Swing analysis device and program

Abstract

This invention provides a swing analysis device and program that can accurately determine the movement and trajectory of the club head face using existing ballistics measurement devices, without requiring the installation of a camera to film the swing from above. [Solution] The system includes a feature acquisition unit 21 that acquires multiple feature quantities at the moment when the club head 41a of the golf club 41 collides with the golf ball 42 when the golf club 41 is swung, and an estimation unit 22 that estimates at least one of the temporal change in the angle of the face of the club head 41a and the movement trajectory of the club head 41a based on the multiple feature quantities acquired by the feature acquisition unit 21.

Description

Technical Field

[0001] The present invention relates to a swing analysis device and a program for analyzing the temporal changes and movement trajectories of the face surface of a club head during the impact of a golf club and the swing before and after the impact.

Background Art

[0002] Conventionally, various devices have been proposed for photographing a golfer's swing and providing the photographed information. By providing the photographed information of the swing to the golfer, it is possible to promote the improvement of golf and to promote the selection of a golf club suitable for the golfer.

[0003] As the above-described device, for example, in Patent Document 1, a golf club and a golf ball are photographed from above when the golf club is swung, the face surface of the club head included in each photographed image is detected, and a line segment representing the detected plurality of face surfaces is displayed. By displaying a line segment representing the face surface in this way, it is possible to recognize the opening of the face surface during the impact and the swing before and after the impact.

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0005] Here, important elements of a golfer's swing include the movement of the clubhead face and the trajectory of the clubhead during and around impact. By recognizing the movement and trajectory of the clubhead face during and around impact, it is possible to understand the characteristics of a golfer's swing and select a golf club that matches those characteristics.

[0006] While the device described in Patent Document 1 above can display line segments representing the club head face and display movement trajectories, it requires a camera to film the swing from above. This results in a large device, and depending on the installation environment, it may be difficult to install the camera to film from above. Furthermore, it incurs additional construction time and costs.

[0007] In view of the above problems, the present invention aims to provide a swing analysis device and program that can accurately determine the movement and trajectory of the club head face using existing ballistic measurement devices, without requiring the installation of a camera that photographs the swing from above. [Means for solving the problem]

[0008] The swing analysis device of the present invention comprises a feature acquisition unit that acquires a plurality of feature quantities at the moment when the club head of the golf club collides with the golf ball when the golf club is swung, and an estimation unit that estimates at least one of the temporal change in the angle of the club head's face and the movement trajectory of the club head based on the plurality of feature quantities acquired by the feature acquisition unit. [Effects of the Invention]

[0009] According to the swing analysis device of the present invention, when a golf club is swung, multiple feature quantities are acquired at the moment the club head of the golf club collides with the golf ball, and based on these multiple feature quantities, at least one of the temporal change in the angle of the club head's face and the movement trajectory of the club head is estimated. Therefore, by acquiring the above-mentioned feature quantities using existing ballistic measurement devices, the movement of the club head's face and its movement trajectory can be determined with high accuracy without installing a camera that films the swing from above. [Brief explanation of the drawing]

[0010] [Figure 1] This figure shows a schematic configuration of a golf impact analysis system using one embodiment of the display control device of the present invention. [Figure 2] A flowchart illustrating the processing flow of the golf impact analysis system shown in Figure 1. [Figure 3] This figure shows an example of projected images of line segments representing multiple clubfaces and line segments representing the clubhead's movement trajectory, estimated using eight feature quantities measured by a ballistic measurement device. [Figure 4] This figure shows an example of projected images of line segments representing multiple clubfaces and line segments representing the clubhead's movement trajectory, estimated using five feature quantities measured by a ballistics measurement device. [Figure 5] This figure shows an example of projected images of line segments representing multiple clubfaces and line segments representing the clubhead's movement trajectory, estimated using four feature quantities measured by a ballistic measurement device. [Modes for carrying out the invention]

[0011] The following describes in detail a golf impact analysis system using one embodiment of the swing analysis device of the present invention, with reference to the drawings. The golf impact analysis system of this embodiment is characterized by its method for estimating the temporal change in the angle of the club head face and the trajectory of the club head's movement when a golf club is swung, but first, the golf impact analysis system as a whole will be described. Figure 1 is a schematic diagram of the golf impact analysis system 1 of this embodiment.

