Tactical graph recognition method and system on football field based on tactical relevancy

Abstract

The invention relates to the technical field of computer recognition, in particular to a tactical graph recognition method and system on a football field based on tactical relevancy, and the method comprises the steps: building a coordinate system based on the football field, and collecting the position data of a player and any moving target of a ball in each frame; obtaining spatial distance relevancy, speed acceleration relevancy and historical tactical relevancy to generate a relevancy matrix; a weight matrix is obtained, and the tactical relevancy of any two players is determined in combination with a relevancy matrix; constructing a tactical correlation graph, defining the tactical correlation degree as the weight of a corresponding edge in the tactical correlation graph, selecting any vertex in the edge with the maximum weight as a starting point to obtain a plurality of polygons, screening, and combining the screened polygons to obtain a tactical graph of any frame; the spatial distance relevancy, the speed acceleration relevancy and the historical tactical relevancy of every two players are analyzed, the tactical relevancy of the players is comprehensively determined and visually presented in a tactical graph, and the accuracy is higher.

Description

Technical Field

[0001] The present invention relates to the field of computer recognition technology, and in particular to a method and system for recognizing tactical graphics on a football field based on tactical relevance. Background Art

[0002] During football training and competition, the positions of players and the ball are often complex and changeable. With the continuous advancement of football game technology and the growing demand for data analysis, traditional tactical analysis methods are difficult to automatically and intuitively display tactical graphics. Existing tactical recognition methods usually rely on manual experience analysis and rely on the experience of experts to judge the tactics of real-time players. They cannot effectively and automatically identify the tactical connection between players, and manual analysis is inefficient. It is impossible to quickly obtain the connection between the two based on the real-time changing player positions and the trajectory of the ball in motion, and thus cannot accurately capture complex tactical intentions and the team's overall tactical layout, and cannot meet the high requirements of modern football games for tactical analysis. Summary of the invention

[0003] In order to solve the technical problem that the existing tactical recognition mainly relies on manual work, resulting in low recognition efficiency and accuracy, and cannot meet the high demand for tactical analysis in modern football games, the purpose of the present invention is to provide a tactical graphic recognition method on a football field based on tactical relevance. The technical solution adopted is as follows: Construct a coordinate system based on the football field and collect the position data of any moving target of the player and the ball in each frame; According to the position data, spatial distance correlation, speed acceleration correlation and historical tactical correlation are obtained in sequence to generate a correlation matrix; Assign weights to the spatial distance correlation, speed acceleration correlation and historical tactical correlation respectively to obtain a weight matrix, and determine the tactical correlation between any two players in combination with the correlation matrix; Construct a tactical correlation graph, and define the tactical correlation as the weight of the corresponding edge in the tactical correlation graph. Select any vertex in the edge with the largest weight as the starting point to obtain several polygons, and filter them. Merge the filtered polygons to obtain the tactical graph of any frame.

[0004] Preferably, a coordinate system is constructed based on the football field to collect position data of any moving target of the player and the ball, including: Based on the football field, a plane rectangular coordinate system is constructed with the lower left corner of the top view as the origin. The camera is used to collect the position data of any moving target of the player and the ball in each frame, which is recorded as ; in, Indicates the frame number. Indicates the total number of frames; represents the number of players, represents the total number of players; Indicates the team to which the players on the football field belong. Represents the total number of teams.

[0005] Preferably, spatial distance correlation, speed acceleration correlation and historical tactical correlation are sequentially acquired according to the position data to generate a correlation matrix, including: Based on the players' position data, the straight-line distance between any two players is obtained, a judgment threshold is set to determine the authenticity of the interaction between the two players, and the spatial distance correlation is calculated; The player's speed and acceleration are obtained according to the player's position data combined with the frame interval of each frame, and the speed angle and acceleration angle are respectively obtained based on the coordinate system, and the speed correlation and acceleration correlation are correspondingly calculated, and the speed correlation and acceleration correlation are combined to obtain the speed-acceleration correlation; Analyze the average tactical relevance of two players in the previous frame adjacent to the current frame, and obtain the historical tactical relevance through the contribution weight; A tactical correlation matrix is ​​constructed through spatial distance correlation, speed acceleration correlation and historical tactical correlation. The average distance between two players and the ball is calculated to determine the correction coefficient. The tactical correlation matrix is ​​corrected based on the correction coefficient to generate a correlation matrix.

[0006] Preferably, obtaining the straight-line distance between any two players based on the position data of the players, setting a judgment threshold to determine the authenticity of the interaction between the two players, and calculating the spatial distance correlation includes: Based on the players' position data, the straight-line distance between any two players is obtained. The corresponding calculation formula is:

[0007] in, Indicates Players and Straight line distance between players; represents the total number of players; Set judgment threshold ,When the straight-line distance is less than the judgment threshold, it means that the interaction between the two players is real; when the straight-line distance is greater than the judgment threshold, it means that the interaction between the two players is not real, and the attenuation coefficient is constructed; Calculate the spatial distance correlation, the corresponding calculation formula is:

[0008] in, Indicates Spatial distance correlation of frames; represents a constant; Represents the attenuation coefficient.

