Golf swing analysis system and analysis method

Abstract

To provide an analysis system and an analysis method for a golf swing that can enhance analysis accuracy with a simple structure.SOLUTION: An analysis system for a golf swing uses a golf club 2 comprising a grip 21, a shaft 22, and a head 23. The analysis system includes a swing sensor 100 for measuring first data that is time-series data of at least one of angular velocity and acceleration of the golf club 2 during a golf swing, a ballistic sensor 200 for measuring second data that is data related to a ballistic trajectory of a ball 4 hit by the golf swing, and a processing device 300 for receiving the first data and the second data, and executing predetermined processing. The processing device 300 includes a feature quantity calculation unit for calculating a predetermined feature quantity from the first data, and an estimation unit for estimating an initial condition of the head during the golf swing by using the feature quantity and the second data.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present disclosure relates to a system and method for analyzing a golf swing. [Background technology]

[0002] In order to analyze a golf swing, a system has been proposed in which a high-precision camera or the like is used to directly capture images of the behavior of the head of a golf club during a swing (see, for example, Patent Document 1 below). [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Laid-Open No. 2007-167549 DISCLOSURE OF THE INVENTION [Problem to be solved by the invention]

[0004] However, the analytical device of Patent Document 1 has a problem in that the equipment is large-scale.

[0005] The present disclosure has been devised in view of the above problems, and has as its main object to provide a golf swing analysis system and analysis method that are simple in configuration and capable of analyzing a golf swing. [Means for solving the problem]

[0006] The present disclosure relates to a golf swing analysis system using a golf club having a grip, a shaft, and a head, including a swing sensor that measures first data which is time-series data of at least one of an angular velocity and an acceleration of the golf club during a golf swing, a trajectory sensor for measuring second data which is data related to a trajectory of a ball struck by the golf swing, and a processing device that receives the first data and the second data and executes predetermined processing. The processing device includes a feature quantity calculation unit that calculates a predetermined feature quantity from the first data, and an estimation unit that estimates an initial condition of the head during the golf swing using the feature quantity and the second data. It is a golf swing analysis system.

Advantages of the Invention

[0007] By adopting the above configuration, the golf swing analysis system of the present disclosure enables analysis of a golf swing with a simple configuration.

Brief Description of the Drawings

[0008]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Figure 11

Figure 12

Figure 13

Figure 14

[0009] Hereinafter, an embodiment of the present disclosure will be described with reference to the drawings. The specific configurations shown in the embodiments and drawings are for the purpose of understanding the contents of the present disclosure, and the present disclosure is not limited to the specific configurations shown. Furthermore, in multiple embodiments, the same or common elements are designated by the same reference numerals throughout the specification, and redundant explanations will be omitted.

[0010] Fig. 1 shows an overall configuration diagram of a golf swing analysis system 1 of this embodiment. Fig. 2 shows a block configuration diagram of the analysis system 1 of this embodiment. The analysis system 1 of this embodiment analyzes the swing of a golfer 3, which is useful for, for example, effectively fitting a golf club 2 or giving lessons to the golfer 3.

[0011] As shown in Figures 1 and 2, the analysis system 1 of this embodiment is for analyzing a golf swing by a golfer 3 using a golf club 2, and includes, for example, a swing sensor 100, a trajectory sensor 200, and a processing device 300.

[0012] [Golf Clubs] The golf club 2 has, for example, a grip 21, a shaft 22, and a head 23. In this embodiment, a wood-type golf club is shown as the golf club 2. In other embodiments, the golf club 2 may be an iron-type or a putter-type club.

[0013] [Swing sensor] The swing sensor 100 can measure first data, which is time-series data of at least one of the angular velocity and acceleration of the golf club 2 during a golf swing. As shown in FIG. 2 , the swing sensor of this embodiment includes an angular velocity sensor 101 and an acceleration sensor 102. Therefore, the swing sensor 100 of this embodiment can measure, as the first data, time-series data of both the angular velocity and acceleration of the golf club 2 during a golf swing. In another aspect, the swing sensor 100 may measure, as the first data, only one of the angular velocity and acceleration of the golf club 2 during a golf swing.

