Water sports training interactive method, system and medium based on virtual reality

Abstract

The invention relates to the technical field of data processing, and in particular to a water sports training interactive method, system and medium based on virtual reality. The method comprises: in response to a training start instruction triggered by a user, a standard action model of a training task is played cyclically through a display, and N motion data are acquired through an inertial motion capture device; based on the motion data and the standard action model, the action difference of M key actions is determined, and then a target key action and a target key part corresponding to the target key action are determined; surface electromyography signals of the target key part are obtained, and an expected improvement degree of the target key action is determined based on the surface electromyography signals and the action difference degree, and the target key action with an expected improvement degree greater than an improvement degree threshold is used as a training action; in response to a reinforcement training instruction triggered by the user, interactive training is performed on the training action. The invention can improve the training effect of water sports.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a water sports training interaction method, system and medium based on virtual reality. Background Art

[0002] The application of virtual reality (VR) technology in water sports training is a rapidly developing field. It provides athletes with a safe and controllable training platform by simulating real water environments and sports conditions. Compared with traditional water training, VR technology can create a realistic water environment, including waves, currents and different weather conditions. The VR training system can be carried out without being restricted by weather and other external conditions, allowing athletes to experience various situations in simulated competitions.

[0003] However, in the process of water sports training based on virtual reality, only scene experience is often provided, which is difficult to effectively improve the training effect. Therefore, how to effectively use the collected training data, analyze and process the training data, provide interactive feedback on the training effect, and improve the training effect has become a technical problem that needs to be solved urgently. Summary of the invention

[0004] To solve the above problems, the present invention provides a method, system and medium for water sports training interaction based on virtual reality, aiming to provide interactive feedback of training effects by analyzing and processing training data, thereby improving training effects.

[0005] In order to achieve the above object, the present invention provides the following technical solutions:

[0006] On the one hand, an embodiment of the present invention provides a water sports training interaction method based on virtual reality, which is applied to a virtual reality device, wherein the virtual reality device includes a display and an inertial motion capture device, and the method includes the following steps:

[0007] In response to a training start instruction triggered by a user, a standard motion model of a training task is played in a loop through a display, and motion data of a target user in the execution of the most recent N training tasks are collected through an inertial motion capture device to obtain N motion data; wherein the N motion data correspond to the N training tasks one by one, the training task includes M key actions, and M and N are both positive integers;

[0008] Determine the action differences of the M key actions based on the motion data and the standard action model, record the key actions whose action differences are greater than the difference threshold as target key actions, and determine the target key parts corresponding to the target key actions;

[0009] Acquire the surface electromyographic signal of the target key part, determine the expected improvement degree of the target key action based on the surface electromyographic signal and the action difference, and use the target key action with the expected improvement degree greater than the improvement degree threshold as the training action;

[0010] In response to the intensive training instruction triggered by the user, interactive training is performed on the training action.

[0011] Optionally, determining the action differences of the M key actions based on the motion data and the standard action model includes:

[0012] Sort the N training tasks in order from near to far from the current time, and obtain a standard action model and M motion data; wherein the standard action model includes standard features and standard time of M key actions, the standard features include a standard starting position and a standard ending position, and the motion data includes key features and action time of M key actions, and the key features include a starting position and an ending position;

[0013] For M key actions, the amplitude difference is determined based on the standard features and key features of the key actions, the time difference is determined based on the standard time and action time of the key actions, and the action difference of the key actions is determined based on the amplitude difference and time difference of the key actions in N training tasks.

[0014] Optionally, the amplitude difference is calculated by the following formula:

[0015] ;

[0016] Among them, A ij is the amplitude difference of the i-th key action in the j-th training task, S ij is the starting position of the i-th key action in the j-th training task, E ij is the ending position of the i-th key action in the j-th training task; S j is the standard starting position of the ith key action; E j is the standard starting position of the i-th key action; i=1,2,...,M, j=1,2,...,N.

[0017] Optionally, the action difference is calculated by the following formula:

[0018] ;

[0019] Among them, Ac i is the action difference of the i-th key action, represents normalization processing, T ijis the action time of the i-th key action in the j-th training task, T i is the standard time of the i-th key action; K1 is the adjustment factor, 0<K1<1.

