Interaction animation generation method, system and device based on action recognition

Abstract

This application discloses an interactive animation generation method, system, and device based on action recognition, including: associating a target user and a target role; collecting first action data of the target user and preprocessing it to obtain second action data; determining whether the second action data includes a key action corresponding to a preset standard action; if it includes a key action, generating a key action tag based on the key action's timestamp and name, and recording the key action tag; when a new key action tag is generated, determining whether a new key action tag combination that meets preset conditions exists; if it exists, acquiring complex action data corresponding to the key action tag combination; and driving the target role to perform actions based on the second action data and the complex action data. This solves the problem that existing technologies still have significant technical obstacles in controlling complex actions, and can only provide simple actions and interactions.

Description

Technical Field

[0001] This application relates to the field of computer animation production technology, and in particular to interactive animation generation methods, systems and devices based on motion recognition. Background Technology

[0002] With the rapid development of computer graphics and virtual reality technologies, interactive animation generation has become an important field of research and application. Traditional animation generation methods mainly rely on manual design and keyframe technology. This method usually requires animators to manually adjust the posture of each frame according to the needs of the plot. Although it can produce high-quality animation effects, its creative process is tedious and inefficient. In order to improve the efficiency and accuracy of animation production, motion capture technology has been widely used in recent years and has become one of the core technologies of interactive animation generation. Motion capture technology captures the motion data of humans or other objects in real time through sensors and camera equipment, and then converts it into digital information to reconstruct motion in a virtual environment. Through this technology, virtual characters can quickly achieve natural and smooth movements, greatly improving the efficiency of animation production, and exhibiting more realistic interactive effects in the combination of motion capture and virtual characters.

[0003] However, despite significant advancements in motion capture technology for animation production, existing techniques still face several bottlenecks, particularly in the control and interaction of complex movements. Firstly, current motion capture systems often rely on limited sensor deployment, making it difficult to accurately capture minute details and changes in complex movements. This is especially true when dealing with multi-dimensional, multi-degree-of-freedom, high-difficulty movements, where the system's capture accuracy and real-time data processing capabilities are limited. Furthermore, while modern motion capture technology can provide relatively realistic dynamic effects in animation generation, its real-time response capability for complex interactions between characters and their environment remains relatively limited. Specifically, during interaction, the real-time nature and naturalness of the user's actions and the virtual character's reactions cannot be perfectly matched, thus restricting the smoothness and interactivity of the animation.

[0004] In conclusion, although motion capture technology has made some progress in the field of interactive animation generation, existing technologies still face significant technical obstacles in terms of controlling complex movements and the real-time performance and accuracy of interactive processes. This results in existing interactive animations based on motion capture technology only providing simple movements and interactions in games or other similar fields, with poor playability. Summary of the Invention

[0005] This invention provides a method, system, and device for generating interactive animations based on motion recognition. It offers a solution for automatically generating interactive animations based on motion capture, and at least solves the problem that existing technologies still have significant technical obstacles in terms of controlling complex actions, the real-time performance and accuracy of interactive processes, and can only provide simple actions and interactions with poor playability.

[0006] This application provides an interactive animation generation method based on action recognition, including:

[0007] The target user and target role are associated so that the target user can control the target role through their own actions.

[0008] The action data of the target user is continuously collected as the first action data, and the second action data is obtained after preprocessing the first action data;

[0009] Analyze the second action data and determine whether the second action data includes a key action corresponding to a preset standard action;

[0010] If the second action data includes the key action, then a key action tag is generated based on the timestamp and name of the key action, and the key action tag is recorded.

[0011] When a new key action label is generated, it is determined whether there is a new combination of key action labels that meets the preset conditions;

[0012] If a new combination of key action tags that meets the preset conditions exists, then the complex action data corresponding to the combination of key action tags is obtained.

[0013] Based on the second motion data and the complex motion data, the target character is driven to perform actions.

[0014] Optionally, the association based on the target user and the target role, so that the target user can control the target role through their own actions, includes:

[0015] A target character is created in 3D modeling software, and a character model is generated. The character model includes key control nodes for controlling the movements of the target character.

[0016] Collect motion capture data of the target user to obtain the target user's key skeletal points;

[0017] The 3D modeling software establishes a connection between the key skeletal points and the key control nodes, enabling the target user to control the target character through their own actions.

