, the average communication time from another synthetic terminal to the network element is calculated as v w The equation is:

[0026]

[0027] In the equation, u j,k,d is the time point when the network element receives the kth information frame of the jth synthetic terminal, u j,k,w is the time point when the jth synthetic terminal transmits the kth information frame to the network element, and l is the total number of information frames transmitted in the past 6S.

[0028] Further, in step 2-2, the average communication time from the network element to the local synthetic terminal is calculated as v d The equation is:

[0029]

[0030] In the equation, u′ j,k,w is the time point when the local synthesis terminal receives the kth information frame transmitted by the jth synthesis terminal from the network element, u′ j,k,dis the time point when the kth information frame of the jth synthetic terminal is transmitted from the network element to the local synthetic terminal, and l is the total number of information frames transmitted in the past 6S.

[0031] Furthermore, in step 2-3, the equation for calculating the average total communication time v from another synthetic terminal to the network element and then to the local synthetic terminal is:

[0032] υ=υ w +υ d

[0033] In the equation, υ w is the average time taken for the communication from the other synthetic terminal to the network element, υ d It is the average communication time from the network element to the local synthetic terminal.

[0034] Furthermore, in step 3, the equation for constructing the synthetic terminal state evaluation mode involving communication time is:

[0035]

[0036] In the equation, are the binary value, process noise value and observation noise value of the calibrated audio and video data set of the jth synthetic terminal at time u, respectively; are the binary values ​​of the audio and video data set received by the network element at time u by the jth synthetic terminal, the process noise value and the observation noise value, that is, before calibration; j,u It is the average total communication time when the j-th synthetic terminal communicates with other synthetic terminals at time u.

[0037] Further, in step 4, the equation for constructing an evaluation model of an audio and video data set with communication time and audio and video data loss is:

[0038]

[0039] In the equation, are the binary value, process noise value and observation noise value of the calibrated audio and video data set of the jth synthetic terminal at the time ua*g respectively; are the binary values ​​of the audio and video data set received by the network element at the jth synthetic terminal at the time ua*g, the process noise value and the observation noise value, that is, before calibration; j,u-a*g is the average total communication time of the jth synthetic terminal when ua*g communicates with other synthetic terminals, a is the frequency of continuous audio and video data loss, and g is the time interval between two continuous communications.

[0040] Further, in step 5, a method for constructing an audio and video dataset evaluation method according to the audio and video dataset evaluation mode includes:

[0041] Step 5-1: According to the sequence number comparison of the information frame, determine whether there is any information frame loss in the information frame transmission through the network element;

[0042] Step 5-2: If no information frame is lost, the effect of communication time on the evaluation of other audio and video data sets is evaluated, and step 3 is executed;

[0043] Step 5-3: If the frequency or duration of the continuous loss of information frames is lower than the critical amount of safe communication, the effect of synchronous communication time and audio and video data loss on other audio and video data sets is evaluated, and step 4 is executed;

[0044] Step 5-4: If there is frame loss, then determine whether it is continuous frame loss based on the comparison of the frame sequence number. If the frequency or duration of continuous frame loss exceeds the safe communication threshold, it is considered as communication interruption, and the evaluation of other audio and video data sets is terminated accordingly.

[0045] A device for synthesizing folk dance motion data for three-dimensional animation, comprising:

[0046] The sensor is connected to a synthesis terminal which is in communication with the synthesis terminal. The synthesis terminal is connected to another synthesis terminal via a network element. The sensor is used to obtain audio and video data sets, process noise, and observation noise of professional dancers and transmit them to the synthesis terminal. The synthesis terminal is used to perform data fusion on the audio and video data sets, so as to achieve the purpose of synthesizing folk dance movement data for three-dimensional animation.

[0047] Modules that run on the synthetic terminal include:

[0048] An acquisition module, which is used to acquire communication messages, audio and video data sets of the synthesis terminal via the network element and other synthesis terminals;

[0049] Construction module 1, which is used to construct another synthetic terminal to network element communication time average v according to the communication time point of another synthetic terminal to network element communication in the previous 6S w , the average communication time from the network element to the local synthetic terminal v d , the mode of the average total communication time v from another synthetic terminal to the network element and then to the local synthetic terminal;

[0050] Evaluation module 1, which is used to construct a synthetic terminal status evaluation model involving communication time through the communication time average υ;

[0051] Evaluation module 2, which is used to construct an audio and video data set evaluation model involving communication time and audio and video data loss through a synthetic terminal state evaluation model involving communication time;

[0052] Construction module two is used to construct an audio and video dataset evaluation method based on the audio and video dataset evaluation model.