[0012] As shown in Figure 1, the golf impact analysis system 1 of this embodiment comprises a ball flight measurement device 10, a control device 20, and a projection device 30. The ball flight measurement device 10 and the control device 20, and the control device 20 and the projection device 30 are connected via wired or wireless communication, and are configured to allow the exchange of various signals.

[0013] The ball flight measurement device 10 measures eight feature quantities at the time of impact when the golfer 40 swings the golf club 41 and hits the golf ball 42: the speed of the golf ball 42, launch direction, sidespin, head speed of the club head 41a, club path, face-to-target, face-to-path, and point of impact. In addition to the above eight feature quantities, the ball flight measurement device 10 can acquire more than ten other measurement items, but in this embodiment, these are not used in the estimation process of face plane and trajectory information, which will be described later, so their explanation is omitted.

[0014] The speed of the golf ball 42 is the speed of the golf ball 42 measured immediately after the club head 41a impacts the golf ball 42. The launch direction is the direction in which the golf ball 42 flies immediately after the club head 41a impacts the golf ball 42.

[0015] Sidespin is the number of rotations of the golf ball 42 immediately after the club head 41a impacts the golf ball 42.

[0016] The head speed of the club head 41a is the moving speed of the club head 41a at the time when the club head 41a impacts the golf ball 42.

[0017] The club path is the trajectory of the club head 41a immediately before the club head 41a and the golf ball 42 meet impact.

[0018] Face-to-target is the orientation of the face surface of the club head 41a with respect to the target line. The target line is a straight line that intersects the golf ball 42 as shown in, for example, FIG. 1.

[0019] Face-to-path is the degree of opening and closing of the face surface of the club head 41a with respect to the club path.

[0020] The impact point is the position where the face surface of the club head 41a and the golf ball 42 contacted when the club head 41a and the golf ball 42 impacted each other.

[0021] As the trajectory measurement device 10, for example, GCQuad (manufactured by Foresight Sports) can be used. GCQuad can measure the above eight feature amounts by photographing the moment of impact between the club head of the golf club 41 and the golf ball with four cameras. However, the trajectory measurement device 10 is not limited to GCQuad, and other existing devices can be used.

[0022] Also, instead of measuring the above eight feature amounts with one trajectory measurement device 10, the eight feature amounts may be measured using a plurality of existing trajectory measurement devices 10. For example, golf ball trajectory measuring devices using various technologies such as general-purpose infrared rays, X-band radars, K-band radars, lasers, stereo cameras, and machine vision, or measuring devices for performing three-dimensional analysis of the club head 41a can be used.

[0023] The control device 20 is composed of a computer and includes hardware such as a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), semiconductor memory such as ROM (Read Only Memory) and RAM (Random Access Memory), storage such as a hard disk, and a communication interface. In this embodiment, the control device 20 corresponds to the swing analysis device of the present invention.

[0024] The control device 20 includes a feature acquisition unit 21, an estimation unit 22, a control unit 23, a display unit 24, and an input unit 25.

[0025] An embodiment of the swing analysis program of the present invention is installed in the semiconductor memory or hard disk of the control device 20. The feature acquisition unit 21, estimation unit 22, and control unit 23 described above function as a result of this swing analysis program being executed by the CPU and GPU. In this embodiment, all the functions of the above-described units are performed by the swing analysis program; however, the embodiment is not limited to this, and some or all of the functions may be configured using hardware such as an ASIC (Application Specific Integrated Circuit), FPGA (Field-Programmable Gate Array), or other electrical circuits.

[0026] The following describes each part of the control device 20 in detail.

[0027] The feature acquisition unit 21 acquires multiple feature quantities at the moment when the club head 41a of the golf club 41 collides with the golf ball 42 (the moment of impact) when the golf club 41 is swung. Specifically, the feature acquisition unit 21 in this embodiment acquires eight features measured by the ballistic measurement device 10 described above. When the eight feature quantities are acquired, the coordinates of the tee position (installation position P shown in Figure 1) in the ground space coordinates are also acquired.

