Intelligent animation modeling method and system based on three-dimensional technology

Abstract

The invention discloses an intelligent animation modeling method and system based on a three-dimensional technology, and particularly relates to the technical field of animation modeling. Motion data of a performer are acquired in real time, the captured data are preprocessed, and mapping and optimization of the motion data and a three-dimensional role are completed in combination with a skeleton modeling technology; for a multi-actor interaction scene, abnormal changes of a mark point shielding rate and a mismatching rate are analyzed, and the accuracy of multi-role action tracking of the system is evaluated; after the capture system reaches the expected precision, simulating and testing the generated three-dimensional animation, optimizing animation data by combining a physical engine to enable the animation data to accord with a physical rule, exporting the optimized animation in a compatible format, and completing the integration of roles and scenes through a real-time rendering technology to generate a high-quality three-dimensional animation effect; the motion capture accuracy and the animation generation quality in a multi-role complex interaction scene are remarkably improved, and smooth, accurate and real three-dimensional role animation modeling is achieved.

Description

Technical Field

[0001] The present invention relates to the field of animation modeling technology, and in particular to an intelligent animation modeling method and system based on three-dimensional technology. Background Art

[0002] Intelligent animation modeling based on 3D technology is an intelligent modeling method based on 3D technology. It greatly simplifies the complex animation production process through algorithms and automation tools, improving efficiency and accuracy. This technology combines the principles of computer graphics, artificial intelligence (AI) and animation production, making animation modeling no longer completely dependent on manual operations, but more dependent on data-driven generation methods, such as learning to generate animation models from existing data through machine learning.

[0003] For example, in traditional animation modeling, in order to create a character, each frame of the character's action needs to be manually drawn, while intelligent animation modeling with 3D technology can obtain the actor's real action data through motion capture technology, and combine AI for automatic optimization and bone binding to generate smooth and realistic 3D character animation. This method has been widely used in film and game production. For example, "Avatar" uses motion capture technology to generate character movements, combined with intelligent algorithms to improve the character's facial expressions and body dynamic models, thereby achieving realistic 3D animation effects.

[0004] The prior art has the following deficiencies: During the motion capture process, occlusion between multiple actors, overlapping movements, or confusion of markers can make it difficult for the device to accurately track the independent movements of each character. For example, when simulating hugs, wrestling, or intensive interaction scenes, the capture system may not be able to distinguish the motion trajectories of different actors, resulting in motion data loss, misbinding, or merging errors, which can cause the movements to appear confusing or unnatural when generating animations. In addition, due to confusion of markers, the motion trajectories of different actors may be incorrectly merged, causing the character behavior generated by intelligent animation modeling to be seriously inconsistent with expectations. This destroys the interaction logic between characters, especially in scenes that require highly precise interactions (such as movie special effects or training simulations), which directly renders the output animation unusable. Summary of the invention

[0005] The purpose of the present invention is to provide an intelligent animation modeling method and system based on three-dimensional technology to solve the shortcomings of the background technology.

[0006] In order to achieve the above object, the present invention provides the following technical solution: an intelligent animation modeling method based on three-dimensional technology, comprising the following steps: S1: Use multi-view motion capture equipment to obtain the performer's motion data in real time, including setting markers on the performer's key parts to record their position, rotation and motion trajectory; S2: After preprocessing the captured motion data, create a skeletal model of the target 3D character, including joint positions and hierarchical relationships, and map the preprocessed motion data onto the skeletal model through scale adjustment and weight optimization; S3: Use artificial intelligence to optimize the skeletal animation, including motion smoothing and keyframe extraction, and simultaneously generate character facial animations to achieve natural matching of expressions and actions. Complete the un-captured part of the motion through deep learning and generate smooth transition animations; S4: For multi-actor interaction scenarios, analyze the abnormal changes in the marker occlusion rate and marker mis-matching rate during the marker tracking process of the capture system, and evaluate the motion tracking ability of the capture system for multiple characters; S5: When the capture system can accurately distinguish and record the independent motion trajectories of each actor, simulate and test the generated 3D animation, discover and correct potential problems, including penetration and joint over-limit, and optimize the animation data in combination with the physics engine to make it conform to physical laws; S6: Export the optimized animation in a compatible format and integrate it into the target scene. Complete the integration of the character and the scene through real-time rendering technology, add lights, materials, and special effects to generate the final high-quality animation effect.

[0007] Preferably, in S2, according to the body type of the 3D character, adjust the bone lengths to match the target model. Specifically: Use the automatic Retargeting algorithm to scale the motion ratio in the captured data to fit the bones of the character, bind the cleaned motion data to the skeletal model to generate a preliminary animation, use the Retargeting technology to map the preprocessed motion data to the joints of the character's bones, automatically adjust the bone ratio differences of different characters, and set the weight distribution for the bone binding of the character model. The weights at the joint parts need to be evenly distributed.

[0008] Preferably, in S4, after analyzing the abnormal changes in the marker occlusion rate during the marker tracking process of the capture system, generate a marker occlusion rate fluctuation index. The method for obtaining the marker occlusion rate fluctuation index is: Construct a time series of the marker occlusion rate , where represents the marker occlusion rate of the Nth frame, and the value range is 0 ≤ ≤ 10, N is the total number of frames in the time series. Set the length of the sliding window to W, that is, the number of frames included in the window. For the tth frame, the sliding average is calculated by the formula: ; when t < W, the number of frames included in the window is t, is the occlusion rate of the ith frame; for the tth frame, the occlusion rate and the sliding average The absolute deviation calculation formula is: ; The deviation value of the tth frame represents the difference between the current occlusion rate and the sliding average trend. The occlusion rate fluctuation index of the marker point is calculated. The expression is: ; In the formula, CHK is the occlusion rate fluctuation index of the marker point, and N is the total number of frames representing the time series length of the occlusion rate data.