[0018] Optionally, the continuously collected action data of the target user is the first action data, and the second action data is obtained after preprocessing the first action data, including:

[0019] The target user's action data is continuously collected as the first action data, which includes the coordinate data of key skeleton points changing over time.

[0020] Based on the coordinate data of the key skeleton points changing over time, the trajectory data of the key skeleton points is obtained;

[0021] Based on the trajectory data of the key skeletal points, the trajectory data of the key skeletal points is smoothed at least to obtain the second motion data.

[0022] Optionally, parsing the second action data and determining whether the second action data includes a key action corresponding to a preset standard action includes:

[0023] Analyze the second motion data to obtain the trajectory data of each key skeletal point;

[0024] Based on the trajectory data of each key skeletal point, the relative motion data between each key skeletal point is obtained;

[0025] Determine whether the relative motion data that matches the preset standard action is included within the preset sliding time window;

[0026] If the relative motion data includes the relative motion data that matches the preset standard motion, then the second motion data includes the key motion corresponding to the preset standard motion.

[0027] Optionally, before the step of determining whether a new combination of key action tags that meets preset conditions exists when a new key action tag is generated, the method further includes:

[0028] An empty tag sequence is created to store key action tags. The tag sequence is configured to be cleared whenever no key action tag is added to the tag sequence within a preset time threshold.

[0029] The tag sequence is also configured to add a new key action tag to the tag sequence when a new key action tag is generated.

[0030] Optionally, when a new key action tag is generated, determining whether a new combination of key action tags that meets preset conditions includes:

[0031] When a new key action label is generated, the new key action label is added to the label sequence;

[0032] Determine whether, after adding a new key action tag, all the key action tags in the tag sequence can form a key action tag combination that meets preset conditions or form part of a key action tag combination that meets preset conditions.

[0033] If a combination of key action labels that meets the preset conditions can be formed, then the combination of key action labels is recorded.

[0034] If it can form part of a key action tag combination that meets the preset conditions, then wait;

[0035] If a key action tag combination that meets the preset conditions cannot be formed, or if a key action tag combination that meets the preset conditions cannot be formed, then the tag sequence is cleared and the new key action tag is added back to the tag sequence.

[0036] When the tag sequence is cleared, if there is a recorded key action tag combination in the tag sequence, then there is a new key action tag combination that meets the preset conditions, and the new key action tag combination that meets the preset conditions is configured as the latest recorded key action tag combination in the tag sequence.

[0037] Optional, also includes:

[0038] Obtain the average time for the target user to complete a standard action, and set the time threshold based on the input setting parameters.

[0039] Optionally, driving the target character to perform actions based on the second action data and the complex action data includes:

[0040] When the complex action data is not obtained, the target character is driven to perform actions based on the second action data;

[0041] When the complex motion data is obtained, the target character is driven to perform actions based on the complex motion data.

[0042] On the other hand, an interactive animation generation system based on motion recognition includes a motion capture module and an animation generation module;

[0043] The motion capture module is configured as follows:

[0044] The action data of the target user is continuously collected as the first action data, and the second action data is obtained after preprocessing the first action data;

[0045] The animation generation module is configured as follows:

[0046] The target user and target role are associated so that the target user can control the target role through their own actions.

[0047] Analyze the second action data and determine whether the second action data includes a key action corresponding to a preset standard action;

[0048] If the second action data includes the key action, then a key action tag is generated based on the timestamp and name of the key action, and the key action tag is recorded.

[0049] When a new key action label is generated, it is determined whether there is a new combination of key action labels that meets the preset conditions;

[0050] If a new combination of key action tags that meets the preset conditions exists, then the complex action data corresponding to the combination of key action tags is obtained.

[0051] Based on the second motion data and the complex motion data, the target character is driven to perform actions.

[0052] In another aspect, embodiments of this application also provide an apparatus including a memory and a processor, wherein the memory stores a computer program and the processor executes the computer program to implement the above-described method.

[0053] In another aspect, embodiments of this application also provide a computer-readable storage medium storing a computer program, wherein a processor executes the computer program to implement the above-described method.

