Motion capture collection method and system based on artificial intelligence

Abstract

The invention provides an artificial intelligence-based motion capture collection method and system, and the method comprises the steps: carrying out the multi-dimensional collection of the sign representation information of a human body based on a multi-dimensional sensor, and carrying out the preprocessing of the collected sign representation information; training and optimizing a deep learning model based on the preprocessed sign representation information, and performing multi-dimensional application scene interaction adaptation on the trained and optimized deep learning model; and fusing the real-time sign information collected by the multi-dimensional sensor, inputting a fusion result into the adapted deep learning model for analysis, and feeding back an analysis result to a corresponding management terminal based on a multi-dimensional application scene interaction adaption result. The motion capture efficiency and reliability are improved, meanwhile, the motion capture operation is simplified, and the motion capture effect is guaranteed.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a motion capture acquisition method and system based on artificial intelligence. Background Art

[0002] At present, with the continuous development of science and technology, motion capture technology has become an indispensable part of the film, television, game and other industries. In recent years, motion capture technology based on artificial intelligence has gradually attracted attention due to its advantages such as high precision, real-time and stability.

[0003] However, traditional motion capture methods mainly rely on electromagnetic induction, optical markers and inertial measurement, but these methods have problems such as expensive equipment, complex operation and strong limitations. At the same time, they cannot actively learn motion capture, resulting in reduced capture efficiency and accuracy.

[0004] Therefore, in order to overcome the above-mentioned defects, the present invention provides a motion capture acquisition method and system based on artificial intelligence. Summary of the invention

[0005] The present invention provides a motion capture acquisition method and system based on artificial intelligence, which are used to perform multi-dimensional acquisition of human body vital sign representation information through multi-dimensional sensors, thereby ensuring the comprehensiveness and reliability of the acquired vital sign representation information, so as to facilitate the training and optimization of the deep learning model according to the acquired vital sign representation information. Secondly, the acquired vital sign representation information is preprocessed, and the deep learning model is trained and optimized according to the preprocessing result, thereby ensuring the accuracy and reliability of deep learning. At the same time, the deep learning model is interactively adapted to multi-dimensional application scenarios, thereby facilitating the deep learning model to be able to be used in different application scenarios, thereby improving the reliability of action capture and acquisition in different application scenarios. Finally, the acquired real-time vital sign information is fused, thereby facilitating the deep learning model to comprehensively and effectively capture human body movements as a whole, and transmitting the fusion result to the adapted deep learning model for analysis, thereby ensuring the accuracy and reliability of the final motion information, and feeding back the obtained analysis result to the management terminal for management, thereby improving the efficiency and reliability of motion capture, and at the same time, simplifying the operation of motion capture and ensuring the effect of motion capture.

[0006] The present invention provides a motion capture acquisition method based on artificial intelligence, comprising:

[0007] Step 1: Collect the human body's vital sign information in multiple dimensions based on the multi-dimensional sensor, and pre-process the collected vital sign information;

[0008] Step 2: Train and optimize the deep learning model based on the preprocessed vital sign representation information, and perform multi-dimensional application scenario interactive adaptation on the trained and optimized deep learning model;

[0009] Step 3: Fuse the real-time vital sign information collected by multi-dimensional sensors, and input the fusion results into the adapted deep learning model for analysis, and feed back the analysis results to the corresponding management terminal based on the interactive adaptation results of the multi-dimensional application scenarios.

[0010] Preferably, in a motion capture acquisition method based on artificial intelligence, in step 1, multi-dimensional acquisition of human body vital sign representation information is performed based on a multi-dimensional sensor, including:

[0011] Acquire the collection items of information representing physical signs of the human body, and determine the collection parts on the human body corresponding to different collection items;

[0012] Extracting the part features of the collected part, marking specific tracking points of the multi-dimensional sensor based on the part features, and performing fixed-point tracking configuration of the multi-dimensional sensor based on the marking results;

[0013] Based on the fixed-point tracking configuration result, a data collection instruction is sent to the multi-dimensional sensor, and based on the data collection instruction, the multi-dimensional sensor is controlled to track the corresponding collection part in real time to obtain the vital sign representation information of the human body.

[0014] Preferably, in a motion capture acquisition method based on artificial intelligence, in step 1, the collected vital sign representation information is preprocessed, including:

[0015] Acquire the collected physical sign representation information, perform dimension splitting on the physical sign representation information, and perform serialization processing on the physical sign representation information after dimension splitting to obtain a physical sign representation information sequence;

[0016] Compare the states of the vital sign representation information at adjacent moments in each dimension, and determine the change amount of the vital sign representation information in each dimension based on the state comparison;

[0017] Different changes are digitally encoded based on encoding rules, and the data encoding results are logically associated based on the vital sign characterization information sequence to obtain a digital signal corresponding to the vital sign characterization information, and the vital sign characterization information is preprocessed based on the digital signal.