[0009] Preferably, the player's speed and acceleration are obtained according to the player's position data combined with the frame interval of each frame, and the speed angle and the acceleration angle are respectively obtained based on the coordinate system, and the speed correlation and the acceleration correlation are correspondingly calculated, and the speed correlation and the acceleration correlation are combined to obtain the speed acceleration correlation, including: According to the player's position data and the frame interval of each frame, the player's speed and acceleration are obtained, which are recorded as and ; Based on the coordinate system, the velocity angle and acceleration angle are obtained respectively, which are recorded as and ,and ; Calculate the speed correlation, the corresponding calculation formula is:

[0010] in, Indicates Speed ​​relevance of frames; Indicates players; Indicates players; Calculate the acceleration correlation, the corresponding calculation formula is:

[0011] in, Indicates Acceleration correlation of frames; The velocity correlation and acceleration correlation are combined to obtain the velocity-acceleration correlation. The corresponding calculation formula is:

[0012]

[0013] in, Indicates The velocity-acceleration correlation of the frame; express The minimum value in .

[0014] Preferably, the average tactical relevance of two players in the previous frame adjacent to the current frame is analyzed, and the historical tactical relevance is obtained by the contribution weight. The corresponding calculation formula is:

[0015] in, Indicates the historical-tactical relevance of the frame; Indicates The average tactical relevance of the two players in the frame; Represents the weight coefficient.

[0016] Preferably, a tactical correlation matrix is ​​constructed through spatial distance correlation, speed acceleration correlation and historical tactical correlation, the average distance between two players and the ball is calculated to determine the correction coefficient, and the tactical correlation matrix is ​​corrected based on the correction coefficient to generate a correlation matrix, including: Construct a tactical correlation matrix, recorded as ; Calculate the average distance between the two players and the ball. The corresponding calculation formula is: ,in, represents the average distance between the two players and the ball, Indicates The straight-line distance between the player and the ball; Indicates The straight-line distance between the player and the ball; Determine the correction coefficient, the corresponding calculation formula is: ,in, represents the correction factor; The tactical correlation matrix is ​​corrected based on the correction coefficient to generate the correlation matrix. The corresponding calculation formula is:

[0017] in, represents the correlation matrix; , , They represent the corrected spatial distance correlation, speed acceleration correlation and historical tactical correlation respectively.

[0018] Preferably, weights are assigned to the spatial distance correlation, the speed acceleration correlation and the historical tactical correlation respectively to obtain a weight matrix, and the tactical correlation between any two players is determined in combination with the correlation matrix, including: Determine the weight matrix, denoted as ,in, , , They represent the weights corresponding to the spatial distance correlation, speed acceleration correlation and historical tactical correlation respectively; Combined with the correlation matrix, the tactical correlation between two players is determined. The corresponding calculation formula is:

[0019] in, Indicates tactical relevance; Represents the correlation matrix.

[0020] Preferably, a tactical correlation graph is constructed, and the tactical correlation is defined as the weight of the corresponding edge in the tactical correlation graph, and any vertex in the edge with the largest weight is selected as a starting point to obtain a number of polygons, and the filtered polygons are merged to obtain a tactical graph of any frame, including: Based on the first frame, a tactical correlation graph is constructed, denoted as ,in, Represents the teams on a football field; represents the total number of teams on the football field; Indicates The collection of position data for all players on a team; Indicates The set of tactical correlations between any two players of a team is recorded as the edge set of the tactical correlation graph; According to the edge set Select any vertex in the largest edge as the starting point and record it as the vertex , set the filtering threshold, from the edge set Select the included vertices , and obtain several polygons from the edges whose vertex number is greater than the screening threshold; Calculate the average tactical relevance for any polygon, and the corresponding calculation formula is:

[0021]

[0022] in, represents the average tactical relevance of the polygons; represents the increase coefficient; Indicates the total number of players and balls in the current analyzed team; Represents the number of sides of the polygon; Represents the first The tactical relevance of the edge; Sort the polygons in descending order according to the average tactical relevance, and obtain the first initial tactical graph in sequence until the Initial tactical graph, wherein the first initial tactical graph is recorded as ,Will The player position data is from Delete Medium tactical relevance from , and process all polygons in the same way until the The collection of position data for all players in a team When the number of position data points in is less than or equal to 2; All the processed initial tactical graphs are merged to obtain the tactical graph of any frame, which is recorded as ,in, Indicates Frame Tactical graphics for each team; A collection representing the position data of all players in the initial tactical graph; Represents the set of tactical correlations between any two players in all initial tactical graphs.

[0023] To solve the above problems, the present application also provides: a tactical graphic recognition system on a football field based on tactical relevance, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the steps of a tactical graphic recognition method on a football field based on tactical relevance as described in any one of the preceding items are implemented.

