Striking action multi-dimensional analysis method, device and system and storage medium

Abstract

The embodiment of the invention provides a striking action multi-dimensional analysis method, device and system and a storage medium, and the method comprises the steps: synchronously collecting training data of a trainee in time, the training data comprising leg strength data, striking strength data and posture data; the training data are input into a preset multi-channel feature fusion model, fusion features of the trainee are output, and the fusion features correspond to leg strength features, hitting strength features and posture features of the trainee; and inputting the fusion features into a preset feature analysis network, and outputting action improvement suggestions for the training personnel. According to the technical scheme provided by the invention, the problems that data synchronization and integration become difficult and real-time interaction analysis cannot be realized due to independent operation in the prior art are solved.

Description

Technical Field

[0001] This document relates to the field of sports science and motion analysis, and in particular to a multi-dimensional analysis method, device, system and storage medium for striking actions. Background Art

[0002] Three-dimensional mechanical measurement technology, such as the three-dimensional force platform, can accurately measure the force and torque data of athletes in the three axes of X, Y, and Z based on the principle of resistive strain. These data play a vital role in the analysis of athletes' starting and jumping movements. In addition, optical motion capture technology uses reflective markers attached to different parts of the athlete's body to capture the movement trajectory of these markers and digitally record the athlete's body movements.

[0003] Although three-dimensional mechanical measurement and optical motion capture technologies each have high accuracy and stability, there are still significant deficiencies in combined applications. First, these technologies usually operate independently, which makes data synchronization and integration difficult and makes real-time interactive analysis impossible. Second, when dealing with complex movements such as martial arts, existing systems have difficulty capturing fine body movements and corresponding mechanical data at the same time, resulting in limited accuracy of the assessment. In addition, the sensitivity and accuracy of some commonly used mechanical sensor devices, such as sandbags, have not yet reached the optimal state, making it difficult to provide sufficiently detailed feedback data, thus affecting the accuracy of the analysis results. Summary of the invention

[0004] In view of the above analysis, the present application aims to propose a multi-dimensional analysis method, device, system and storage medium for striking actions to assist identification experts in making accurate judgments.

[0005] In a first aspect, one or more embodiments of this specification provide a method for multi-dimensional analysis of striking actions, including:

[0006] Acquiring training data of a trainee synchronously in time, wherein the training data includes leg strength data, striking force data and posture data;

[0007] Inputting the training data into a preset multi-channel feature fusion model, and outputting fusion features of the trainee, wherein the fusion features correspond to the leg strength features, striking force features, and posture features of the trainee; and

[0008] The fused features are input into a preset feature analysis network, and suggestions for improving the movements of the trainee are output.

[0009] Furthermore, the training data of the trainees is collected synchronously in time, including:

[0010] Generate standard time; and

[0011] The standard time is sent to a sensor used to collect the leg strength data, the striking force data and the posture data, so that the sensor can calibrate the local time according to the standard time and return the collected data and the collection time of the data.

[0012] Furthermore, outputting the fusion features of the trainer includes:

[0013] Based on multiple channels, respectively extracting the leg strength feature, the striking force feature and the posture feature according to the leg strength data, the striking force data and the posture data; and

[0014] Based on the time series, feature fusion is performed on the leg strength feature, the striking force feature and the posture feature.

[0015] Further, the multi-channel feature fusion model includes: a first channel, a second channel and a third channel; and

[0016] Extracting the leg strength feature, the striking force feature and the posture feature respectively includes:

[0017] In the first channel, encoding the leg strength data and extracting the leg strength features;

[0018] In the second channel, encoding the striking force data and extracting the striking force features; and

[0019] In the third channel, the posture data is encoded and the posture features are extracted.

[0020] In a second aspect, one or more embodiments of this specification provide a multi-dimensional analysis device for striking actions, including: a collection module, a feature fusion module, and a feature analysis module;

[0021] The acquisition module is used to synchronously acquire the training data of the trainee in time, wherein the training data includes leg strength data, striking force data and posture data;

[0022] The feature fusion module is used to input the training data into a preset multi-channel feature fusion model, and output the fusion features of the trainee, wherein the fusion features correspond to the leg strength features, the striking force features, and the posture features of the trainee; and

[0023] The feature analysis module is used to take the fusion feature as input and output action improvement suggestions for the trainee.