[0014] 1, for example, it is desirable that the swing sensor 100 be attachable to the golf club 2. In a preferred embodiment, the swing sensor 100 of this embodiment is detachable from the grip 21 or shaft 22 of the golf club 2. It is desirable that the swing sensor 100 be small and lightweight so as not to interfere with the swing motion of the golfer 3.

[0015] The swing sensor 100 of this embodiment measures first data related to a local coordinate system defined for the golf club 2. This coordinate system has orthogonal x-, y-, and z-axes. The z-axis coincides with the axial direction of the shaft 22, and the direction from the head 23 to the grip 21 is considered positive. The y-axis is a direction along the target ball flight line when the golf club 2 is addressed, and can also be considered the front-to-back direction of the head 23 (face-to-backface direction). On the y-axis, the direction toward the front (ball flight direction) is considered positive. The x-axis is a direction perpendicular to the y- and z-axes, and the direction from the heel side to the toe side of the head 23 is considered positive.

[0016] The swing sensor 100 of this embodiment can measure the angular velocity and acceleration around the above three axes as the first data respectively. FIGS. 3 and 4 are graphs showing the results of measuring the angular velocity and acceleration around the three axes with the angular velocity sensor 101 and the acceleration sensor 102 respectively for the swing of a certain golfer 3. The locations where large changes occur correspond to the moment when the ball is struck. The first data is acquired in time series at a predetermined sampling period (for example, 1 millisecond).

[0017] As shown in FIG. 2, the swing sensor 100 of this embodiment may further include a communication unit 103 for providing the first data to the processing device 300. The communication unit 103 is preferably a wireless method so as not to interfere with the swing operation, but a wired method using a cable may also be used. Further, the swing sensor 100 may be provided with a removable storage medium (not shown) instead of the communication unit 103 or together with the communication unit 103. In this case, the first data may be taken into the processing device 300 via the storage medium.

[0018] [Ballistic sensor] In the analysis system 1 of this embodiment, the golfer 3 is scheduled to actually strike the ball 4 by a golf swing. The ballistic sensor 200 of this embodiment can measure the second data which is data related to the trajectory of the ball struck by the golf swing to be analyzed. In this specification, the "data related to the trajectory of the ball" is sufficient as long as it is data for specifying the motion state of the ball 4 struck by the golf club, and includes, for example, at least one of ball speed, launch angle, spin angle, backspin and side spin, preferably a plurality of them.

[0019] In this embodiment, the trajectory sensor 200 is installed, for example, on the opposite side of the target ball flight line from the golfer 3. The trajectory sensor 200 incorporates, for example, a camera and a control device (not shown). The camera captures an image of the struck ball 4, and the control device analyzes the captured image data to measure the second data. Various commercially available trajectory measurement devices can be used as the trajectory sensor 200, and suitable devices are small and portable, such as "SkyTrak" (a registered trademark of SkyTrak, LLC).

[0020] 2, the trajectory sensor of this embodiment includes a ball speed measurement unit 201 for measuring the speed of the ball 4, a launch angle measurement unit 202 for measuring the launch angle of the ball 4, a swing angle measurement unit 203 for measuring the left / right swing angle of the ball 4 relative to the target flight line, a backspin measurement unit 204 for measuring the backspin of the ball 4, and a sidespin measurement unit 205 for measuring the sidespin of the ball 4. As such, the trajectory sensor 200 of this embodiment represents the most preferable one that can measure all five of the above-mentioned exemplary pieces of data related to the ball trajectory. In other aspects, the trajectory sensor 200 only needs to measure at least one of the above-mentioned five pieces of data, and preferably measures two or more.

[0021] The ballistic sensor 200 of this embodiment further includes a communication unit 206 for providing second data to the processing device 300. The communication unit 206 of this embodiment is a wireless system, but may also be a wired system using a cable. Furthermore, the ballistic sensor 200 may include a removable storage medium (not shown) in place of the communication unit 206, or in addition to the communication unit 206. In this case, the second data may be input to the processing device 300 via the storage medium.

[0022] [Processing equipment] The processing device 300 of the present embodiment receives first data and second data and executes a predetermined process. Such a processing device 300 is realized, for example, as various general-purpose personal computers, tablet computers, smartphones, and further as dedicated terminals. In the present embodiment, a desktop computer is illustrated in FIG. 1.