[0024] The present invention has the following beneficial effects: 1. This application first constructs a coordinate system, obtains the position data of the moving target, analyzes the correlation between the spatial position, speed, acceleration and historical cooperation relationship between any two players, and determines the tactical correlation between the players based on the position data of the ball; by constructing the initial tactical graph, it can accurately identify all polygons with the largest average tactical correlation, and merge them on this basis to obtain the actual tactical graph corresponding to the team in each frame, which can effectively identify the tactics that the players may execute on the field and express them in an intuitive way; it is suitable for football training and competitions with complex positions, formations and tactics, and can deeply explore the tactical connection between players, accurately identify the tactical content of each moment, that is, each frame, and express it intuitively in a graphical way, providing a clearer display of on-field features.

[0025] 2. The present invention also provides a tactical graphic recognition system on a football field based on tactical relevance, which is used to implement the aforementioned tactical graphic recognition method on a football field based on tactical relevance. The system has the same beneficial effects as the aforementioned tactical graphic recognition method on a football field based on tactical relevance, and will not be elaborated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings required for use in the embodiments or the prior art descriptions are 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 work.

[0027] Figure 1A flowchart of an implementation method of a tactical graphic recognition method on a football field based on tactical relevance provided by an embodiment of the present invention; Figure 2 A schematic diagram of spatial distance correlation of a tactical graphic recognition method on a football field based on tactical correlation provided by an embodiment of the present invention; Figure 3 A schematic diagram of speed-acceleration correlation of a tactical graphic recognition method on a football field based on tactical correlation provided by one embodiment of the present invention; Figure 4 A schematic diagram of any possible initial tactical graph of a method for identifying tactical graphs on a football field based on tactical relevance provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0028] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following is a detailed description of a method and system for recognizing tactical graphics on a football field based on tactical relevance proposed by the present invention, its specific implementation method, structure, features and effects, in conjunction with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0029] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0030] The specific scheme of a method and system for recognizing tactical graphics on a football field based on tactical relevance provided by the present invention is described in detail below in conjunction with the accompanying drawings.

[0031] Since the existing tactical identification on the football field mostly relies on the manual acquisition of experts, professors and other experienced people, the efficiency is low and the accuracy is low. It is impossible to accurately obtain the tactical connection between the players and the ball in real time, and it is impossible to capture the complex tactical intentions and the overall tactical layout of the team, and it is impossible to meet the high requirements of modern football games for tactical analysis. The first embodiment of the present invention provides a tactical graphic recognition method on a football field based on tactical relevance. The method analyzes the position data of the moving target by constructing a coordinate system, sequentially obtains the spatial distance correlation, the speed acceleration correlation and the historical tactical correlation, determines the tactical correlation, constructs the initial tactical graphic, analyzes it, and obtains the actual tactical graphic corresponding to each frame of the team, which can effectively identify the tactics that the players may execute on the field and express them in an intuitive way. In order to solve a tactical graphic recognition method on a football field based on tactical relevance, the second embodiment of the present invention provides a tactical graphic recognition system on a football field based on tactical relevance. The system is essentially a software system, which is composed of various units that realize corresponding functions. The specific steps in the method are now introduced in detail.

[0032] See also Figure 1 , which shows an implementation flow chart of a method for identifying tactical graphics on a football field based on tactical relevance provided by an embodiment of the present invention, the method comprising: Step S1: construct a coordinate system based on the football field, and collect the position data of any moving target of the player and the ball in each frame; Step S2: obtaining spatial distance correlation, speed acceleration correlation and historical tactical correlation in sequence according to the position data to generate a correlation matrix; Step S3: assigning weights to the spatial distance correlation, speed acceleration correlation and historical tactical correlation respectively to obtain a weight matrix, and determining the tactical correlation between any two players in combination with the correlation matrix; Step S4: construct a tactical correlation graph, and define the tactical correlation as the weight of the corresponding edge in the tactical correlation graph, select any vertex in the edge with the largest weight as the starting point to obtain several polygons, and filter them, and merge the filtered polygons to obtain the tactical graph of any frame.

[0033] To better illustrate, the existing tactical recognition on the football field mostly relies on experienced manual acquisition by experts, professors, etc., which is inefficient and has low accuracy. It is unable to accurately obtain the tactical connection between players and the ball in real time, and cannot capture complex tactical intentions and the team's overall tactical layout, and cannot meet the high requirements of tactical analysis in modern football games. In this regard, the present application proposes a tactical graphic recognition method on a football field based on tactical relevance, constructs tactical graphics, and can automatically recognize complex formations and tactics on the football field according to the connection between moving targets in real-time movement. It has high reliability and accuracy, and is presented in the form of tactical graphics, which is clear and intuitive, and can adapt to complex football training and competition scenes.

[0034] Furthermore, step S1 includes: Based on the football field, a plane rectangular coordinate system is constructed with the lower left corner of the top view as the origin. The camera is used to collect the position data of any moving target of the player and the ball in each frame, which is recorded as ; in, Indicates the frame number. Indicates the total number of frames; represents the number of players, represents the total number of players; Indicates the team to which the players on the football field belong. Represents the total number of teams.