[0054] Compared with the prior art, the present invention has the following advantages and beneficial effects:

[0055] This invention discloses an interactive animation generation method, system, and device based on action recognition. The method includes: associating a target user with a target role, enabling the target user to control the target role through their own actions; continuously collecting action data from the target user as first action data; preprocessing the first action data to obtain second action data; parsing the second action data to determine whether it includes a key action corresponding to a preset standard action; if the second action data includes the key action, generating a key action tag based on the key action's timestamp and name, and recording the key action tag; when a new key action tag is generated, determining whether a new key action tag combination that meets preset conditions exists; if a new key action tag combination that meets preset conditions exists, acquiring complex action data corresponding to the key action tag combination; and driving the target role to perform actions based on the second action data and the complex action data. This invention at least solves the problem that existing technologies still have significant technical obstacles in controlling complex actions, the real-time performance and accuracy of the interaction process, and can only provide simple actions and interactions with poor playability. Attached Figure Description

[0056] To more clearly illustrate the technical solutions in the specific embodiments of this application or the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. In all the drawings, similar elements or parts are generally identified by similar reference numerals. In the drawings, the elements or parts are not necessarily drawn to scale.

[0057] Figure 1 This is a flowchart illustrating the interactive animation generation method based on action recognition in this application;

[0058] Figure 2 This is a schematic diagram of the structure of one of the devices in this application;

[0059] The diagram is labeled as follows: 101-Processor, 102-Communication bus, 103-Network interface, 104-User interface, 105-Memory.

[0060] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0061] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present application.

[0062] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0063] Example 1

[0064] like Figure 1 As shown, an interactive animation generation method based on action recognition includes:

[0065] S1. Associate target users and target roles so that target users can control target roles through their own actions.

[0066] Optionally, motion capture technology can be used to collect motion data of the target user and process the collected data to obtain key skeleton points and their trajectory data.

[0067] Optionally, motion capture technology can employ optical capture, inertial capture, or video capture.

[0068] Based on key skeletal points, 3D modeling software is used to bind these key skeletal points to the key control nodes of the target character, so that the target user can control the target character through their own actions.

[0069] S2. Continuously collect the target user's action data as the first action data, and obtain the second action data after preprocessing the first action data.

[0070] Optionally, preprocessing methods may include one or more of the following: noise reduction, interpolation, normalization, data alignment, and pose correction.

[0071] S3. Analyze the second action data and determine whether the second action data includes a key action corresponding to the preset standard action.

[0072] By using posture recognition technology or skeletal point recognition technology, the second action data is analyzed to determine whether the second action data includes key actions corresponding to preset standard actions. Generally speaking, preset standard actions are simple actions with simple, stable, and clear trajectories of skeletal points, such as "straight punch", "hook punch", and "front kick".

[0073] S4. If the second action data includes key actions, generate key action tags based on the timestamp and name of the key actions, and record the key action tags.

[0074] Optionally, if the key actions are "straight punch", "hook punch", or "front kick", the generated key action labels can be "straight punch - action start time - action end time", "hook punch - action start time - action end time", or "front kick - action start time - action end time". Alternatively, "straight punch", "hook punch", and "front kick" can be replaced with unique identifiers such as "A", "B", and "C" through preset key action label mapping.

[0075] S5. When a new key action label is generated, determine whether there is a new key action label combination that meets the preset conditions.

[0076] Specifically, a key action tag combination that meets the preset conditions refers to key actions that conform to a preset order and the time required to complete the key actions meets the preset requirements, such as completing the actions "A", "C", and "B" in sequence within 0.5 seconds, or completing the actions "A", "A", "B", "C", and "B", with the interval between two adjacent actions not exceeding 0.1 seconds.

[0077] S6. If a new combination of key action labels that meets the preset conditions exists, then obtain the complex action data corresponding to the combination of key action labels.

[0078] Optionally, complex motion data is pre-recorded and used to control the target character to complete a set of specified actions. This approach allows interactive motion videos or games to achieve complex actions that users cannot perform through gestures or movements, but instead of relying on buttons or other less engaging methods like existing solutions, effectively improving the playability of interactive motion videos or games.

[0079] Specifically, if the actions "A", "C", and "B" are completed in sequence within 0.5 seconds, "Special Move X" is released in the interactive animation. If the actions "A", "A", "B", "C", and "B" are completed in sequence, and the interval between two adjacent actions does not exceed 0.1 seconds, "Special Move Y" is released in the interactive animation. If a new key action tag combination that meets the preset conditions is "Special Move X", then the complex action data corresponding to "Special Move X" is read. The complex action data is configured to include at least complex action anchor points, complex action key points, and complex action key point trajectory data, wherein the complex action anchor points, complex action key points, and key skeletal points correspond to one or more of them.

[0080] S7. Drive the target character to perform actions based on the second action data and complex action data.