[0023] The processing device 300 of the present embodiment includes a display as a display unit 304 and a keyboard and a mouse as an input unit 305, respectively. Results of processes executed by the processing device 300 and the like are appropriately displayed on the display unit 304. Further, the input unit 305 can input information necessary for operating the processing device 300, instructions necessary for the displayed results, and the like.

[0024] As shown in FIG. 2, the processing device 300 of the present embodiment further includes a control unit 301, a storage unit 306, a feature amount calculation unit 302, an estimation unit 303, and a communication unit 307.

[0025] The communication unit 307 can receive the first data from the communication unit 103 of the swing sensor 100 and the second data from the communication unit 206 of the ballistic sensor 200, respectively. The communication unit 307 of the present embodiment is a wireless method, but a wired method using a cable may also be used. Further, the processing device 300 may be provided with a removable storage medium (not shown) instead of the communication unit 307 or together with the communication unit 307. In this case, the feature amount and the second data may be taken into the processing device 300 via the storage medium.

[0026] The storage unit 306 includes, for example, a magnetic storage unit or a non-volatile memory in which a program for causing the processing device 300 to execute a predetermined process is stored, and a volatile memory for temporarily storing working information. The control unit 301 executes a predetermined process according to the program stored in the storage unit 306. Further, the control unit 301 can store the processing result in the storage unit 306 or display it on the display unit 304.

[0027] [Feature Quantity Calculation Unit] The feature quantity calculation unit 302 can calculate a predetermined feature quantity from the first data. The feature quantity calculation unit 302 of the present embodiment receives the first data as shown in FIGS. 3 and 4, calculates the feature quantity, and stores this, for example, in the storage unit 306. The feature quantity calculation unit 302 is realized, for example, by causing the control unit 301 to function according to a program. In other aspects, the feature quantity calculation unit 302 may be implemented by various dedicated processors or the like.

[0028] For example, various indicators related to the swing of the golfer 3 can be adopted as the above-described feature quantities. Generally, when the swing of the golf club 2 changes, the hitting position of the ball 4 by the head 23 also changes. Further, the golf club 2 generates unique vibrations for each hitting position by the head 23. Therefore, the vibration of the golf club 2 that occurs after hitting the ball is a feature quantity related to the golf swing. In the present embodiment, paying attention to such a situation, a spectrogram is adopted as the feature quantity of the first data (the angular velocity and acceleration of the golf club 2).

[0029] The spectrogram is the result of calculating the frequency spectrum of the first data, which is time-series data. The spectrogram of the present embodiment includes the intensity as a signal component of the frequency of the angular velocity of the golf club 2. FIG. 5 shows an example of such a spectrogram. As shown in the upper part of FIG. 5, the feature quantity of the present embodiment includes the spectrogram (intensity) of the angular velocity of the golf club 2 about the x-axis, y-axis, and z-axis of the local coordinate system defined for the golf club 2. In the upper part of FIG. 5, each spectrogram is a three-dimensional graph in which the horizontal axis represents time, the vertical axis represents frequency, and the color density represents the intensity of the frequency. A darker color means a higher intensity of the frequency.

[0030] The range of application of the spectrogram is, for example, a predetermined time range including before and after the moment when the ball 4 is hit with the golf club 2. As shown in Fig. 3, the time when the ball 4 is hit is, for example, when a large change (peak) appears in the angular velocity of the golf club 2. Therefore, the range for calculating the spectrogram is extracted as a time range t1 of several milliseconds before and after the time of this peak, based on the time of this peak.

[0031] To analyze a golf swing, at least one feature of the first data is sufficient. To further improve the accuracy of the analysis, in a preferred embodiment, the feature of the first data further includes a spectrogram including a phase as a signal component of the frequency of the angular velocity of the golf club 2. An example of such a spectrogram is shown in the bottom part of Fig. 5.