[0024] Furthermore, the acquisition module is used to generate standard time; and send the standard time to the sensor, which is used to collect the leg strength data, the impact force data and the posture data, so that the sensor can calibrate the local time according to the standard time and return the collected data and the collection time of the data.

[0025] Furthermore, the feature fusion module is used to extract the leg strength feature, the strike force feature and the posture feature respectively based on the leg strength data, the strike force data and the posture data based on multiple channels; and to perform feature fusion on the leg strength feature, the strike force feature and the posture feature based on time series.

[0026] Further, the multi-channel feature fusion model includes: a first channel, a second channel and a third channel; and

[0027] The feature fusion module is used to encode the leg strength data and extract the leg strength features in the first channel; to encode the striking force data and extract the striking force features in the second channel; and to encode the posture data and extract the posture features in the third channel.

[0028] The feature analysis module is used to determine the correlation coefficient between the optical spectrum and each spectrum stored in the first database based on the Pearson correlation coefficient model; and determine that the spectrum whose correlation coefficient exceeds a preset threshold is a standard spectrum related to the optical spectrum of the evidence.

[0029] In a third aspect, one or more embodiments of this specification provide a multi-dimensional analysis system for striking actions, including:

[0030] Three-dimensional force platform, optical motion capture camera, force measurement sensor, data fusion processor and high-precision time synchronization device;

[0031] The three-dimensional force platform is placed under the ground of the training ground; the optical motion capture cameras are distributed at four corners around the three-dimensional force platform; the force measurement sensor is set in a sandbag; the high-precision time synchronization device is integrated in the data fusion processor; the data fusion processor is respectively connected to the three-dimensional force platform, the optical motion capture camera and the force measurement sensor signal through data cables.

[0032] In a fourth aspect, one or more embodiments of the present specification provide a storage medium for storing computer-executable instructions, characterized in that when the computer-executable instructions are executed, the steps of the training method applied to the time-domain convolutional network model described in any one of the first aspects are implemented.

[0033] Compared with the prior art, this application can at least achieve the following technical effects:

[0034] The training data of the trainees are collected synchronously in time to lay the foundation for subsequent feature fusion. The training data is input into the preset multi-channel feature fusion model, and the fusion features of the trainees are output. The fusion features correspond to the leg strength features, striking force features and posture features of the trainees. The fusion features are input into the preset feature analysis network, and suggestions for improving the trainees' movements are output. The technical problem of inaccurate analysis results caused by isolated analysis of leg strength, striking force and posture is solved. In this solution, the multi-channel feature fusion model is used to fuse the leg strength features, striking force features and posture features, making the analysis results more accurate. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] In order to more clearly illustrate one or more embodiments of this specification or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this specification. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0036] Figure 1 A flowchart of a multi-dimensional analysis method of striking action provided by one or more embodiments of this specification;

[0037] Figure 2 A schematic diagram of the structure of a multi-dimensional analysis device for striking actions provided in one or more embodiments of this specification. DETAILED DESCRIPTION

[0038] In order to enable those skilled in the art to better understand the technical solutions in one or more embodiments of this specification, the following will be combined with the drawings in one or more embodiments of this specification to clearly and completely describe the technical solutions in one or more embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this specification, not all of the embodiments. Based on one or more embodiments of this specification, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of this document.

[0039] The present application embodiment provides a method for multi-dimensional analysis of striking actions, such as Figure 1 As shown, the following steps are included:

[0040] Step 1: synchronously collect the training data of the trainee in time, wherein the training data includes leg strength data, striking force data and posture data.

[0041] In the embodiment of the present application, the striking action refers to the various actions of the athlete using various parts of the body, such as the head, hand, arm, shoulder, elbow, foot, leg, knee, etc., to strike the sandbag. The leg strength data refers to the force generated by the leg on the ground during the strike, which mainly plays a supporting and auxiliary role, and the striking force data refers to the force borne by the sandbag. The posture data is the various postures of the athlete during the completion of the striking action. Obviously, in the striking process, the above three elements need to be coordinated with each other, so it is necessary to ensure time synchronization during collection, so as to better analyze whether the current striking action has defects.

[0042] Step 2: Input the training data into the preset multi-channel feature fusion model and output the fusion features of the trainees.