[0081] Optionally, when new complex motion data is generated, the complex motion data is immediately used to drive the target character's actions; otherwise, the second motion data is used to drive the target character's actions.

[0082] By adopting the above solution, target users can control complex actions through basic operations. This solves at least the problem that existing technologies still have significant technical obstacles in terms of controlling complex actions, the real-time performance and accuracy of the interaction process, and can only provide simple actions and interactions with poor playability.

[0083] Example 2

[0084] This embodiment, based on embodiment 1, provides an interactive animation generation method based on action recognition, comprising:

[0085] S1. Associate target users and target roles so that target users can control target roles through their own actions.

[0086] Optionally, motion capture technology can be used to collect motion data of the target user and process the collected data to obtain key skeleton points and their trajectory data.

[0087] Optionally, motion capture technology can employ optical capture, inertial capture, or video capture.

[0088] Based on key skeletal points, 3D modeling software is used to bind these key skeletal points to the key control nodes of the target character, so that the target user can control the target character through their own actions.

[0089] Optionally, association can be established based on target users and target roles, enabling target users to control target roles through their own actions, including:

[0090] Create the target character in 3D production software and generate a character model. The character model includes key control nodes for controlling the target character's movements.

[0091] Collect motion capture data of the target user to obtain the target user's key skeletal points;

[0092] By using 3D modeling software, the connection between key skeletal points and key control nodes is established so that the target user can control the target character through their own actions.

[0093] S2. Continuously collect the target user's action data as the first action data, and obtain the second action data after preprocessing the first action data.

[0094] Optionally, preprocessing methods may include one or more of the following: noise reduction, interpolation, normalization, data alignment, and pose correction.

[0095] Optionally, the target user's action data is continuously collected as the first action data, and the second action data is obtained after preprocessing the first action data, including:

[0096] The target user's action data is continuously collected as the first action data, which includes the coordinate data of key skeleton points changing over time.

[0097] Based on the coordinate data of key skeleton points changing over time, obtain the trajectory data of key skeleton points;

[0098] Based on the trajectory data of key skeleton points, the trajectory data of key skeleton points is smoothed at least to obtain the second motion data.

[0099] Specifically, noise can be removed using filters to at least smooth the trajectory data of key skeletal points.

[0100] Optionally, noise processing includes smoothing, Kalman filtering, and wavelet transform; interpolation includes linear interpolation, spline interpolation, and polynomial interpolation; normalization includes position normalization, velocity normalization, and scale normalization; data alignment includes time synchronization and spatial alignment; and attitude restoration includes inverse kinematics and skeleton constraints.

[0101] S3. Analyze the second action data and determine whether the second action data includes a key action corresponding to the preset standard action.

[0102] By using posture recognition technology or skeletal point recognition technology, the second action data is analyzed to determine whether the second action data includes key actions corresponding to preset standard actions. Generally speaking, preset standard actions are simple actions with simple, stable, and clear trajectories of skeletal points, such as "straight punch", "hook punch", and "front kick".

[0103] Optionally, the second motion data is parsed to determine whether it includes key actions corresponding to preset standard actions, including:

[0104] Analyze the second motion data to obtain the trajectory data of each key skeletal point;

[0105] Based on the trajectory data of each key skeletal point, the relative motion data between each key skeletal point is obtained;

[0106] Determine whether the relative motion data matching the preset standard action is included within the preset sliding time window;

[0107] If relative motion data matching the preset standard motion is included, then the second motion data includes key motions corresponding to the preset standard motion.

[0108] S4. If the second action data includes key actions, generate key action tags based on the timestamp and name of the key actions, and record the key action tags.

[0109] Optionally, if the key actions are "straight punch", "hook punch", or "front kick", the generated key action labels can be "straight punch - action start time - action end time", "hook punch - action start time - action end time", or "front kick - action start time - action end time". Alternatively, "straight punch", "hook punch", and "front kick" can be replaced with unique identifiers such as "A", "B", and "C" through preset key action label mapping.

[0110] S5. When a new key action label is generated, determine whether there is a new key action label combination that meets the preset conditions.

[0111] Specifically, a key action tag combination that meets the preset conditions refers to key actions that conform to a preset order and the time required to complete the key actions meets the preset requirements, such as completing the actions "A", "C", and "B" in sequence within 0.5 seconds, or completing the actions "A", "A", "B", "C", and "B", with the interval between two adjacent actions not exceeding 0.1 seconds.