[0032] The lower part of FIG. 5 shows a spectrogram (phase) of the angular velocity of the golf club 2 around the x-axis, y-axis, and z-axis of the local coordinate system defined for the golf club 2. In general, as the impact position between the head 23 and the ball 4 changes, the head 23 behaves by opening and closing, for example, around the axis of the shaft 22. This behavior is expressed as a change in the phase (phase angle) of the vibration of the golf club 2. Therefore, by adding a spectrogram that indicates a time change in the phase of the frequency as a feature, the accuracy of golf swing analysis can be further improved.

[0033] In the lower part of Figure 5, each spectrogram is a three-dimensional graph with the horizontal axis representing time, the vertical axis representing frequency, and the color depth representing phase. Darker colors indicate larger phases. Similar to the upper part of Figure 5, the time range of this spectrogram is a predetermined time range t1 that includes the time before and after the moment when the golf club 2 strikes the ball 4.

[0034] In this embodiment, since the first data also includes time-series data of the acceleration of the golf club 2 during a swing, the feature amount calculation unit 302 further calculates a spectrogram (intensity, phase) of the time-series data of the acceleration as well. This increases the number of explanatory variables when performing regression analysis of the features of the golf swing, thereby further improving the accuracy of the analysis of the golf swing.

[0035] The upper part of Fig. 6 shows a three-dimensional spectrogram graph with the horizontal axis representing time, the vertical axis representing frequency, and the color depth representing intensity, for the acceleration of the golf club 2. The lower part of Fig. 6 shows a three-dimensional spectrogram graph with the horizontal axis representing time, the vertical axis representing frequency, and the color depth representing phase, for the acceleration of the golf club 2.

[0036] As described above, the feature calculation unit 302 of this embodiment calculates feature quantities of 12 components from the first data obtained from one golf swing. However, the present disclosure is not limited to this example. For example, if the first data includes time-series data of only the angular velocity of the golf club 2, only the intensity spectrogram (three components around the x, y, and z axes) or only the phase spectrogram (three components around the x, y, and z axes) may be used as the feature quantity. Similarly, if the first data includes time-series data of only the acceleration of the golf club 2, only the intensity spectrogram (three components around the x, y, and z axes) or only the phase spectrogram (three components around the x, y, and z axes) may be used as the feature quantity.

[0037] [Estimation part] The estimation unit 303 of this embodiment can estimate the initial conditions of the head 23 using the feature amount calculated by the feature amount calculation unit 302 and the second data.

[0038] In this specification, the "initial conditions of the head" refers to information that specifies the state of the head 23 during a swing or the state of hitting the ball, and includes, for example, at least one of the head speed, face angle, approach angle, dynamic loft angle, blow angle, left / right impact point, and up / down impact point. The details of these are as follows:

[0039] "Head speed" refers to the speed F of the head 23 during a swing just before striking the ball. This speed F is defined by velocities Fx, Fy, and Fz in the directions of the axes of an XYZ coordinate system defined in a three-dimensional swing space. The X axis is horizontal and aligned with the target ball flight direction D, the Z axis is vertical, and the Y axis is perpendicular to both the X and Z axes. "Face angle" refers to the angle α of the face 23a relative to a vertical plane VP perpendicular to the target ball flight direction D, as viewed from a planar perspective of the swing. "Entry angle" refers to the angle β of the path K of the head 23 during a swing relative to the target ball flight direction D, as viewed from a planar perspective of the swing. As shown in FIG. 8, "dynamic loft angle" refers to the angle γ of the face 23a relative to the vertical plane VP, as viewed from a side of the swing. "Blow angle" refers to the angle δ of the path K of the head 23 during a swing relative to a horizontal plane HP, as viewed from a side of the swing. Of these initial conditions of the head, the "face angle α" and the "dynamic loft angle γ" change during the golf swing of the head 23, and therefore may be defined as values at a specific position of the head 23 during the swing.

[0040] Also, as shown in Figure 9, the "left and right impact points" and "up and down impact points" are the positions where the ball 4 is hit with the face 23a of the head 23, and respectively mean the X coordinate value and the Y coordinate value in the XY coordinate system with the area center of gravity FC of the face 23a as the origin.

[0041] Conventional golf swing estimation devices rely on data measured by a sensor attached to the golf club 2, but the analysis system 1 of this embodiment estimates the initial conditions of the head by further taking into account second data, i.e., data regarding the trajectory of the ball 4 hit by the golf swing.

