CN114037928A

CN114037928A - Ball motion analysis method, device and system based on edge calculation

Info

Publication number: CN114037928A
Application number: CN202111195242.7A
Authority: CN
Inventors: 陈浩
Original assignee: Shenzhen Jiuzhou Electric Appliance Co Ltd
Current assignee: Shenzhen Jiuzhou Electric Appliance Co Ltd
Priority date: 2021-10-13
Filing date: 2021-10-13
Publication date: 2022-02-11

Abstract

The invention discloses a ball game analysis method, device and system based on edge calculation, and relates to the technical field of sports auxiliary equipment. The method comprises the following steps: acquiring position data of a target player and video frame data of a sports field; obtaining real-time batting data according to the position data; inputting the real-time batting data into a prediction model to obtain a predicted batting point; acquiring an actual ball falling point of a target ball by utilizing an image recognition technology according to video frame data; judging and analyzing according to the predicted ball drop point and the actual ball drop point to obtain a judgment result; the system comprises a position acquisition device, a positioning base station device, a video acquisition device and an edge calculation device for realizing the method. The invention solves the problems of single function and low digitalization and intelligentization degree of the sports auxiliary equipment in the prior art, and realizes the purpose of intelligent judgment of ball games in a sports field based on edge calculation.

Description

Ball motion analysis method, device and system based on edge calculation

Technical Field

The invention relates to the technical field of sports auxiliary equipment, in particular to a ball game analysis method, a ball game analysis device and a ball game analysis system based on edge calculation.

Background

The sports items are various, and basketball, football, badminton, table tennis and other ball games are popular among people. At present, in these ball games, the traditional scoring and referee mode is directly through manual card turning record and manual judgement, and there are also some scoring and referee modes at present through manual entry system, then push to the display screen to display, and judge by manually looking up the video, but in these modes, the human factor still dominates. Some sports auxiliary devices such as electronic scoreboards and intelligent referee devices are gradually appeared later, but the devices still have the problems of single function and low digitization and intelligence degrees.

Disclosure of Invention

The main purposes of the invention are as follows: the utility model provides a ball game analysis method, a ball game analysis device and a ball game analysis system based on edge calculation, which aim to solve the technical problems of single function and low digitization and intelligence degree of the sports auxiliary equipment in the prior art.

In order to achieve the purpose, the invention adopts the following technical scheme:

in a first aspect, the present invention provides a method for analyzing ball games based on edge calculation, the method comprising:

acquiring position data of a target player and video frame data of a sports field; wherein the video frame data comprises a target sphere;

obtaining real-time batting data according to the position data; wherein the hitting real-time data comprises hitting position data, hitting angle data and hitting acceleration data of the target player;

inputting the real-time batting data into a prediction model to obtain a predicted batting point of the target ball;

acquiring an actual ball falling point of the target ball by utilizing an image recognition technology according to the video frame data;

and performing judgment analysis according to the predicted ball falling point and the actual ball falling point to obtain a judgment result.

Optionally, in the above ball game analysis method based on edge calculation, after the step of obtaining the position data of the target player and the video frame data of the sports ground, the method further includes:

acquiring a moving object and identity information thereof by utilizing a human shape recognition technology according to the video frame data;

if the identity information of the moving object is a non-target player, predicting a moving track to obtain a first predicted track of the moving object;

judging whether the first predicted track conflicts with the sports field or not;

and if the first predicted track conflicts with the sports field, marking the moving object and carrying out first alarm prompt.

Optionally, in the above ball game analysis method based on edge calculation, after the step of predicting the movement trajectory to obtain the first predicted trajectory of the moving object if the identity information of the moving object is a non-target player, the method further includes:

if the identity information of the moving object is a target player, predicting a moving track according to the position data of the target player to obtain a second predicted track of the target player;

judging whether the first predicted track and the second predicted track conflict or not;

and if the first predicted track conflicts with the second predicted track, marking the moving object and carrying out second alarm prompt.

Optionally, in the above method for analyzing ball sports based on edge calculation, the position data includes UWB positioning data and nine-axis gyroscope data;

the step of obtaining real-time data of the ball hitting according to the position data comprises the following steps:

obtaining batting acceleration data of the target player according to the nine-axis gyroscope data;

identifying the batting action according to the batting acceleration data to obtain batting time points of the target player;

obtaining the batting position data of the target player according to the UWB positioning data and the nine-axis gyroscope data corresponding to the batting time point;

and obtaining the relative angle, the batting strength and the absolute angle of the batting action according to the angle, the specific force and the magnetic force of the batting position data in the three-dimensional direction so as to obtain the batting angle data of the target player.