[0043] In an embodiment of the present application, posture data is obtained by an optical motion capture device, leg strength data is obtained by a three-dimensional force measuring platform, and striking force data is obtained by a flexible sensor arranged in a sandbag. It can be seen that the posture data is image data, the leg strength data is three-dimensional data and changes over time, and the striking force data is one-dimensional data and changes over time. Since the three data dimensions are realized in different forms, a multi-channel mode is used for feature extraction to prevent feature loss. Afterwards, feature fusion is performed to obtain fused features. Among them, the fused features correspond to the leg strength features, striking force features and posture features of the trainee.

[0044] Step 3: Input the fused features into the preset feature analysis network and output suggestions for improving the trainees’ actions.

[0045] In the embodiment of the present application, the fusion feature is compared with the standard data to obtain action improvement suggestions. The standard data can be real data, such as the data of excellent athletes or coaches when performing a certain action using the method of the present application. The standard data can also be data set to reach the training standard, such as in order to enhance strength training, pre-set at a standard value of a certain action striking force, and then allow athletes to continuously train so that their striking force reaches the standard value.

[0046] In the embodiment of the present application, in order to achieve time synchronization of the three parts of data, the server or host can generate a standard time when the device is started. Then, the standard time is sent to the sensor, which is used to collect the leg force data, the blow force data and the posture data, so that the sensor can calibrate the local time according to the standard time and return the collected data and the collection time of the data.

[0047] It should be noted that the sensors in the embodiment of the present application include: sensors in the optical motion capture device for sensing reflection, sensors in the sandbag for sensing striking force, and sensors in the three-dimensional force platform set under the ground of the venue. The server or host will send the standard time to the above three servers at the same time.

[0048] In an embodiment of the present application, in order to better extract features, based on multi-channel, the leg strength feature, the blow force feature and the posture feature are respectively extracted according to the leg strength data, the blow force data and the posture data. In order to improve the accuracy of the evaluation result, based on the time series, the leg strength feature, the blow force feature and the posture feature are subjected to feature fusion. In a real scene, the multi-channel feature fusion model can select a time domain convolutional network or other neural network or model based on time domain processing data.

[0049] In the embodiment of the present application, the multi-channel feature fusion model includes: a first channel, a second channel and a third channel; the specific process of extracting features is:

[0050] In the first channel, the leg strength data is encoded and the leg strength features are extracted; in the second channel, the striking force data is encoded and the striking force features are extracted; in the third channel, the posture data is encoded and the posture features are extracted.

[0051] The present application embodiment provides a device for multi-dimensional analysis of striking actions, such as Figure 2 As shown, it includes: a collection module 201, a feature fusion module 202 and a feature analysis module 203;

[0052] The acquisition module 201 is used to acquire the training data of the trainee synchronously in time, and the training data includes leg strength data, striking force data and posture data.

[0053] The feature fusion module 202 is used to input the training data into a preset multi-channel feature fusion model and output the fusion features of the trainee, where the fusion features correspond to the trainee's leg strength features, striking force features and posture features.

[0054] The feature analysis module 203 is used to take the fused features as input and output action improvement suggestions for the trainer.

[0055] In an embodiment of the present application, the acquisition module 201 is used to generate standard time; and send the standard time to the sensor, which is used to collect leg strength data, impact force data and posture data, so that the sensor can calibrate the local time according to the standard time and return the collected data and the collection time of the data.

[0056] In an embodiment of the present application, the feature fusion module 202 is used to extract leg strength features, strike force features and posture features respectively based on leg strength data, strike force data and posture data based on multiple channels; and to perform feature fusion of leg strength features, strike force features and posture features based on time series.

[0057] In the embodiment of the present application, the multi-channel feature fusion model includes: a first channel, a second channel and a third channel;

[0058] The feature fusion module 202 is used to encode leg strength data and extract leg strength features in the first channel; encode striking force data and extract striking force features in the second channel; and encode posture data and extract posture features in the third channel.

[0059] The feature analysis module 203 is used to determine the correlation coefficient between the optical spectrum and each spectrum stored in the first database based on the Pearson correlation coefficient model; and determine that the spectrum with a correlation coefficient exceeding a preset threshold is a standard spectrum related to the optical spectrum of the evidence.