[0018] Preferably, a motion capture acquisition method based on artificial intelligence pre-processes vital sign representation information based on digital signals, including:

[0019] Obtaining the digital signal corresponding to the obtained vital sign representation information, and determining the average value of the digital signals of the adjacent target points of each point, and replacing the target value of the current point based on the average value;

[0020] Determine the filtering frequency band of the digital signal corresponding to the vital sign characterization information based on the replacement result, configure the filter parameters based on the filtering frequency band, and perform filtering processing on the vital sign characterization information based on the parameter configuration result;

[0021] Determine the value characteristics of the digital signal of the vital sign representation information in the time domain based on the filtering processing result, and use the value characteristics of the time domain as the first data feature;

[0022] At the same time, the digital signal of the vital sign representation information is converted into a frequency domain based on a preset rule, and the distribution and intensity characteristics of different frequency components of the digital signal of the vital sign representation information are determined based on the frequency domain conversion result, and the distribution and intensity characteristics of the different frequency components are used as the second data features;

[0023] The first data feature and the second data feature are aggregated to obtain the target data feature of the vital sign representation information.

[0024] Preferably, in a motion capture acquisition method based on artificial intelligence, in step 2, the deep learning model is trained and optimized based on the preprocessed vital sign representation information, and the trained and optimized deep learning model is interactively adapted to multi-dimensional application scenarios, including:

[0025] Obtaining preprocessed vital sign representation information, and dividing the vital sign representation information into data objects based on preset human body monitoring parts to obtain a sub-action data set;

[0026] Extracting data features of the sub-action data set, and determining the action posture of the corresponding monitoring part based on the data features;

[0027] The execution action of the monitoring part is split based on the action posture to obtain the action branch set and the corresponding joint points, and the action parameters of each action branch in the action branch set are quantified based on the split result and the target value of the sub-action data set;

[0028] Based on the quantization results, the execution parameter features of each action branch are obtained. At the same time, the position change features of the joint points under the corresponding execution parameter features are obtained, and the execution parameter features and the position change features of the joint points are associated;

[0029] The correlation results of the execution parameter characteristics and the position change characteristics of the joint points of the same monitoring part in different scenarios are statistically analyzed, and an action control group is constructed based on the statistical results;

[0030] Mapping analysis is performed on the action control group to obtain the action feature representation of each monitored part in time and space dimensions and the corresponding action feature parameters;

[0031] Iteratively train the deep learning model based on the action feature representation and action feature parameters, and based on the model loss value of the deep learning model after each iterative training;

[0032] Based on the model loss value, the model optimization direction and parameters for the next iterative training are determined, and based on the model loss value, model optimization direction and parameters, the deep learning model is negatively feedback iteratively optimized to complete the training and optimization of the deep learning model.

[0033] Preferably, in a motion capture acquisition method based on artificial intelligence, in step 2, the trained and optimized deep learning model is interactively adapted to multi-dimensional application scenarios, including:

[0034] Obtain the trained and optimized deep learning model, and at the same time, obtain the application scenario of the deep learning model, and determine the corresponding interaction requirements based on the execution items of the application scenario;

[0035] Determine the output and interaction methods of deep learning models in different application scenarios based on interaction requirements, and add auxiliary coordination mechanisms to the deep learning models based on the output and interaction methods;

[0036] Based on the added results, add an execution logic judgment mechanism to the subsidiary coordination mechanisms of different application scenarios, and associate the execution logic judgment mechanism with the deep learning model through parameters;

[0037] Based on the parameter association results, interactive adaptation of the deep learning model to multi-dimensional application scenarios is completed.

[0038] Preferably, in a motion capture acquisition method based on artificial intelligence, in step 3, real-time vital sign information collected by multi-dimensional sensors is fused, and the fusion result is input into the adapted deep learning model for analysis, including:

[0039] Obtain real-time vital sign information collected by multi-dimensional sensors, and extract timestamp information corresponding to the real-time vital sign information;

[0040] The real-time vital sign information collected by the multi-dimensional sensors is time-aligned based on the timestamp, and the subject objects corresponding to the real-time vital sign information collected by the sensors of each dimension are respectively extracted based on the time alignment result;

[0041] Determine the fusion logic of the real-time vital sign information based on the distribution position of the subject object in the human body, and determine the fusion data nodes between the real-time vital sign information based on the fusion logic. At the same time, determine the weight of each subject object based on the action representation of each subject object;

[0042] The real-time vital sign information collected by multi-dimensional sensors is fused based on the weights of each subject object and the fusion data nodes between the real-time vital sign information, and the fusion results are input into the adapted deep learning model for analysis to obtain the target action features corresponding to the real-time vital sign information.

[0043] Preferably, in a motion capture acquisition method based on artificial intelligence, in step 3, the analysis result is fed back to the corresponding management terminal based on the multi-dimensional application scenario interactive adaptation result, including:

[0044] Obtain target action features corresponding to real-time vital sign information, and receive interaction requests sent by the management terminal;

[0045] Extract the scene identifier in the interaction request, and match the scene identifier with the preset scene interaction mechanism to determine the target scene interaction mechanism corresponding to the current application scene;

[0046] Feedback the target action features to the management terminal based on the target scene interaction mechanism, and create a temporary cache file in the management terminal;

[0047] The received target action features are cached in a temporary cache file.

[0048] The present invention provides a motion capture acquisition system based on artificial intelligence, comprising:

[0049] A data acquisition and preprocessing module is used to collect multi-dimensional information on the body's vital signs based on multi-dimensional sensors, and to preprocess the collected vital signs;

[0050] Model building and adaptation module, used to train and optimize the deep learning model based on the preprocessed vital sign representation information, and to interactively adapt the trained and optimized deep learning model to multi-dimensional application scenarios;

[0051] The analysis and interaction module is used to fuse the real-time vital sign information collected by multi-dimensional sensors, input the fusion results into the adapted deep learning model for analysis, and feed back the analysis results to the corresponding management terminal based on the interactive adaptation results of the multi-dimensional application scenarios.