Optionally, in the above method for analyzing ball motions based on edge calculation, the step of obtaining the actual ball drop point of the target ball by using an image recognition technology according to the video frame data includes:

and identifying a target sphere and a sports field by utilizing an image identification technology according to the video frame data to obtain an actual ball falling point of the target sphere and a side line of the sports field.

Optionally, in the above method for analyzing ball game based on edge calculation, the step of performing referee analysis according to the predicted ball drop point and the actual ball drop point to obtain a referee result includes:

judging whether the predicted ball falling point exceeds the sideline or not and whether the actual ball falling point exceeds the sideline or not;

if the predicted ball drop point exceeds the sideline, or the actual ball drop point exceeds the sideline, obtaining a judgment result of the failure of serving or batting of the target ball;

and if the predicted ball drop point does not exceed the sideline and the actual ball drop point does not exceed the sideline, obtaining a judgment result of the ball catching failure of the target ball.

Optionally, in the above method for analyzing ball game based on edge calculation, after the step of performing referee analysis according to the predicted ball drop point and the actual ball drop point to obtain a referee result, the method further includes:

obtaining the score of the target player according to the judgment result and a preset scoring rule;

and drawing the motion trail of the target player, and storing the motion trail, the batting real-time data and the judgment result.

In a second aspect, the present invention provides an edge-computing-based ball game analysis apparatus, the apparatus comprising:

the data acquisition module is used for acquiring position data of a target player and video frame data of a sports field; wherein the video frame data comprises a target sphere;

the batting identification module is used for obtaining batting real-time data according to the position data; wherein the hitting real-time data comprises hitting position data, hitting angle data and hitting acceleration data of the target player;

the trajectory prediction module is used for inputting the batting real-time data into a prediction model to obtain a predicted batting point of the target ball;

the image identification module is used for acquiring the actual ball falling point of the target ball by utilizing an image identification technology according to the video frame data;

and the judge analysis module is used for carrying out judge analysis according to the predicted ball falling point and the actual ball falling point to obtain a judge result.

In a third aspect, the present invention provides a system for analyzing ball games based on edge calculation, the system comprising:

the position acquisition device is used for sending out a positioning signal in real time;

the positioning base station device is used for monitoring the positioning signals and generating position data of the target player;

the video acquisition device is used for acquiring video frame data of a sports field in real time; and

and the edge calculation device is used for realizing the ball game analysis method based on the edge calculation.

One or more technical solutions provided by the present invention may have the following advantages or at least achieve the following technical effects:

according to the method, the device and the system for analyzing the ball games based on the edge calculation, the real-time batting data are obtained according to the position data of the target player, then the real-time batting data are input into the prediction model, the predicted drop point of the target ball is obtained, meanwhile, the actual drop point of the target ball is obtained by utilizing the image recognition technology according to the video frame data of the sports field, finally, the judgment analysis is carried out according to the predicted drop point and the actual drop point, the judgment result is obtained, and the purpose of carrying out intelligent judgment on the ball games in the sports field based on the edge calculation is achieved. The invention integrates the positioning identification technology and the video identification technology, realizes the edge judgment analysis in the sports field, improves the digitization and the intelligent degree of the edge computing device in the digital sports technology, reduces the artificial participation amount, correspondingly reduces the artificial error and improves the accuracy of the sports analysis.

Drawings

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.

FIG. 1 is a schematic flow chart of a first embodiment of a method for analyzing ball game based on edge calculation according to the present invention;

FIG. 2 is a functional block diagram of a first embodiment of an edge-based ball game analysis apparatus according to the present invention;

FIG. 3 is a schematic diagram of the connection of a first embodiment of the edge-based ball game analysis system according to the present invention;

fig. 4 is a schematic diagram of a hardware structure of the edge computing device in fig. 3.

The implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.

Detailed Description

In order to make the objects, technical solutions and advantages of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.

It should be noted that, in the present invention, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or system. Without further limitation, an element defined by the phrase "comprising … …" does not exclude the presence of other like elements in a process, method, article, or system that comprises the element. In addition, in the present invention, if there is a description referring to "first", "second", etc., the description of "first", "second", etc. is for descriptive purposes only and is not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature.