[0028] The estimation unit 22 estimates the temporal change in the angle of the clubhead 41a's face and the movement trajectory of the clubhead 41a based on a plurality of features acquired by the feature acquisition unit 21. The angle of the clubhead 41a's face is the angle of the clubhead 41a's face when viewed from above during the swing, and the movement trajectory of the clubhead 41a is the movement trajectory of the clubhead 41a when viewed from above during the swing.

[0029] Specifically, the estimation unit 22 of this embodiment has a learning model obtained by machine learning in advance, which involves the relationship between the eight feature quantities acquired in advance and the temporal change in the angle of the clubface during the swing at the time the feature quantities were acquired, and the movement trajectory of the club head.

[0030] The learning model is machine-learned using techniques such as CNN (Convolutional Neural Network), but the machine learning method is not limited to this, and other known methods can be used.

[0031] The estimation unit 22 then inputs the eight features acquired by the feature acquisition unit 21 to the learning model to estimate the temporal change in the angle of the club head 41a's face and the movement trajectory of the club head 41a. In this process, the coordinates of the tee's position (installation position P shown in Figure 1) are also used.

[0032] In other words, the estimation unit 22 uses eight previously acquired features as explanatory variables and a pre-trained machine learning model, with the temporal change in the angle of the clubface and the trajectory of the clubhead movement at the time the eight features were acquired as objective variables, to estimate the temporal change in the angle of the clubface and the trajectory of the clubhead movement during any given swing.

[0033] The eight explanatory features used to generate the learning model can be measured using the same equipment as the ballistic measurement device 10 described above. Furthermore, the temporal change in the angle of the clubhead face and the clubhead's movement trajectory, which are the target variables used to generate the learning model, can be determined, for example, based on images of the clubhead taken from above by a camera during a golf club swing.

[0034] One method for determining the temporal change in the angle of the clubhead's face based on images taken of the clubhead from above is to detect the toe and heel of the clubhead in the image and determine the line segment connecting the detected toe and heel as the line segment representing the face. For example, by determining the line segment representing the face from multiple images taken at a frame rate of 1 ms, the temporal change in the angle of the face can be determined. In machine learning, the angle of the line segment representing the face is used as the target variable.

[0035] Methods for detecting the toe and heel from captured images include, for example, marking the club head and detecting those marks, or using a machine learning model obtained by annotating captured images of the club head's toe and heel positions to perform the detection.

[0036] Furthermore, while the above explanation describes detecting the line segment connecting the toe and heel of the club head as the line segment representing the face, if the golf club is a driver, the boundary line between the face and crown of the driver may be detected as the line segment representing the face. In this case as well, the boundary line can be detected using a machine learning model obtained by machine learning annotating the position of the boundary line between the face and crown of the club head included in the captured image. As for machine learning, machine learning using semantic segmentation or key point machine learning that takes heatmaps into consideration can be used.

[0037] Furthermore, as a method for determining the movement trajectory of the club head based on images taken of the club head from above, for example, by determining the center coordinates of the line segments representing the face from each image captured at a frame rate of 1 ms as described above, and then determining the line segment connecting the center coordinates obtained from each image, the movement trajectory of the club head can be detected. When performing machine learning, the center coordinates of the line segments representing the face are used as the target variable.

[0038] Furthermore, the training model may be converted to an ONNX model to speed up processing. Various existing statistical methods can also be used to remove outliers from the training data.

[0039] Next, the control unit 23 controls the entire golf impact analysis system 1. Specifically, the control unit 23 communicates with the ball flight measurement device 10 via a communication interface, acquires eight feature quantities measured by the ball flight measurement device 10, and inputs these eight feature quantities into a learning model to estimate the temporal changes in the club head face and the trajectory of the club head's movement.

[0040] The control unit 23 generates line segments representing multiple face surfaces based on the angles of multiple face surfaces output from the learning model, and generates line segments connecting the center coordinates of multiple face surfaces based on the center coordinates of multiple face surfaces output from the learning model.

[0041] The control unit 23 then communicates with the projection device 30 via a communication interface, and the projection device 30 projects the line segments representing the multiple face surfaces described above onto the floor surface in chronological order, and also generates line segments connecting the center coordinates of the multiple face surfaces and projects them onto the floor surface as the movement trajectory of the club head.