[0112] Optionally, before determining whether a new combination of key action tags that meets preset conditions exists when a new key action tag is generated, the method further includes:

[0113] Create an empty tag sequence to store key action tags. The tag sequence is configured to be cleared whenever no key action tag is added to the tag sequence within a preset time threshold.

[0114] The tag sequence is also configured to add new key action tags to the tag sequence when new key action tags are generated.

[0115] Optionally, when a new key action label is generated, it is determined whether a new combination of key action labels that meets preset conditions exists, including:

[0116] When a new key action label is generated, the new key action label is added to the label sequence;

[0117] Determine whether, after adding a new key action label, all key action labels in the label sequence can form a key action label combination that meets preset conditions or form part of a key action label combination that meets preset conditions.

[0118] If a combination of key action labels that meets the preset conditions can be formed, then the combination of key action labels is recorded.

[0119] If it can form part of a key action tag combination that meets the preset conditions, then wait;

[0120] If a key action label combination that meets the preset conditions cannot be formed, or if a key action label combination that meets the preset conditions cannot be formed, the label sequence will be cleared and the new key action label will be added back to the label sequence.

[0121] When the tag sequence is cleared, if there is a recorded key action tag combination in the tag sequence, then there is a new key action tag combination that meets the preset conditions. The new key action tag combination that meets the preset conditions is configured as the latest recorded key action tag combination in the tag sequence.

[0122] Specifically, if the key action label combination includes "AC", "AAC", and "AACB", and the current key action label in the label sequence is only "A", then if a new key action label is "A", it will form "AA", which is part of "AAC". The process will wait. If a new key action label is added to the label sequence within the time threshold, the process will proceed again. If no new key action label is added to the label sequence within the time threshold, since "AA" is not a key action label combination, there is no recorded key action label combination in the label sequence, and the label sequence can be cleared directly. If the new key action label is "C", it will form "A". "C" represents the key action label combination. Therefore, the label sequence records the combination "AC". If no new key action label is added to the label sequence within the time threshold, the label sequence is cleared and "AC" is output as a new key action label combination that meets the preset conditions. If a new key action label is added to the label sequence within the time threshold, the judgment is made again. If the new key action label is "B", forming "AB", since "AB" can neither form a key action label combination that meets the preset conditions nor form part of a key action label combination that meets the preset conditions, the label sequence needs to be cleared and "B" needs to be added back to the label sequence.

[0123] Optional, also includes:

[0124] Obtain the average time for the target user to complete the standard action, and set the time threshold based on the input settings parameters.

[0125] Specifically, the target user or other administrators can input setting parameters to adjust the time threshold. The smaller the time threshold, the more difficult it is to trigger complex action data.

[0126] Specifically, the time threshold is a * the average time for the target user to complete the standard action, where 0.001 ≤ a ≤ 1.

[0127] Optional, also includes:

[0128] Get the last key action label in the label sequence. Set the time threshold according to the connection difficulty of the key actions corresponding to the last key action label. The greater the connection difficulty of the key actions, the larger the time threshold.

[0129] The difficulty of connecting key movements is configured based on the maximum sum of the distances between each key bone point in the key movement and each key bone point in the target character's standard pose.

[0130] S6. If a new combination of key action labels that meets the preset conditions exists, then obtain the complex action data corresponding to the combination of key action labels.

[0131] Optionally, complex motion data is pre-recorded and used to control the target character to complete a set of specified actions. This approach allows interactive motion videos or games to achieve complex actions that users cannot perform through gestures or movements, but instead of relying on buttons or other less engaging methods like existing solutions, effectively improving the playability of interactive motion videos or games.

[0132] Specifically, if the actions "A", "C", and "B" are completed in sequence within 0.5 seconds, "Special Move X" is released in the interactive animation. If the actions "A", "A", "B", "C", and "B" are completed in sequence, and the interval between two adjacent actions does not exceed 0.1 seconds, "Special Move Y" is released in the interactive animation. If a new key action tag combination that meets the preset conditions is "Special Move X", then the complex action data corresponding to "Special Move X" is read. The complex action data is configured to include at least complex action anchor points, complex action key points, and complex action key point trajectory data, wherein the complex action anchor points, complex action key points, and key skeletal points correspond to one or more of them.

[0133] S7. Drive the target character to perform actions based on the second action data and complex action data.