[0053] The beneficial effect of the present invention is that, compared with the prior art, the present invention can collect past communication time points and information frames, and instantly evaluate the communication time. The evaluated communication time is correct, and the audio and video data set of the synthetic terminal can be calibrated according to the communication time, thereby improving the accuracy of the synthetic terminal state. When the synthetic terminal has continuous audio and video data loss (the duration or frequency of continuous audio and video data loss is not higher than the critical amount of safe communication), the audio and video data set of the synthetic terminal can be evaluated, thereby improving the stability of the communication connection of the synthetic terminal. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] Figure 1 It is a partial flow chart of the method for synthesizing folk dance motion data for three-dimensional animation described in the present invention;

[0055] Figure 2 It is a schematic diagram of the module structure of the device for synthesizing folk dance motion data for three-dimensional animation described in the present invention. DETAILED DESCRIPTION

[0056] In the sharing era, a synthetic terminal often transmits the audio and video data set of a professional dancer to another synthetic terminal connected to it for communication. However, during the period when a synthetic terminal transmits the audio and video data set of a professional dancer to another synthetic terminal connected to it for communication, communication delays and audio and video data loss often occur during the period when several synthetic terminals transmit the audio and video data set of the professional dancer to each other under the interference of external noise sensors. Communication delays will cause errors between the audio and video data set of the professional dancer received by the synthetic terminal and the actual audio and video data set of the professional dancer. Information frame loss will make the synthetic terminal unable to receive the audio and video data set of another synthetic terminal at a certain point in time. The current common method of transmitting the audio and video data set of the professional dancer to each other is to control the changing address of the synthetic terminal under the condition that there is no communication delay and audio and video data loss to allow the synthetic terminals to execute the transmission of the audio and video data set of the professional dancer to each other, which is obviously not suitable for current communication rules. The present invention can collect past communication time points and information frames, and instantly evaluate the communication time. The evaluated communication time is correct, and the audio and video data set of the synthetic terminal can be calibrated according to the communication time, thereby improving the accuracy of the synthetic terminal state. When the synthetic terminal has continuous audio and video data loss (the duration or frequency of the continuous audio and video data loss is not higher than the critical amount of safe communication), the audio and video data set of the synthetic terminal can be evaluated, thereby improving the stability of the communication connection of the synthetic terminal.

[0057] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely expressed in combination with the drawings in the embodiments of the present invention. The embodiments expressed in this application are only embodiments of a part of the present invention, not all embodiments. According to the spirit of the present invention, other embodiments obtained by ordinary technicians in this field without creative work are all within the scope of protection of the present invention.

[0058] like Figure 1 As shown, the method for synthesizing folk dance motion data for three-dimensional animation of the present invention comprises:

[0059] The sensor obtains the audio and video data set, process noise, and observation noise of professional dancers and transmits them to the synthesis terminal; the synthesis terminal performs data fusion on the audio and video data set to achieve the purpose of synthesizing folk dance movement data for three-dimensional animation;

[0060] In addition, during the period when the synthesis terminal transmits the audio and video data set of the professional dancer to another synthesis terminal connected to the synthesis terminal, the method further includes the following method running on the synthesis terminal:

[0061] In a preferred but non-limiting embodiment of the present invention, before step 1, the process comprises:

[0062] First, construct a real communication time pattern, which is a probability distribution; the equation for the probability distribution of communication time is:

[0063]

[0064] In the equation, υ is the communication time, ν is the mean of the communication time, ε is the variance of the communication time, and e is the Euler number. Then execute the following process:

[0065] Step 1: Obtain communication messages, audio and video data sets of the synthetic terminal via the network element and other synthetic terminals;

[0066] In a preferred but non-restrictive implementation of the present invention, in step 1, the communication message between the synthetic terminal via the network element and another synthetic terminal is the process noise and observation noise transmitted to the synthetic terminal by another synthetic terminal; the audio and video data set of the synthetic terminal via the network element and another synthetic terminal is the audio and video data set transmitted to the synthetic terminal by another synthetic terminal.

[0067] In a preferred but non-limiting embodiment of the present invention, in step 1, the communication messages and the transmission of audio and video data sets between the synthesis terminal and another synthesis terminal via the network element are transmitted in the structure of information frames.