[0042] The display unit 24 includes a display device such as a liquid crystal display. The input unit 25 includes an input device such as a mouse or keyboard. Alternatively, the control device 20 may be configured from a tablet terminal, and the display unit 24 and input unit 25 may be configured from a touch panel.

[0043] Furthermore, the display unit 24 may also display line segments representing the multiple face surfaces mentioned above, as well as the movement trajectory of the club head.

[0044] Furthermore, in this embodiment, the control unit 23 communicates with the ballistic measurement device 10 via a communication interface to acquire eight feature quantities measured by the ballistic measurement device 10. However, the system is not limited to this configuration, and the user may set and input the eight feature quantities measured by the ballistic measurement device 10 using the input unit 25.

[0045] Returning to Figure 1, the projection device 30 consists of a projector or a laser beam irradiation device, and as described above, under the control of the control unit 23 of the control device 20, it projects onto the floor surface a line segment representing the face of the club head 41a and the movement trajectory of the club head.

[0046] The projection device 30 is installed so as to be able to project and display line segments representing the face of the club head 41a and the trajectory of the club head's movement within a predetermined projection range that includes the installation position P of the golf ball 42 on the floor surface near its center. The projection device 30 may be installed on a support member such as a stand, or it may be installed on the ceiling.

[0047] Next, we will explain the processing flow of the Golf Impact Analysis System 1, referring to the flowchart shown in Figure 2.

[0048] First, each device of the golf impact analysis system 1 is activated (S10). Next, as shown in Figure 1, a golfer stands near the installation position P of the golf ball 42 and places the golf ball 42 at installation position P.

[0049] Then, the user sets and inputs a command to start measurement for the ballistic measurement device 10, and measurement by the ballistic measurement device 10 begins (S12).

[0050] After the ball flight measurement device 10 starts measuring, the golfer swings the golf club 41 and hits the golf ball 42 (S14).

[0051] While the golfer swings the golf club 41, the ball flight measurement device 10 performs measurements (S16), and the eight feature quantities described above are output to the control device 20. The ball flight measurement device 10 terminates the measurement after a predetermined time has elapsed from the start of the measurement (S18).

[0052] The eight feature quantities output from the ballistic measurement device 10 are input to the control device 20 and acquired by the feature quantity acquisition unit 21 (S20). Then, the estimation unit 22 inputs the eight feature quantities acquired by the feature quantity acquisition unit 21 into the learning model described above to estimate the temporal change in the angle of the club head 41a's face and the movement trajectory of the club head 41a (S22). Specifically, the estimation unit 22 estimates and outputs the angles of multiple face surfaces arranged in a time series as the temporal change in the angle of the face surface, and estimates and outputs the center coordinates of multiple face surfaces as the movement trajectory of the club head.

[0053] Then, the control unit 23 generates line segments representing multiple face surfaces arranged in a time series based on the angles of multiple face surfaces output from the estimation unit 22, generates line segments representing the movement trajectory of the club head by connecting the center coordinates of the multiple face surfaces, and combines these and projects them onto the floor surface using the projection device 30 (S24).

[0054] In the above embodiment, the temporal change of the club head's face and the club head's movement trajectory were estimated, but at least one of these may be estimated.

[0055] Furthermore, in the above embodiment, eight features were used: golf ball speed, launch direction, sidespin, club head speed, club path, face-to-target, face-to-path, and point of impact. However, the system is not limited to these; other features may be added or replaced as long as they are measured at the moment of collision between the golf club head and the golf ball. While it is preferable to have eight or more features, five or four features may also be used. The number of features used when training the learning model may also be changed to match the number of features input to the learning model.

[0056] Next, an example of a projected image projected onto the floor surface by the above embodiment will be described.

[0057] Figures 3A and 3B show examples of projected images of line segments F representing multiple face surfaces and line segments T representing the movement trajectory of the club head 41a, which were estimated by measuring eight features using the GCQuad (manufactured by ForesightSports) as the ballistic measurement device 10 as described above and inputting these into a learning model.