[0035] It is explained that a camera is used to record the situation on the football field in real time, that is, various existing perspective conversion, target detection, target tracking and identity matching methods are used to obtain the position information of the players and the ball on the field, and the position data of each player and the ball, that is, the corresponding position coordinates, are determined according to the constructed plane rectangular coordinate system.

[0036] It can be explained that tactical relevance refers to the degree of cooperation and collaboration between players on the football field based on the tactical intentions set by the coach and the behavior of teammates. It can reflect how players cooperate, understand and respond to each other's actions on the football field, so as to accurately reflect the deployment of tactics.

[0037] Furthermore, step S2 includes: Step S21: based on the position data of the players, the straight-line distance between any two players is obtained, a judgment threshold is set to determine the authenticity of the interaction between the two players, and the spatial distance correlation is calculated.

[0038] To explain, spatial distance correlation refers to a correlation indicator of how players effectively occupy the field space and cooperate with teammates through positioning, running and passing, that is, by analyzing the straight-line distance between players, the position changes of players are analyzed; the greater the spatial distance between two players, the lower the degree of cooperation between them, and when the spatial distance is below a certain threshold, the degree of cooperation is more stable.

[0039] See also Figure 2 , which shows a schematic diagram of the spatial distance correlation of a tactical graphic recognition method on a football field based on tactical correlation provided by an embodiment of the present invention; wherein, a high spatial distance correlation, that is, a short straight-line distance between two players is represented by a solid line; a low spatial distance correlation, that is, a long straight-line distance between two players is represented by a dotted line.

[0040] Furthermore, step S21 includes: Based on the players' position data, the straight-line distance between any two players is obtained. The corresponding calculation formula is:

[0041] in, Indicates Players and Straight line distance between players; represents the total number of players; Set judgment threshold ,When the straight-line distance is less than the judgment threshold, it means that the interaction between the two players is real; when the straight-line distance is greater than the judgment threshold, it means that the interaction between the two players is not real, and the attenuation coefficient is constructed; Calculate the spatial distance correlation, the corresponding calculation formula is:

[0042] in, Indicates Spatial distance correlation of frames; represents a constant; Represents the attenuation coefficient.

[0043] Understandably, the preset judgment threshold , and the judgment threshold The value is set according to actual needs; when the straight-line distance is less than the judgment threshold, it means that the interaction between the two players is real, that is, the interaction and defense between the players are relatively stable, and the closeness of the cooperation between the two is not affected by the change of the distance interval. At this time, the corresponding spatial distance correlation is a constant value; when the straight-line distance is greater than the judgment threshold, it means that the interaction between the two players is unreal, that is, the straight-line distance between the two players is far. At this time, the lower the spatial distance correlation, the overall negative correlation is present. It is difficult for the two players to have effective interaction due to the distance problem, and the relationship between the spatial distance correlation and the straight-line distance shows a rapid attenuation characteristic. In order to construct the attenuation coefficient, a negative exponential function is used to describe the situation where the interaction is unreal.

[0044] Step S22: The player's speed and acceleration are obtained according to the player's position data combined with the inter-frame interval of each frame, and the speed angle and acceleration angle are respectively obtained based on the coordinate system, and the speed correlation and acceleration correlation are correspondingly calculated, and the speed correlation and acceleration correlation are combined to obtain the speed-acceleration correlation.

[0045] To explain, speed-acceleration correlation refers to the relationship and degree of interaction between speed and acceleration of a player during movement, where speed is used to describe the rate of change of a player's displacement per unit time; acceleration is the rate at which speed changes per unit time; that is, the difference in speed and acceleration vectors between two players is obtained. The greater the difference, the lower the cooperative relationship; conversely, the higher the cooperative relationship.

[0046] It can be understood that speed and acceleration are collectively referred to as motion vectors. The greater the difference in the size and angle of the motion vectors between the two players, the smaller the corresponding speed correlation and acceleration correlation. In actual sports, when the difference between either speed or acceleration tends to be extremely large, the speed-acceleration correlation will tend to zero, so it is necessary to simultaneously consider the impact of these two factors on the final correlation. When the size and direction differences of the motion vectors are both zero, that is, the motion states of the two players are exactly the same, it can be regarded that the degree of coordination between the two has reached the highest level and the tactical effect is the best. And through exponential operations, the speed-acceleration correlation decays rapidly as the difference increases. The trigonometric function converts the difference between speed and acceleration into a numerical value, which effectively reflects the impact of the angle factor on the speed-acceleration correlation.

[0047] See also Figure 3 , which shows a schematic diagram of speed acceleration correlation of a tactical graphic recognition method on a football field based on tactical correlation provided by an embodiment of the present invention.