In the present invention, suffixes such as "module", "part", or "unit" used to represent elements are used only for facilitating the description of the present invention, and have no specific meaning in themselves. Thus, "module", "component" or "unit" may be used mixedly. The specific meanings of the above terms in the present invention can be understood by those skilled in the art according to specific situations. In addition, the technical solutions of the respective embodiments may be combined with each other, but must be realized by those skilled in the art, and when the technical solutions are contradictory or cannot be realized, such a combination of technical solutions should be considered to be absent and not be within the protection scope of the present invention.

In view of the technical problems of single function and low digitalization degree and intelligentization degree of the sports auxiliary equipment in the prior art, the invention provides a ball game analysis method based on edge calculation, and the general idea is as follows:

acquiring position data of a target player and video frame data of a sports field; wherein the video frame data comprises a target sphere; obtaining real-time batting data according to the position data; wherein the hitting real-time data comprises hitting position data, hitting angle data and hitting acceleration data of the target player; inputting the real-time batting data into a prediction model to obtain a predicted batting point of the target ball; acquiring an actual ball falling point of the target ball by utilizing an image recognition technology according to the video frame data; and performing judgment analysis according to the predicted ball falling point and the actual ball falling point to obtain a judgment result.

Through the technical scheme, the real-time batting data is obtained according to the position data of the target player, then the real-time batting data is input into the prediction model, the predicted batting point of the target ball is obtained, meanwhile, the actual batting point of the target ball is obtained by utilizing an image recognition technology according to the video frame data of the sports field, finally, the judgment analysis is carried out according to the predicted batting point and the actual batting point, the judgment result is obtained, and the purpose of carrying out intelligent judgment on ball sports in the sports field based on edge calculation is achieved. The invention integrates the positioning identification technology and the video identification technology, realizes the edge judgment analysis in the sports field, improves the digitization and the intelligent degree of the edge computing device in the digital sports technology, reduces the artificial participation amount, correspondingly reduces the artificial error and improves the accuracy of the sports analysis.

Example one

Referring to the flow chart of fig. 1, a first embodiment of the present invention is provided for a ball game analysis method based on edge calculation, which can be applied to an edge calculation device of a digital sports field such as a sports field and an indoor gym. The device can realize network connection with the cloud server of long-range or backstage, and when the marginal computing device provided near-end service for the athletic field, the cloud server can visit this marginal computing device's historical data. The edge computing device can provide faster response for the user, and the requirement is solved at the edge end, so that the processing efficiency is improved, and the load of the cloud server is reduced.

Specifically, the edge computing device is a terminal device capable of implementing network connection, and may be a computer, a tablet computer, a portable computer, an embedded industrial personal computer, or other terminal devices.

Fig. 4 is a schematic diagram of a hardware structure of the edge computing device. The apparatus may include: a processor 1001, such as a CPU (Central Processing Unit), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005.

Those skilled in the art will appreciate that the hardware configuration shown in FIG. 4 does not constitute a limitation of the edge computing device, and may include more or fewer components than those shown, or some components in combination, or a different arrangement of components.

Specifically, the communication bus 1002 is used for realizing connection communication among these components;

the user interface 1003 is used for connecting a client and performing data communication with the client, and the user interface 1003 may include an output unit such as a display screen and a speaker, and an input unit such as a keyboard and a microphone;

the network interface 1004 is used for connecting to the backend server and performing data communication with the backend server, and the network interface 1004 may include an input/output interface, such as a standard wired interface, a wireless interface, such as a Wi-Fi interface;

the memory 1005 is used for storing various types of data, such as instructions of any application or method in the edge computing device and application-related data, and the memory 1005 may be a high-speed RAM memory, or a stable memory such as a disk memory, or alternatively, the memory 1005 may be a storage device independent of the processor 1001;

specifically, with reference to fig. 4, the memory 1005 may include an operating system, a network communication module, a user interface module, and a computer program, wherein the network communication module is mainly used for connecting to the cloud server and performing data communication with the cloud server;

the processor 1001 is used to call up a computer program stored in the memory 1005 and perform the following operations:

Based on the edge calculation device, the following describes in detail the ball game analysis method based on edge calculation in this embodiment, taking an indoor badminton stadium as an example, with reference to the flowchart shown in fig. 1. The method may comprise the steps of:

step S10: acquiring position data of a target player and video frame data of a sports field; wherein the video frame data comprises a target sphere.