[0058] Figure 3A is an example of a projected image when an iron is used as the golf club 41. It projects a line segment F representing the clubface and the trajectory T of the clubhead, along with a 3D image IG of the iron clubhead and a 3D image BG of the golf ball. The 3D image IG of the clubhead moves towards the 3D image BG of the golf ball along the trajectory T of the clubhead, and when it reaches the 3D image BG of the golf ball, the 3D image BG of the golf ball moves in the direction of launch. In Figure 3A, the line segment F representing the clubface and the trajectory T are displayed up to the position of the 3D image BG of the golf ball, but it is also possible to continue to estimate and display the line segment F representing the clubface and the trajectory T after the clubhead has reached the golf ball.

[0059] Figure 3B is an example of a projected image when a driver is used as the golf club 41. It projects a 3D image DG of the driver club head and a 3D image BG of the golf ball, along with a line segment F representing the club face and the club head's movement trajectory T. The 3D image DG of the club head moves towards the 3D image BG of the golf ball along the club head's movement trajectory T, and when it reaches the 3D image BG of the golf ball, the 3D image BG of the golf ball moves in the launch direction. In Figure 3B, the line segment F representing the club head's face and the movement trajectory T may also be estimated and displayed after the club head reaches the golf ball.

[0060] Experiments conducted by the applicant revealed that the line segment F representing the club head face and the line segment T representing the club head's movement trajectory, as shown in the projection images of Figures 3A and 3B, are very close to the line segment representing the club head face and the line segment representing the club head's movement trajectory obtained from a photograph taken of the club head from above. This indicates that the temporal change in the angle of the club head face and the movement trajectory of the actual club head 41a can be represented with high accuracy.

[0061] Next, Figures 4A and 4B show examples of projected images of line segments F representing multiple face surfaces and line segments T representing the movement trajectory of the club head 41a, which were estimated by measuring five features (ball speed, launch direction, sidespin, head speed, and club path) using a GC3 (manufactured by ForesightSports) as the ball flight measurement device 10 and inputting these into a learning model.

[0062] Figure 4A shows an example of a projected image when an iron is used as the golf club 41, and Figure 4B shows an example of a projected image when a driver is used as the golf club 41. The projection and movement of the 3D image IG of the iron club head, the 3D image DG of the driver club head, and the 3D image BG of the golf ball are the same as in the examples in Figures 3A and 3B. In addition, in Figures 4A and 4B, the line segment F representing the face of the club head and the movement trajectory T may be estimated, calculated, and displayed after the club head reaches the golf ball.

[0063] According to experiments conducted by the applicant, when compared with the example projection images in Figures 3A and 3B, which use eight feature quantities, there were some slight differences in the position and angle of the line segment F representing the face of the club head 41a and the line segment representing the movement trajectory T of the club head, but these differences were not significant enough to be considered problematic.

[0064] Next, Figures 5A and 5B show examples of projected images of line segments F representing multiple face surfaces and line segments T representing the movement trajectory of the club head, estimated by measuring four feature quantities (ball speed, launch direction, sidespin, and head speed) using a GCQuad (manufactured by ForesightSports) or GC3 (manufactured by ForesightSports) as the ball flight measurement device 10 and inputting these into a learning model. Note that a measuring instrument with fewer measurement items than the GCQuad or GC3 may be used as the ball flight measurement device 10.

[0065] Figure 5A shows an example of a projected image when an iron is used as the golf club 41, and Figure 5B shows an example of a projected image when a driver is used as the golf club 41. The projection and movement of the 3D image IG of the iron club head, the 3D image DG of the driver club head, and the 3D image BG of the golf ball are the same as in the examples in Figures 3A and 3B. In addition, in Figures 5A and 5B, the line segment F representing the face of the club head and the movement trajectory T may be estimated, calculated, and displayed after the club head reaches the golf ball.

[0066] According to experiments conducted by the applicant, when comparing the line segment F representing the face of the club head 41a and the line segment T representing the movement trajectory of the club head, which are included in the projected images shown in Figures 5A and 5B, with the example projected images in Figures 3A and 3B using eight features and the example projected images in Figures 4A and 4B using five features, there were some slight differences in the position and angle of the line segment F representing the face and the accuracy of the curvature of the movement trajectory T, but these differences were not significant enough to be considered problematic.