[0020] Optionally, the acquiring of the surface electromyographic signal of the target key part, determining the muscle fatigue of the target key action based on the surface electromyographic signal, and determining the target key action to be trained based on the muscle fatigue and the action difference, includes:

[0021] Acquire surface electromyographic signals collected from the target key part in the most recent N training tasks, and determine the muscle fatigue degree of the target key part in the N training tasks based on the surface electromyographic signals;

[0022] Obtaining the amplitude difference of the target key action in the most recent N training tasks, and obtaining N improvement degrees based on the amplitude difference of the target key action in the N training tasks; wherein the N improvement degrees correspond to the N training tasks one by one; and the improvement degrees are used to characterize the degree of improvement of the amplitude difference;

[0023] Linearly fitting the muscle fatigue degree of the target key part in N training tasks and the N improvement degrees to obtain a corresponding relationship between the improvement degree and the muscle fatigue degree;

[0024] Acquire a surface electromyographic signal of the target key part, obtain a current muscle fatigue degree of the target key part based on the surface electromyographic signal, and determine an expected improvement degree corresponding to the current muscle fatigue degree based on the corresponding relationship as the current expected improvement degree of the target key part;

[0025] Deriving the N improvement degrees, taking the improvement degree with the smallest derivative as the improvement degree threshold corresponding to the target key part, and determining whether the current expected improvement degree of each target key part is greater than the improvement degree threshold;

[0026] Determine each target key part corresponding to the target key action, and if it is determined that the current expected improvement degree of each target key part is greater than the corresponding improvement degree threshold, then use the target key action as a training action.

[0027] Optionally, the improvement degree of the target key action is calculated by the following formula:

[0028] ;

[0029] Among them, P ijrepresents the improvement of the i-th target key action in the j-th training task, m is the total number of target key actions, k=1,2,...,m; w1, w2 are weight coefficients, 0≤w1≤1, 0≤w2≤1, and w1+w2=1; mean represents the average, mean(A ij ) is the mean value of the amplitude difference of the i-th target key action in N training tasks, A kj A represents the magnitude difference of the kth target key action in the jth training task, i,j+1 Represents the amplitude difference of the i-th target key action in the j+1-th training task.

[0030] Optionally, in response to the enhanced training instruction triggered by the user, performing interactive training on the training action includes:

[0031] Determine the standard action corresponding to the training action, match the instruction video corresponding to the standard action from a pre-established action instruction library, and play the instruction video through a display when the user performs the training action; wherein the action instruction library includes instruction videos corresponding to M standard actions in the standard action model.

[0032] On the other hand, an embodiment of the present invention provides a water sports training interactive system based on virtual reality, comprising:

[0033] at least one processor;

[0034] at least one memory for storing at least one program;

[0035] When the at least one program is executed by the at least one processor, the at least one processor implements the above method.

[0036] On the other hand, an embodiment of the present invention provides a computer-readable storage medium, in which a program executable by a processor is stored. When the program executable by the processor is executed by the processor, it is used to perform the above method.

[0037] The beneficial effects of the present invention are as follows: the present invention discloses a water sports training interaction method, system and medium based on virtual reality. The present invention collects and analyzes the motion data of the target user in the execution of the latest N training tasks respectively, obtains the action differences of M key actions in the training tasks, and screens out the key actions with larger action differences as the key actions that need intensive training; by combining and analyzing the surface electromyographic signals and the action differences of the target key parts, the expected improvement of the target key actions is determined, and the target key actions with larger expected improvement are screened out for intensive training; the present invention processes and analyzes the motion data collected based on the virtual reality interaction, and provides intensive guidance for key actions through real-time data analysis during training interaction, thereby improving the training effect of water sports. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the embodiments of the present invention 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 of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0039] Figure 1 It is a flowchart of a water sports training interactive method based on virtual reality according to an embodiment of the present invention;

[0040] Figure 2 It is a structural schematic diagram of a water sports training interactive system based on virtual reality according to an embodiment of the present invention. DETAILED DESCRIPTION

[0041] The following will be combined with the embodiments and drawings to clearly and completely describe the concept, specific structure and technical effects disclosed in the present invention, so as to fully understand the purpose, scheme and effect disclosed in the present invention. It should be noted that the embodiments and features in the embodiments in this application can be combined with each other without conflict.