[0009] Preferably, in S4, after analyzing the abnormal change of the mark point mismatch rate of the capture system during the mark point tracking process, a mark point mismatch rate abnormality index is generated, and the method for obtaining the mark point mismatch rate abnormality index is: Constructing a time series of marker mismatch rates ,in Represents the mismatch rate of the Gth frame, and calculates the mean of the sequence And subtract the mean from each point to get a zero-mean sequence ; s is the number of frames, the sequence of false matching rate Perform FFT transformation to obtain frequency domain representation ; ; In the formula, is the complex representation of the frequency component k, containing amplitude and phase information, is the kernel function of Fourier transform; for each frequency component , calculate the amplitude: ; In the formula, is the amplitude of frequency component k, and for The real and imaginary parts of , extract the amplitude set of high-frequency components ; According to the amplitude of the high-frequency component, the abnormal index of the mismatch rate of the marked point is calculated, and the expression is: ; Where FGH is the abnormal index of the mismatch rate of the marked points.

[0010] Preferably, the marker point occlusion rate fluctuation index and the marker point mismatch rate anomaly index are converted into a comprehensive feature vector, and the comprehensive feature vector is used as the input of the machine learning model. The machine learning model uses each group of comprehensive feature vectors to predict the capture system's motion tracking accuracy value labels for multiple characters as the prediction target, and takes minimizing the sum of prediction errors of all capture systems' motion tracking accuracy value labels for multiple characters as the training target. The machine learning model is trained until the sum of prediction errors converges, and the model training is stopped. The motion tracking accuracy value of the capture system for multiple characters is determined according to the model output results, wherein the machine learning model is a polynomial regression model.

[0011] Preferably, the acquired motion tracking accuracy value of the capture system for multiple characters is compared with a motion tracking accuracy reference threshold pre-set according to historical data. If the motion tracking accuracy value of the capture system for multiple characters is greater than or equal to the pre-set motion tracking accuracy reference threshold, it means that the capture system has high motion tracking accuracy for multiple characters. At this time, an accurate motion tracking signal is generated, which means that the capture system has a strong motion tracking capability for multiple characters. If the motion tracking accuracy value of the capture system for multiple characters is less than the pre-set motion tracking accuracy reference threshold, it means that the capture system has low motion tracking accuracy for multiple characters. At this time, an inaccurate motion tracking signal is generated, which means that the capture system has a weak motion tracking capability for multiple characters.

[0012] Preferably, in S5, when the capture system can accurately distinguish and record the independent motion trajectory of each actor, that is, the motion tracking accuracy value of the capture system for multiple characters generated within a fixed time period is greater than or equal to a preset motion tracking accuracy reference threshold, the generated three-dimensional animation is simulated and tested, and the motion tracking accuracy values ​​generated within a subsequent fixed time period that are greater than or equal to the preset motion tracking accuracy reference threshold are collected, and a data set is established, the mean and standard deviation of the data set are calculated, and after analyzing the data set, potential problems are predicted in advance based on the analysis results.

[0013] Preferably, if the mean of the motion tracking accuracy values ​​in the data set is greater than or equal to the reference threshold of the mean of the motion tracking accuracy values, and the standard deviation of the motion tracking accuracy values ​​is less than the reference threshold of the standard deviation of the motion tracking accuracy values, it indicates that the capture system can accurately distinguish and record the independent motion trajectory of each character, and the generated three-dimensional animation has a small error and conforms to the laws of physics, and the capture device and algorithm continue to be maintained under the current configuration; If the mean value of the motion tracking accuracy is greater than or equal to the reference threshold of the mean value of the motion tracking accuracy, and the standard deviation of the motion tracking accuracy is greater than or equal to the reference threshold of the standard deviation of the motion tracking accuracy, it indicates that the capture system still fluctuates in some time periods, and the motion tracking capability is unstable, which affects the local quality of the 3D animation. It is necessary to optimize the robustness and anti-occlusion capability of the capture algorithm to enhance its adaptability to dynamically changing scenes; If the mean value of the motion tracking accuracy is less than the reference threshold of the mean value of the motion tracking accuracy, and the standard deviation of the motion tracking accuracy is greater than or equal to the reference threshold of the standard deviation of the motion tracking accuracy, it indicates that the overall performance of the capture system is insufficient and unstable. The capture system has serious defects in its ability to track the motion of multiple characters, and comprehensive optimization is required from the device configuration and algorithm levels. If the mean value of the motion tracking accuracy value is less than the reference threshold of the mean value of the motion tracking accuracy value, and the standard deviation of the motion tracking accuracy value is less than the reference threshold of the standard deviation of the motion tracking accuracy value, it indicates that the performance of the capture system is poor but stable, but cannot meet the high-precision requirements. The equipment and algorithm need to be optimized to improve the accuracy of motion tracking.

[0014] The present invention also provides an intelligent animation modeling system based on three-dimensional technology, including a motion capture module, a data preprocessing and skeleton modeling module, an AI animation optimization module, a multi-role tracking evaluation module, an animation simulation and physical optimization module, and an animation rendering and integration module: Motion capture module: Use multi-view motion capture equipment to obtain the performer's motion data in real time, including setting markers on the performer's key parts to record their position, rotation and motion trajectory; Data preprocessing and skeleton modeling module: After preprocessing the captured motion data, a skeleton model of the target 3D character is created, including joint positions and hierarchical relationships, and the preprocessed motion data is mapped to the skeleton model through proportion adjustment and weight optimization; AI Animation Optimization Module: Uses artificial intelligence to optimize skeletal animation, including motion smoothing and keyframe extraction, while generating character facial animation to achieve a natural match between expression and motion, and uses deep learning to complete uncaptured motions to generate smooth transition animations; Multi-character tracking evaluation module: For multi-actor interaction scenes, analyze the abnormal changes in the marker occlusion rate and marker mismatch rate during the marker tracking process of the capture system to evaluate the capture system's ability to track the movements of multiple characters; Animation simulation and physics optimization module: When the capture system can accurately distinguish and record the independent movement trajectory of each actor, the generated 3D animation is simulated and tested to find and correct potential problems, including penetration and joint overrun, and the animation data is optimized in combination with the physics engine to make it conform to the laws of physics; Animation rendering and integration module: Export the optimized animation in a compatible format and integrate it into the target scene. Use real-time rendering technology to integrate characters and scenes, add lighting, materials and special effects, and generate the final high-quality animation effect.