Specifically, the position data includes UWB (Ultra Wide Band) positioning data and nine-axis gyroscope data. The UWB positioning data comprises two-dimensional position data, the UWB positioning precision reaches 10CM, and the position data of the target player can be accurately obtained; the nine-axis gyroscope data comprise three-dimensional acceleration data and three-dimensional position data, and the nine-axis gyroscope can sense information such as horizontal, vertical, pitching, course, angular speed and the like of an object in the moving process, so that the three-dimensional posture data of the target player can be accurately acquired.

In the specific implementation process, position acquisition can be realized through a motion bracelet provided with a UWB positioning sensor and a nine-axis gyroscope sensor and a corresponding UWB positioning base station, and the position data is transmitted to an edge computing device in a wireless manner, so that the edge computing device can acquire the position data of a target player; the number of the UWB positioning base stations is correspondingly set to be a plurality according to the size of the sports field, so that accurate position data can be conveniently acquired. Can also realize video acquisition through the network camera that sets up at the sports ground both ends, give edge computing device through wireless transmission, edge computing device can acquire the video frame data of sports ground, and the video of the ball sports item that is going on in the concrete collection sports ground contains target sportsman, target spheroid and sports ground in the video promptly, can also contain the peripheral passageway of sports ground, auditorium etc.. The acquisition of the position data and the video frame data needs to be synchronized, the acquisition intervals are the same, and the minimum time interval is taken as the basis.

In this embodiment, wear the motion bracelet through every badminton person on the hand of hitting the ball to and in the peripheral top of the short sideline in badminton court both ends, respectively hoist a high definition network camera, obtain badminton person's position data and the video frame data in badminton court.

Step S30: obtaining real-time batting data according to the position data; wherein the hitting real-time data comprises hitting position data, hitting angle data and hitting acceleration data of the targeted player.

Specifically, the step S30 may include:

step S31: obtaining batting acceleration data of the target player according to the nine-axis gyroscope data;

step S32: identifying the batting action according to the batting acceleration data to obtain batting time points of the target player;

step S33: obtaining the batting position data of the target player according to the UWB positioning data and the nine-axis gyroscope data corresponding to the batting time point;

step S34: and obtaining the relative angle, the batting strength and the absolute angle of the batting action according to the angle, the specific force and the magnetic force of the batting position data in the three-dimensional direction so as to obtain the batting angle data of the target player.

In the specific implementation process, the nine-axis gyroscope can directly acquire the acceleration of the target player, when the acceleration is detected to reach the maximum value, the acceleration is the moment when the hand of the target player hits the middle ball, the moment action is the ball hitting action, and the time point corresponding to the moment is the ball hitting time point; then, directly obtaining hitting acceleration data (Acc _ X, Acc _ Y and Acc _ Z) of the target player, obtaining a plane position (Pos _ X and Pos _ Y) of the target player from UWB positioning data, and obtaining a height position (Pos _ Z) of the hitting player of the target player from nine-axis gyroscope data so as to obtain hitting position data (Pos _ X, Pos _ Y and Pos _ Z) of the target player; and then obtaining a relative Angle Angle _ X of the batting action according to the Angle corresponding to the position, obtaining batting strength Angle _ Y of the batting action according to the specific force corresponding to the position, and obtaining an absolute Angle Angle _ Z of the batting action according to the magnetic force corresponding to the position, thereby obtaining batting Angle data (Angle _ X, Angle _ Y and Angle _ Z) of the target player, namely obtaining batting real-time data of the target player.

Step S50: and inputting the real-time hitting data into a prediction model to obtain a predicted ball falling point of the target ball.

Specifically, the prediction model is a multi-input multi-output neural network model using a deep learning algorithm. Before step S50, an initial model may be constructed, and then some sample data or historical data may be used to train the model to obtain a trained neural network model, that is, the prediction model. Then, the model is continuously trained by the obtained batting real-time data during each practice of the edge computing device, so that the prediction accuracy of the model is improved.

In the implementation process, the hitting position data (Pos _ X, Pos _ Y, Pos _ Z), the hitting Angle data (Angle _ X, Angle _ Y, Angle _ Z) and the hitting acceleration data (Acc _ X, Acc _ Y, Acc _ Z) are input into the prediction model together, and the predicted Ball drop points (Ball _ X, Ball _ Y, Ball _ Z) of the target Ball are output.

Step S70: and obtaining the actual ball falling point of the target ball by utilizing an image recognition technology according to the video frame data.