[0067] As mentioned above, experiments conducted by the applicant showed that the greater the number of features, the higher the accuracy of the line segment F representing the face and the trajectory T of the club head.

[0068] According to the golf impact analysis system of the above embodiment, when a golf club 41 is swung, multiple feature quantities are acquired at the moment when the club head 41a of the golf club 41 collides with the golf ball 42, and based on these multiple feature quantities, at least one of the temporal change in the angle of the club face of the club head 41a and the movement trajectory of the club head 41a is estimated. Therefore, by acquiring the above-mentioned feature quantities using an existing ballistic measurement device 10 or the like, the movement of the club face of the club head 41a and its movement trajectory can be determined with high accuracy without installing a camera that photographs the swing from above.

[0069] Furthermore, in the golf impact analysis system of the above embodiment, the temporal change in the angle of the club head 41a's face and the movement trajectory of the club head 41a are estimated by inputting multiple features into a learning model obtained through machine learning in advance, thereby enabling more accurate estimation of these.

[0070] Furthermore, in the golf impact analysis system of the above embodiment, the features used are the speed of the golf ball, launch direction, sidespin, club head speed, club path, face-to-target, face-to-path, and point of impact. As a result, these features can be measured by an existing ball flight measurement device 10, and the temporal change in the angle of the clubface and the movement trajectory of the club head 41a can be estimated with higher accuracy.

[0071] In the above embodiment, the eight feature quantities described above were used, but if the closure rate can be measured by the ball flight measurement device 10, the closure rate may also be added. The closure rate is the degree to which the face rotates (open / close ratio) as the club head moves towards the impact position, and is measured as a relative value to the club path.

[0072] Since the closure rate is the rate of change of the club head face measured by 3D 6dof (degree of freedom), it cannot be immediately used for a 2D representation of the face as shown in Figures 3 to 5. However, in the above embodiment, it is used as an explanatory variable in the learning model, so it can be used for a 2D representation of the face.

[0073] According to the applicant's experiments, it was found that using the closure rate allows for more accurate acquisition of the temporal change in the angle of the clubhead face after impact and the trajectory of its movement.

[0074] Here, it is known that mis-shots, which occur when the point of impact is off-center towards the toe or heel of the clubhead, are partly caused by the clubhead face itself being pushed back by the ball's gravity. In recent years, golf clubs designed with a larger MOI (moment of inertia) to resist this push have appeared on the market, making it possible to hit more stable straight shots even on mis-shots (off-center shots) where the clubface is not centered.

[0075] As mentioned above, by displaying the temporal changes in the angle of the clubhead face after impact and its trajectory with greater precision, it is possible to display on the floor how much the clubhead was pushed back after impact. This is therefore very effective in comparing golf clubs from the perspective of observing the effect of MOI.

[0076] Furthermore, in the golf impact analysis system of the above embodiment, multiple line segments representing the face surface are arranged in a time series and projected to represent the temporal change in the angle of the face surface, making it possible to recognize the temporal change in the angle of the face surface more clearly.

[0077] Furthermore, in the golf impact analysis system of the above embodiment, a line segment representing the movement trajectory of the club head 41a is projected and displayed as the movement trajectory of the club head 41a, so that the movement trajectory of the club head 41a can be recognized more clearly.

[0078] It should be noted that the present invention is not limited to the embodiments described above, and the components can be modified and implemented in practice without departing from the spirit of the invention. Furthermore, various inventions can be formed by appropriately combining the multiple components disclosed in the embodiments described above. For example, all the components shown in the embodiments may be combined as appropriate. It goes without saying that various modifications and applications are possible without departing from the spirit of the invention.

[0079] The following further notes are disclosed regarding the present invention.

[0080] (Note 1) The swing analysis device of the present invention comprises a feature acquisition unit that acquires a plurality of feature quantities at the moment when the club head of the golf club collides with the golf ball when the golf club is swung, and an estimation unit that estimates at least one of the temporal change in the angle of the club head's face and the movement trajectory of the club head based on the plurality of feature quantities acquired by the feature acquisition unit.