[0015] In the above technical solution, the technical effects and advantages provided by the present invention are: 1. The present invention significantly improves the motion capture and 3D animation modeling capabilities in complex multi-role interactive scenes through innovative multi-view capture technology, data preprocessing, artificial intelligence optimization, anomaly analysis and physical engine integration. The capture performance is quantified using the marker point occlusion rate fluctuation index and the mismatch rate anomaly index, and the motion tracking accuracy of the capture system is dynamically evaluated and optimized by driving the machine learning model with a comprehensive feature vector. This method can quickly discover and correct potential problems, including marker point confusion, motion errors and data loss, making the capture system more stable and efficient in complex multi-role scenes, and laying a solid foundation for generating high-precision 3D animations.

[0016] 2. The present invention combines deep learning and physical engine technology to achieve smooth motion, keyframe optimization and natural transition in the animation generation process, and supports high-precision presentation of complex expressions and details. Through real-time analysis and optimization decisions of captured data, it ensures that the animation output conforms to physical laws and has minimal errors, and finally completes the high-quality integration of characters and scenes through real-time rendering technology. The overall technical system improves the accuracy and robustness of motion capture, effectively solves the problem of chaotic and unnatural motion in multi-role scenes of existing technologies, and provides strong technical support for applications such as film and television special effects, virtual reality, and game animation. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0018] Figure 1 The present invention is a flow chart of the method.

[0019] Figure 2 It is a system module diagram of the present invention. DETAILED DESCRIPTION

[0020] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0021] Example 1, please refer to Figure 1 As shown, the intelligent animation modeling method based on three-dimensional technology described in this embodiment includes the following steps: S1: Use multi-view motion capture equipment to obtain the performer's motion data in real time, including setting markers on the performer's key parts to record their position, rotation and motion trajectory; S2: After preprocessing the captured motion data, a skeletal model of the target 3D character is created, including joint positions and hierarchical relationships, and the preprocessed motion data is mapped to the skeletal model through proportion adjustment and weight optimization; S3: Uses AI to optimize skeletal animation, including motion smoothing and keyframe extraction, while generating character facial animation to achieve a natural match between expression and motion, and uses deep learning to complete uncaptured motions to generate smooth transition animations; S4: For multi-actor interaction scenes, analyze the abnormal changes in the marker occlusion rate and marker mismatch rate during the marker tracking process of the capture system to evaluate the capture system's ability to track the movements of multiple characters; S5: When the capture system can accurately distinguish and record the independent movement trajectory of each actor, the generated 3D animation is simulated and tested to find and correct potential problems, including model penetration and joint overrun, and the animation data is optimized in combination with the physics engine to make it conform to the laws of physics; S6: Export the optimized animation in a compatible format and integrate it into the target scene. Use real-time rendering technology to integrate the characters and scenes, add lighting, materials and special effects, and generate the final high-quality animation effect.

[0022] Use multi-view motion capture equipment to obtain the performer's motion data in real time. The specific implementation steps include: Equipment configuration and layout: Select suitable multi-view motion capture equipment (such as optical capture system, inertial capture system or hybrid capture system) to ensure that all angles of the capture scene are covered. Arrange multiple high-resolution cameras at the capture site with a certain overlap area between the cameras to ensure that the marker points are not blocked by a single perspective. Calibrate the equipment and unify the coordinate system of multiple cameras to ensure the consistency and accuracy of the captured data. Selection and setting of marker points: Key part selection: According to the performer's anatomical structure, set reflective or active markers at key parts of the body, such as joints (shoulders, elbows, knees), limbs, torso, head and fingers. Number and distribution of marker points: According to the complexity of the action and the needs of the three-dimensional model, distribute a sufficient number of marker points to ensure that the motion trajectory of each joint and part can be accurately captured.

[0023] Performers perform movements, and motion capture equipment captures the 3D position and rotation angle of each marker in real time at a high frame rate (usually 60 fps or higher). The capture system calculates the spatial coordinates of the markers through multi-view data fusion to generate a complete motion trajectory. The timestamp and trajectory data are recorded synchronously to provide a time series basis for subsequent processing. During the multi-view fusion process, the algorithm automatically detects the occluded markers and uses other view data to supplement the occlusion information. Adjust the camera layout or introduce dynamic occlusion compensation technology to reduce data loss caused by overlapping or overlapping performer movements.

[0024] S2: After preprocessing the captured motion data, a skeletal model of the target 3D character is created, including joint positions and hierarchical relationships, and the preprocessed motion data is mapped to the skeletal model through proportion adjustment and weight optimization.

[0025] Preprocess the captured motion data and use filtering algorithms (such as Kalman filtering or low-pass filtering) to eliminate jitter and noise in the captured data. Use interpolation methods to repair short-term abnormal data (such as marker offset). For parts with occlusion or missing markers, restore the missing data through trajectory prediction algorithms (such as timing prediction models based on deep learning). Ensure the temporal continuity and spatial integrity of the motion trajectory. Convert the captured motion data into a standardized format (such as FBX or BVH) to facilitate compatibility with different animation software and tools. Align the data on the time axis to ensure time synchronization between different clips.

[0026] Define the joint positions (such as shoulders, elbows, knees, etc.) and rotation axes according to the anatomical structure of the 3D character. Ensure that the joint positions are consistent with the key point positions in the captured data. Establish the parent-child hierarchy of bones to ensure the correctness of motion transmission, for example, the movement of the thigh bone will be transmitted to the calf and foot. Determine the degrees of freedom (DOF) of the bones and limit the rotation range of the joints to conform to physiological laws.