Specifically, the step S70 may include:

step S71: and identifying a target sphere and a sports field by utilizing an image identification technology according to the video frame data to obtain an actual ball falling point of the target sphere and a side line of the sports field.

Specifically, for a video frame image of video frame data sent by a camera, an image recognition technology is used for recognizing a target sphere and a sports field side line in the target sphere. According to the multi-frame video image of the real-time video frame data, when the target sphere falls to the ground and rebounds, the track of the target sphere turns back, and correspondingly, the turning back point is the actual falling ball point of the target sphere.

Meanwhile, after each practice is finished, the predicted ball falling point can be corrected according to the actual ball falling point, the prediction model is updated, and the prediction accuracy is improved.

In this embodiment, according to the videos of the badminton court sent by the two cameras, the actual ball falling point of the badminton and the sideline of the badminton court are identified by using an image identification technology.

Step S90: and performing judgment analysis according to the predicted ball falling point and the actual ball falling point to obtain a judgment result.

Specifically, the step S90 may include:

step S91: judging whether the predicted ball falling point exceeds the sideline or not and whether the actual ball falling point exceeds the sideline or not;

step S92: if the predicted ball drop point exceeds the sideline, or the actual ball drop point exceeds the sideline, obtaining a judgment result of the failure of serving or batting of the target ball;

when a player serves, if the predicted ball falling point exceeds the side line, the target player, namely the serving party, is in error in the current serving, and whether the actual ball falling point obtained by the video frame data is in the side line or out of the side line, the player is judged to have failed in serving; if the predicted ball falling point does not exceed the borderline, the ball serving party does not have a fault in the ball serving process, but in an actual game, the predicted ball falling point does not exceed the borderline, and the actual ball falling point still exceeds the borderline, so that the ball serving failure of the player is still determined.

After the ball serving party serves, if the ball receiving party does not contact the ball, the target player is still the ball serving party player, in the process, the ball receiving party does not contact the ball, the target player does not change, if the actual ball falling point acquired by the video frame data exceeds the side line, the fact that the ball serving fault exists in the ball serving party player is indicated, and at the moment, the ball serving failure of the ball serving party player can be directly judged. If the ball receiver touches the ball, the target player becomes the ball receiver, and the ball receiving action is the hitting action. At this time, if the predicted ball-drop point of the original tee-off does not exceed the borderline, and the player of the receiver touches the ball when receiving the ball, the target player is converted, and returns to step S10 to continue to acquire the position data and the video frame data, and after the ball-receiving operation, the predicted ball-drop point and the actual ball-drop point are acquired again correspondingly. At the moment, if the predicted ball falling point exceeds the side line, the fact that the ball catching error exists in the player of the ball catching party is shown, and whether the actual ball falling point obtained by the video frame data is in the side line or out of the side line, the target player for catching the ball is judged to have failed in ball striking; if the predicted ball falling point does not exceed the borderline and the actual ball falling point exceeds the borderline, the ball catching error of the ball catching square player is also indicated, and the ball hitting failure of the ball catching target player is judged.

Step S93: and if the predicted ball drop point does not exceed the sideline and the actual ball drop point does not exceed the sideline, obtaining a judgment result of the ball catching failure of the target ball.

Predicting that the ball falling point does not exceed the sideline, indicating that the ball hitting or ball serving does not exceed the boundary, and no error exists in the ball hitting or ball serving party, then judging whether the ball receiving party receives the ball according to the actual ball falling point obtained by the video frame data, if the ball receiving party accurately counterclicks the ball, indicating that the ball receiving party successfully receives the ball, and then returning to the step S10 to continuously obtain the position data and the video frame data; if the ball receiver can not accurately counter hit the ball, the ball directly falls in the sports field, namely the actual ball falling point does not exceed the sideline, which indicates that the ball receiver fails to receive the ball.

The intelligent judgment function of the edge computing device is realized through the steps. The method has the advantages that the ball game items are subjected to digitalized and intelligent referees, referee results are obtained, on-site video display is carried out, and more convenient and intelligent referee services are provided.

In one embodiment, after step S10, the method may further include:

step S21: and acquiring the moving object and the identity information thereof by utilizing a human shape recognition technology according to the video frame data.