[0134] Optionally, when new complex motion data is generated, the complex motion data is used immediately to drive the target character to perform actions; otherwise, the second motion data is used to drive the target character to perform actions.

[0135] By adopting the above solution, target users can control complex actions through basic operations. This solves at least the problem that existing technologies still have significant technical obstacles in terms of controlling complex actions, the real-time performance and accuracy of the interaction process, and can only provide simple actions and interactions with poor playability.

[0136] Optionally, based on the second motion data and complex motion data, the target character is driven to perform actions, including:

[0137] When complex motion data is not available, the target character is driven to perform actions based on the second motion data.

[0138] When complex motion data is acquired, the target character is driven to perform actions based on the complex motion data.

[0139] Optionally, based on the second motion data and complex motion data, the target character is driven to perform actions, including:

[0140] When complex motion data is not available, the target character is driven to perform actions based on the second motion data.

[0141] When complex motion data is acquired, the initial pose of the complex motion data to be executed and the current pose of the target character are obtained based on the complex motion data. Then, the pre-animation motion data is obtained based on the initial pose of the complex motion data and the current pose of the target character. The pre-animation motion data and the complex motion data are used sequentially to drive the target character to perform the action. The pre-animation motion data is configured to be the motion data required to move from the target character's current pose to the initial pose of the complex motion data.

[0142] Example 3

[0143] An interactive animation generation system based on motion recognition, including a motion capture module and an animation generation module;

[0144] The motion capture module is configured as follows:

[0145] The action data of the target user is continuously collected as the first action data, and the second action data is obtained after preprocessing the first action data;

[0146] The animation generation module is configured as follows:

[0147] Associate target users with target roles so that target users can control target roles through their own actions;

[0148] Analyze the second action data and determine whether the second action data includes a key action corresponding to the preset standard action;

[0149] If the second action data includes key actions, then key action tags are generated based on the timestamp and name of the key actions, and the key action tags are recorded.

[0150] When a new key action label is generated, it is determined whether there is a new combination of key action labels that meets the preset conditions;

[0151] If a new combination of key action labels that meets the preset conditions exists, then the complex action data corresponding to the combination of key action labels is obtained.

[0152] Based on the second motion data and complex motion data, drive the target character to perform actions.

[0153] Optionally, association can be established based on target users and target roles, enabling target users to control target roles through their own actions, including:

[0154] Create the target character in 3D production software and generate a character model. The character model includes key control nodes for controlling the target character's movements.

[0155] Collect motion capture data of the target user to obtain the target user's key skeletal points;

[0156] By using 3D modeling software, the connection between key skeletal points and key control nodes is established so that the target user can control the target character through their own actions.

[0157] Optionally, the target user's action data is continuously collected as the first action data, and the second action data is obtained after preprocessing the first action data, including:

[0158] The target user's action data is continuously collected as the first action data, which includes the coordinate data of key skeleton points changing over time.

[0159] Based on the coordinate data of key skeleton points changing over time, obtain the trajectory data of key skeleton points;

[0160] Based on the trajectory data of key skeleton points, the trajectory data of key skeleton points is smoothed at least to obtain the second motion data.

[0161] Optionally, the second motion data is parsed to determine whether it includes key actions corresponding to preset standard actions, including:

[0162] Analyze the second motion data to obtain the trajectory data of each key skeletal point;

[0163] Based on the trajectory data of each key skeletal point, the relative motion data between each key skeletal point is obtained;

[0164] Determine whether the relative motion data matching the preset standard action is included within the preset sliding time window;

[0165] If relative motion data matching the preset standard motion is included, then the second motion data includes key motions corresponding to the preset standard motion.

[0166] Optionally, before determining whether a new combination of key action tags that meets preset conditions exists when a new key action tag is generated, the method further includes:

[0167] Create an empty tag sequence to store key action tags. The tag sequence is configured to be cleared whenever no key action tag is added to the tag sequence within a preset time threshold.

[0168] The tag sequence is also configured to add new key action tags to the tag sequence when new key action tags are generated.

[0169] Optionally, when a new key action label is generated, it is determined whether a new combination of key action labels that meets preset conditions exists, including:

[0170] When a new key action label is generated, the new key action label is added to the label sequence;

[0171] Determine whether, after adding a new key action label, all key action labels in the label sequence can form a key action label combination that meets preset conditions or form part of a key action label combination that meets preset conditions.