[0048] Furthermore, step S22 includes: According to the player's position data and the frame interval of each frame, the player's speed and acceleration are obtained, which are recorded as and ; Based on the coordinate system, the velocity angle and acceleration angle are obtained respectively, which are recorded as and ,and ; Calculate the speed correlation, the corresponding calculation formula is:

[0049] in, Indicates Speed ​​relevance of frames; Indicates players; Indicates players; Calculate the acceleration correlation, the corresponding calculation formula is:

[0050] in, Indicates Acceleration correlation of frames; The velocity correlation and acceleration correlation are combined to obtain the velocity-acceleration correlation. The corresponding calculation formula is:

[0051]

[0052] in, Indicates The velocity-acceleration correlation of the frame; express The minimum value in .

[0053] Specifically, for the position data of the first frame and the last frame in the acquisition process, the backward difference quotient and the forward difference quotient are used respectively, and the intermediate frame uses the intermediate difference quotient, that is, the speed and acceleration of the corresponding analysis frame are obtained by the changed position data in the two frames; the player's speed and acceleration are obtained according to the player's position data combined with the inter-frame interval of each frame; by analyzing the coordinate system, the angle between the speed and acceleration in the current frame can be obtained, thereby calculating the speed correlation and acceleration correlation respectively, to jointly determine the speed-acceleration correlation.

[0054] Step S23: Analyze the average tactical relevance of two players in the previous frame adjacent to the current frame, and obtain the historical tactical relevance through the contribution weight.

[0055] To clarify, the historical tactical relevance refers to the tactical relevance of the previous frames corresponding to the current frame, that is, the past tactical relevance between players; the contribution weight is used to measure the effect of the average tactical relevance of the two players in the previous frame on the historical tactical relevance of the current analysis frame.

[0056] Furthermore, in step S23, the corresponding calculation formula is:

[0057] in, Indicates the historical-tactical relevance of the frame; Indicates The average tactical relevance of the two players in the frame; Represents the weight coefficient.

[0058] Specifically, for the current The analysis of the historical tactical relevance of a frame depends to a certain extent on its adjacent previous The average tactical correlation between two players in a frame, i.e. , assuming The higher the result value of , it means that there was a close cooperation relationship between the two players. In the next frame within a short period of time, the tactical cooperation relationship between the two players may remain unchanged. When there are two frames, it is considered that there is still a high tactical correlation between the two players; that is, the tactical correlation of the adjacent previous frame makes a certain contribution to the tactical correlation of the next frame. The contribution weight is set to quantify the influence of the previous frame on the next frame, and the contribution weight is combined with the average tactical correlation to obtain the historical tactical correlation between the players. The larger the contribution weight, the more important the historical tactical correlation.

[0059] Step S24: construct a tactical correlation matrix through spatial distance correlation, speed acceleration correlation and historical tactical correlation, calculate the average distance between the two players and the ball to determine the correction coefficient, and correct the tactical correlation matrix based on the correction coefficient to generate a correlation matrix.

[0060] Understandably, the analysis is made based on the three data dimensions of spatial distance correlation, speed acceleration correlation and historical tactical correlation, so as to flexibly adjust the importance of different dimensions in evaluating the cooperative relationship between players, obtain the cooperative relationship between players and the ball in a more comprehensive and systematic way, and adapt to changing on-field situations.

[0061] Furthermore, step S24 includes: Construct a tactical correlation matrix, recorded as ; Calculate the average distance between the two players and the ball. The corresponding calculation formula is: ,in, represents the average distance between the two players and the ball, Indicates The straight-line distance between the player and the ball; Indicates The straight-line distance between the player and the ball; Determine the correction coefficient, the corresponding calculation formula is: ,in, represents the correction factor; The tactical correlation matrix is ​​corrected based on the correction coefficient to generate the correlation matrix. The corresponding calculation formula is:

[0062] in, represents the correlation matrix; , , They represent the corrected spatial distance correlation, speed acceleration correlation and historical tactical correlation respectively.

[0063] Specifically, firstly, a tactical correlation matrix is ​​constructed based on the three data of spatial distance correlation, speed acceleration correlation and historical tactical correlation obtained above; then, the straight-line distances between the two players currently analyzed and the ball are obtained to obtain the average distance between the two; secondly, if the distance between the player and the ball is farther, the effect on tactical play is smaller, so the distance between the player and the ball is analyzed comprehensively, and a correction coefficient is used to correct the tactical correlation of the three dimensions to judge the influence of the distance between the player and the ball on the overall tactical effect. When the average distance between the player and the ball increases linearly, the correction coefficient will also decrease linearly accordingly, and then the tactical correlation matrix is ​​corrected by the correction coefficient to obtain the correlation matrix of the two players.

[0064] Furthermore, step S3 includes: Step S31: Determine the weight matrix, denoted as ,in, , , They respectively represent the weights corresponding to the spatial distance correlation, speed acceleration correlation and historical tactical correlation.