[0042] refer to Figure 1 ,like Figure 1 The present invention provides a method for interactive water sports training based on virtual reality, which is applied to a virtual reality device. The virtual reality device includes a display and an inertial motion capture device. The method includes the following steps:

[0043] S100, in response to a training start instruction triggered by a user, a standard motion model of a training task is played in a loop through a display, and motion data of a target user in the execution of the most recent N training tasks are respectively collected through an inertial motion capture device to obtain N motion data; wherein the N motion data correspond to the N training tasks one by one, the training task includes M key actions, and M and N are both positive integers;

[0044] Specifically, when the target user is doing water sports training, he / she wears an inertial motion capture device, which is a wearable device. The core principle of the inertial motion capture device is based on motion reconstruction technology. By combining the measurement data of the sensor and the initial position and posture information of the device, the motion trajectory and posture changes of the human body or object are reconstructed. The present invention uses the XSENS inertial motion capture system to record and analyze the posture and movements of the target user, and outputs motion data. Each key action in the motion data is identified by image recognition technology. In the most recent N training tasks, the training task is decomposed into multiple key actions, and then the key features and action time corresponding to the key actions are identified. Each training task corresponds to a motion data, and a total of N motion data are obtained, reflecting the user's training status in the most recent N training tasks.

[0045] S200, determining the action differences of the M key actions based on the motion data and the standard action model, recording the key actions whose action differences are greater than the difference threshold as target key actions, and determining the target key parts corresponding to the target key actions;

[0046] Specifically, by comparing the motion data with the standard motion model, the action differences of M key actions are obtained, and the key actions with action differences greater than the difference threshold are screened and recorded as target key actions; the key actions that need intensive training are preliminarily screened out.

[0047] S300, acquiring a surface electromyographic signal of the target key part, determining an expected improvement degree of the target key action based on the surface electromyographic signal and the action difference, and taking the target key action with an expected improvement degree greater than an improvement degree threshold as a training action;

[0048] S400, in response to a reinforcement training instruction triggered by a user, performing interactive training on the training action.

[0049] Specifically, in response to the intensive training instructions triggered by the user, targeted interactive training is performed on weak key movements through the display and inertial motion capture equipment to improve the training effect.

[0050] The present invention collects and analyzes the motion data of the target user in the latest N training tasks, obtains the motion differences of M key actions in the training tasks, and screens out the key actions with larger motion differences as the key actions that need intensive training; by combining and analyzing the surface electromyography signals and the motion differences of the target key parts, the expected improvement of the target key actions is determined, and the target key actions with larger expected improvement are screened out for intensive training, so that targeted training can be performed on the key actions, and the user can be helped to improve the training effect through real-time data analysis; the present invention processes and analyzes the motion data collected based on virtual reality interaction, and provides intensive guidance for key actions through real-time data analysis during training interaction, thereby improving the training effect of water sports.

[0051] In some embodiments, in S200, determining the action differences of the M key actions based on the motion data and the standard action model includes:

[0052] Sort the N training tasks in order from near to far from the current time, and obtain a standard action model and M motion data; wherein the standard action model includes standard features and standard time of M key actions, the standard features include a standard starting position and a standard ending position, and the motion data includes key features and action time of M key actions, and the key features include a starting position and an ending position;

[0053] For M key actions, the amplitude difference is determined based on the standard features and key features of the key actions, the time difference is determined based on the standard time and action time of the key actions, and the action difference of the key actions is determined based on the amplitude difference and time difference of the key actions in N training tasks.

[0054] The amplitude difference quantifies the deviation of the movement amplitude in each training task, reflecting the user's grasp of the movement amplitude. The time difference quantifies the time of the movement in each training task, reflecting the user's follow-up of the movement.

[0055] In some embodiments, the amplitude difference is calculated by the following formula:

[0056] ;

[0057] Among them, A ij is the amplitude difference of the i-th key action in the j-th training task, S ij is the starting position of the i-th key action in the j-th training task, E ij is the ending position of the i-th key action in the j-th training task; S j is the standard starting position of the ith key action; Ej is the standard starting position of the i-th key action; i=1,2,...,M, j=1,2,...,N.