[0172] If a combination of key action labels that meets the preset conditions can be formed, then the combination of key action labels is recorded.

[0173] If it can form part of a key action tag combination that meets the preset conditions, then wait;

[0174] If a key action label combination that meets the preset conditions cannot be formed, or if a key action label combination that meets the preset conditions cannot be formed, the label sequence will be cleared and the new key action label will be added back to the label sequence.

[0175] When the tag sequence is cleared, if there is a recorded key action tag combination in the tag sequence, then there is a new key action tag combination that meets the preset conditions. The new key action tag combination that meets the preset conditions is configured as the latest recorded key action tag combination in the tag sequence.

[0176] Optional, also includes:

[0177] Obtain the average time for the target user to complete the standard action, and set the time threshold based on the input settings parameters.

[0178] Optionally, based on the second motion data and complex motion data, the target character is driven to perform actions, including:

[0179] When complex motion data is not available, the target character is driven to perform actions based on the second motion data.

[0180] When complex motion data is acquired, the target character is driven to perform actions based on the complex motion data.

[0181] Example 4

[0182] This embodiment provides a device including a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement any of the methods described above.

[0183] Specifically, such as Figure 2 As shown, Figure 2This is a schematic diagram of the device structure of the hardware operating environment involved in the embodiments of this application. The device is an electronic device and may include: a processor 101, such as a central processing unit (CPU), a communication bus 102, a user interface 104, a network interface 103, and a memory 105. The communication bus 102 is used to realize the connection and communication between these components. The user interface 104 may include a display screen and an input unit such as a keyboard. Optionally, the user interface 104 may also include a standard wired interface and a wireless interface. The network interface 103 may optionally include a standard wired interface and a wireless interface (such as a Wi-Fi interface). The memory 105 may be a storage device independent of the aforementioned processor 101. The memory 105 may be a high-speed random access memory (RAM) or a stable non-volatile memory (NVM), such as at least one disk storage device. The processor 101 may be a general-purpose processor, including a central processing unit, a network processor, etc., or it may be a digital signal processor, an application-specific integrated circuit, a field-programmable gate array or other programmable logic device, discrete gate or transistor logic device, or discrete hardware component.

[0184] Those skilled in the art will understand that the appendix Figure 2 The structure shown does not constitute a limitation on the electronic device and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0185] like Figure 2 As shown, the memory 105, which serves as a storage medium, may include an operating system, a network communication module, a user interface module, and an application for implementing an interactive animation generation method based on motion recognition.

[0186] exist Figure 2 In the electronic device shown, the network interface 103 is mainly used for data communication with the network server; the user interface 104 is mainly used for data interaction with the user; the processor 101 and the memory 105 in this application can be set in the electronic device, and the electronic device can call the application program stored in the memory 105 to implement the interactive animation generation method based on action recognition through the processor 101 to implement the above method.

[0187] Example 5

[0188] This embodiment provides a computer-readable storage medium on which a computer program is stored, and a processor executes the computer program to implement any of the methods described above.

[0189] In some embodiments, the computer-readable storage medium may be a memory such as FRAM, ROM, PROM, EPROM, EEPROM, flash memory, magnetic surface memory, optical disk, or CD-ROM; or it may be a device including one or any combination of the above-mentioned memories. The computer may be a variety of computing devices, including smart terminals and servers.

[0190] In the above embodiments of this disclosure, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0191] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units can be a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual couplings, direct couplings, or communication connections may be through some interfaces; indirect couplings or communication connections between units or modules may be electrical or other forms.

[0192] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0193] Furthermore, the functional units in the various embodiments of this disclosure can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0194] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable non-volatile storage medium. Based on this understanding, the technical solution of this disclosure, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a non-volatile storage medium and includes several instructions to cause a device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this disclosure. The aforementioned non-volatile storage medium includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0195] The above are merely preferred embodiments of this disclosure. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principles of this disclosure, and these improvements and modifications should also be considered within the scope of protection of this disclosure.