[0027] Adjust the bone lengths to match the target model based on the 3D character's body type (e.g., size, proportions). Use the automatic Retargeting algorithm to scale the motion in the captured data to fit the character's bones. Bind the cleaned motion data to the bone model to generate preliminary animations. Use Retargeting technology to map the preprocessed motion data to the character's skeleton joints to ensure spatial consistency of the motion trajectory. Automatically adjust for differences in bone proportions between different characters to ensure natural movements. Set weight distribution for the character model's bone binding to optimize the natural deformation of the character's skin. Weights at joints need to be evenly distributed to avoid overstretching or deformation. Use skin weight automatic calculation tools or manual fine-tuning for higher accuracy.

[0028] S3: Uses AI to optimize skeletal animation, including motion smoothing and keyframe extraction, while generating character facial animation to achieve a natural match between expression and motion, and uses deep learning to complete the uncaptured motion to generate smooth transition animations.

[0029] AI optimization of skeletal animation eliminates subtle jitter or discontinuity in motion capture data, making skeletal animation smoother. Use deep learning models (such as RNN or Transformer) to perform timing analysis on motion data and predict the smooth transition value of each frame. Apply Bezier curves or Kalman filtering technology to smooth and optimize joint trajectories to ensure that the movements conform to the natural movement laws of the human body.

[0030] Keyframe extraction is to reduce redundant data of skeletal animation and efficiently describe the core content of the action by extracting keyframes. AI algorithms (such as principal component analysis PCA) are used to analyze the changes in key points in the action data and automatically select keyframes. When extracting frames, action peak points and direction change points are retained first, while intermediate redundant frames are deleted to reduce computational complexity.

[0031] Facial animation generation and optimization: Generate facial animation that matches the skeleton movements naturally to enhance the emotional expression of the character. Use expression recognition algorithms (such as expression classification models based on convolutional neural networks) to identify and classify facial motion capture data and extract basic expression data (such as happiness, anger, surprise, etc.). Map the facial capture data to the character's facial bones or Blend Shape control points to ensure the naturalness and smoothness of expression changes.

[0032] Dynamic expression generation, using AI to generate subtle facial expressions that are not captured, making animations more realistic. Use generative adversarial networks (GAN) or variational autoencoders (VAE) to predict detailed expressions (such as micro-expressions, upturned corners of the mouth, etc.). Adjust the weight distribution of facial bones and skin meshes in real time to optimize the naturalness of facial expressions and avoid unnecessary stretching or distortion.

[0033] Deep learning completes uncaptured actions, predicts uncaptured action trajectories through AI, and generates complete animation data. Use deep learning models (such as LSTM or Transformer) to model time series action data and predict occluded or uncaptured joint trajectories. The model input includes captured joint positions, speeds, and direction changes, and the output is the completed complete action trajectory.

[0034] Generate natural transition animations between action clips to make the action flow smoothly. Generate transition frames between action clips through a temporal generation model (such as Temporal GAN). Optimize joint acceleration and inertia changes to ensure that the transition animation complies with physical laws and has natural visual effects.

[0035] S4: For the multi-actor interaction scenario, analyze the abnormal changes in the marker occlusion rate and marker mis-matching rate during the marker tracking process of the capture system, and evaluate the action tracking ability of the capture system for multiple characters.

[0036] In the multi-actor interaction scenario, use a multi-view motion capture device to record the marker positions, trajectories, and time series data of each actor. Ensure that the capture system simultaneously collects the visibility status of all markers, including information on occluded markers.

[0037] Divide the captured marker data into three categories: Visible markers: Markers successfully tracked and recorded by the capture system. Occluded markers: Markers that cannot be captured due to actor movement overlap or perspective limitations. Mis-matched markers: Markers that are incorrectly assigned to other actors or body parts.

[0038] Occlusion rate = Number of occluded markers / Total number of markers; Calculate the occlusion rate for each frame, and record the average occlusion rate and peak occlusion rate for the entire capture process. Plot the change curve of the occlusion rate through the time series, and analyze the abnormal fluctuation points of the occlusion rate in multi-character interaction. Determine the specific action scenarios where high occlusion rates occur (such as hugging, wrestling, etc.), and evaluate the capture ability of the system in such high-occlusion situations.

[0039] Mis-matching rate = Number of mis-matched markers / Total number of markers; Count the number of mis-matched markers in each frame, and calculate the average mis-matching rate and peak mis-matching rate. Identify the specific positions and trajectories of the mis-matched markers, and analyze whether they are caused by action overlap, dense marker distribution, or algorithm errors. For scenarios with a high mis-matching rate, verify whether there are problems with the marker assignment algorithm of the capture system (such as assignment rules based on distance or trajectory prediction).

[0040] After analyzing the abnormal changes in the marker occlusion rate during the marker tracking process of the capture system, generate a marker occlusion rate fluctuation index. The method for obtaining the marker occlusion rate fluctuation index is as follows: Construct a time series of the marker occlusion rate , where represents the marker occlusion rate of the Nth frame, and the value range is 0 ≤ ≤ 10, N is the total number of frames in the time series. Set the length of the sliding window to W, that is, the number of frames included in the window. The larger the window, the higher the smoothing degree, but short-term fluctuations may be masked. For the tth frame, the sliding average is calculated as follows: ; when t < W, the number of frames included in the window is t (only calculate the existing data if it is less than W). is the occlusion rate of the ith frame. For the tth frame, the occlusion rate and the sliding average The absolute deviation calculation formula is: ; is the deviation value of the tth frame, indicating the difference between the current occlusion rate and the sliding average trend. The occlusion rate fluctuation index of the marker point is calculated. The expression is: ; In the formula, CHK is the occlusion rate fluctuation index of the marker point, and N is the total number of frames representing the time series length of the occlusion rate data.

[0041] When the marker occlusion rate fluctuation index is large, it means that the marker occlusion rate of the capture system has drastic changes, which is manifested as abnormally high marker occlusion rates in some frames, while other frames may be lower. Such drastic fluctuations usually indicate that the system's tracking ability in multi-character interaction scenes is not stable enough and is easily affected by overlapping movements, occlusions, or changes in perspective. This means that the capture system lacks robustness in complex scenes, which may result in incomplete or incorrect mapping of the movement trajectories of some characters, thus affecting the quality of the final animation.