And carrying out human shape recognition on the video frame data to obtain a moving object, namely a moving person, and recognizing the identity information of the person, wherein the identity information mainly comprises whether the person is a target player or not. For example, when a person is identified, whether position data corresponding to the position is obtained is judged, if not, the person is not a target player, and if corresponding position information exists in the position data, the person is a target player, so that the identity information of all moving objects in the video frame data can be obtained. The identity information may also be obtained according to preset features, for example, if it is preset that a moving object wearing clothes with a specific color or having a specific mark on the body is a target player, feature recognition may be performed on all moving objects in the video frame data to obtain the identity information of all moving objects.

Step S22: and if the identity information of the moving object is a non-target player, predicting a moving track to obtain a first predicted track of the moving object.

The video generally has a plurality of moving objects, and after the identification information of a certain moving object is not a target player, the trajectory prediction can be performed on the moving object, wherein the technology for performing the trajectory prediction on the moving object in the video is the prior art, and is not described herein again; the UWB bracelet can be worn by the mobile object to acquire position data of the mobile object, and track prediction is carried out, so that a first predicted track of the mobile object is obtained.

Step S23: and judging whether the first prediction track conflicts with the sports field.

The camera can take the video frame data into with the motion field completely when shooing, and the user can be directly to video frame data mark region, as predetermineeing the motion field region, based on predetermineeing the motion field region in the video frame data, after obtaining first prediction orbit, judges whether this orbit and predetermine the motion field region and have the conflict, and whether promptly first prediction orbit can enter into predetermineeing the motion field region, if can, judges that there is the conflict, if can, judges that there is not the conflict.

Step S24: and if the first predicted track conflicts with the sports field, marking the moving object and carrying out first alarm prompt.

If the first predicted track conflicts with the sports field, the first predicted track indicates that the moving object is about to enter or enters the sports field, the match of the players can be influenced, and prompt reminding is needed. And to video frame data, generally can carry out the rebroadcast at the motion venue scene, at this moment, can directly mark this mobile object in this video, can also trigger simultaneously and report to the police, for example report through the speaker that there is non-sportsman to break into the motion field, the suggestion this mobile object in time leaves the motion field, avoids taking place the collision.

Further, after step S22, the method may further include:

step S25: and if the identity information of the moving object is the target player, predicting a moving track according to the position data of the target player to obtain a second predicted track of the target player.

And if the position of the obtained moving object is overlapped with the obtained UWB positioning position data by utilizing the human shape recognition technology according to the video frame data, the identity information of the moving object is the target player. And when the identity information of a certain moving object is identified as the target player, directly predicting the track of the target player based on the UWB positioning position data to obtain a second predicted track of the target player.

Step S26: and judging whether the first predicted track and the second predicted track conflict or not.

In a game, not only players but also referees in the field exist, and after a moving object with a non-target player identity is obtained in step S22, a first predicted track corresponding to the moving object and a second predicted track corresponding to the moving object with the target player identity obtained in step S25 are subjected to collision judgment, that is, whether an intersection point exists between the two predicted tracks is judged.

Step S27: and if the first predicted track conflicts with the second predicted track, marking the moving object and carrying out second alarm prompt.

When the two predicted tracks have intersection points, namely the first predicted track and the second predicted track have conflict, the two moving objects are likely to collide together, early warning is timely carried out, the moving objects can be reminded to stop moving in time, and safety accidents are prevented.

The safety monitoring function of the edge computing device is realized through the steps. Whether the sportsman or the nonsportsman in the sports stadium is monitored safely, the alarm prompt is timely carried out, and safety accidents are prevented.

In another embodiment, after step S90, the method may further include:

step S101: and obtaining the score of the target player according to the judgment result and a preset scoring rule.

Specifically, the score can be displayed on site through a display screen, so that intelligent scoring is realized.

Step S102: and drawing the motion trail of the target player, and storing the motion trail, the batting real-time data and the judgment result.

Specifically, the movement track, the real-time hitting data and the judgment result are stored and used for analyzing the score of the target player and the reason of score loss or score loss in the follow-up analysis, analyzing the walking condition of the player in the movement by combining the playback video and the like. The drawn motion track, the obtained real-time batting data and the judgment result are stored on the edge computing device, the cloud server can directly use the data to directly obtain a data report or obtain an analysis report according to some preset data analysis strategies, so that the motion analysis of the target player is realized, and a user can know the batting or service failure of the target player or the reason of the failed batting, such as improper batting position, improper batting strength or improper batting angle and the like.