[0058] In some embodiments, the action difference is calculated by the following formula:

[0059] ;

[0060] Among them, Ac i is the action difference of the i-th key action, represents normalization processing, T ij is the action time of the i-th key action in the j-th training task, T i is the standard time of the i-th key action; K1 is the adjustment factor, 0<K1<1.

[0061] It should be noted that for the i-th key action, the position deviation is reflected by counting its starting position deviation and ending position deviation in N training tasks, and the position deviation is weighted by the deviation between the action time and the standard time, so as to reflect the action difference of the key action as a whole; the action time in the above formula represents the duration of the key action, reflecting the speed of the key action. The faster the action, the faster the exp(K1*(T ij -T i ) / j) is larger; after calculating the difference between the action time and the standard time in each training task, the difference is adjusted according to the order of the training tasks. The closer the training task is to the current time, the higher the value of exp(K1*(T ij -T i The larger the value of ) / j), the greater the influence of the corresponding position deviation on the action difference, thus more accurately reflecting the user's current training status.

[0062] In some embodiments, in S300, acquiring the surface electromyographic signal of the target key part, determining the muscle fatigue of the target key action based on the surface electromyographic signal, and determining the target key action to be trained based on the muscle fatigue and the action difference, includes:

[0063] S310, obtaining surface electromyographic signals collected from the target key part in the most recent N training tasks, and determining the muscle fatigue degree of the target key part in the N training tasks based on the surface electromyographic signals;

[0064] Specifically, the virtual reality device also includes a surface electromyography test device, which adopts a Cometa wireless surface electromyography test device. The Xsens inertial motion capture device is integrated with the Cometa wireless surface electromyography test device to record electromyography activity while capturing motion; by determining the rate of change of the amplitude of the surface electromyography signal over time in N training tasks, the smaller the rate of change of the amplitude over time, the lowest degree of muscle fatigue; the larger the rate of change, the higher the degree of muscle fatigue.

[0065] S320, obtaining the amplitude difference of the target key action in the most recent N training tasks, and obtaining N improvement degrees based on the amplitude difference of the target key action in the N training tasks; wherein the N improvement degrees correspond to the N training tasks one by one; and the improvement degrees are used to characterize the degree of improvement of the amplitude difference;

[0066] Specifically, the amplitude difference reflects the improvement degree corresponding to the current training task. A positive improvement indicates that the amplitude difference is smaller and the training effect is better; a negative improvement indicates that the amplitude difference is larger and the training effect is worse.

[0067] S330, performing linear fitting on the muscle fatigue degree of the target key part in the N training tasks and the N improvement degrees to obtain a corresponding relationship between the improvement degree and the muscle fatigue degree;

[0068] Specifically, each target key part corresponding to the target key action is determined, and the muscle fatigue degree of each target key part and the improvement degree of the target key action are linearly fitted respectively to obtain the corresponding relationship between the improvement degree and the muscle fatigue degree of each target key part; linear regression is used to perform linear fitting on the improvement degree and muscle fatigue degree, which can roughly reflect the corresponding relationship between the improvement degree and muscle fatigue degree, so as to facilitate the subsequent determination of whether there is still room for improvement in the intensive training of the target key action, thereby improving the targeted nature of the training.

[0069] S340, acquiring a surface electromyographic signal of the target key part, obtaining a current muscle fatigue degree of the target key part based on the surface electromyographic signal, and determining an expected improvement degree corresponding to the current muscle fatigue degree based on the corresponding relationship as the current expected improvement degree of the target key part;

[0070] S350, deriving the N improvement degrees, taking the improvement degree with the smallest derivative as the improvement degree threshold corresponding to the target key part, and determining whether the current expected improvement degree of each target key part is greater than the improvement degree threshold;

[0071] S360, determining each target key part corresponding to the target key action, and if it is determined that the current expected improvement degree of each target key part is greater than the corresponding improvement degree threshold, the target key action is used as a training action.