[0052] Preferably, a motion capture acquisition system based on artificial intelligence, a data acquisition and preprocessing module, comprises:

[0053] A collection part determination unit, used to obtain collection items of information representing physical signs of a human body, and determine collection parts corresponding to different collection items on the human body;

[0054] A sensor configuration unit, used for extracting the part features of the collection part, marking specific tracking points of the multi-dimensional sensor based on the part features, and performing fixed-point tracking configuration of the multi-dimensional sensor based on the marking results;

[0055] The data acquisition unit is used to send data acquisition instructions to the multi-dimensional sensor based on the fixed-point tracking configuration result, and control the multi-dimensional sensor to track the corresponding acquisition part in real time based on the data acquisition instruction to obtain the vital sign representation information of the human body.

[0056] Compared with the prior art, the present invention has the following beneficial effects:

[0057] 1. Multi-dimensional collection of human body's vital sign representation information is performed through multi-dimensional sensors, ensuring the comprehensiveness and reliability of the collected vital sign representation information, so as to facilitate the training and optimization of the deep learning model according to the collected vital sign representation information. Secondly, the collected vital sign representation information is preprocessed, and the deep learning model is trained and optimized according to the preprocessing results, ensuring the accuracy and reliability of deep learning. At the same time, the deep learning model is interactively adapted to multi-dimensional application scenarios, so as to ensure that the deep learning model can be used in different application scenarios, thereby improving the reliability of action capture and collection in different application scenarios. Finally, the collected real-time vital sign information is fused, so that the deep learning model can capture human body movements comprehensively and effectively as a whole, and the fusion results are transmitted to the adapted deep learning model for analysis, ensuring the accuracy and reliability of the final motion information, and the obtained analysis results are fed back to the management terminal for management, which improves the efficiency and reliability of motion capture. At the same time, it also simplifies the operation of motion capture and ensures the effect of motion capture.

[0058] 2. By determining the collection items of human body's vital signs information, the collection parts can be accurately and effectively determined according to the collection items, so as to facilitate the fixed-point tracking configuration of the multi-dimensional sensor according to the determined collection parts. Secondly, according to the configuration results, the issued data collection instructions are received in real time, and when the data collection instructions are received, the multi-dimensional sensor is promptly controlled to track the corresponding collection parts in real time, so as to realize the comprehensive and effective collection of human body's vital signs information, and provide data support for the comprehensive training of deep learning models.

[0059] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures specifically pointed out in this application document.

[0060] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0062] Figure 1 A motion capture acquisition method based on artificial intelligence in an embodiment of the present invention;

[0063] Figure 2 This is a flowchart of step 1 in a motion capture method based on artificial intelligence in an embodiment of the present invention;

[0064] Figure 3 The structure diagram of an artificial intelligence-based motion capture system in an embodiment of the present invention. DETAILED DESCRIPTION

[0065] The preferred embodiments of the present invention are described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0066] Embodiment 1:

[0067] This embodiment provides a motion capture acquisition method based on artificial intelligence, such as Figure 1 As shown, including:

[0068] Step 1: Collect the human body's vital sign information in multiple dimensions based on the multi-dimensional sensor, and pre-process the collected vital sign information;

[0069] Step 2: Train and optimize the deep learning model based on the preprocessed vital sign representation information, and perform multi-dimensional application scenario interactive adaptation on the trained and optimized deep learning model;

[0070] Step 3: Fuse the real-time vital sign information collected by multi-dimensional sensors, and input the fusion results into the adapted deep learning model for analysis, and feed back the analysis results to the corresponding management terminal based on the interactive adaptation results of the multi-dimensional application scenarios.

[0071] In this embodiment, the multi-dimensional sensor refers to a plurality of sensors of different types, which are used to collect different vital sign representation information of the human body.

[0072] In this embodiment, the physical sign representation information refers to the movement information, posture information, and expression information of the human body during exercise.

[0073] In this embodiment, multi-dimensional acquisition refers to the process of acquiring vital sign representation information of the human body through a multi-dimensional sensor.

[0074] In this embodiment, preprocessing refers to performing denoising, filtering, feature extraction and other processing on the collected vital sign representation information.

[0075] In this embodiment, multi-dimensional application scenario interaction adaptation refers to ensuring that the constructed deep learning model can be used in different application scenarios. For example, in the field of human-computer interaction, it realizes functions such as gesture recognition, facial expression recognition, and body posture recognition; in the field of virtual reality, it realizes functions such as virtual character motion simulation and animation production.

[0076] In this embodiment, fusing the real-time vital sign information collected by the multi-dimensional sensors refers to associating the collected real-time vital sign information, in order to conduct a more comprehensive analysis of the movement trajectory of the human body.

[0077] The working principle and beneficial effects of the above technical solution are: multi-dimensional collection of human body vital sign representation information is performed through multi-dimensional sensors, ensuring the comprehensiveness and reliability of the collected vital sign representation information, so as to facilitate the training and optimization of the deep learning model according to the collected vital sign representation information; secondly, the collected vital sign representation information is preprocessed, and the deep learning model is trained and optimized according to the preprocessing results, ensuring the accuracy and reliability of deep learning; at the same time, the deep learning model is interactively adapted to multi-dimensional application scenarios, so as to ensure that the deep learning model can be used in different application scenarios, thereby improving the reliability of action capture and collection in different application scenarios; finally, the collected real-time vital sign information is fused, so that the deep learning model can capture human body movements comprehensively and effectively as a whole, and the fusion results are transmitted to the adapted deep learning model for analysis, ensuring the accuracy and reliability of the final motion information, and the obtained analysis results are fed back to the management terminal for management, which improves the efficiency and reliability of motion capture, and at the same time, simplifies the operation of motion capture and ensures the effect of motion capture.

