Badminton racket use performance test system based on machine vision

Abstract

The invention discloses a badminton racket using performance testing system based on machine vision, and relates to the field of badminton racket performance testing. Structural parameters of a to-be-detected racket are obtained, the to-be-detected racket is driven to beat a badminton body in a static state in a uniform circular motion mode with the center of a holding part as the circle center, and ball hitting parameters at the moment when the string face of the to-be-detected racket makes contact with the badminton body for the first time in the beating process of the to-be-detected racket are collected; the method comprises the following steps: acquiring a process image of a to-be-tested racket and a badminton body from a contact state to a separation state in a badminton body hitting process at a fixed sampling frequency, calculating the maximum deformation of a racket rod of the to-be-tested racket, acquiring test parameters of a holding part of the to-be-tested racket, and constructing a neural network model; and outputting a mapping relation between the structure parameter and the batting parameter and the maximum deformation of the racket rod and the test parameter, and calculating a quantitative evaluation value of the use performance of the racket to be tested under the condition of the same influence factor by adopting a control comparison method.

Description

Technical Field

[0001] The invention relates to the field of badminton racket performance testing, in particular to a badminton racket performance testing system based on machine vision. Background Art

[0002] Badminton is a sport that involves the whole body. Long-term badminton training can enhance the participants' cardiopulmonary function, speed up nerve response, improve muscle coordination, and further enhance strength and speed. It has a broad audience base. The performance of a badminton racket is closely related to its structural size, material, craftsmanship and other factors. Good performance can help users achieve better sports results.

[0003] In the existing badminton racket performance index system, hardness is an important index for evaluating racket performance, and the hardness of the racket frame and shaft directly affects the control effect when hitting the ball. Under the same hitting conditions, the higher the hardness and the greater the strength, the less interference it has on the hitting, and it is more conducive to controlling the hitting. At present, the elasticity test method (QB / T2770-2006) is generally used to test the hardness of badminton rackets, and the bending stiffness EI is obtained as the calibration of its hardness.

[0004] As an evaluation characterization of the mechanical properties of a badminton racket, hardness has a great impact on the overall performance of the racket. However, in actual use, the performance of the racket is also affected by many other factors, such as the weaving form, weaving density, regional distribution, bonding, vibration during ball return, etc. A single one-dimensional index of racket hardness is difficult to accurately reflect its performance status during use. To this end, we propose a badminton racket performance test system based on machine vision. Summary of the invention

[0005] The main purpose of the present invention is to provide a badminton racket performance testing system based on machine vision, which can effectively solve the problems in the background technology.

[0006] In order to achieve the above object, the technical solution adopted by the present invention is:

[0007] A badminton racket performance testing system based on machine vision, including a feature parameter acquisition module, a racket clamping module, an image acquisition module, a hitting data acquisition module, a test data acquisition module, a motion analysis module, and a motion simulation module;

[0008] The characteristic parameter acquisition module is used to acquire the structural parameters of the racket to be tested, and the structural parameters include the hardness value of the racket shaft, the hardness value of the racket frame, the string surface weaving density, and the string surface tightness;

[0009] The racket clamping module is used to rigidly clamp the gripping portion of the racket to be tested, and drive the racket to be tested to hit the badminton body in a stationary state, wherein the hitting action is a uniform circular motion with the center of the gripping portion as the center of the circle;

[0010] The data acquisition module is used to collect the hitting parameters when the string surface of the racket to be tested first contacts the badminton body during the uniform circular motion of the racket to be tested. The hitting parameters include hitting angle, hitting force, and hitting speed. The hitting angle is the angle between the vertical plane where the rotation center is located and the plane where the racket frame center of the racket to be tested is located. The hitting speed is determined according to the following formula, specifically:

[0011]

[0012] In the formula, v q It is expressed as the hitting speed value of the qth hitting action; R q It is represented as the distance between the center of the grip and the point of the hitting area during the qth hitting action; ω q It is expressed as the angular velocity value of the circular motion during the qth striking action;

[0013] The image acquisition module is used to acquire, at a fixed sampling frequency, an image of a process in which the racket to be tested and the badminton body change from a contact state to a separation state during the hitting process of the badminton body;

[0014] The motion analysis module is used to calculate the maximum deformation of the racket shaft of the racket to be tested according to the acquired process image. The calculation formula of the maximum deformation of the racket shaft is:

[0015]

[0016] Where A represents the maximum deformation of the racket during striking; L i It is expressed as the distance between the i-th reference node of the racket to be tested and the rotation center of the grip in the natural state; L' i It is expressed as the distance between the i-th reference node of the racket to be tested and the line connecting the rotation center of the grip during the hitting process, where the distance L between the i-th reference node of the racket to be tested and the line connecting the rotation center of the grip in the natural state is i It is determined according to the following formula, specifically:

[0017]

[0018] Wherein, L represents the distance between the rotation center of the grip of the racket to be tested and its farthest end in the natural state;

[0019] The test data acquisition module is used to obtain the test parameters of the grip of the racket to be tested during the hitting process of the badminton body, and the test parameters include the maximum vibration frequency and the maximum force value;

[0020] The motion simulation module is used to construct a neural network model with structural parameters and hitting parameters as inputs and with the maximum deformation of the racket shaft and test parameters as outputs, and outputs the mapping relationship between the structural parameters and hitting parameters and the maximum deformation of the racket shaft and the test parameters according to the obtained network model, wherein the neural network model is a three-layer structured BP neural network model of input layer-hidden layer-output layer, wherein the number of neurons in the input layer is equal to the type of input parameters, the number of neurons in the output layer is equal to the type of output parameters, and the number of neurons in the hidden layer is determined according to the following formula, specifically:

[0021]

[0022] Among them, h is the number of neurons in the hidden layer; It is represented by rounding W upwards; m is the number of nodes in the input layer, n is the number of nodes in the output layer, and a is an integer from 1 to 9.

[0023] The testing method of the system comprises the following steps:

[0024] S1: Obtaining the structural parameters of the racket to be tested, including the hardness of the racket shaft, the hardness of the racket frame, the density of the string surface, and the tightness of the string surface;

[0025] S2: rigidly clamping the grip of the racket to be tested, driving the racket to be tested to perform uniform circular motion with the grip as the center, and hitting the badminton body in a stationary state during the rotation process;

[0026] S3: measuring the hitting angle, hitting force and hitting speed at the moment when the string surface of the racket to be tested first contacts the badminton body during hitting;

[0027] S4: collecting images of the process from the contact state to the separation state of the racket to be tested and the badminton body during the hitting process of the badminton body at a fixed sampling frequency;

[0028] S5: Calculating the maximum deformation of the racket shaft of the racket to be tested according to the acquired process image;

[0029] S6: obtaining the maximum vibration frequency and the maximum force value of the grip of the racket to be tested during the hitting process of the badminton body;

[0030] S7: taking the acquired structural parameters and hitting parameters as input and the maximum deformation of the racket shaft and the test parameters as output, constructing a neural network module, and outputting a mapping relationship between the structural parameters and hitting parameters and the maximum deformation of the racket shaft and the test parameters according to the acquired network model;

[0031] S8: Based on the acquired mapping relationship, the control comparison method is used to calculate the quantitative evaluation value of the performance of the racket to be tested under the same influencing factors. The expression of the calculation model is:

[0032]

[0033] In the formula, Uv represents the quantitative evaluation value of performance; It is expressed as when the t-th structural parameter and the r-th hitting parameter are fixed values, the performance quantification evaluation value Uv is equal to the constant G; v k is expressed as the kth evaluation parameter, where the evaluation parameters include the maximum deformation of the racket shaft, the maximum vibration frequency and the maximum force value of the grip of the racket to be tested during the hitting of the badminton body, λ k is represented as the weight value of the kth evaluation parameter, and λ 1 / λ 2 / λ 3 Both∈(0,1).