[0068] Step 2: Based on the communication time points of the other synthetic terminals to the network element in the previous 6S (the communication time points include the start time point of the information frame transmission, the time point when the information frame arrives at the network element, etc.), construct the average communication time of the other synthetic terminals to the network element v w , the average communication time from the network element to the local synthetic terminal v d , the mode of the average total communication time v from another synthetic terminal to the network element and then to the local synthetic terminal;

[0069] In a preferred but non-limiting embodiment of the present invention, step 2 specifically comprises:

[0070] Step 2-1: Calculate the average communication time from another synthetic terminal to the network element v w ;

[0071] In a preferred but non-limiting embodiment of the present invention, in step 2-1, the average communication time v from another synthetic terminal to the network element is calculated. w The equation is:

[0072]

[0073] In the equation, u j,k,d is the time point when the network element receives the kth information frame of the jth synthetic terminal, u j,k,w is the time point when the jth synthetic terminal transmits the kth information frame to the network element, l is the total number of information frames transmitted in the previous 6S, the value of l in this application is one hundred, and n is the total number of synthetic terminals connected to the network element for communication.

[0074] Step 2-2: Calculate the average communication time from the network element to the local synthetic terminal v d ;

[0075] In a preferred but non-limiting embodiment of the present invention, in step 2-2, the average communication time v from the network element to the local synthetic terminal is calculated. d The equation is:

[0076]

[0077] In the equation, u′ j,k,w is the time point when the local synthesis terminal receives the kth information frame transmitted by the jth synthesis terminal from the network element, u′ j,k,d is the time point when the kth information frame of the jth synthetic terminal is transmitted by the network element to the local synthetic terminal, l is the total number of information frames transmitted in the past 6S, and the value of l in this application is one hundred.

[0078] Step 2-3: Calculate the average total communication time v from another synthetic terminal to the network element and then to the local synthetic terminal.

[0079] In a preferred but non-limiting embodiment of the present invention, in step 2-3, the equation for calculating the average total communication time v from another synthetic terminal to the network element and then to the local synthetic terminal is:

[0080] υ=υ w +υ d

[0081] In the equation, υ w is the average time taken for the communication from the other synthetic terminal to the network element, υ d It is the average communication time from the network element to the local synthetic terminal.

[0082] Step 3: Construct a synthetic terminal status evaluation model involving communication time through the average communication time v;

[0083] In a preferred but non-limiting embodiment of the present invention, in step 3, the equation for constructing the synthetic terminal state evaluation model involving communication time is:

[0084]

[0085] In the equation, are the binary value, process noise value and observation noise value of the calibrated audio and video data set of the jth synthetic terminal at time u, respectively; are the binary values ​​of the audio and video data set received by the network element at time u by the jth synthetic terminal, the process noise value and the observation noise value, that is, before calibration; j,u It is the average total communication time when the j-th synthetic terminal communicates with other synthetic terminals at time u.

[0086] Step 4: construct an audio and video data set evaluation model involving both communication time and audio and video data loss through a synthetic terminal status evaluation model involving communication time;

[0087] In a preferred but non-limiting embodiment of the present invention, in step 4, the equation for constructing an audio and video data set evaluation model with communication time and audio and video data loss is:

[0088]

[0089] In the equation, are the binary value, process noise value and observation noise value of the calibrated audio and video data set of the jth synthetic terminal at the time ua*g respectively; are the binary values ​​of the audio and video data set received by the network element at the jth synthetic terminal at the time ua*g, the process noise value and the observation noise value, that is, before calibration; j,u-a*gIt is the average total communication time of the jth synthetic terminal when ua*g communicates with other synthetic terminals, a is the frequency of continuous audio and video data loss, g is the time interval between two continuous communications, which can be 0.2S in this application.

[0090] Step 5: Construct an audio and video dataset evaluation method based on the audio and video dataset evaluation model.