[0065] As an optional implementation, in this embodiment, the hierarchical analysis method is used to find the corresponding weights of the correlation matrix, that is, by constructing a hierarchical model, the complex decision-making problem is decomposed into multiple levels and factors; specifically, firstly, a judgment matrix of the correlation matrix is ​​constructed to evaluate the relative importance between different data elements, and the corresponding logical expression is:

[0066] in, Represents the judgment matrix, and each row and column of the corresponding data are the relative weight values ​​of spatial distance correlation, speed acceleration correlation, and historical tactical correlation. It can be explained that Indicates the importance of the indicator relevance of the first row to the indicator relevance of the second row, represented by integers 1 to 9, and the same applies to the other data elements; then the judgment matrix Perform consistency check, that is, check whether there is any logical contradiction in the judgment matrix to ensure that the judgment matrix The rationality of Normalization is performed to obtain the maximum eigenvalue of the correlation matrix and the corresponding weight matrix to reflect the relative importance of each data element in the correlation matrix, which is recorded as .

[0067] Step S32: Determine the tactical correlation between the two players in combination with the correlation matrix. The corresponding calculation formula is:

[0068] in, Indicates tactical relevance; Represents the correlation matrix.

[0069] It can be understood that through the above steps, the influence of the three data dimensions of spatial distance correlation, speed acceleration correlation and historical tactical correlation on the dynamic changes and tactical layout on the football field are obtained respectively. In order to be able to display the tactical deployment more intuitively, it is also possible to use graphics to represent it, and convert the abstract data into intuitive visual images, that is, to construct tactical graphics, so as to help coaches, players and analysts better understand the tactical intentions and the situation on the field, and then optimize the tactical layout and execution.

[0070] See also Figure 4 , which shows a schematic diagram of any possible initial tactical graph of a method for identifying tactical graphs on a football field based on tactical relevance provided by an embodiment of the present invention.

[0071] Furthermore, step S4 includes: Step S41: construct a tactical correlation graph based on the first frame, denoted as ,in, Represents the teams on a football field; represents the total number of teams on the football field; Indicates The collection of position data for all players on a team; Indicates The set of tactical correlations between any two players of a team is recorded as the edge set of the tactical correlation graph.

[0072] Specifically, according to the number of frames analyzed, a tactical correlation graph is constructed starting from the first frame, and then an initial possible tactical correlation graph in each frame is obtained, wherein two players form an edge, and the tactical correlation between the two players is used as the weight of the corresponding edge.

[0073] Step S42: Based on the edge set Select any vertex in the largest edge as the starting point and record it as the vertex , set the filtering threshold, from the edge set Select the included vertices , and obtain several polygons from the edges whose number of vertices is greater than the screening threshold.

[0074] Specifically, according to the edge with the greatest tactical relevance in the edge set obtained in the aforementioned step S41, any vertex of the two vertices is selected as the starting point, that is, vertex , also means starting point ; Based on the starting point More vertices are selected to construct a polygon. In this embodiment, the screening threshold is 3, that is, the vertices As the starting point, it is necessary to select more than or equal to 3 vertices to form a polygon. Otherwise, if the number of selected vertices is less than 3, it does not form a polygon. Then, all the selected vertices are sorted counterclockwise according to the polar angle, that is, every three consecutive points in the selected vertices are defined as , calculate the vector If these three outer products have the same sign, it means that the polygon is a convex polygon, recorded as , and similarly obtain the logical expression of each polygon in each frame.

[0075] Step S43: Calculate the average tactical relevance for any polygon, and the corresponding calculation formula is:

[0076]

[0077] in, represents the average tactical relevance of the polygons; represents the increase coefficient; Indicates the total number of players and balls in the current analyzed team; Represents the number of sides of the polygon; Represents the polygon The tactical relevance of an edge.

[0078] It is explained that if the number of sides constituting the polygon is large, the analysis will be more difficult and the tactical relevance will be higher, so it is proposed to increase the coefficient The average tactical relevance is corrected to make the obtained average tactical relevance more accurate, so as to improve the understanding ability of subsequent construction of tactical graphics.

[0079] Step S44: Sort the polygons in descending order according to the average tactical relevance, and obtain the first initial tactical graph in sequence until the first initial tactical graph is obtained. Initial tactical graph, wherein the first initial tactical graph is recorded as ,Will The player position data is from Delete Medium tactical relevance from , and process all polygons in the same way until the The collection of position data for all players in a team When the number of position data points in is less than or equal to 2.

[0080] Specifically, the average tactical relevance obtained above is sorted from large to small, and the one with the largest average tactical relevance is taken as the first initial tactical graph, which is recorded as , the player position data and the tactical relevance included therein are deleted from the data elements in the overall tactical relevance graph; the polygon whose average tactical relevance is slightly lower than that of the first initial tactical graph is recorded as the second initial tactical graph, that is , repeat the deletion step, and so on, until the position data of all players in the analyzed team in the total tactical correlation graph is less than and equal to 2 data elements, stop the operation of step S44, and obtain several initial tactical graphs, which are recorded as ,in, Indicates the total number of initial tactical graphs finally obtained.

[0081] Step S45: Merge all the processed initial tactical graphs to obtain a tactical graph of any frame, which is recorded as ,in, Indicates Frame Tactical graphics for each team; A collection representing the position data of all players in the initial tactical graph; Represents the set of tactical correlations between any two players in all initial tactical graphs.