[0042] When the marker occlusion rate fluctuation index is small, it means that the occlusion rate of the capture system is relatively stable in the entire time series and the fluctuation range is small. This shows that the system can better deal with the occlusion problem in multi-role interaction and the tracking ability of the markers is relatively stable. Even when the character movements are complex and overlap frequently, the capture system can still continue to track each marker and generate complete and reliable motion data. Capture systems with small fluctuation indexes usually have strong adaptability and accuracy, and are suitable for high-precision animation production and complex scene capture.

[0043] After analyzing the abnormal changes in the mark point mismatch rate of the capture system during the mark point tracking process, the mark point mismatch rate abnormal index is generated. The method for obtaining the mark point mismatch rate abnormal index is as follows: Input data: time series of marker mismatch rate ,in Represents the mismatch rate of the Gth frame, and calculates the mean of the sequence And subtract the mean from each point to get a zero-mean sequence ; s is the number of frames; for the sequence of false matching rate Perform FFT transformation to obtain frequency domain representation ; ; In the formula, is the complex representation of the frequency component k, containing amplitude and phase information, is the kernel function of Fourier transform; for each frequency component , calculate the amplitude: ; In the formula, is the amplitude of frequency component k, and for The real and imaginary parts of Determine the high frequency range , the high frequency part usually indicates the rapid change characteristics of the mismatch rate. Set the high frequency range to the last 30% of the total frequency or apply a specific frequency threshold (such as >1Hz); extract the amplitude set of the high frequency component ; According to the amplitude of the high-frequency component, the abnormal index of the mismatch rate of the marked point is calculated, and the expression is: ; Where FGH is the abnormal index of the mismatch rate of the marked points.

[0044] When the marker mismatch rate anomaly index is large, it means that the capture system has low marker allocation accuracy in multi-role interaction scenes, and mismatches are frequent and fluctuating violently. This may mean that the system lacks sufficient robustness in complex scenes and cannot effectively distinguish markers of different characters or body parts, especially in cases of overlapping or rapid switching of actions. As a result, the generated action data may be inaccurate, with crossed or misaligned character actions, which will affect the quality and use of animation modeling.

[0045] When the marker mismatch rate anomaly index is small, it indicates that the capture system's allocation of markers is relatively stable, with fewer mismatches and smaller fluctuations. This reflects that the system has strong marker tracking and allocation capabilities in multi-role interaction scenes, can accurately distinguish different characters and body parts, and can ensure the integrity and accuracy of captured data even in complex movements or frequent character interactions. Such a system is suitable for high-precision animation production and complex scene modeling, and the generated animation data is more reliable.

[0046] The marker point occlusion rate fluctuation index and the marker point mismatch rate anomaly index are converted into a comprehensive feature vector, and the comprehensive feature vector is used as the input of the machine learning model. The machine learning model uses each group of comprehensive feature vectors to predict the capture system's motion tracking accuracy value labels for multiple characters as the prediction target, and takes minimizing the sum of prediction errors of all capture systems' motion tracking accuracy value labels for multiple characters as the training target. The machine learning model is trained until the sum of prediction errors converges, and the model training is stopped. The motion tracking accuracy value of the capture system for multiple characters is determined according to the model output results, wherein the machine learning model is a polynomial regression model.

[0047] The method for obtaining the accuracy value of the motion tracking of multiple characters by the capture system is as follows: from the comprehensive feature vector training data of the trained machine learning model, the corresponding function expression is obtained: ; In the formula, is the output function of the model, CHK is the fluctuation index of the marker occlusion rate, FGH is the abnormal index of the marker mismatch rate, To capture the system's motion tracking accuracy for multiple characters.

[0048] The acquired motion tracking accuracy value of the capture system for multiple characters is compared with the motion tracking accuracy reference threshold pre-set according to historical data. If the motion tracking accuracy value of the capture system for multiple characters is greater than or equal to the pre-set motion tracking accuracy reference threshold, it means that the capture system has high motion tracking accuracy for multiple characters. At this time, an accurate motion tracking signal is generated, which means that the capture system has strong motion tracking capability for multiple characters. If the motion tracking accuracy value of the capture system for multiple characters is less than the pre-set motion tracking accuracy reference threshold, it means that the motion tracking accuracy of the capture system for multiple characters is low. At this time, an inaccurate motion tracking signal is generated, which means that the capture system has weak motion tracking capability for multiple characters.

[0049] S5: When the capture system can accurately distinguish and record the independent movement trajectory of each actor, the generated 3D animation is simulated and tested to discover and correct potential problems, and the animation data is optimized in combination with the physics engine to make it conform to the laws of physics.

[0050] When the capture system is able to accurately distinguish and record the independent motion trajectory of each actor, that is, the motion tracking accuracy values ​​of the capture system for multiple characters generated within a fixed time period are greater than or equal to the preset motion tracking accuracy reference threshold, the generated three-dimensional animation is simulated and tested, and the motion tracking accuracy values ​​generated within a subsequent fixed time period that are greater than or equal to the preset motion tracking accuracy reference threshold are collected, and a data set is established, the mean and standard deviation of the data set are calculated, and after analyzing them, potential problems are predicted in advance based on the analysis results.

[0051] If the mean of the motion tracking accuracy values ​​in the data set is greater than or equal to the reference threshold of the mean of the motion tracking accuracy values, and the standard deviation of the motion tracking accuracy values ​​is less than the reference threshold of the standard deviation of the motion tracking accuracy values, it indicates that the system has a high motion tracking capability within a fixed time period, while showing good stability and consistency. The capture system can reliably distinguish and record the independent motion trajectory of each character. The generated 3D animation has a small error, conforms to the laws of physics, and has a low subsequent optimization cost. Under the current configuration, continue to maintain or slightly optimize the capture equipment and algorithm, and focus on subsequent animation physics enhancement and detail optimization.