[0034] The present invention has the following beneficial effects:

[0035] Compared with the prior art, the technical solution of the present invention obtains the structural parameters of the racket to be tested, including the hardness value of the racket shaft, the hardness value of the racket frame, the density of the string surface weaving, and the tightness of the string surface, and rigidly clamps the grip of the racket to be tested, drives the racket to be tested to perform uniform circular motion with the grip as the center, and hits a badminton body in a stationary state during the rotation process, and measures the hitting angle, hitting force, and hitting speed values ​​at the moment when the string surface of the racket to be tested and the badminton body first contact during the hitting process, collects the process image of the racket to be tested and the badminton body from the contact state to the separation state during the hitting process of the badminton body at a fixed sampling frequency, and calculates the maximum deformation of the racket shaft of the racket to be tested according to the acquired process image , the maximum vibration frequency and maximum force value of the grip of the racket to be tested during the hitting of the badminton body are obtained, the obtained structural parameters and hitting parameters are used as input, and the maximum deformation of the racket shaft and the test parameters are used as output, a neural network module is constructed, and the mapping relationship between the obtained network model output structural parameters and hitting parameters and the maximum deformation of the racket shaft and the test parameters is obtained. According to the obtained mapping relationship, the control comparison method is used to calculate the quantitative evaluation value of the use performance of the racket to be tested under the same influencing factors. By simulating the hitting action, multi-dimensional dynamic parameters are obtained as the evaluation basis for the use performance of the badminton racket, which can truly and accurately reflect its performance status during use. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 The overall structure diagram of the badminton racket performance testing system based on machine vision of the present invention;

[0037] Figure 2 It is a flowchart of the implementation steps of the test system;

[0038] Figure 3 A schematic diagram of the hitting action process of the racket to be tested;

[0039] Figure 4 is a schematic diagram of reference node distribution;

[0040] Figure 5 Schematic diagram of the neural network structure constructed for the present invention. DETAILED DESCRIPTION

[0041] The present invention will be further described below in conjunction with specific implementation methods, wherein the accompanying drawings are only used for exemplary descriptions and represent only schematic diagrams rather than actual drawings, and should not be understood as limiting the present invention. In order to better illustrate the specific implementation methods of the present invention, some parts of the accompanying drawings may be omitted, enlarged or reduced, and do not represent the size of the actual product.

[0042] Example 1

[0043] The specific implementation process of the technical solution of the present invention includes the following steps:

[0044] Step 1: Obtain the structural parameters of the racket to be tested, including the hardness value of the racket shaft, the hardness value of the racket frame, the density of the string surface weaving, and the tightness of the string surface;

[0045] It should be noted that, in this embodiment, two methods are provided for measuring the hardness of the badminton racket shaft and the racket frame. Method 1: elasticity test method (QB / T2770-2006), the test method is: take a fixed distance, apply a static load force at the midpoint, measure the displacement of the midpoint, and determine the hardness of the racket shaft according to the displacement; Method 2: use its bending stiffness EI to characterize the hardness of the badminton racket shaft and racket frame, and measure by applying a load to the badminton racket shaft / frame. The calculation formula is: EI=mf 2 π 2 l 3 / 12, where m is mass, unit is g, f is the vibration frequency value when the load is applied, and l is the length value;

[0046] Step 2: Rigidly clamp the grip of the racket to be tested, and drive the racket to be tested to make uniform circular motion with the grip as the center, as shown in the figure. Figure 3 As shown, during the rotation, the badminton body in a stationary state is struck;

[0047] Step 3: Measure the hitting angle, hitting force and hitting speed at the moment when the string surface of the racket to be tested first contacts the badminton body during the hitting process, where the hitting angle is the angle between the vertical plane where the rotation center is located and the plane where the center of the racket frame of the racket to be tested is located, and the hitting speed is determined according to the following formula, specifically:

[0048]

[0049] In the formula, v q It is expressed as the hitting speed value of the qth hitting action; R q It is represented as the distance between the center of the grip and the point of the hitting area during the qth hitting action; ω q It is expressed as the angular velocity value of the circular motion during the qth striking action;

[0050] Step 4: Collecting images of the process from the contact state to the separation state of the racket to be tested and the badminton body during the hitting process of the badminton body at a fixed sampling frequency;

[0051] Step 5: Calculate the maximum deformation of the racket shaft of the racket to be tested according to the acquired process image. The calculation formula is:

[0052]

[0053] Where A represents the maximum deformation of the racket during striking; L i It is expressed as the distance between the i-th reference node of the racket to be tested and the rotation center of the grip in the natural state; L' i It is expressed as the distance between the i-th reference node of the racket to be tested and the line connecting the rotation center of the grip during the hitting process, as shown in the attached figure. Figure 4 The reference node distribution diagram is shown in FIG. 1 , where the distance L between the i-th reference node of the racket to be tested and the rotation center of the grip is i It is determined according to the following formula, specifically:

[0054]

[0055] Wherein, L represents the distance between the rotation center of the grip of the racket to be tested and its farthest end in the natural state;

[0056] Step 6: Obtain the maximum vibration frequency and maximum force value of the grip of the racket to be tested during the hitting process of the badminton body;

[0057] Step 7: Take the obtained structural parameters and hitting parameters as input, and the maximum deformation of the racket shaft and the test parameters as output, and build a neural network module. According to the obtained network model output, the mapping relationship between the structural parameters and hitting parameters and the maximum deformation of the racket shaft and the test parameters is constructed. The neural network model is a three-layer structured BP neural network model of input layer-hidden layer-output layer, as shown in the attached figure. Figure 5 As shown, the number of neurons in the input layer is equal to the type of input parameters, the number of neurons in the output layer is equal to the type of output parameters, and the number of neurons in the hidden layer is determined according to the following formula, specifically:

[0058]

[0059] Among them, h is the number of neurons in the hidden layer; It is represented by rounding W upwards; m is the number of neurons in the input layer, n is the number of neurons in the output layer, and a is an integer from 1 to 9;

[0060] It should be noted that in this model, the number of neurons in the input layer is m=7, the number of neurons in the output layer is n=3, and in this embodiment, a=5, then the number of neurons in the hidden layer is Rounding up, we have h=9, and the neural network model constructed in this embodiment is a three-layer structured BP neural network model with 7 input layer neurons, 9 hidden layer neurons, and 3 output layer neurons;

[0061] Step 8: Based on the acquired mapping relationship, the control comparison method is used to calculate the quantitative evaluation value of the performance of the racket to be tested under the same influencing factors. The expression of the calculation model is:

[0062]

[0063] In the formula, Uv represents the quantitative evaluation value of performance; It is expressed as when the t-th structural parameter and the r-th hitting parameter are fixed values, the performance quantification evaluation value Uv is equal to the constant G; v k is expressed as the kth evaluation parameter, where the evaluation parameters include the maximum deformation of the racket shaft, the maximum vibration frequency and the maximum force value of the grip of the racket to be tested during the hitting of the badminton body, λ k is represented as the weight value of the kth evaluation parameter, and λ 1 / λ 2 / λ 3 All∈(0,1);

[0064] It should be noted that when evaluating the performance of two different badminton rackets, when the control structure parameters and the hitting parameters are at the same level, if the weighted value of the maximum deformation of the racket shaft, the maximum vibration frequency of the grip of the racket to be tested during the hitting of the badminton body and the maximum force value is smaller, the performance is better, otherwise, the performance is worse. Similarly, when it is necessary to compare a certain evaluation index, the values ​​of the remaining index parameters can be controlled at the same level, so as to calculate the performance of different badminton rackets under the same influencing factors.

[0065] The above shows and describes the basic principles and main features of the present invention and the advantages of the present invention. It should be understood by those skilled in the art that the present invention is not limited to the above embodiments. The above embodiments and descriptions are only for explaining the principles of the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, which fall within the scope of the present invention to be protected. The scope of protection of the present invention is defined by the attached claims and their equivalents.

Claims

1. A badminton racket performance testing system based on machine vision, characterized in that: It includes a characteristic parameter acquisition module, a racket clamping module, an image acquisition module, a hitting data acquisition module, a test data acquisition module, a motion analysis module, and a motion simulation module; The characteristic parameter acquisition module is used to acquire the structural parameters of the racket to be tested, wherein the structural parameters include the hardness value of the racket shaft, the hardness value of the racket frame, the string surface weaving density, and the string surface tightness; The racket clamping module is used to rigidly clamp the gripping portion of the racket to be tested, and drive the racket to be tested to hit the badminton body in a stationary state, wherein the hitting action is a uniform circular motion with the center of the gripping portion as the center of the circle; The data acquisition module is used to collect the hitting parameters when the string surface of the racket to be tested first contacts the badminton body during the uniform circular motion of the racket to be tested, and the hitting parameters include hitting angle, hitting force, and hitting speed; The image acquisition module is used to acquire, at a fixed sampling frequency, an image of a process in which the racket to be tested and the badminton body change from a contact state to a separation state during the hitting process of the badminton body; The motion analysis module is used to calculate the maximum deformation of the racket shaft of the racket to be tested according to the acquired process image; The test data acquisition module is used to obtain the test parameters of the grip of the racket to be tested during the hitting process of the badminton body, and the test parameters include the maximum vibration frequency and the maximum force value; The motion simulation module is used to construct a neural network model with structural parameters and hitting parameters as input and maximum deformation of the racket shaft and test parameters as output, and outputs a mapping relationship between the structural parameters and hitting parameters and the maximum deformation of the racket shaft and test parameters based on the obtained network model.