[0082] It can be understood that the aforementioned steps S41 to S44 are for the initial tactical graph obtained for the current analysis frame, merging all the initial tactical graphs obtained, obtaining the tactical graph of the corresponding frame, and then obtaining the tactical graphs of all frames, that is, ,in, It can be explained that by constructing a tactical correlation graph and screening it, it is possible to accurately identify all polygons with the largest average tactical correlation, record them as the initial tactical graph, and merge them on this basis to obtain the tactical graph that actually exists on the court at every moment.

[0083] Understandably, firstly, a coordinate system is constructed to obtain the position data of the moving target, analyze the correlation between the spatial position, speed, acceleration and historical cooperation relationship between any two players, and determine the tactical correlation between the players based on the position data of the ball; by constructing the initial tactical graph, all polygons with the largest average tactical correlation can be accurately identified, and on this basis, they are merged to obtain the actual tactical graph corresponding to the team in each frame, which can effectively identify the tactics that the players may execute on the field and express them in an intuitive way; it is suitable for football training and competitions with complex positions, formations and tactics, and can deeply explore the tactical connection between players, accurately identify the tactical content of each moment, that is, each frame, and express it intuitively in a graphical way, providing a clearer display of on-field features.

[0084] An embodiment of the present invention also proposes a tactical graphic recognition system on a football field based on tactical relevance, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of a tactical graphic recognition method on a football field based on tactical relevance as described in any of the aforementioned embodiments are implemented.

[0085] It is to be noted that a tactical graphic recognition system on a football field based on tactical relevance has the same beneficial effects as the tactical graphic recognition method on a football field based on tactical relevance provided above, and will not be described in detail here.

[0086] It should be noted that the sequence of the above embodiments of the present invention is only for description and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the accompanying 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.

[0087] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

Claims

1. A method for identifying tactical graphics on a football field based on tactical relevance, characterized in that: The method comprises: Construct a coordinate system based on the football field and collect the position data of any moving target of the player and the ball in each frame; According to the position data, spatial distance correlation, speed acceleration correlation and historical tactical correlation are obtained in sequence to generate a correlation matrix; Assign weights to the spatial distance correlation, speed acceleration correlation and historical tactical correlation respectively to obtain a weight matrix, and determine the tactical correlation between any two players in combination with the correlation matrix; Construct a tactical correlation graph, and define the tactical correlation as the weight of the corresponding edge in the tactical correlation graph. Select any vertex in the edge with the largest weight as the starting point to obtain several polygons, and filter them. Merge the filtered polygons to obtain the tactical graph of any frame.

2. A method for identifying tactical graphics on a football field based on tactical relevance according to claim 1, characterized in that: Construct a coordinate system based on the football field to collect the position data of any moving target of the players and the ball, including: Based on the football field, a plane rectangular coordinate system is constructed with the lower left corner of the top view as the origin. The camera is used to collect the position data of any moving target of the player and the ball in each frame, which is recorded as ; in, Indicates the frame number. Indicates the total number of frames; represents the number of players, represents the total number of players; Indicates the team to which the players on the football field belong. Represents the total number of teams.

3. The method for identifying tactical graphics on a football field based on tactical relevance according to claim 1, characterized in that: According to the position data, spatial distance correlation, speed acceleration correlation and historical tactical correlation are obtained in turn to generate a correlation matrix, including: Based on the players' position data, the straight-line distance between any two players is obtained, a judgment threshold is set to determine the authenticity of the interaction between the two players, and the spatial distance correlation is calculated; The player's speed and acceleration are obtained according to the player's position data combined with the frame interval of each frame, and the speed angle and acceleration angle are respectively obtained based on the coordinate system, and the speed correlation and acceleration correlation are correspondingly calculated, and the speed correlation and acceleration correlation are combined to obtain the speed-acceleration correlation; Analyze the average tactical relevance of two players in the previous frame adjacent to the current frame, and obtain the historical tactical relevance through the contribution weight; A tactical correlation matrix is ​​constructed through spatial distance correlation, speed acceleration correlation and historical tactical correlation. The average distance between two players and the ball is calculated to determine the correction coefficient. The tactical correlation matrix is ​​corrected based on the correction coefficient to generate a correlation matrix.

4. A method for identifying tactical graphics on a football field based on tactical relevance according to claim 3, characterized in that: Based on the players' position data, the straight-line distance between any two players is obtained, a judgment threshold is set to determine the authenticity of the interaction between the two players, and the spatial distance correlation is calculated, including: Based on the players' position data, the straight-line distance between any two players is obtained. The corresponding calculation formula is: ； in, Indicates Players and Straight line distance between players; represents the total number of players; Set judgment threshold ,When the straight-line distance is less than the judgment threshold, it means that the interaction between the two players is real; when the straight-line distance is greater than the judgment threshold, it means that the interaction between the two players is not real, and the attenuation coefficient is constructed; Calculate the spatial distance correlation, the corresponding calculation formula is: ； in, Indicates Spatial distance correlation of frames; represents a constant; Represents the attenuation coefficient.