[0091] In a preferred but non-limiting embodiment of the present invention, in step 5, a method for constructing an audio and video dataset evaluation method according to an audio and video dataset evaluation mode includes:

[0092] Step 5-1: Based on the sequence number of the information frame (the sequence number is always continuous, if it is not continuous, it is lost), determine whether there is any information frame loss in the information frame transmission through the network element;

[0093] Step 5-2: If no information frame is lost, the effect of communication time on the evaluation of other audio and video data sets is evaluated, and step 3 is executed;

[0094] Step 5-3: If the frequency or duration of the continuous loss of information frames is lower than the critical amount of safe communication, the effect of synchronous communication time and audio and video data loss on other audio and video data sets is evaluated, and step 4 is executed;

[0095] Step 5-4: If there is frame loss, then determine whether it is continuous frame loss based on the comparison of the frame sequence number. If the frequency or duration of continuous frame loss exceeds the safe communication threshold, it is considered as communication interruption, and the evaluation of other audio and video data sets is terminated accordingly.

[0096] The security communication critical value in step 5-3 of the present application represents a value used to evaluate whether the audio and video data set evaluated by the method is correct. The value is the continuous information frame loss market or the continuous audio and video data loss frequency, specifically 0.6s or six times. If the frequency or duration of continuous audio and video data loss is higher than the security communication critical value, the evaluated audio and video data set is deemed incorrect and the evaluation will not be performed. If it is lower than the security communication critical value, the evaluation can be performed.

[0097] like Figure 2 As shown, the device for synthesizing folk dance motion data for three-dimensional animation of the present invention comprises:

[0098] The sensor is connected to a synthesis terminal (the synthesis terminal can be a computer, and the synthesis terminals are also connected to each other, just as the synthesis terminals are connected to each other in a WLAN), and the synthesis terminal is connected to another synthesis terminal via a network element (the network element can be a router or a switch). The sensor is used to obtain the audio and video data set, process noise, and observation noise of the professional dancer and transmit them to the synthesis terminal; the synthesis terminal is used to perform data fusion on the audio and video data set, so as to achieve the purpose of synthesizing folk dance movement data for three-dimensional animation;

[0099] Modules that run on the synthetic terminal include:

[0100] An acquisition module, which is used to acquire communication messages, audio and video data sets of the synthesis terminal via the network element and other synthesis terminals;

[0101] Construction module 1, which is used to construct another synthetic terminal to network element communication time average v according to the communication time point of another synthetic terminal to network element communication in the previous 6S w , the average communication time from the network element to the local synthetic terminal v d , the mode of the average total communication time v from another synthetic terminal to the network element and then to the local synthetic terminal;

[0102] Evaluation module 1, which is used to construct a synthetic terminal status evaluation model involving communication time through the communication time average υ;

[0103] Evaluation module 2, which is used to construct an audio and video data set evaluation model involving communication time and audio and video data loss through a synthetic terminal state evaluation model involving communication time;

[0104] Construction module two is used to construct an audio and video dataset evaluation method based on the audio and video dataset evaluation model.

[0105] The beneficial effect of the present invention is that, compared with the prior art, the present invention can collect past communication time points and information frames, and instantly evaluate the communication time. The evaluated communication time is correct, and the audio and video data set of the synthetic terminal can be calibrated according to the communication time, thereby improving the accuracy of the synthetic terminal state. When the synthetic terminal has continuous audio and video data loss (the duration or frequency of continuous audio and video data loss is not higher than the critical amount of safe communication), the audio and video data set of the synthetic terminal can be evaluated, thereby improving the stability of the communication connection of the synthetic terminal.

[0106] The present disclosure can be a system, method and / or computer program product. The computer program product can include a computer-readable backup medium carrying computer-readable program instructions for causing a processor to implement various aspects of the disclosure.

[0107] The computer readable backup medium can be a tangible network capable of retaining and backing up the instructions used by the instruction execution network. The computer readable backup medium can be, but is not limited to, an electrical backup network, a magnetic backup network, an optical backup network, an electromagnetic backup network, a semiconductor backup network, or any suitable combination of the above. Further examples of computer readable backup media (non-exhaustive list) include: portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), static random access memory (SRAM), portable compact disk read-only memory (HD-ROM), digital versatile disk (DXD), memory stick, floppy disk, mechanically encoded network, such as punch cards or protrusions in grooves with instructions backed up thereon, and any suitable combination of the above. The computer readable backup medium used herein is not to be construed as a transient signal per se, such as a radio wave or other freely propagating electromagnetic wave, an electromagnetic wave propagating through a waveguide or other transmission medium (e.g., a light pulse through a power line cable), or an electrical signal transmitted through wires.