The batting analysis function of the edge computing device is realized through the steps. The competition process can be conveniently reviewed after the competition, and the skills of athletes are improved.

According to the method for analyzing the ball sports based on the edge calculation, the real-time batting data is obtained according to the position data of the target player, then the real-time batting data is input into the prediction model, the predicted ball drop point of the target ball is obtained, meanwhile, the actual ball drop point of the target ball is obtained by utilizing the image recognition technology according to the video frame data of the sports field, finally, judgment analysis is carried out according to the predicted ball drop point and the actual ball drop point, the judgment result is obtained, and the purpose of carrying out intelligent judgment on the ball sports in the sports field based on the edge calculation is achieved. The invention integrates the positioning identification technology and the video identification technology, realizes the edge judgment analysis in the sports field, improves the digitization and the intelligent degree of the edge computing device in the digital sports technology, reduces the artificial participation amount, correspondingly reduces the artificial error and improves the accuracy of the sports analysis. The ball game analysis method based on edge calculation provided by the embodiment can not only realize intelligent judgment, but also realize safety monitoring and batting analysis.

Example two

Based on the same inventive concept, referring to fig. 2, a first embodiment of the edge-computing-based ball game analyzing apparatus of the present invention is provided, which may be a virtual apparatus. The following describes in detail the ball game analysis device based on edge calculation according to this embodiment with reference to the schematic functional block diagram shown in fig. 2, where the device may include:

Further, the apparatus may further include a first alarm module, and the first alarm module may specifically include:

the mobile object identification unit is used for acquiring a mobile object and identity information thereof by utilizing a human shape identification technology according to the video frame data;

the first track prediction unit is used for predicting a moving track to obtain a first predicted track of the moving object if the identity information of the moving object is a non-target player;

the first conflict judgment unit is used for judging whether the first predicted track conflicts with the sports field or not;

and the first alarm prompting unit is used for marking the moving object and carrying out first alarm prompting if the first predicted track conflicts with the sports field.

Further, the apparatus may further include a second alarm module, and the second alarm module may specifically include:

the second track prediction unit is used for predicting a moving track according to the position data of the target player to obtain a second predicted track of the target player if the identity information of the moving object is the target player;

a second conflict judgment unit configured to judge whether there is a conflict between the first predicted trajectory and the second predicted trajectory;

and the second alarm prompting unit is used for marking the moving object and carrying out second alarm prompting if the first predicted track conflicts with the second predicted track.

Further, the position data includes UWB positioning data and nine-axis gyroscope data; the ball striking identification module may include:

the acceleration data acquisition unit is used for acquiring batting acceleration data of the target player according to the nine-axis gyroscope data;

the batting time point acquisition unit is used for identifying batting actions according to the batting acceleration data and acquiring batting time points of the target player;

the hitting position data acquisition unit is used for acquiring hitting position data of the target player according to the UWB positioning data and the nine-axis gyroscope data corresponding to the hitting time point;

and the batting angle data acquisition unit is used for acquiring the relative angle, batting strength and absolute angle of batting action according to the angle, specific force and magnetic force of the batting position data in the three-dimensional direction so as to acquire the batting angle data of the target player.

Further, the image recognition module is specifically configured to:

Further, the referee analysis module may include:

the judgment analysis unit is used for judging whether the predicted ball drop point exceeds the sideline or not and whether the actual ball drop point exceeds the sideline or not;

the first judgment result unit is used for obtaining a judgment result of the failure of service or batting of the target ball if the predicted ball drop point exceeds the sideline or the actual ball drop point exceeds the sideline;

and the second judgment result unit is used for obtaining a judgment result of the failed ball catching of the target ball if the predicted ball falling point does not exceed the sideline and the actual ball falling point does not exceed the sideline.

Further, the apparatus may further include:

the score counting module is used for obtaining the score of the target player according to the judgment result and a preset scoring rule;

and the player analysis module is used for drawing the motion track of the target player and storing the motion track, the real-time batting data and the judgment result so as to analyze the reason that the score of the target player is scored or lost.

It should be noted that, for the functions that can be realized by each module in the edge-computation-based ball game analysis apparatus provided in this embodiment and the corresponding achieved technical effects, reference may be made to the description of the specific implementation manners in each embodiment of the edge-computation-based ball game analysis method of the present invention, and for the sake of brevity of the description, no further description is given here.