[0042] A golf swing affects the bending and twisting of the shaft 22, the moving speed of the head 23, the orientation, angle, or position of the face 23a, and this influence is reflected in data regarding the trajectory of the hit ball 4, that is, ball speed, launch angle, spin axis, backspin, and side spin, etc. Therefore, by using both the feature amounts of the first data measured from the golf swing and the second data measured from the trajectory of the ball 4 affected by it, the analysis of the swing can be accurately performed without considering the characteristics of the shaft 22 and the head 23. Further, in the analysis system 1 of the present embodiment, since it is not necessary to directly observe the behavior of the head 23 of the golf club 2 during the swing, the initial conditions of the head can be accurately estimated simply and with high precision.

[0043] The estimation unit 303 is preferably configured using, for example, AI. The estimation unit 303 of the present embodiment employs a learned machine learning model. An example thereof is shown in FIG. 10.

[0044] As shown in FIG. 10, for example, the feature amount of the first data, the second data, and the initial conditions of the head are input as learning data to the estimation unit 303. Then, by using regression or the like in which the initial conditions of the head are the target variable and the feature amount of the first data and the second data are the explanatory variables, a machine learning model for outputting the initial conditions of the head is obtained. For the regression, in consideration of the fitting accuracy, for example, either a linear regression model or a non-linear regression model may be adopted.

[0045] The learning data is prepared by collecting hitting data in a plurality of golf swings. For each data, for each golf swing, the feature amount (spectrogram) of the first data, the second data, and the initial conditions of the head (for example, left and right hitting points) are created as a set. The initial conditions of the head can be obtained in advance, for example, by imaging the golf club 2 during the golf swing with a high-resolution camera.

[0046] In addition, by changing the initial conditions of the head of the learning data to any one of the head speed, face angle, approach angle, dynamic loft angle, blow angle, or up-and-down hitting, an inference model for estimating each of these can be obtained. In the analysis system 1 of the present embodiment, by inputting the feature amounts of the first data of the golf swing performed by the golfer 3 and the second data into the estimation unit 303 using the machine learning model, the initial conditions of the desired head can be estimated.

[0047] [Method for Analyzing Golf Swing] FIG. 11 is a flowchart for explaining the golf swing analysis method of the present embodiment. The golf swing analysis method of the present embodiment includes a step S1 of measuring first data that is time-series data of at least one of the angular velocity and acceleration of the golf club 2 during a golf swing, a step S2 of measuring second data that is data related to the trajectory of the ball 4 struck by the golf swing, and a processing step S3 of executing predetermined processing using the first data and the second data. Steps S1 and S2 can be respectively performed by the swing sensor 100 and the trajectory sensor 200 as already described.

[0048] In addition, the processing step S3 includes a calculation step S31 of calculating predetermined feature amounts from the first data, and an estimation step S32 of estimating the initial conditions of the head 23 using the feature amounts and the second data. These steps S31 and S32 can be performed by the processing device 300 as already described.

[0049] [Modification Example of Estimation Step] FIG. 12 shows a modification example of the estimation step S32. This modification example estimates the hitting information of the head 23 and information other than the hitting information as the initial conditions of the head 23. That is, this modification example can estimate at least two head initial conditions. Note that "hitting information" means the above-described left-and-right hitting and / or up-and-down hitting. Also, "information other than hitting information" means any one of the head speed, face angle, approach angle, dynamic loft angle, and blow angle.

[0050] In the estimation step S32 of this example, a first estimation step S321 for estimating hitting information using the feature amount of the first data and the second data, the hitting information estimated in the first estimation step S321, the feature amount of the first data, and the second data are used to estimate information other than the hitting information in a second estimation step S322. Therefore, in this modification example, when estimating the initial conditions of the head, information that has already been estimated is further considered. According to this, the estimation accuracy of information other than the hitting information is further improved. In the second estimation step S322, a machine learning model learned separately from the first estimation step S321 is adopted. This machine learning model is obtained by learning to estimate a desired head initial condition from the hitting information and information other than the hitting information.