[0052] If the mean value of the motion tracking accuracy value is greater than or equal to the reference threshold of the mean value of the motion tracking accuracy value, and the standard deviation of the motion tracking accuracy value is greater than or equal to the reference threshold of the standard deviation of the motion tracking accuracy value, it indicates that the system still fluctuates in some time periods and the motion tracking capability is not stable enough. Although the overall performance is up to standard, inaccurate tracking or large errors may occur in local time periods, affecting the local quality of 3D animation. Short-term marker mismatch or occlusion problems may occur in complex interactive scenes. Focus on troubleshooting time periods with large errors (source of high standard deviation) and optimize the robustness and anti-occlusion capabilities of the capture algorithm. Enhance adaptability to dynamically changing scenes (such as rapid character interactions).

[0053] If the mean value of the motion tracking accuracy value is less than the reference threshold of the mean value of the motion tracking accuracy value, and the standard deviation of the motion tracking accuracy value is greater than or equal to the reference threshold of the standard deviation of the motion tracking accuracy value, it indicates that the overall performance of the capture system is insufficient and exhibits significant instability. The system has serious defects in its ability to track the motion of multiple characters, and may frequently experience problems such as missing or mismatching of marker points. The generated 3D animation has many errors and is difficult to meet physical laws and application requirements. Comprehensive optimization should be carried out from the aspects of device configuration (such as increasing the viewing angle or improving the resolution) and algorithm level (such as enhancing multi-target tracking). Frame-by-frame analysis should be performed for time periods with large error fluctuations to identify the key factors that cause system performance fluctuations.

[0054] If the mean motion tracking accuracy value is less than the reference threshold for the mean motion tracking accuracy value, and the standard deviation of the motion tracking accuracy value is less than the reference threshold for the standard deviation of the motion tracking accuracy value, it indicates that the system performance is poor but stable, and the error margin is relatively consistent. The system may have systematic biases or insufficient capabilities when capturing multi-character motions, but the volatility is low. The generated animation is of low quality with good overall consistency, but it cannot meet high-precision requirements. Make structural improvements to systemic problems such as insufficient marker resolution or poor occlusion handling. Optimize the basic capabilities of the device or algorithm to improve the accuracy of motion tracking.

[0055] S6: Export the optimized animation in a compatible format and integrate it into the target scene. Use real-time rendering technology to integrate the characters and scenes, add lighting, materials and special effects, and generate the final high-quality animation effect.

[0056] Choose the appropriate file format based on the target application requirements: FBX (Filmbox): supports skeletal animation, materials, lighting, and scene data, suitable for game engines (such as Unity, Unreal Engine) and film and television production. OBJ: only exports static 3D models, suitable for static scenes or further modeling. Alembic (ABC): efficiently stores complex animation data (such as cloth or hair simulation), suitable for movie special effects production.

[0057] Ensure that animation data is exported completely: Skeleton data: including joint positions, hierarchical relationships, and action keyframes. Materials and textures: bind materials and UV textures to avoid material loss after the model is imported into the target software. Special effects information: such as particle effects or dynamic simulations (cloth, hair, etc.). Compress or simplify redundant data (such as redundant keyframes or high-resolution textures) to improve the performance of exported files and ensure compatibility and loading efficiency.

[0058] Import the exported animation file into the target scene editing tool (such as Unity, Unreal Engine or Maya). Check whether the imported animation is fully loaded, especially the binding relationship and movement smoothness of the skeletal animation. Set the character's initial position and movement path in the scene: ensure that the character animation dynamically matches the scene elements (such as terrain and obstacles) to avoid model penetration. Introduce collision detection to ensure that the character's movements are consistent with the scene's physical rules.

[0059] Add and adjust the types and parameters of lights in the scene: Point light: used to simulate local light sources (such as torches and light bulbs). Parallel light: simulate natural light (such as sunlight). Ambient light: evenly illuminate the scene to ensure that the details of the characters are visible. Adjust lighting effects: introduce dynamic shadows and global illumination technology to enhance the realism and visual depth of the scene.

[0060] Apply Physically Based Rendering (PBR) materials: set reflectivity, roughness, metalness and other parameters according to the needs of the character and scene to enhance the sense of reality. Add dynamic texture maps: such as skin details of the character, water reflections in the scene and skybox effects. Add particle effects: character dynamic performance (such as dust effects when running, the trajectory of waving weapons). Scene effects (such as raindrops, fire, smoke). Dynamic simulation effects: such as cloth swinging and hair fluttering, calculated in real time by the physical engine.

[0061] Enable real-time rendering technology (such as Ray Tracing or rasterization): Dynamic light and shadow are calculated in real time to achieve realistic light reflection, refraction and scattering effects. Optimize frame rate to ensure smooth playback of high-quality animations on target devices. Add post-processing effects: Depth of field: highlight foreground characters and blur background details. Motion blur: simulate the visual blur effect when the character moves quickly. Color correction: adjust the hue, brightness and contrast of the animation to unify the visual style.

[0062] Output high-quality video or interactive animation files according to the target platform: Video format: such as MP4, MOV, for promotion, demonstration, etc. Interactive format: such as EXE, HTML5, for games or virtual reality scenes.

[0063] Test the animation effects on the target platform: Ensure that the characters and scene movements are coordinated, and there are no problems such as clipping or freezing. Verify that the lighting and special effects meet expectations. Further optimize based on feedback to ensure that the final quality of the animation meets the application requirements.

[0064] In this embodiment, a multi-view motion capture device is used to obtain the performer's motion data in real time, and its position, rotation and motion trajectory are recorded through markers. After preprocessing the captured data, a skeleton model of the target three-dimensional character is created, and the data is mapped to the skeleton model. The basic animation generation is completed through scale adjustment and weight optimization. Subsequently, artificial intelligence technology is used to optimize the skeleton animation, including motion smoothing, key frame extraction and expression generation, and deep learning is used to complete the uncaptured motion to achieve smooth and natural transition animation. For multi-actor interactive scenes, the abnormal changes in the marker occlusion rate and mismatch rate are analyzed to evaluate the system's multi-role tracking capability. When the motion tracking meets the accuracy requirements, the generated animation is simulated and tested to find and correct potential problems, such as penetration and joint overrun, and the animation data is optimized in combination with the physical engine to make it conform to the laws of physics. Finally, the optimized animation is exported in a compatible format and integrated into the target scene, and lighting, materials and special effects are added through real-time rendering technology to generate high-quality three-dimensional animation effects.