[0078] Embodiment 2:

[0079] Based on Example 1, this embodiment provides a motion capture acquisition method based on artificial intelligence, such as Figure 2 As shown, in step 1, multi-dimensional collection of human body vital sign representation information is performed based on a multi-dimensional sensor, including:

[0080] Step 101: Acquire collection items of information representing physical signs of a human body, and determine collection locations corresponding to different collection items on the human body;

[0081] Step 102: extracting the part features of the collected part, marking specific tracking points of the multi-dimensional sensor based on the part features, and performing fixed-point tracking configuration on the multi-dimensional sensor based on the marking results;

[0082] Step 103: Based on the fixed-point tracking configuration result, a data collection instruction is issued to the multi-dimensional sensor, and based on the data collection instruction, the multi-dimensional sensor is controlled to track the corresponding collection part in real time to obtain the vital sign representation information of the human body.

[0083] In this embodiment, the collection items refer to the types of vital sign representation information that need to be collected, such as the movement of each tissue, the posture presented at different times during the operation process, and the user's expression.

[0084] In this embodiment, the part feature refers to information such as the corresponding position of the collected part on the human body.

[0085] In this embodiment, the specific tracking point marking refers to limiting the tracking object of the corresponding sensor according to the part characteristics, ensuring that each sensor can comprehensively and effectively monitor and collect the motion data of the corresponding collection part.

[0086] In this embodiment, the fixed-point tracking configuration refers to configuring specific operating parameters corresponding to each sensor during the tracking process.

[0087] The working principle and beneficial effects of the above technical solution are: by determining the collection items of the vital signs representation information of the human body, the collection part can be accurately and effectively determined according to the collection items, so as to facilitate the fixed-point tracking configuration of the multi-dimensional sensor according to the determined collection part; secondly, the data collection instructions issued are received in real time according to the configuration results, and when the data collection instructions are received, the multi-dimensional sensor is promptly controlled to track the corresponding collection part in real time, so as to realize the comprehensive and effective collection of the vital signs representation information of the human body, and provide data support for the comprehensive training of the deep learning model.

[0088] Embodiment 3:

[0089] On the basis of Example 1, this embodiment provides a motion capture acquisition method based on artificial intelligence. In step 1, the collected vital sign representation information is preprocessed, including:

[0090] Acquire the collected physical sign representation information, perform dimension splitting on the physical sign representation information, and perform serialization processing on the physical sign representation information after dimension splitting to obtain a physical sign representation information sequence;

[0091] Compare the states of the vital sign representation information at adjacent moments in each dimension, and determine the change amount of the vital sign representation information in each dimension based on the state comparison;

[0092] Different changes are digitally encoded based on encoding rules, and the data encoding results are logically associated based on the vital sign characterization information sequence to obtain a digital signal corresponding to the vital sign characterization information, and the vital sign characterization information is preprocessed based on the digital signal.

[0093] In this embodiment, dimension splitting refers to splitting the vital sign representation information according to data types, for example, it can be split into action information, posture information, and expression information.

[0094] In this embodiment, serialization processing refers to arranging the split vital sign representation information, that is, determining the specific data content corresponding to different moments, wherein the sequence of vital sign representation information is the serialization processing result.

[0095] In this embodiment, the encoding rule is set in advance, for example, it can be binary encoding.

[0096] The working principle and beneficial effects of the above technical solution are: by splitting and analyzing the vital sign representation information, the change amount of the vital sign representation information in each dimension can be accurately and effectively determined, and different change amounts are digitally encoded through coding rules to achieve format conversion of the vital sign representation information and obtain the corresponding digital signal, thereby facilitating the preprocessing of the vital sign representation information and providing convenience for the training and optimization of the deep learning model.

[0097] Embodiment 4:

[0098] On the basis of Example 3, this embodiment provides a motion capture acquisition method based on artificial intelligence, which pre-processes vital sign representation information based on digital signals, including:

[0099] Obtaining the digital signal corresponding to the obtained vital sign representation information, and determining the average value of the digital signals of the adjacent target points of each point, and replacing the target value of the current point based on the average value;

[0100] Determine the filtering frequency band of the digital signal corresponding to the vital sign characterization information based on the replacement result, configure the filter parameters based on the filtering frequency band, and perform filtering processing on the vital sign characterization information based on the parameter configuration result;

[0101] Determine the value characteristics of the digital signal of the vital sign representation information in the time domain based on the filtering processing result, and use the value characteristics of the time domain as the first data feature;

[0102] At the same time, the digital signal of the vital sign representation information is converted into a frequency domain based on a preset rule, and the distribution and intensity characteristics of different frequency components of the digital signal of the vital sign representation information are determined based on the frequency domain conversion result, and the distribution and intensity characteristics of the different frequency components are used as the second data features;

[0103] The first data feature and the second data feature are aggregated to obtain the target data feature of the vital sign representation information.

[0104] In this embodiment, the target value refers to the specific value size corresponding to the data of the current position point.