[0051] As described above, the embodiments of the present disclosure have been described in detail. However, the present disclosure is not limited to the above specific disclosure, and various modifications can be made and implemented within the scope of the technical idea described in the claims.

Example

[0052] Hereinafter, more specific examples of the present disclosure will be described. It should be noted that the present disclosure is not limited to such examples. The main specifications of this example are as follows.

[0053] [Initial Conditions of the Head] As the initial conditions of the head, the head speed, face angle, approach angle, dynamic loft angle, blow angle, left - right hitting point, and up - down hitting point are adopted, and respective machine learning models are constructed.

[0054] [First Data] The angular velocity and acceleration of the golf club during the golf swing are respectively measured around the three axes of the local coordinate system.

[0055] [Feature Amount of the First Data] For the angular velocity and acceleration of the first data respectively, spectrograms (intensity, phase) are calculated (a total of 12 components).

[0056] [Second data] As the second data, five components of ball speed, launch angle, deflection angle, backspin and sidespin were measured.

[0057] [Machine learning model for estimation] As an example, a machine learning model for inferring left and right hitting points is described. First, a correlation analysis is performed between the feature amounts of the first data, the second data, and the left / right impact points as the initial conditions of the head. This correlation analysis is performed for each of the 12 spectrogram components of the feature amounts of the first data. Figure 13 is a graph showing an example of the analysis results. The graph in Figure 13 has frequency on the vertical axis, time on the horizontal axis, and p-value on the hue, with 0 on the horizontal axis representing the moment the ball is hit.

[0058] In Figure 13, it can be seen that the two regions enclosed by ellipses (for example, the region of frequencies of approximately 10 to 40 Hz and 50 to 100 Hz immediately after hitting the ball) have low p-values. Therefore, from the analysis results of Figure 13, several pieces of data with low p-values are extracted as primary training data as data with a high correlation with the left and right impact points. In this way, by selecting training data based on the p-value, it becomes possible to extract high-quality training data that is effective for estimating the initial conditions of the head (left and right impact points), and ultimately to perform efficient machine learning.

[0059] Next, as shown in FIG. 14, regression is performed using the training data selected by the p-value. In the regression, the feature quantities of the narrowed-down first data and the second data are used as explanatory variables, and the initial condition of the head (here, the left / right impact point) is used as the objective variable. In this example, a machine learning model for estimating the initial condition of the head (left / right impact point) is defined using lasso regression, which is a method of regularized linear regression. With this regression, explanatory variables with a regression coefficient of 0 are excluded, and explanatory variables with a regression coefficient other than 0 are adopted. This helps remove explanatory variables that do not contribute to estimating the left / right impact point and prevent overlearning.

[0060] Also, in this embodiment, after the regularized linear regression, a machine learning model for the final left and right hitting points was set using GPR (Gaussian process regression), which is a method of non-linear regression. In GPR, a new machine learning model is set to estimate the initial conditions of the head (here, the left and right hitting points), which are the target variables, using the features of the first data further narrowed down by the Lasso regression and the second data as explanatory variables. Note that if it can be evaluated that the machine learning model obtained by the Lasso regression has higher estimation accuracy than the machine learning model obtained by GPR, the machine learning model obtained by the Lasso regression may be adopted.

[0061] Using the same procedure, machine learning models for the initial conditions of other heads were set.

[0062] Table 1 shows the verification errors (RMSE) for the left and right hitting points, face angle, and approach angle as representative examples of the initial conditions of the head estimated in this embodiment. The verification error is calculated by the k-fold cross-validation method (k = 173). Also, as a comparative example, the results of an analysis system (comparative example) that calculates the initial conditions of the head by imaging the golf club head during the swing with a camera and analyzing the imaging data are shown together.

[0063]

Table 1

[0064] As is clear from Table 1, it was confirmed that this embodiment can maintain the same analysis accuracy as the conventional analysis system using camera data with a simple configuration without using large-scale equipment.

[0065] [This Disclosure] This disclosure includes the following.