[0065] Example 2, please refer to Figure 2 As shown, the intelligent animation modeling system based on three-dimensional technology described in this embodiment includes a motion capture module, a data preprocessing and skeleton modeling module, an AI animation optimization module, a multi-role tracking evaluation module, an animation simulation and physical optimization module, and an animation rendering and integration module: Motion capture module: Use multi-view motion capture equipment to obtain the performer's motion data in real time, including setting markers on the performer's key parts to record their position, rotation and motion trajectory; Data preprocessing and skeleton modeling module: After preprocessing the captured motion data, a skeleton model of the target 3D character is created, including joint positions and hierarchical relationships, and the preprocessed motion data is mapped to the skeleton model through proportion adjustment and weight optimization; AI Animation Optimization Module: Uses artificial intelligence to optimize skeletal animation, including motion smoothing and keyframe extraction, while generating character facial animation to achieve a natural match between expression and motion, and uses deep learning to complete uncaptured motions to generate smooth transition animations; Multi-character tracking evaluation module: For multi-actor interaction scenes, analyze the abnormal changes in the marker occlusion rate and marker mismatch rate during the marker tracking process of the capture system to evaluate the capture system's ability to track the movements of multiple characters; Animation simulation and physics optimization module: When the capture system can accurately distinguish and record the independent movement trajectory of each actor, the generated 3D animation is simulated and tested to find and correct potential problems, including penetration and joint overrun, and the animation data is optimized in combination with the physics engine to make it conform to the laws of physics; Animation rendering and integration module: Export the optimized animation in a compatible format and integrate it into the target scene. Use real-time rendering technology to integrate characters and scenes, add lighting, materials and special effects, and generate the final high-quality animation effect.

[0066] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0067] It should be understood that the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. A and B can be singular or plural. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship, but it may also indicate an "and / or" relationship. Please refer to the context for specific understanding.

[0068] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0069] The above description is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.

Claims

1. An intelligent animation modeling method based on three-dimensional technology, characterized in that: The following steps are involved: S1: Use multi-view motion capture equipment to obtain the performer's motion data in real time, including setting markers on the performer's key parts to record their position, rotation and motion trajectory; S2: After preprocessing the captured motion data, a skeletal model of the target 3D character is created, including joint positions and hierarchical relationships, and the preprocessed motion data is mapped to the skeletal model through proportion adjustment and weight optimization; S3: Uses AI to optimize skeletal animation, including motion smoothing and keyframe extraction, while generating character facial animation to achieve a natural match between expression and motion, and uses deep learning to complete uncaptured motions to generate smooth transition animations; S4: For multi-actor interaction scenes, analyze the abnormal changes in the marker occlusion rate and marker mismatch rate during the marker tracking process of the capture system to evaluate the capture system's ability to track the movements of multiple characters; S5: When the capture system can accurately distinguish and record the independent movement trajectory of each actor, the generated 3D animation is simulated and tested to find and correct potential problems, including model penetration and joint overrun, and the animation data is optimized in combination with the physics engine to make it conform to the laws of physics; S6: Export the optimized animation in a compatible format and integrate it into the target scene. Use real-time rendering technology to integrate the characters and scenes, add lighting, materials and special effects, and generate the final high-quality animation effect.

2. The intelligent animation modeling method based on three-dimensional technology according to claim 1, characterized in that: In S2, the bone length is adjusted according to the body shape of the three-dimensional character to match the target model. Specifically, the automatic Retargeting algorithm is used to scale the action ratio in the captured data to match the skeleton of the character, and the cleaned action data is bound to the skeleton model to generate a preliminary animation. The Retargeting technology is used to correspond the pre-processed action data to the joints of the character skeleton, and the differences in bone proportions of different characters are automatically adjusted. The weight distribution is set for the skeleton binding of the character model, and the weights of the joints need to be evenly distributed.

3. The intelligent animation modeling method based on three-dimensional technology according to claim 1 is characterized in that: In S4, after analyzing the abnormal change of the marker occlusion rate of the capture system during the marker tracking process, a marker occlusion rate fluctuation index is generated. The method for obtaining the marker occlusion rate fluctuation index is as follows: Construct the time series of the marker point occlusion rate , where represents the marker point occlusion rate of the Nth frame, and the value range is 0 ≤ ≤ 10, N is the total number of frames in the time series. Set the length of the sliding window to W, that is, the number of frames included in the window. For the tth frame, the sliding average is calculated as follows: ; when t < W, the number of frames included in the window is t, is the occlusion rate of the ith frame; for the tth frame, the occlusion rate and the sliding average The absolute deviation is calculated as follows: ; is the deviation value of the tth frame, indicating the difference between the current occlusion rate and the sliding average trend. Calculate the marker point occlusion rate fluctuation index, and the expression is: ; in the formula, CHK is the marker point occlusion rate fluctuation index, and N is the total number of frames, indicating the length of the time series of the occlusion rate data.

4. The intelligent animation modeling method based on three-dimensional technology according to claim 3 is characterized in that: In S4, after analyzing the abnormal change of the mark point mismatch rate during the mark point tracking process of the capture system, a mark point mismatch rate abnormality index is generated. The method for obtaining the mark point mismatch rate abnormality index is as follows: Constructing a time series of marker mismatch rates ,in Represents the mismatch rate of the Gth frame, and calculates the mean of the sequence And subtract the mean from each point to get a zero-mean sequence ; s is the number of frames, the sequence of false matching rate Perform FFT transformation to obtain frequency domain representation ; ; In the formula, is the complex representation of the frequency component k, containing amplitude and phase information, is the kernel function of Fourier transform; for each frequency component , calculate the amplitude: ; In the formula, is the amplitude of frequency component k, and for The real and imaginary parts of , extract the amplitude set of high-frequency components ; According to the amplitude of the high-frequency component, the abnormal index of the mismatch rate of the marked point is calculated, and the expression is: ; Where FGH is the abnormal index of the mismatch rate of the marked points.