[0105] In this embodiment, the filtering frequency band is a specific frequency range corresponding to the data to be filtered out in the digital signal, that is, the data in this frequency range needs to be filtered out.

[0106] In this embodiment, the first data feature refers to the value distribution of the vital sign representation information in the time domain.

[0107] In this embodiment, the preset rule is set in advance and is used to convert the format of the vital sign representation information, that is, to convert the vital sign representation information into a frequency domain signal.

[0108] In this embodiment, the distribution and intensity characteristics refer to the distribution of data signals of different frequencies in the vital sign representation information in the frequency domain and the corresponding value changes.

[0109] The working principle and beneficial effects of the above technical solution are: by cleaning the corresponding digital signal of the vital sign characterization information, the accuracy and reliability of the obtained vital sign characterization information are ensured; secondly, by processing and extracting features of the cleaned vital sign characterization information, the target data features of the vital sign characterization information are effectively extracted.

[0110] Embodiment 5:

[0111] Based on Example 1, this embodiment provides a motion capture acquisition method based on artificial intelligence. In step 2, the deep learning model is trained and optimized based on the preprocessed vital sign representation information, and the trained and optimized deep learning model is interactively adapted to multi-dimensional application scenarios, including:

[0112] Obtaining preprocessed vital sign representation information, and dividing the vital sign representation information into data objects based on preset human body monitoring parts to obtain a sub-action data set;

[0113] Extracting data features of the sub-action data set, and determining the action posture of the corresponding monitoring part based on the data features;

[0114] The execution action of the monitoring part is split based on the action posture to obtain the action branch set and the corresponding joint points, and the action parameters of each action branch in the action branch set are quantified based on the split result and the target value of the sub-action data set;

[0115] Based on the quantization results, the execution parameter features of each action branch are obtained. At the same time, the position change features of the joint points under the corresponding execution parameter features are obtained, and the execution parameter features and the position change features of the joint points are associated;

[0116] The correlation results of the execution parameter characteristics and the position change characteristics of the joint points of the same monitoring part in different scenarios are statistically analyzed, and an action control group is constructed based on the statistical results;

[0117] Mapping analysis is performed on the action control group to obtain the action feature representation of each monitored part in time and space dimensions and the corresponding action feature parameters;

[0118] Iteratively train the deep learning model based on the action feature representation and action feature parameters, and based on the model loss value of the deep learning model after each iterative training;

[0119] Based on the model loss value, the model optimization direction and parameters for the next iterative training are determined, and based on the model loss value, model optimization direction and parameters, the deep learning model is negatively feedback iteratively optimized to complete the training and optimization of the deep learning model.

[0120] In this embodiment, the preset human body monitoring parts are known in advance, such as legs, head, arms, etc., in order to effectively split the physical sign representation information.

[0121] In this embodiment, the sub-action data set refers to the splitting of the vital sign representation information according to the preset human body monitoring parts (ie, the vital sign representation information is split into specific data corresponding to each human body monitoring part according to the preset human body monitoring parts).

[0122] In this embodiment, the data feature refers to the value range corresponding to the sub-action data set and the corresponding data structure.

[0123] In this embodiment, splitting the execution action of the monitored part refers to splitting the execution action of the monitored part into corresponding components. For example, when the legs are walking, the execution action of the legs can be split into a lifting part, an extending part, and a falling part, etc., wherein the action branch set is the splitting result.

[0124] In this embodiment, the joint point refers to the associated position between different actions after the execution actions of the monitoring part are split.

[0125] In this embodiment, the execution parameter feature refers to the specific action motion situation corresponding to each action branch, for example, the amplitude of the action.

[0126] In this embodiment, the position change feature refers to the change of the motion trajectory of the joint point during the motion process.

[0127] In this embodiment, the motion feature representation refers to all motion conditions presented by each monitored part in different scenarios.

[0128] In this embodiment, the motion characteristic parameter refers to the specific motion size corresponding to each monitored part during the movement process.

[0129] In this embodiment, the model loss value refers to the performance loss of the deep learning model after each iterative training. The smaller the model loss value, the better the performance of the model loss value.

[0130] In this embodiment, the model optimization direction and parameters for the next iterative training refer to the parameters that need to be optimized for the training direction of the next training and the training parameter values ​​in the training direction based on the previous training of the deep learning model.

[0131] The working principle and beneficial effects of the above technical solution are: by splitting the vital sign representation information, the sub-action data set corresponding to each monitoring part can be accurately and effectively determined; secondly, the sub-action data set of each monitoring part is analyzed to effectively determine the execution parameter characteristics and position change characteristics of each monitoring part in different scenarios, and the action feature representation and the corresponding action feature parameters are locked, thereby providing a training basis for training the deep learning model; finally, the deep learning model is iteratively trained through the obtained action feature representation and action feature parameters, ensuring the training effect of the deep learning model, thereby ensuring the reliability of action capture and collection in different application scenarios.

[0132] Embodiment 6:

[0133] On the basis of Example 1, this embodiment provides a motion capture acquisition method based on artificial intelligence. In step 2, the trained and optimized deep learning model is interactively adapted to multi-dimensional application scenarios, including:

[0134] Obtain the trained and optimized deep learning model, and at the same time, obtain the application scenario of the deep learning model, and determine the corresponding interaction requirements based on the execution items of the application scenario;

[0135] Determine the output and interaction methods of deep learning models in different application scenarios based on interaction requirements, and add auxiliary coordination mechanisms to the deep learning models based on the output and interaction methods;

[0136] Based on the added results, add an execution logic judgment mechanism to the subsidiary coordination mechanisms of different application scenarios, and associate the execution logic judgment mechanism with the deep learning model through parameters;

[0137] Based on the parameter association results, interactive adaptation of the deep learning model to multi-dimensional application scenarios is completed.