[0108] The computer readable program instructions expressed herein can be downloaded from the computer readable backup medium to each inference / processing power grid line, or downloaded to an external computer or external backup power grid line through a wireless network, such as the Internet, a local area network, a wide area network and / or a wireless network. The wireless network can include copper transmission cables, power transmission lines, wireless transmission, routers, firewalls, switches, gateway computers and / or edge service devices. The wireless network adapter card or wireless network interface in each inference / processing power grid line receives the computer readable program instructions from the wireless network and forwards the computer readable program instructions for storage in the computer readable backup medium in each inference / processing power grid line.

[0109] The computer program instructions for performing the operations of the present disclosure can be assembler instructions, instruction set architecture (ISA) instructions, machine instructions, machine-related instructions, microcode, firmware instructions, conditional setting values, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Sdaletal A, H++, etc., and conventional procedural programming languages ​​such as "H" language or similar programming languages. The computer-readable program instructions can be executed completely on the client computer, partially on the client computer, as a separate software package, partially on the client computer and partially on the remote computer, or completely on the remote computer or server. In the case of a remote computer, the remote computer can be connected to the client computer through any other wireless network, including a local area network (LAb) or a wide area network (WAb), or can be connected to an external computer (just like using an Internet service provider to connect through the Internet). In some embodiments, the electronic circuit is customized by using the status values ​​of computer-readable program instructions, such as a programmable logic circuit, a field programmable gate array (FPGA) or a programmable logic array (PLA), and the electronic circuit can execute computer-readable program instructions to achieve various aspects of the overhead disclosure.

[0110] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents, and any modifications or equivalent replacements that do not deviate from the spirit and scope of the present invention should be covered within the protection scope of the claims of the present invention.

Claims

1. A method for synthesizing folk dance motion data for three-dimensional animation, characterized in that: include: The sensor obtains the audio and video data set, process noise, and observation noise of professional dancers and transmits them to the synthesis terminal; the synthesis terminal performs data fusion on the audio and video data set to achieve the purpose of synthesizing folk dance movement data for three-dimensional animation; In addition, during the period when the synthesis terminal transmits the audio and video data set of the professional dancer to another synthesis terminal connected to the synthesis terminal for communication, the method further includes: Step 1: Obtain communication messages, audio and video data sets of the synthetic terminal via the network element and other synthetic terminals; Step 2: Based on the communication time points of other synthetic terminals to network elements in the previous 6S, construct the average communication time of other synthetic terminals to network elements v w , the average communication time from the network element to the local synthetic terminal v d , the mode of the average total communication time v from another synthetic terminal to the network element and then to the local synthetic terminal; Step 3: Construct a synthetic terminal status evaluation model involving communication time through the average communication time v; Step 4: construct an audio and video data set evaluation model involving both communication time and audio and video data loss through a synthetic terminal status evaluation model involving communication time; Step 5: Construct an audio and video dataset evaluation method based on the audio and video dataset evaluation model.

2. The method for synthesizing folk dance motion data for three-dimensional animation according to claim 1, characterized in that: Before step 1, include: First, construct a real communication time pattern, which is a probability distribution; the equation for the probability distribution of communication time is: In the equation, υ is the communication time, ν is the mean of the communication time, ε is the variance of the communication time, and e is the Euler number.

3. The method for synthesizing folk dance motion data for three-dimensional animation according to claim 2, characterized in that: In step 1, the communication message between the synthesis terminal and another synthesis terminal via the network element is the process noise and observation noise transmitted to the synthesis terminal by another synthesis terminal; the audio and video data set of the synthesis terminal via the network element and another synthesis terminal is the audio and video data set transmitted to the synthesis terminal by another synthesis terminal; In step 1, the communication messages and the transmission of audio and video data sets between the composite terminal and another composite terminal via the network element are transmitted in the structure of information frames.

4. The method for synthesizing folk dance motion data for three-dimensional animation according to claim 3, characterized in that: Step 2 specifically includes: Step 2-1: Calculate the average communication time from another synthetic terminal to the network element v w ; Step 2-2: Calculate the average communication time from the network element to the local synthetic terminal v d ; Step 2-3: Calculate the average total communication time v from another synthetic terminal to the network element and then to the local synthetic terminal.

5. The method for synthesizing folk dance motion data for three-dimensional animation according to claim 4, characterized in that: In step 2-1, calculate the average communication time v from another synthetic terminal to the network element w The equation is: In the equation, u j,k ,d is the time point when the network element receives the kth information frame of the jth synthetic terminal, u j,k ,w is the time point when the jth synthetic terminal transmits the kth information frame to the network element, and l is the total number of information frames transmitted in the past 6S.