[0066] This disclosure (1) is an analysis system for a golf swing using a golf club having a grip, a shaft, and a head, a swing sensor that measures first data, which is time-series data of at least one of the angular velocity and acceleration of the golf club during the golf swing, A trajectory sensor for measuring second data which is data related to the trajectory of a ball struck by the golf swing, and a processing device that receives the first data and the second data and executes a predetermined process, wherein the processing device, includes a feature amount calculation unit that calculates a predetermined feature amount from the first data, and an estimation unit that estimates the initial conditions of the head during the golf swing using the feature amount and the second data. It is an analysis system for golf swings.

[0067] The present disclosure (2) is the golf swing analysis system according to the present disclosure (1), wherein the feature amount is a spectrogram of the first data.

[0068] The present disclosure (3) is the golf swing analysis system according to the present disclosure (2), wherein the spectrogram includes the intensity of the frequency of at least one of the angular velocity and the acceleration.

[0069] The present disclosure (4) is the golf swing analysis system according to the present disclosure (2) or (3), wherein the spectrogram includes the phase of at least one of the angular velocity and the acceleration.

[0070] The present disclosure (5) is the golf swing analysis system according to any combination of the present disclosures (1) to (4), wherein the estimation unit is a learned machine learning model.

[0071] The present disclosure (6) is the golf swing analysis system according to the present disclosure (5), wherein the machine learning model is learned to output the initial conditions of the head from the feature amount and the second data.

[0072] The present disclosure (7) is the golf swing analysis system according to the present disclosure (5) or (6), wherein the machine learning model is a linear regression model or a non-linear regression model.

[0073] The present disclosure (8) is an analysis system for a golf swing in any combination with any one of the present disclosures (1) to (7), wherein the second data includes at least one of ball speed, launch angle, spin axis angle, backspin, and side spin of the hit ball.

[0074] The present disclosure (9) is an analysis system for a golf swing in any combination with any one of the present disclosures (1) to (8), wherein the initial conditions of the head include at least one of head speed, face angle, approach angle, dynamic loft angle, blow angle, left - right impact point, and up - down impact point.

[0075] The present disclosure (10) is a method for analyzing a golf swing using a golf club having a grip, a shaft, and a head, measuring first data that is time - series data of at least one of angular velocity and acceleration of the golf club during the golf swing; measuring second data that is data related to the trajectory of the ball struck by the golf swing; and including a processing step of performing predetermined processing using the first data and the second data, wherein the processing step includes a calculation step of calculating a predetermined feature amount from the first data, and an estimation step of estimating the initial conditions of the head using the feature amount and the second data. It is a method for analyzing a golf swing.

[0076] The present disclosure (11) is the method for analyzing a golf swing according to the present disclosure (10), wherein the estimation step is performed by a machine - learning model that has learned the initial conditions of the head from the feature amount and the second data.

[0077] The present disclosure (12) is such that the estimation step estimates the impact point information of the head and information other than the impact point information as the initial conditions of the head. The estimation step includes a first estimation step of estimating the hitting information using the feature amount and the second data, and a second estimation step of estimating information other than the hitting information using the hitting information estimated in the first estimation step, the feature amount, and the second data, which is the golf swing analysis method according to the present disclosure (10) or (11).

[0078] The present disclosure (13) is a processing device that analyzes a golf swing using a golf club having a grip, a shaft, and a head, and a communication unit for receiving first data that is time-series data of at least one of the angular velocity and acceleration of the golf club during a golf swing, and second data that is data related to the trajectory of a ball struck by the golf swing, a feature amount calculation unit that calculates a predetermined feature amount from the first data, and an estimation unit that estimates an initial condition of the head during the golf swing using the feature amount and the second data. It is a processing device for analyzing a golf swing.

[0079] The present disclosure (14) is a program for analyzing a golf swing using a golf club having a grip, a shaft, and a head, and a step of receiving first data that is time-series data of at least one of the angular velocity and acceleration of the golf club during a golf swing, and second data that is data related to the trajectory of a ball struck by the golf swing, a calculation step of calculating a predetermined feature amount from the first data, an estimation step of estimating an initial condition of the head during the golf swing using the feature amount and the second data, and It is a program for analyzing a golf swing that causes a computer to execute.