[0138] In this embodiment, the execution project refers to the type of motion capture that needs to be executed through a deep learning model.

[0139] In this embodiment, the interaction requirement refers to the ultimate purpose to be achieved.

[0140] In this embodiment, the subsidiary collaboration mechanism refers to a collaboration scheme configured during the application of the deep learning model to achieve the purpose of scene interaction. The purpose is to ensure the effective operation of the deep learning model and to facilitate timely coordination of the deep learning model according to the needs of different application scenarios.

[0141] In this embodiment, the execution logic judgment mechanism is used to determine whether the deep learning model meets the corresponding execution conditions, so as to facilitate timely scene interaction adaptation through the deep learning model when the conditions are met.

[0142] The working principle and beneficial effects of the above technical solution are: by determining the application scenarios of the deep learning model, the interaction requirements of different application scenarios can be locked, thereby facilitating the interactive adaptation of the deep learning model to different application scenarios according to the interaction requirements, thereby ensuring that the deep learning model can be used in different application scenarios.

[0143] Embodiment 7:

[0144] Based on Example 1, this embodiment provides a motion capture acquisition method based on artificial intelligence. In step 3, the real-time vital sign information collected by the multi-dimensional sensor is fused, and the fusion result is input into the adapted deep learning model for analysis, including:

[0145] Obtain real-time vital sign information collected by multi-dimensional sensors, and extract timestamp information corresponding to the real-time vital sign information;

[0146] The real-time vital sign information collected by the multi-dimensional sensors is time-aligned based on the timestamp, and the subject objects corresponding to the real-time vital sign information collected by the sensors of each dimension are respectively extracted based on the time alignment result;

[0147] Determine the fusion logic of the real-time vital sign information based on the distribution position of the subject object in the human body, and determine the fusion data nodes between the real-time vital sign information based on the fusion logic. At the same time, determine the weight of each subject object based on the action representation of each subject object;

[0148] The real-time vital sign information collected by multi-dimensional sensors is fused based on the weights of each subject object and the fusion data nodes between the real-time vital sign information, and the fusion results are input into the adapted deep learning model for analysis to obtain the target action features corresponding to the real-time vital sign information.

[0149] In this embodiment, the subject object refers to the specific monitoring part corresponding to the real-time vital sign information.

[0150] In this embodiment, the fusion logic is used to represent the logic of fusion of real-time vital sign information between different subject objects when performing real-time vital sign information fusion.

[0151] In this embodiment, the fusion data node refers to a data fusion position point between different real-time vital sign data when different real-time vital sign information is being fused.

[0152] The working principle and beneficial effects of the above technical solution are: by analyzing the collected real-time vital sign information, accurate and effective fusion of different real-time vital sign information of different monitoring is achieved, and the fusion results are input into the deep learning model for training, which provides a guarantee for determining the target motion characteristics and ensures the reliability and accuracy of motion capture.

[0153] Embodiment 8:

[0154] On the basis of Example 1, this embodiment provides a motion capture acquisition method based on artificial intelligence. In step 3, the analysis result is fed back to the corresponding management terminal based on the multi-dimensional application scenario interactive adaptation result, including:

[0155] Obtain target action features corresponding to real-time vital sign information, and receive interaction requests sent by the management terminal;

[0156] Extract the scene identifier in the interaction request, and match the scene identifier with the preset scene interaction mechanism to determine the target scene interaction mechanism corresponding to the current application scene;

[0157] Feedback the target action features to the management terminal based on the target scene interaction mechanism, and create a temporary cache file in the management terminal;

[0158] The received target action features are cached in a temporary cache file.

[0159] In this embodiment, the scene identifier is a marking symbol used to distinguish different scenes.

[0160] In this embodiment, the target scene interaction mechanism refers to a scene interaction mechanism applicable to the current application scene, which is one of the preset scene interaction mechanisms.

[0161] The working principle and beneficial effects of the above technical solution are: by analyzing the interaction request, the scene identifier corresponding to the interaction request is locked, so as to determine the corresponding target scene interaction mechanism according to the scene identifier, and the target action features obtained according to the target scene interaction mechanism are fed back to the management terminal for caching, so as to achieve effective management of the captured target action features.

[0162] Embodiment 9:

[0163] This embodiment provides a motion capture acquisition system based on artificial intelligence, such as Figure 3 As shown, including:

[0164] A data acquisition and preprocessing module is used to collect multi-dimensional information on the body's vital signs based on multi-dimensional sensors, and to preprocess the collected vital signs;

[0165] Model building and adaptation module, used to train and optimize the deep learning model based on the preprocessed vital sign representation information, and to interactively adapt the trained and optimized deep learning model to multi-dimensional application scenarios;

[0166] The analysis and interaction module is used to fuse the real-time vital sign information collected by multi-dimensional sensors, input the fusion results into the adapted deep learning model for analysis, and feed back the analysis results to the corresponding management terminal based on the interactive adaptation results of the multi-dimensional application scenarios.