5. A method for identifying tactical graphics on a football field based on tactical relevance according to claim 4, characterized in that: The player's speed and acceleration are obtained according to the player's position data combined with the frame interval of each frame, and the speed angle and acceleration angle are obtained based on the coordinate system, and the speed correlation and acceleration correlation are calculated accordingly. The speed correlation and acceleration correlation are combined to obtain the speed acceleration correlation, including: According to the player's position data and the frame interval of each frame, the player's speed and acceleration are obtained, which are recorded as and ; Based on the coordinate system, the velocity angle and acceleration angle are obtained respectively, which are recorded as and ,and ; Calculate the speed correlation, the corresponding calculation formula is: ； in, Indicates Speed ​​relevance of frames; Indicates players; Indicates players; Calculate the acceleration correlation, the corresponding calculation formula is: ； in, Indicates Acceleration correlation of frames; The velocity correlation and acceleration correlation are combined to obtain the velocity-acceleration correlation. The corresponding calculation formula is: ； ； in, Indicates The velocity-acceleration correlation of the frame; express The minimum value in .

6. A method for identifying tactical graphics on a football field based on tactical relevance according to claim 5, characterized in that: Analyze the average tactical relevance of the two players in the previous frame adjacent to the current frame, and obtain the historical tactical relevance through the contribution weight. The corresponding calculation formula is: ； in, Indicates the historical-tactical relevance of the frame; Indicates The average tactical relevance of the two players in the frame; Represents the weight coefficient.

7. A method for identifying tactical graphics on a football field based on tactical relevance according to claim 6, characterized in that: The tactical correlation matrix is ​​constructed through spatial distance correlation, speed acceleration correlation and historical tactical correlation, the average distance between two players and the ball is calculated to determine the correction coefficient, and the tactical correlation matrix is ​​corrected based on the correction coefficient to generate a correlation matrix, including: Construct a tactical correlation matrix, recorded as ; Calculate the average distance between the two players and the ball. The corresponding calculation formula is: ,in, represents the average distance between the two players and the ball, Indicates The straight-line distance between the player and the ball; Indicates The straight-line distance between the player and the ball; Determine the correction coefficient, the corresponding calculation formula is: ,in, represents the correction factor; The tactical correlation matrix is ​​corrected based on the correction coefficient to generate the correlation matrix. The corresponding calculation formula is: ； in, represents the correlation matrix; , , They represent the corrected spatial distance correlation, speed acceleration correlation and historical tactical correlation respectively.

8. The method for identifying tactical graphics on a football field based on tactical relevance according to claim 1, characterized in that: Weights are assigned to the spatial distance correlation, speed acceleration correlation and historical tactical correlation respectively to obtain a weight matrix. The tactical correlation between any two players is determined by combining the correlation matrix, including: Determine the weight matrix, denoted as ,in, , , They represent the weights corresponding to the spatial distance correlation, speed acceleration correlation and historical tactical correlation respectively; Combined with the correlation matrix, the tactical correlation between two players is determined. The corresponding calculation formula is: ； in, Indicates tactical relevance; Represents the correlation matrix.

9. The method for identifying tactical graphics on a football field based on tactical relevance according to claim 1, characterized in that: Construct a tactical correlation graph, and define the tactical correlation as the weight of the corresponding edge in the tactical correlation graph. Select any vertex in the edge with the largest weight as the starting point to obtain several polygons, and filter them. Merge the filtered polygons to obtain the tactical graph of any frame, including: Based on the first frame, a tactical correlation graph is constructed, denoted as ,in, Represents the teams on a football field; represents the total number of teams on the football field; Indicates The collection of position data for all players on a team; Indicates The set of tactical correlations between any two players of a team is recorded as the edge set of the tactical correlation graph; According to the edge set Select any vertex in the largest edge as the starting point and record it as the vertex , set the filtering threshold, from the edge set Select the included vertices , and obtain several polygons from the edges whose vertex number is greater than the screening threshold; Calculate the average tactical relevance for any polygon, and the corresponding calculation formula is: ； ； in, represents the average tactical relevance of the polygons; represents the increase coefficient; Indicates the total number of players and balls in the current analyzed team; Represents the number of sides of the polygon; Represents the first The tactical relevance of the edge; Sort the polygons in descending order according to the average tactical relevance, and obtain the first initial tactical graph in sequence until the Initial tactical graph, wherein the first initial tactical graph is recorded as ,Will The player position data is from Delete Medium tactical relevance from , and process all polygons in the same way until the The collection of position data for all players in a team When the number of position data points in is less than or equal to 2; All the processed initial tactical graphs are merged to obtain the tactical graph of any frame, which is recorded as ,in, Indicates Frame Tactical graphics for each team; A collection representing the position data of all players in the initial tactical graph; Represents the set of tactical correlations between any two players in all initial tactical graphs.

10. A tactical pattern recognition system on a football field based on tactical relevance, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of a method for recognizing tactical graphics on a football field based on tactical relevance as described in any one of claims 1 to 9 are implemented.

Images