[0060] The embodiment of the present application provides a multi-dimensional analysis system for striking actions, including:

[0061] Three-dimensional force platform, optical motion capture camera, force measurement sensor, data fusion processor and high-precision time synchronization device;

[0062] The three-dimensional force platform is placed under the ground of the training ground; the optical motion capture cameras are distributed at the four corners around the three-dimensional force platform; and the force measurement sensor is set in the sandbag. The high-precision time synchronization device is integrated in the data fusion processor. The data fusion processor is connected to the three-dimensional force platform, the optical motion capture camera and the force measurement sensor signal through data cables.

[0063] Specifically, the trainees train on a three-dimensional force platform, and optical motion capture cameras are arranged around the three-dimensional force platform, for example, one optical capture camera is arranged in the upper and lower front directions, so as to capture the trainees' motions. The trainees hold a force measurement sensor to perform sandbag striking training, and the force measurement sensor is used to collect the strike force data of the trainees. The high-precision time synchronization device sends the standard time to the above-mentioned sensor, and then the above-mentioned sensor transmits the collected data to the data fusion processor via wired or wireless means.

[0064] An embodiment of the present application provides a storage medium for storing computer executable instructions, wherein the computer executable instructions, when executed, perform the steps of the multi-dimensional analysis method of striking actions described in any of the above embodiments.

[0065] The above is a description of a specific embodiment of the specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0066] In the 1930s, improvements to a technology could be clearly distinguished as hardware improvements (for example, improvements to the circuit structure of diodes, transistors, switches, etc.) or software improvements (improvements to the method flow). However, with the development of technology, many improvements to the method flow today can be regarded as direct improvements to the hardware circuit structure. Designers almost always obtain the corresponding hardware circuit structure by programming the improved method flow into the hardware circuit. Therefore, it cannot be said that an improvement in a method flow cannot be implemented using a hardware entity module. For example, a programmable logic device (PLD) (such as a field programmable gate array (FPGA)) is such an integrated circuit whose logical function is determined by the user's programming of the device. Designers can "integrate" a digital system on a PLD by programming it themselves, without having to ask a chip manufacturer to design and produce a dedicated integrated circuit chip. Moreover, nowadays, instead of manually making integrated circuit chips, this kind of programming is mostly implemented by "logic compiler" software, which is similar to the software compiler used when developing and writing programs, and the original code before compilation must also be written in a specific programming language, which is called hardware description language (HDL). There is not only one HDL, but many kinds, such as ABEL (Advanced Boolean Expression Language), AHDL (Altera Hardware Description Language), Confluence, CUPL (Cornell University Programming Language), HDCal, JHDL (Java Hardware Description Language), Lava, Lola, MyHDL, PALASM, RHDL (Ruby Hardware Description Language), etc. The most commonly used ones are VHDL (Very-High-Speed ​​Integrated Circuit Hardware Description Language) and Verilog. Those skilled in the art should also know that it is only necessary to program the method flow slightly in the above-mentioned hardware description languages ​​and program it into the integrated circuit, and then it is easy to obtain the hardware circuit that implements the logic method flow.

[0067] The controller can be implemented in any appropriate manner, for example, the controller can take the form of a microprocessor or processor and a computer-readable medium storing a computer-readable program code (such as software or firmware) that can be executed by the (micro)processor, a logic gate, a switch, an application-specific integrated circuit (ASIC), a programmable logic controller, and an embedded microcontroller. Examples of controllers include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicone Labs C8051F320. The memory controller can also be implemented as part of the control logic of the memory. Those skilled in the art also know that in addition to implementing the controller in a purely computer-readable program code manner, the controller can be implemented in the form of a logic gate, a switch, an application-specific integrated circuit, a programmable logic controller, and an embedded microcontroller by logically programming the method steps. Therefore, this controller can be considered as a hardware component, and the devices included therein for implementing various functions can also be regarded as structures within the hardware component. Or even, the devices for implementing various functions can be regarded as both software modules for implementing the method and structures within the hardware component.

[0068] The systems, devices, modules or units described in the above embodiments may be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, the computer may be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0069] For the convenience of description, the above devices are described in terms of functions and are divided into various units. Of course, when implementing the embodiments of this specification, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0070] It should be understood by those skilled in the art that one or more embodiments of this specification may be provided as a method, system or computer program product. Therefore, one or more embodiments of this specification may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, this specification may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0071] This specification is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of this specification. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0072] These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to act in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture including an instruction device that implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0073] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0074] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0075] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0076] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0077] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0078] One or more embodiments of the present specification may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. One or more embodiments of the present specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules may be located in local and remote computer storage media, including storage devices.