[0167] The working principle and beneficial effects of the above technical solution are: multi-dimensional collection of human body vital sign representation information is performed through multi-dimensional sensors, ensuring the comprehensiveness and reliability of the collected vital sign representation information, so as to facilitate the training and optimization of the deep learning model according to the collected vital sign representation information; secondly, the collected vital sign representation information is preprocessed, and the deep learning model is trained and optimized according to the preprocessing results, ensuring the accuracy and reliability of deep learning; at the same time, the deep learning model is interactively adapted to multi-dimensional application scenarios, so as to ensure that the deep learning model can be used in different application scenarios, thereby improving the reliability of action capture and collection in different application scenarios; finally, the collected real-time vital sign information is fused, so that the deep learning model can capture human body movements comprehensively and effectively as a whole, and the fusion results are transmitted to the adapted deep learning model for analysis, ensuring the accuracy and reliability of the final motion information, and the obtained analysis results are fed back to the management terminal for management, which improves the efficiency and reliability of motion capture, and at the same time, simplifies the operation of motion capture and ensures the effect of motion capture.

[0168] Embodiment 10:

[0169] Based on Example 9, this embodiment provides a motion capture acquisition system based on artificial intelligence, a data acquisition and preprocessing module, including:

[0170] A collection part determination unit, used to obtain collection items of information representing physical signs of a human body, and determine collection parts corresponding to different collection items on the human body;

[0171] A sensor configuration unit, used for extracting the part features of the collection part, marking specific tracking points of the multi-dimensional sensor based on the part features, and performing fixed-point tracking configuration of the multi-dimensional sensor based on the marking results;

[0172] The data acquisition unit is used to send data acquisition instructions to the multi-dimensional sensor based on the fixed-point tracking configuration result, and control the multi-dimensional sensor to track the corresponding acquisition part in real time based on the data acquisition instruction to obtain the vital sign representation information of the human body.

[0173] The working principle and beneficial effects of the above technical solution are: by determining the collection items of the vital signs representation information of the human body, the collection part can be accurately and effectively determined according to the collection items, so as to facilitate the fixed-point tracking configuration of the multi-dimensional sensor according to the determined collection part; secondly, the data collection instructions issued are received in real time according to the configuration results, and when the data collection instructions are received, the multi-dimensional sensor is promptly controlled to track the corresponding collection part in real time, so as to realize the comprehensive and effective collection of the vital signs representation information of the human body, and provide data support for the comprehensive training of the deep learning model.

[0174] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A motion capture acquisition method based on artificial intelligence, characterized in that: include: Step 1: Collect the human body's vital sign information in multiple dimensions based on the multi-dimensional sensor, and pre-process the collected vital sign information; Step 2: Train and optimize the deep learning model based on the preprocessed vital sign representation information, and perform multi-dimensional application scenario interactive adaptation on the trained and optimized deep learning model; Step 3: Fuse the real-time vital sign information collected by multi-dimensional sensors, and input the fusion results into the adapted deep learning model for analysis, and feed back the analysis results to the corresponding management terminal based on the interactive adaptation results of the multi-dimensional application scenarios.

2. The method for motion capture based on artificial intelligence according to claim 1, characterized in that: In step 1, multi-dimensional collection of human body vital sign information is performed based on multi-dimensional sensors, including: Acquire the collection items of information representing physical signs of the human body, and determine the collection parts on the human body corresponding to different collection items; Extracting the part features of the collected part, marking specific tracking points of the multi-dimensional sensor based on the part features, and performing fixed-point tracking configuration of the multi-dimensional sensor based on the marking results; Based on the fixed-point tracking configuration result, a data collection instruction is sent to the multi-dimensional sensor, and based on the data collection instruction, the multi-dimensional sensor is controlled to track the corresponding collection part in real time to obtain the vital sign representation information of the human body.

3. The method for motion capture based on artificial intelligence according to claim 1, characterized in that: In step 1, the collected vital sign representation information is preprocessed, including: Acquire the collected physical sign representation information, perform dimension splitting on the physical sign representation information, and perform serialization processing on the physical sign representation information after dimension splitting to obtain a physical sign representation information sequence; Compare the states of the vital sign representation information at adjacent moments in each dimension, and determine the change amount of the vital sign representation information in each dimension based on the state comparison; Different changes are digitally encoded based on encoding rules, and the data encoding results are logically associated based on the vital sign characterization information sequence to obtain a digital signal corresponding to the vital sign characterization information, and the vital sign characterization information is preprocessed based on the digital signal.

4. The method for motion capture based on artificial intelligence according to claim 3, characterized in that: Preprocessing of vital sign representation information based on digital signals includes: Obtaining the digital signal corresponding to the obtained vital sign representation information, and determining the average value of the digital signals of the adjacent target points of each point, and replacing the target value of the current point based on the average value; Determine the filtering frequency band of the digital signal corresponding to the vital sign characterization information based on the replacement result, configure the filter parameters based on the filtering frequency band, and perform filtering processing on the vital sign characterization information based on the parameter configuration result; Determine the value characteristics of the digital signal of the vital sign representation information in the time domain based on the filtering processing result, and use the value characteristics of the time domain as the first data feature; At the same time, the digital signal of the vital sign representation information is converted into a frequency domain based on a preset rule, and the distribution and intensity characteristics of different frequency components of the digital signal of the vital sign representation information are determined based on the frequency domain conversion result, and the distribution and intensity characteristics of the different frequency components are used as the second data features; The first data feature and the second data feature are aggregated to obtain the target data feature of the vital sign representation information.