[0081] (Note 2) In the swing analysis device described in Appendix 1, the estimation unit can estimate the temporal change in the angle of the club head's face and at least one of the club head's movement trajectory by inputting the multiple features acquired by the feature acquisition unit into a learning model obtained by machine learning in advance, which has been created by learning the relationship between a plurality of features acquired in advance and at least one of the temporal change in the angle of the club head's face during the swing at the time the features were acquired and at least one of the club head's movement trajectory.

[0082] (Note 3) In the swing analysis device described in Appendix 1 or 2, the multiple features may include at least one of the following: golf ball speed, launch direction, sidespin, club head speed, club path, face-to-target, face-to-path, and point of impact.

[0083] (Note 4) In the swing analysis device described in any of Appendix 1 to 3, the multiple features may include all of the following: golf ball speed, launch direction, sidespin, club head speed, club path, face-to-target, face-to-path, impact point, and closure rate.

[0084] (Note 5) The swing analysis device described in any of Appendix 1 to 4 may include a display control unit that displays at least one of the temporal change in the angle of the club head face and the trajectory of the club head movement, as estimated by the estimation unit.

[0085] (Note 6) In the swing analysis device described in Appendix 5, the display control unit can display multiple line segments representing the face in a time series as a temporal change in the angle of the face.

[0086] (Note 7) In the swing analysis device described in Appendix 5 or 6, the display control unit can display a line segment representing the movement trajectory of the club head as the movement trajectory of the club head.

[0087] (Note 8) The swing analysis program of the present invention causes a computer to perform the following steps: acquire multiple feature quantities at the moment when the club head of a golf club collides with a golf ball when a golf club is swung; and estimate at least one of the temporal change in the angle of the club head's face and the trajectory of the club head's movement based on the multiple feature quantities acquired by the feature quantity acquisition unit. [Explanation of Symbols]

[0088] 1. Golf Impact Analysis System 10 Ballistic measurement device 20 Control device 21 Feature Acquisition Unit 22 Estimation part 23 Control Unit 24 Display 25 Input section 30 Projection device 40 Golfers 41 Golf Clubs 41a Club Head 42 golf balls F represents the line segment of the face. P Installation position T Clubhead movement trajectory

Claims

1. A feature acquisition unit that acquires multiple feature quantities at the moment when the club head of the golf club and the golf ball collide when the golf club is swung, A swing analysis device comprising: an estimation unit that estimates at least one of the temporal change in the angle of the club head's face and the movement trajectory of the club head, based on a plurality of features acquired by the feature acquisition unit.

2. The swing analysis device according to claim 1, wherein the estimation unit estimates the temporal change in the angle of the club head's face and at least one of the club head's movement trajectory by inputting the plurality of features acquired by the feature acquisition unit to a learning model obtained by machine learning in advance, which is based on the relationship between a plurality of features acquired in advance and at least one of the temporal change in the angle of the club head's face during a swing when the features were acquired and at least one of the club head's movement trajectory.

3. The swing analysis device according to claim 1, wherein the plurality of features include at least one of the following: the speed of the golf ball, the launch direction, the sidespin, the head speed of the club head, the club path, the face to target, the face to path, the point of impact, and the closure rate.

4. The swing analysis device according to claim 1, wherein the plurality of feature quantities include all of the following: the speed of the golf ball, the launch direction, the sidespin, the head speed of the club head, the club path, the face-to-target, the face-to-path, and the point of impact.

5. The swing analysis device according to claim 1, further comprising a display control unit that displays at least one of the temporal change in the angle of the club head face and the movement trajectory of the club head, as estimated by the estimation unit.

6. The swing analysis device according to claim 5, wherein the display control unit displays a plurality of line segments representing the face surface in a time series as a temporal change in the angle of the face surface.

7. The swing analysis device according to claim 5, wherein the display control unit causes the display control unit to display a line segment representing the movement trajectory of the club head as the movement trajectory of the club head.

8. The steps include: acquiring multiple feature quantities at the moment when the club head of the golf club collides with the golf ball during a golf club swing; A swing analysis program that causes a computer to perform the steps of estimating at least one of the temporal change in the angle of the club head's face and the movement trajectory of the club head, based on a plurality of features acquired by the feature acquisition unit.

Images