Claims

1. A method for generating an interaction animation based on motion recognition, characterized by, The method comprises the following steps: associating a target user with a target character so that the target user can control the target character through his / her own actions; continuously collecting action data of the target user as first action data, and obtaining second action data after pre-processing the first action data; analyzing the second action data to determine whether the second action data includes a key action corresponding to a preset standard action; if the second action data includes the key action, generating a key action label according to a time stamp of the key action and a name of the key action, and recording the key action label; establishing an empty label sequence for storing key action labels, the label sequence being configured to clear the label sequence whenever no key action label is added to the label sequence within a preset time threshold; the label sequence is further configured to add a new key action label to the label sequence when the new key action label is generated; when a new key action label is generated, determining whether there is a new key action label combination that meets a preset condition; if there is a new key action label combination that meets the preset condition, obtaining complex action data corresponding to the key action label combination; driving the target character to perform actions according to the second action data and the complex action data. 2.The motion recognition based interactive animation generation method of claim 1, wherein, The association of the target user and the target character so that the target user can control the target character through his / her own actions comprises: creating a target character in a three-dimensional production software to generate a character model, the character model including key control nodes for controlling actions of the target character; collecting action capture data of the target user to obtain key skeletal points of the target user; establishing a connection between the key skeletal points and the key control nodes through the three-dimensional production software so that the target user can control the target character through his / her own actions. 3.The motion recognition based interactive animation generation method of claim 2, wherein, The continuous collection of action data of the target user as first action data, and the obtaining of second action data after pre-processing the first action data, comprises: continuously collecting action data of the target user as first action data, the first action data including coordinate data of key skeletal points changing over time; obtaining trajectory data of the key skeletal points according to the coordinate data of the key skeletal points changing over time; obtaining second action data after at least smoothing the trajectory data of the key skeletal points. 4.The motion recognition based interactive animation generation method of claim 2, wherein, The analysis of the second action data to determine whether the second action data includes a key action corresponding to a preset standard action comprises: analyzing the second action data to obtain trajectory data of each key skeletal point; obtaining relative motion data between each key skeletal point according to the trajectory data of each key skeletal point; determining whether the relative motion data matching the preset standard action is included within a preset sliding time window; if the relative motion data matching the preset standard action is included, the second action data includes a key action corresponding to a preset standard action. 5.The motion recognition based interactive animation generation method of claim 1, wherein, The judgment whether there is a new key action label combination meeting the preset condition when a new key action label is generated comprises: When a new key action label is generated, the new key action label is added to the label sequence; The judgment whether all key action labels in the label sequence can form a key action label combination meeting the preset condition or a part of the key action label combination meeting the preset condition after the new key action label is added to the label sequence; If the key action label combination meeting the preset condition is formed, the key action label combination is recorded; If a part of the key action label combination meeting the preset condition is formed, waiting is performed; If the key action label combination meeting the preset condition or a part of the key action label combination meeting the preset condition cannot be formed, the label sequence is emptied and the new key action label is added to the label sequence again; When the label sequence is emptied, if there is a recorded key action label combination in the label sequence, there is a new key action label combination meeting the preset condition, and the new key action label combination meeting the preset condition is configured as the latest recorded key action label combination in the label sequence. 6.The motion recognition based interactive animation generation method of claim 1, wherein, Further comprising: Obtaining the average time of a target user completing a standard action, and setting the time threshold based on the average time of the target user completing the standard action according to the input setting parameter. 7.The motion recognition based interactive animation generation method of claim 1, wherein, The driving of the target role to perform actions according to the second action data and the complex action data comprises: When the complex action data is not obtained, the target role is driven to perform actions according to the second action data; When the complex action data is obtained, the target role is driven to perform actions according to the complex action data.

8. An interaction animation generation system based on motion recognition, characterized by, The action capture module and the animation generation module are comprised. The action capture module is configured to: Continuously collect action data of a target user as first action data, and obtain second action data after the first action data is preprocessed; The animation generation module is configured to: Correlate the target user and the target role, so that the target user can control the target role through own actions; Analyze the second action data to judge whether the second action data includes a key action corresponding to a preset standard action; If the second action data includes the key action, generate a key action label according to a time stamp of the key action and a name of the key action, and record the key action label; Establish an empty label sequence for storing key action labels, and the label sequence is configured to empty the label sequence when no key action label is added to the label sequence within a preset time threshold; The label sequence is further configured to add a new key action label to the label sequence when the new key action label is generated; The judgment whether there is a new key action label combination meeting the preset condition when a new key action label is generated; If there is a new key action label combination meeting the preset condition, complex action data corresponding to the key action label combination is obtained; According to the second action data and the complex action data, driving the target character to perform an action.

9. An apparatus, comprising: The device comprises a memory and a processor, the memory stores a computer program, and the processor executes the computer program to realize the method according to any one of claims 1-7.

Images