6. The method for synthesizing folk dance motion data for three-dimensional animation according to claim 5, characterized in that: In step 2-2, the average communication time from the network element to the local synthetic terminal is calculated as v d The equation is: In the equation, u′ j,k,w is the time point when the local synthesis terminal receives the kth information frame transmitted by the jth synthesis terminal from the network element, u′ j,k,d is the time point at which the kth information frame of the jth synthetic terminal is transmitted from the network element to the local synthetic terminal, and l is the total number of information frames transmitted in the past 6S; In step 2-3, the equation for calculating the average total communication time v from another synthetic terminal to the network element and then to the local synthetic terminal is: υ=υ w +u d In the equation, υ w is the average time taken for the communication from the other synthetic terminal to the network element, υ d It is the average communication time from the network element to the local synthetic terminal.

7. The method for synthesizing folk dance motion data for three-dimensional animation according to claim 6, characterized in that: In step 3, the equation for constructing the synthetic terminal status evaluation model involving communication time is: In the equation, are the binary value, process noise value and observation noise value of the calibrated audio and video data set of the jth synthetic terminal at time u, respectively; are the binary values ​​of the audio and video data set received by the network element at time u by the jth synthetic terminal, the process noise value and the observation noise value, that is, before calibration; j,u It is the average total communication time when the j-th synthetic terminal communicates with other synthetic terminals at time u.

8. The method for synthesizing folk dance motion data for three-dimensional animation according to claim 7, characterized in that: In step 4, the equation for constructing the evaluation model of the audio and video data set with communication time and audio and video data loss is: In the equation, are the binary value, process noise value and observation noise value of the calibrated audio and video data set of the jth synthetic terminal at the time ua*g respectively; are the binary values ​​of the audio and video data set received by the network element at the jth synthetic terminal at the time ua*g, the process noise value and the observation noise value, that is, before calibration; j,u-a*g is the average total communication time of the jth synthetic terminal when ua*g communicates with other synthetic terminals, a is the frequency of continuous audio and video data loss, and g is the time interval between two continuous communications.

9. The method for synthesizing folk dance motion data for three-dimensional animation according to claim 8, characterized in that: In step 5, a method for constructing an audio and video dataset evaluation method according to the audio and video dataset evaluation mode includes: Step 5-1: According to the sequence number comparison of the information frame, determine whether there is any information frame loss in the information frame transmission through the network element; Step 5-2: If no information frame is lost, the effect of communication time on the evaluation of other audio and video data sets is evaluated, and step 3 is executed; Step 5-3: If the frequency or duration of the continuous loss of information frames is lower than the critical amount of safe communication, the effect of synchronous communication time and audio and video data loss on other audio and video data sets is evaluated, and step 4 is executed; Step 5-4: If there is frame loss, then determine whether it is continuous frame loss based on the comparison of the frame sequence number. If the frequency or duration of continuous frame loss exceeds the safe communication threshold, it is considered as communication interruption, and the evaluation of other audio and video data sets is terminated accordingly.

10. A device for synthesizing folk dance motion data for three-dimensional animation, characterized in that: include: The sensor is connected to a synthesis terminal which is in communication with the synthesis terminal. The synthesis terminal is connected to another synthesis terminal via a network element. The sensor is used to obtain audio and video data sets, process noise, and observation noise of professional dancers and transmit them to the synthesis terminal. The synthesis terminal is used to perform data fusion on the audio and video data sets, so as to achieve the purpose of synthesizing folk dance movement data for three-dimensional animation. Modules that run on the synthetic terminal include: An acquisition module, which is used to acquire communication messages, audio and video data sets of the synthesis terminal via the network element and other synthesis terminals; Construction module 1, which is used to construct another synthetic terminal to network element communication time average v according to the communication time point of another synthetic terminal to network element communication in the previous 6S w , the average communication time from the network element to the local synthetic terminal v d , the mode of the average total communication time v from another synthetic terminal to the network element and then to the local synthetic terminal; Evaluation module 1, which is used to construct a synthetic terminal status evaluation model involving communication time through the communication time average υ; Evaluation module 2, which is used to construct an audio and video data set evaluation model involving communication time and audio and video data loss through a synthetic terminal state evaluation model involving communication time; Construction module two is used to construct an audio and video dataset evaluation method based on the audio and video dataset evaluation model.

Images