2. The badminton racket performance testing system based on machine vision according to claim 1, characterized in that: The calculation formula for the maximum deformation of the racket rod is: Where A represents the maximum deformation of the racket during striking; L i It is expressed as the distance between the i-th reference node of the racket to be tested and the rotation center of the grip in the natural state; L' i It is expressed as the distance between the i-th reference node of the racket to be tested and the rotation center of the grip during the hitting process.

3. The badminton racket performance testing system based on machine vision according to claim 1, characterized in that: The neural network model is a three-layer BP neural network model of input layer-hidden layer-output layer, wherein the number of neurons in the input layer is equal to the type of input parameters, the number of neurons in the output layer is equal to the type of output parameters, and the number of neurons in the hidden layer is determined according to the following formula, specifically: Among them, h is the number of neurons in the hidden layer; It is represented by rounding W upwards; m is the number of nodes in the input layer, n is the number of nodes in the output layer, and a is an integer from 1 to 9.

4. The badminton racket performance testing system based on machine vision according to claim 2 is characterized in that: The distance L between the i-th reference node of the racket to be tested and the rotation center of the grip i It is determined according to the following formula, specifically: Wherein, L represents the distance between the rotation center of the grip of the racket to be tested and its farthest end in the natural state.

5. The badminton racket performance testing system based on machine vision according to claim 1, characterized in that: The hitting angle is the angle between the vertical plane where the rotation center is located and the plane where the center of the racket frame of the racket to be tested is located. The hitting speed is determined according to the following formula, specifically: In the formula, v q It is expressed as the hitting speed value of the qth hitting action; R q It is represented as the distance between the center of the grip and the point of the hitting area during the qth hitting action; ω q It is expressed as the angular velocity value of the circular motion during the qth striking action.

6. The badminton racket performance testing system based on machine vision according to claim 1, characterized in that: The testing method of the system comprises the following steps: S1: Obtaining the structural parameters of the racket to be tested, including the hardness of the racket shaft, the hardness of the racket frame, the density of the string surface, and the tightness of the string surface; S2: rigidly clamping the grip of the racket to be tested, driving the racket to be tested to perform uniform circular motion with the grip as the center, and hitting the badminton body in a stationary state during the rotation process; S3: measuring the hitting angle, hitting force and hitting speed at the moment when the string surface of the racket to be tested first contacts the badminton body during hitting; S4: collecting images of the process from the contact state to the separation state of the racket to be tested and the badminton body during the hitting process of the badminton body at a fixed sampling frequency; S5: Calculating the maximum deformation of the racket shaft of the racket to be tested according to the acquired process image; S6: obtaining the maximum vibration frequency and the maximum force value of the grip of the racket to be tested during the hitting process of the badminton body; S7: taking the acquired structural parameters and hitting parameters as input and the maximum deformation of the racket shaft and the test parameters as output, constructing a neural network module, and outputting a mapping relationship between the structural parameters and hitting parameters and the maximum deformation of the racket shaft and the test parameters according to the acquired network model; S8: Based on the acquired mapping relationship, the control comparison method is used to calculate the quantitative evaluation value of the performance of the racket to be tested under the same influencing factors. The expression of the calculation model is: In the formula, Uv represents the quantitative evaluation value of performance; It is expressed as when the t-th structural parameter and the r-th hitting parameter are fixed values, the performance quantification evaluation value Uv is equal to the constant G; v k is expressed as the kth evaluation parameter, where the evaluation parameters include the maximum deformation of the racket shaft, the maximum vibration frequency and the maximum force value of the grip of the racket to be tested during the hitting of the badminton body, λ k is represented as the weight value of the kth evaluation parameter, and λ1 / λ2 / λ3 are all ∈(0,1).

Images