[0072] Specifically, for each target key part corresponding to the target key action, if the expected improvement degree is greater than the corresponding improvement degree threshold, it means that the muscle fatigue degree is relatively small, and training can be strengthened, which is expected to improve the training effect to a certain extent; if it is lower than the improvement degree threshold, stop training the target key action corresponding to the target key part.

[0073] As an improvement of the above embodiment, the improvement degree of the target key action is calculated by the following formula:

[0074] ;

[0075] Among them, P ij represents the improvement of the i-th target key action in the j-th training task, m is the total number of target key actions, k=1,2,...,m; w1, w2 are weight coefficients, 0≤w1≤1, 0≤w2≤1, and w1+w2=1; mean represents the average, mean(A ij ) is the mean value of the amplitude difference of the i-th target key action in N training tasks, A kj A represents the magnitude difference of the kth target key action in the jth training task, i,j+1 Represents the amplitude difference of the i-th target key action in the j+1-th training task.

[0076] It should be noted that A kj is a variable, A ij is a constant, the amplitude difference mean(A ij ) is calculated by the following formula:

[0077] ;

[0078] In this embodiment, the amplitude difference between the target key action in the current training task and other target key actions is compared, and the improvement mean of the target key action in N training tasks is combined to reflect the quality of the target key action among all target key actions; the amplitude difference between the target key action in the current training task and the next training task is analyzed for the rate of change to reflect the change trend of the target key action in adjacent training tasks; the improvement of the target key action is comprehensively reflected from the sample space and sample time to obtain a more comprehensive and accurate evaluation.

[0079] In some embodiments, in S400, in response to the enhanced training instruction triggered by the user, interactive training is performed on the training action, including:

[0080] Determine the standard action corresponding to the training action, match the instruction video corresponding to the standard action from a pre-established action instruction library, and play the instruction video through a display when the user performs the training action; wherein the action instruction library includes instruction videos corresponding to M standard actions in the standard action model.

[0081] Specifically, when the display plays the standard action corresponding to the training action, the instruction video is played, thereby providing enhanced instruction on the user's training action and improving the training effect.

[0082] refer to Figure 2 The embodiment of the present invention further provides a water sports training interactive system based on virtual reality, comprising:

[0083] at least one processor;

[0084] at least one memory for storing at least one program;

[0085] When the at least one program is executed by the at least one processor, the at least one processor implements the above method.

[0086] The contents of the above method embodiments are all applicable to this embodiment. The functions specifically implemented by this embodiment are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments, which will not be repeated here.

[0087] Although the description of the present disclosure has been quite detailed and specifically describes several described embodiments, it is not intended to be limited to any of these details or embodiments or any particular embodiment, but should be regarded as providing a broad possible interpretation of these claims by reference to the appended claims, taking into account the prior art, so as to effectively cover the intended scope of the present disclosure. In addition, the above description of the present disclosure is based on the embodiments foreseeable by the inventor, and its purpose is to provide a useful description, and those non-substantial changes to the present disclosure that have not yet been foreseen may still represent equivalent changes to the present disclosure.