Description of Reference Numerals

[0080] 1 Analysis system 2. Golf clubs 4 balls 21 Grip 22 shaft 23 head 23a face 100 Swing Sensor 200 Ballistic Sensor 300 Processing Equipment 302 Feature Calculation Unit 303 Estimation Department

Claims

1. A golf swing analysis system using a golf club having a grip, a shaft, and a head, a swing sensor that measures first data which is time series data of at least one of the angular velocity and acceleration of the golf club during a golf swing, a trajectory sensor for measuring second data which is data related to the trajectory of the ball struck by the golf swing, including a processing device that receives the first data and the second data and executes predetermined processing, wherein the processing device includes a feature quantity calculation unit that calculates a predetermined feature quantity from the first data, and an estimation unit that estimates the initial conditions with the initial conditions of the head during the golf swing as the target variable and the feature quantity and the second data as explanatory variables by regression, wherein the initial conditions include at least the position where the ball is struck by the face of the head, a golf swing analysis system.

2. The golf swing analysis system according to claim 1, wherein the feature quantity is a spectrogram of the first data.

3. The golf swing analysis system according to claim 2, wherein the spectrogram includes the intensity of the frequency of at least one of the angular velocity and acceleration.

4. The golf swing analysis system according to claim 2 or 3, wherein the spectrogram includes the phase of at least one of the angular velocity and acceleration.

5. The golf swing analysis system according to any one of claims 1 to 4, wherein the estimation unit is a learned machine learning model.

6. The golf swing analysis system according to claim 5, wherein the machine learning model is learned to output the initial conditions of the head from the feature quantity and the second data.

7. The golf swing analysis system according to claim 5 or 6, wherein the machine learning model is a linear regression model or a non-linear regression model.

8. The golf swing analysis system according to any one of claims 1 to 7, wherein the second data includes at least one of the ball velocity, launch angle, spin axis angle, backspin, and side spin of the struck ball.

9. The golf swing analysis system according to any one of claims 1 to 8, wherein the initial conditions of the head include at least one of a face angle, an approach angle, a dynamic loft angle, a blow angle, a left and right hitting point as the hitting position, and an up and down hitting point as the hitting position.

10. A method for analyzing a golf swing using a golf club having a grip, a shaft, and a head, comprising: measuring first data that is time-series data of at least one of an angular velocity and an acceleration of the golf club during a golf swing; measuring second data that is data related to a trajectory of a ball struck by the golf swing; including a processing step of executing a predetermined process using the first data and the second data; The processing step includes: a calculation step of calculating a predetermined feature amount from the first data; an estimation step of estimating an initial condition of the head using the feature amount and the second data; The estimation step estimates the hitting point information of the head and information other than the hitting point information as the initial condition of the head; The estimation step includes a first estimation step of estimating the hitting point information using the feature amount and the second data; a second estimation step of estimating information other than the hitting point information using the hitting point information estimated in the first estimation step, the feature amount, and the second data; A method for analyzing a golf swing.

11. The golf swing analysis method according to claim 10, wherein the estimation step is performed by a machine learning model that learns the initial condition of the head from the feature amount and the second data.

12. A processing device for analyzing a golf swing using a golf club having a grip, a shaft, and a head, comprising: a communication unit for receiving first data that is time-series data of at least one of an angular velocity and an acceleration of the golf club during a golf swing, and second data that is data related to a trajectory of a ball struck by the golf swing; a feature amount calculation unit for calculating a predetermined feature amount from the first data; an estimation unit for estimating the initial condition by regression in which the initial condition of the head during the golf swing is a target variable and the feature amount and the second data are explanatory variables; The initial conditions include at least the position where the ball is struck on the face of the head. A processing device for analyzing a golf swing.

13. A program for analyzing a golf swing using a golf club having a grip, a shaft, and a head, the steps of receiving first data which is time-series data of at least one of the angular velocity and the acceleration of the golf club during the golf swing, and second data which is data related to the trajectory of the ball struck by the golf swing; a calculating step of calculating a predetermined feature amount from the first data; an estimating step of estimating the initial conditions, wherein the initial conditions include at least the position where the ball is struck on the face of the head, by regression with the initial conditions of the head during the golf swing as the objective variable and the feature amount and the second data as the explanatory variables; A program for analyzing a golf swing to be executed by a computer.

Images