[0079] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0080] The above description is only an embodiment of this document and is not intended to limit this document. For those skilled in the art, this document may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of this document should be included in the scope of the claims of this document.

Claims

1. A multi-dimensional analysis method of striking action, characterized in that: include: Acquiring training data of a trainee synchronously in time, wherein the training data includes leg strength data, striking force data and posture data; Inputting the training data into a preset multi-channel feature fusion model, and outputting fusion features of the trainee, wherein the fusion features correspond to the leg strength features, striking force features, and posture features of the trainee; and The fused features are input into a preset feature analysis network, and suggestions for improving the movements of the trainee are output.

2. The method according to claim 1, characterized in that The training data of the trainees is collected synchronously in time, including: Generate standard time; and The standard time is sent to a sensor used to collect the leg strength data, the striking force data and the posture data, so that the sensor can calibrate the local time according to the standard time and return the collected data and the collection time of the data.

3. The method according to claim 1, characterized in that Output the fusion features of the trainer, including: Based on multiple channels, respectively extracting the leg strength feature, the striking force feature and the posture feature according to the leg strength data, the striking force data and the posture data; and Based on the time series, feature fusion is performed on the leg strength feature, the striking force feature and the posture feature.

4. The method according to claim 3, characterized in that The multi-channel feature fusion model includes: a first channel, a second channel and a third channel; and Extracting the leg strength feature, the striking force feature and the posture feature respectively includes: In the first channel, encoding the leg strength data and extracting the leg strength features; In the second channel, encoding the striking force data and extracting the striking force features; and In the third channel, the posture data is encoded and the posture features are extracted.

5. A multi-dimensional analysis device for striking actions, characterized in that: include: Acquisition module, feature fusion module and feature analysis module; The acquisition module is used to synchronously acquire the training data of the trainee in time, wherein the training data includes leg strength data, striking force data and posture data; The feature fusion module is used to input the training data into a preset multi-channel feature fusion model, and output the fusion features of the trainee, wherein the fusion features correspond to the leg strength features, the striking force features, and the posture features of the trainee; and The feature analysis module is used to take the fusion feature as input and output action improvement suggestions for the trainee.

6. The device according to claim 5, characterized in that The acquisition module is used to generate standard time; and send the standard time to the sensor, which is used to collect the leg strength data, the impact force data and the posture data, so that the sensor can calibrate the local time according to the standard time and return the collected data and the collection time of the data.

7. The device according to claim 5, characterized in that The feature fusion module is used to extract the leg strength feature, the strike force feature and the posture feature respectively based on the leg strength data, the strike force data and the posture data based on multiple channels; And based on the time sequence, feature fusion is performed on the leg strength feature, the striking force feature and the posture feature.

8. The device according to claim 7, characterized in that The multi-channel feature fusion model includes: a first channel, a second channel and a third channel; and The feature fusion module is used to encode the leg strength data and extract the leg strength features in the first channel; encode the striking force data and extract the striking force features in the second channel; and encode the posture data and extract the posture features in the third channel; The feature analysis module is used to determine the correlation coefficient between the optical spectrum and each spectrum stored in the first database based on the Pearson correlation coefficient model; and determine that the spectrum whose correlation coefficient exceeds a preset threshold is a standard spectrum related to the optical spectrum of the evidence.

9. A multi-dimensional analysis system for striking actions, characterized in that: include: Three-dimensional force platform, optical motion capture camera, force measurement sensor, data fusion processor and high-precision time synchronization device; The three-dimensional force platform is placed under the ground of the training ground; the optical motion capture cameras are distributed at four corners around the three-dimensional force platform; the force measurement sensor is set in a sandbag; the high-precision time synchronization device is integrated in the data fusion processor; the data fusion processor is respectively connected to the three-dimensional force platform, the optical motion capture camera and the force measurement sensor signal through data cables.

10. A storage medium for storing computer executable instructions, characterized in that: When the computer executable instructions are executed, the steps of the multi-dimensional analysis method of striking actions described in any one of claims 1 to 4 are implemented.

Images