5. The intelligent animation modeling method based on three-dimensional technology according to claim 4 is characterized in that: The marker point occlusion rate fluctuation index and the marker point mismatch rate anomaly index are converted into a comprehensive feature vector, and the comprehensive feature vector is used as the input of the machine learning model. The machine learning model uses each group of comprehensive feature vectors to predict the capture system's motion tracking accuracy value labels for multiple characters as the prediction target, and takes minimizing the sum of prediction errors of all capture systems' motion tracking accuracy value labels for multiple characters as the training target. The machine learning model is trained until the sum of prediction errors converges, and the model training is stopped. The motion tracking accuracy value of the capture system for multiple characters is determined according to the model output results, wherein the machine learning model is a polynomial regression model.

6. The intelligent animation modeling method based on three-dimensional technology according to claim 5 is characterized in that: The obtained motion tracking accuracy value of the capture system for multiple characters is compared with the motion tracking accuracy reference threshold value pre-set according to historical data. If the motion tracking accuracy value of the capture system for multiple characters is greater than or equal to the pre-set motion tracking accuracy reference threshold value, it means that the motion tracking accuracy of the capture system for multiple characters is high. At this time, a motion tracking accuracy signal is generated, that is, the capture system has a strong motion tracking capability for multiple characters; If the capture system's motion tracking accuracy value for multiple characters is less than a preset motion tracking accuracy reference threshold, it means that the capture system's motion tracking accuracy for multiple characters is low. At this time, an inaccurate motion tracking signal is generated, which means that the capture system's motion tracking capability for multiple characters is weak.

7. The intelligent animation modeling method based on three-dimensional technology according to claim 1, characterized in that: In S5, when the capture system is able to accurately distinguish and record the independent motion trajectory of each actor, that is, the motion tracking accuracy value of the capture system for multiple characters generated within a fixed time period is greater than or equal to a preset motion tracking accuracy reference threshold, the generated three-dimensional animation is simulated and tested, and the motion tracking accuracy values ​​generated within a subsequent fixed time period that are greater than or equal to the preset motion tracking accuracy reference threshold are collected, and a data set is established, the mean and standard deviation of the data set are calculated, and after analyzing the data set, potential problems are predicted in advance based on the analysis results.

8. The intelligent animation modeling method based on three-dimensional technology according to claim 7 is characterized in that: If the mean value of the motion tracking accuracy values ​​in the data set is greater than or equal to the reference threshold of the mean value of the motion tracking accuracy values, and the standard deviation of the motion tracking accuracy values ​​is less than the reference threshold of the standard deviation of the motion tracking accuracy values, it indicates that the capture system can accurately distinguish and record the independent motion trajectory of each character, and the generated three-dimensional animation has a small error and conforms to the laws of physics. The capture device and algorithm continue to be maintained under the current configuration; If the mean value of the motion tracking accuracy is greater than or equal to the reference threshold of the mean value of the motion tracking accuracy, and the standard deviation of the motion tracking accuracy is greater than or equal to the reference threshold of the standard deviation of the motion tracking accuracy, it indicates that the capture system still fluctuates in some time periods, and the motion tracking capability is unstable, which affects the local quality of the 3D animation. It is necessary to optimize the robustness and anti-occlusion capability of the capture algorithm to enhance its adaptability to dynamically changing scenes; If the mean value of the motion tracking accuracy is less than the reference threshold of the mean value of the motion tracking accuracy, and the standard deviation of the motion tracking accuracy is greater than or equal to the reference threshold of the standard deviation of the motion tracking accuracy, it indicates that the overall performance of the capture system is insufficient and unstable. The capture system has serious defects in its ability to track the motion of multiple characters, and comprehensive optimization is required from the device configuration and algorithm levels. If the mean value of the motion tracking accuracy value is less than the reference threshold of the mean value of the motion tracking accuracy value, and the standard deviation of the motion tracking accuracy value is less than the reference threshold of the standard deviation of the motion tracking accuracy value, it indicates that the performance of the capture system is poor but stable, but cannot meet the high-precision requirements. The equipment and algorithm need to be optimized to improve the accuracy of motion tracking.

9. An intelligent animation modeling system based on three-dimensional technology, used to implement the intelligent animation modeling method based on three-dimensional technology according to any one of claims 1 to 8, characterized in that: Including motion capture module, data preprocessing and skeleton modeling module, AI animation optimization module, multi-role tracking evaluation module, animation simulation and physical optimization module, and animation rendering and integration module: Motion capture module: Use multi-view motion capture equipment to obtain the performer's motion data in real time, including setting markers on the performer's key parts to record their position, rotation and movement trajectory; Data preprocessing and skeleton modeling module: After preprocessing the captured motion data, a skeleton model of the target 3D character is created, including joint positions and hierarchical relationships, and the preprocessed motion data is mapped to the skeleton model through proportion adjustment and weight optimization; AI Animation Optimization Module: Uses artificial intelligence to optimize skeletal animation, including motion smoothing and keyframe extraction, while generating character facial animation to achieve a natural match between expression and motion, and uses deep learning to complete uncaptured motions to generate smooth transition animations; Multi-character tracking evaluation module: For multi-actor interaction scenes, analyze the abnormal changes in the marker occlusion rate and marker mismatch rate during the marker tracking process of the capture system to evaluate the capture system's ability to track the movements of multiple characters; Animation simulation and physics optimization module: When the capture system can accurately distinguish and record the independent movement trajectory of each actor, the generated 3D animation is simulated and tested to find and correct potential problems, including penetration and joint overrun, and the animation data is optimized in combination with the physics engine to make it conform to the laws of physics; Animation rendering and integration module: Export the optimized animation in a compatible format and integrate it into the target scene. Use real-time rendering technology to integrate characters and scenes, add lighting, materials and special effects, and generate the final high-quality animation effect.

Images