Claims

1. A water sports training interactive method based on virtual reality, characterized in that: The method is applied to a virtual reality device, the virtual reality device comprising a display and an inertial motion capture device, and the method comprises the following steps: In response to a training start instruction triggered by a user, a standard motion model of a training task is played in a loop through a display, and motion data of a target user in the execution of the most recent N training tasks are collected through an inertial motion capture device to obtain N motion data; wherein the N motion data correspond to the N training tasks one by one, the training task includes M key actions, and M and N are both positive integers; Determine the action differences of the M key actions based on the motion data and the standard action model, record the key actions whose action differences are greater than the difference threshold as target key actions, and determine the target key parts corresponding to the target key actions; Acquire a surface electromyographic signal of the target key part, determine an expected improvement degree of the target key action based on the surface electromyographic signal and the action difference, and use the target key action with an expected improvement degree greater than an improvement degree threshold as a training action; In response to the intensive training instruction triggered by the user, interactive training is performed on the training action; The step of acquiring the surface electromyographic signal of the target key part, determining the expected improvement degree of the target key action based on the surface electromyographic signal and the action difference, and taking the target key action with the expected improvement degree greater than the improvement degree threshold as the training action includes: Acquire surface electromyographic signals collected from the target key part in the most recent N training tasks, and determine the muscle fatigue degree of the target key part in the N training tasks based on the surface electromyographic signals; Obtaining the amplitude difference of the target key action in the most recent N training tasks, and obtaining N improvement degrees based on the amplitude difference of the target key action in the N training tasks; wherein the N improvement degrees correspond to the N training tasks one by one; and the improvement degrees are used to characterize the degree of improvement of the amplitude difference; Linearly fitting the muscle fatigue degree of the target key part in N training tasks and the N improvement degrees to obtain a corresponding relationship between the improvement degree and the muscle fatigue degree; Acquire a surface electromyographic signal of the target key part, obtain a current muscle fatigue degree of the target key part based on the surface electromyographic signal, and determine an expected improvement degree corresponding to the current muscle fatigue degree based on the corresponding relationship as the current expected improvement degree of the target key part; Deriving the N improvement degrees, taking the improvement degree with the smallest derivative as the improvement degree threshold corresponding to the target key part, and determining whether the current expected improvement degree of each target key part is greater than the improvement degree threshold; Determine each target key part corresponding to the target key action, and if it is determined that the current expected improvement degree of each target key part is greater than the corresponding improvement degree threshold, then use the target key action as a training action.

2. The water sports training interactive method based on virtual reality according to claim 1, characterized in that: The determining the action differences of the M key actions based on the motion data and the standard action model includes: Sort the N training tasks in order from near to far from the current time, and obtain a standard action model and M motion data; wherein the standard action model includes standard features and standard time of M key actions, the standard features include a standard starting position and a standard ending position, and the motion data includes key features and action time of M key actions, and the key features include a starting position and an ending position; For M key actions, the amplitude difference is determined based on the standard features and key features of the key actions, the time difference is determined based on the standard time and action time of the key actions, and the action difference of the key actions is determined based on the amplitude difference and time difference of the key actions in N training tasks.

3. The water sports training interactive method based on virtual reality according to claim 2, characterized in that: The amplitude difference is calculated by the following formula: ； Among them, A ij is the amplitude difference of the i-th key action in the j-th training task, S ij is the starting position of the i-th key action in the j-th training task, E ij is the ending position of the i-th key action in the j-th training task; S j is the standard starting position of the ith key action; E j is the standard starting position of the i-th key action; i=1,2,...,M, j=1,2,...,N.

4. The water sports training interactive method based on virtual reality according to claim 3 is characterized in that: The action difference is calculated by the following formula: ； Among them, Ac i is the action difference of the i-th key action, represents normalization processing, T ij is the action time of the i-th key action in the j-th training task, T i is the standard time of the i-th key action; K1 is the adjustment factor, 0<K1<1.

5. The water sports training interactive method based on virtual reality according to claim 1, characterized in that: The improvement of the target key action is calculated by the following formula: ； Among them, P ij represents the improvement of the i-th target key action in the j-th training task, m is the total number of target key actions, k=1,2,...,m; w1, w2 are weight coefficients, 0≤w1≤1, 0≤w2≤1, and w1+w2=1; mean represents the average, mean(A ij ) is the mean value of the amplitude difference of the i-th target key action in N training tasks, A kj A represents the magnitude difference of the kth target key action in the jth training task, i,j+1 Represents the amplitude difference of the i-th target key action in the j+1-th training task.

6. The water sports training interactive method based on virtual reality according to claim 1, characterized in that: The interactive training of the training action in response to the intensive training instruction triggered by the user includes: Determine the standard action corresponding to the training action, match the instruction video corresponding to the standard action from a pre-established action instruction library, and play the instruction video through a display when the user performs the training action; wherein the action instruction library includes instruction videos corresponding to M standard actions in the standard action model.

7. A water sports training interactive system based on virtual reality, characterized in that: include: at least one processor; at least one memory for storing at least one program; When the at least one program is executed by the at least one processor, the at least one processor implements the method according to any one of claims 1 to 6.

8. A computer-readable storage medium storing a program executable by a processor, characterized in that: The processor-executable program is used to perform the method according to any one of claims 1 to 6 when executed by the processor.

Images