EXAMPLE III

Based on the same inventive concept, referring to fig. 3 and 4, a first embodiment of the edge calculation-based ball game analysis system of the present invention is provided. The following describes in detail the system for analyzing ball game based on edge calculation according to this embodiment with reference to the schematic connection diagram shown in fig. 3, where the system may include:

the edge calculating device is used for realizing the ball game analyzing method based on the edge calculation.

Specifically, the position acquisition device can be UWB location bracelet, wears on sportsman's hand or leg, can select to wear the position according to actual motion item.

The positioning base station device can be a UWB positioning base station and is in communication connection with a UWB positioning bracelet to perform accurate positioning, generate position data and send the position data to the edge computing device.

The video acquisition device can be two high definition network cameras, sets up at the both ends in the sports field, guarantees that the sports field falls completely in the camera can take a photograph the within range, and two cameras all send the video frame data that gather separately for edge computing device.

The edge computing device is a terminal device capable of realizing network connection, and can be a computer, a tablet computer, a portable computer, an embedded industrial personal computer and other terminal devices. As shown in fig. 4, which is a schematic diagram of a hardware structure of an edge computing apparatus, the apparatus may include a processor and a memory, and the memory stores a computer program, and when the computer program is executed by the processor, all or part of the steps of the ball game analyzing method based on edge computing according to the embodiments of the present invention are implemented.

It will be appreciated that the apparatus may also include a communications bus, a user interface and a network interface.

Wherein the communication bus is used for realizing connection communication among the components.

The user interface is used for connecting the client and performing data communication with the client, and the user interface may include an output unit such as a display screen and a speaker, and an input unit such as a keyboard and a microphone.

The network interface is used for connecting the background server and performing data communication with the background server, and the network interface may include an input/output interface, such as a standard wired interface, a wireless interface, such as a Wi-Fi interface.

The memory is used to store various types of data, which may include, for example, instructions for any application or method in the edge computing device, as well as application-related data. The Memory may be implemented by any type of volatile or non-volatile Memory device or combination thereof, such as Static Random Access Memory (SRAM), Erasable Programmable Read-Only Memory (EPROM), Programmable Read-Only Memory (PROM), Read-Only Memory (ROM), magnetic Memory, flash Memory, magnetic or optical disk, or alternatively, the Memory may be a storage device independent of the processor.

The Processor may be an Application Specific Integrated Circuit (ASIC), a Digital Signal Processor (DSP), a Digital Signal Processing Device (DSPD), a Programmable Logic Device (PLD), a Field Programmable Gate Array (FPGA), a controller, a microcontroller, a microprocessor, or other electronic components, and is configured to call a computer program stored in the memory and execute the above edge-computing-based ball game analysis method.

The ball game analysis system based on edge calculation provided by the embodiment realizes the purposes of carrying out intelligent judgment on ball games in a sports field based on sensing equipment and edge calculation and preventing sports safety damage.

It should be noted that the above-mentioned serial numbers of the embodiments of the present invention are merely for description, and do not represent the merits of the embodiments.

The above description is only an alternative embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes performed by the present specification and drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.

Claims

1. A method for analyzing ball game based on edge calculation, the method comprising:

2. A method for analyzing ball game based on edge calculation as claimed in claim 1, wherein after the step of obtaining the position data of the target player and the video frame data of the sports field, the method further comprises:

3. The edge-computing-based ball game analysis method of claim 2, wherein after the step of predicting the movement trajectory if the identity information of the moving object is a non-target player and obtaining the first predicted trajectory of the moving object, the method further comprises:

4. A method for analyzing ball movements based on edge calculations as claimed in claim 1, characterized in that said position data comprises UWB positioning data and nine-axis gyroscope data;

5. The edge-computation-based ball motion analysis method of claim 1, wherein the step of obtaining the actual ball drop point of the target ball by using an image recognition technique according to the video frame data comprises:

6. An edge-computing-based ball game analysis method according to claim 5, wherein said step of performing a referee analysis based on said predicted ball drop point and said actual ball drop point to obtain a referee result comprises:

7. An edge-computing-based ball game analysis method according to any one of claims 1 to 6, wherein after the step of performing a referee analysis based on the predicted ball drop point and the actual ball drop point to obtain a referee result, the method further comprises:

8. An apparatus for analyzing ball game based on edge calculation, the apparatus comprising:

9. An edge-computing-based ball game analysis system, the system comprising:

edge calculation means for implementing the method of ball game analysis based on edge calculation according to any one of claims 1 to 7.