5. The method for motion capture based on artificial intelligence according to claim 1, characterized in that: In step 2, the deep learning model is trained and optimized based on the preprocessed vital sign representation information, and the trained and optimized deep learning model is interactively adapted to multi-dimensional application scenarios, including: Obtaining preprocessed vital sign representation information, and dividing the vital sign representation information into data objects based on preset human body monitoring parts to obtain a sub-action data set; Extracting data features of the sub-action data set, and determining the action posture of the corresponding monitoring part based on the data features; The execution action of the monitoring part is split based on the action posture to obtain the action branch set and the corresponding joint points, and the action parameters of each action branch in the action branch set are quantified based on the split result and the target value of the sub-action data set; Based on the quantization results, the execution parameter features of each action branch are obtained. At the same time, the position change features of the joint points under the corresponding execution parameter features are obtained, and the execution parameter features and the position change features of the joint points are associated; The correlation results of the execution parameter characteristics and the position change characteristics of the joint points of the same monitoring part in different scenarios are statistically analyzed, and an action control group is constructed based on the statistical results; Mapping analysis is performed on the action control group to obtain the action feature representation of each monitored part in time and space dimensions and the corresponding action feature parameters; Iteratively train the deep learning model based on the action feature representation and action feature parameters, and based on the model loss value of the deep learning model after each iterative training; Based on the model loss value, the model optimization direction and parameters for the next iterative training are determined, and based on the model loss value, model optimization direction and parameters, the deep learning model is negatively feedback iteratively optimized to complete the training and optimization of the deep learning model.

6. The method for motion capture based on artificial intelligence according to claim 1, characterized in that: In step 2, the trained and optimized deep learning model is interactively adapted to multi-dimensional application scenarios, including: Obtain the trained and optimized deep learning model, and at the same time, obtain the application scenario of the deep learning model, and determine the corresponding interaction requirements based on the execution items of the application scenario; Determine the output and interaction methods of deep learning models in different application scenarios based on interaction requirements, and add auxiliary coordination mechanisms to the deep learning models based on the output and interaction methods; Based on the added results, add an execution logic judgment mechanism to the subsidiary coordination mechanisms of different application scenarios, and associate the execution logic judgment mechanism with the deep learning model through parameters; Based on the parameter association results, interactive adaptation of the deep learning model to multi-dimensional application scenarios is completed.

7. The method for motion capture based on artificial intelligence according to claim 1, characterized in that: In step 3, the real-time vital sign information collected by the multi-dimensional sensors is fused, and the fusion results are input into the adapted deep learning model for analysis, including: Obtain real-time vital sign information collected by multi-dimensional sensors, and extract timestamp information corresponding to the real-time vital sign information; The real-time vital sign information collected by the multi-dimensional sensors is time-aligned based on the timestamp, and the subject objects corresponding to the real-time vital sign information collected by the sensors of each dimension are respectively extracted based on the time alignment result; Determine the fusion logic of the real-time vital sign information based on the distribution position of the subject object in the human body, and determine the fusion data nodes between the real-time vital sign information based on the fusion logic. At the same time, determine the weight of each subject object based on the action representation of each subject object; The real-time vital sign information collected by multi-dimensional sensors is fused based on the weights of each subject object and the fusion data nodes between the real-time vital sign information, and the fusion results are input into the adapted deep learning model for analysis to obtain the target action features corresponding to the real-time vital sign information.

8. The motion capture acquisition method based on artificial intelligence according to claim 1, characterized in that: In step 3, the analysis results are fed back to the corresponding management terminal based on the multi-dimensional application scenario interactive adaptation results, including: Obtain target action features corresponding to real-time vital sign information, and receive interaction requests sent by the management terminal; Extract the scene identifier in the interaction request, and match the scene identifier with the preset scene interaction mechanism to determine the target scene interaction mechanism corresponding to the current application scene; Feedback the target action features to the management terminal based on the target scene interaction mechanism, and create a temporary cache file in the management terminal; The received target action features are cached in a temporary cache file.

9. A motion capture system based on artificial intelligence, characterized in that: include: A data acquisition and preprocessing module is used to collect multi-dimensional information on the body's vital signs based on multi-dimensional sensors, and to preprocess the collected vital signs; Model building and adaptation module, used to train and optimize the deep learning model based on the preprocessed vital sign representation information, and to interactively adapt the trained and optimized deep learning model to multi-dimensional application scenarios; The analysis and interaction module is used to fuse the real-time vital sign information collected by multi-dimensional sensors, input the fusion results into the adapted deep learning model for analysis, and feed back the analysis results to the corresponding management terminal based on the interactive adaptation results of the multi-dimensional application scenarios.

10. The artificial intelligence-based motion capture system according to claim 9, characterized in that: Data acquisition and preprocessing modules, including: A collection part determination unit, used to obtain collection items of information representing physical signs of a human body, and determine collection parts corresponding to different collection items on the human body; A sensor configuration unit, used for extracting the part features of the collection part, marking specific tracking points of the multi-dimensional sensor based on the part features, and performing fixed-point tracking configuration of the multi-dimensional sensor based on the marking results; The data acquisition unit is used to send data acquisition instructions to the multi-dimensional sensor based on the fixed-point tracking configuration result, and control the multi-dimensional sensor to track the corresponding acquisition part in real time based on the data acquisition instruction to obtain the vital sign representation information of the human body.

Images