Information processing systems, information processing devices, methods, programs, and storage media

Abstract

To accurately evaluate a golf swing using information about the body's joint points. [Solution] The information processing system for evaluating a golf swing includes: a correction means for correcting the position of the starting frame of video data of the golf swing to be evaluated; a first feature generation means for generating a first feature, which is the amount of change in the position of one or more joint points of the body, from the video data; a second feature generation means for generating a second feature, which is the amount of change in the evaluation value calculated from the position of one or more parts of the body, from the video data; and an evaluation calculation means for calculating the evaluation of the golf swing using the first feature and / or the second feature.

Description

Technical Field

[0001] The present invention relates to an information processing system, method, program, and storage medium.

Background Art

[0002] Conventionally, a technique capable of evaluating the magnitude of face rotation during a golfer's swing has been known (see Patent Document 1).

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] The problem to be solved by the present invention is to evaluate a golf swing well using information on body joint points.

Means for Solving the Problems

[0005] [1] An information processing system according to one aspect is an information processing system for evaluating a golf swing, correction means for correcting the position of the start frame of video data obtained by shooting a golf swing to be evaluated, first feature amount generation means for generating a first feature amount which is the amount of change in the position of one or more joint points of the body from the video data, second feature amount generation means for generating a second feature amount which is the amount of change in an evaluation value calculated from the position of one or more parts of the body from the video data, evaluation calculation means for calculating an evaluation of the golf swing using the first feature amount and / or the second feature amount, and includes.

[0006] [2] An information processing system according to one embodiment is described in [1] above, The aforementioned evaluation value is the center of gravity position calculated from the positions of multiple joint points of the body.

[0007] [3] An information processing system according to one embodiment is described in [1] above, The aforementioned evaluation value is the angle between the arm and the torso, calculated from the positions of multiple joint points of the body.

[0008] [4] An information processing system according to one embodiment is, in any of the above [1] to [3], The evaluation calculation means calculates the evaluation by comparing the first feature and the second feature with the first feature and the second feature which serve as evaluation criteria.

[0009] [5] An information processing system according to one embodiment is, in any of the above [1] to [4], The evaluation calculation means is The correlation coefficient between the aforementioned first feature and the first feature that serves as the evaluation criterion is calculated for each joint point, and the average value is taken as the first evaluation. The correlation coefficient between the aforementioned second feature and the second feature used as the evaluation criterion is used as the second evaluation. The first evaluation and the second evaluation are each weighted to calculate the evaluation.

[0010] [6] An information processing system relating to one embodiment is, in any of the above [1] to [5], The evaluation calculation means calculates an evaluation score using an estimation model generated by machine learning using the first and second features as training data.

[0011] [7] An information processing system according to one embodiment is, in any of the above [1] to [6], The correction means corrects the position of the starting frame so that the frame in which the horizontal position of the wrist joint point is at its maximum or minimum becomes the starting frame of the video data.

[0012] [8] An information processing system relating to one aspect is, in any of the above [1] to [7], A handedness determination means for determining the dominant hand of the body performing the golf swing from the aforementioned video data, An inversion means that performs left-right inversion processing on the video data according to the determination result by the handedness determination means, To further prepare.

[0013] [9] An information processing system relating to one aspect is, in any of the above [1] to [8], The system further includes output control means for converting the aforementioned evaluation into an evaluation score and outputting it to the display unit.

[0014]

[10] An information processing system according to one embodiment is, in any of the above [1] to [9], The text generation means further comprises a means for generating text according to the first feature and / or the second feature, The output control means outputs the text to the display unit.

[0015]

[11] An information processing system according to one embodiment is described in

[10] above, The text generation means generates the text according to the relationship between the evaluation score and the threshold.

[0016]

[12] An information processing device according to one embodiment is: An information processing device for evaluating a golf swing, A correction means for correcting the starting frame position of video data of a golf swing to be evaluated, A first feature generation means generates a first feature, which is the amount of change in the position of one or more joint points of the body, from the aforementioned video data. A second feature generation means generates a second feature, which is the amount of change in evaluation values ​​calculated from the position of one or more parts of the body from the aforementioned video data, An evaluation calculation means for calculating an evaluation of a golf swing using the first feature and / or the second feature, It is equipped with.

[0017]

[13] A method relating to one aspect is: A method by which a computer evaluates a golf swing, The steps include correcting the starting frame position of the video data of the golf swing to be evaluated, and The steps include generating a first feature quantity from the aforementioned video data, which is the amount of change in the position of one or more joint points of the body, The steps include generating a second feature, which is the change in evaluation value calculated from the position of one or more parts of the body, from the aforementioned video data, A step of calculating an evaluation of a golf swing using the first feature and / or the second feature, Includes.

[0018]

[14] A program relating to one aspect is: A computer program for performing the method described in

[13] above.

[0019]

[15] A storage medium relating to one aspect is: A computer-readable storage medium containing the program described above

[14] . [Effects of the Invention]

[0020] According to the present invention, a golf swing can be effectively evaluated using information about the joint points of the body. [Brief explanation of the drawing]

[0021] [Figure 1] This block diagram shows an example of the functional configuration of the information processing system 1 according to this embodiment. [Figure 2] This is a block diagram showing an example of the hardware configuration of the information processing system 1 according to this embodiment. [Figure 3] This flowchart shows an example of the operation of the information processing system 1 according to this embodiment. [Figure 4] This diagram shows an example of a joint point (key point) in the body. [Modes for carrying out the invention]

[0022] Embodiments of the present invention will be described in detail below with reference to the attached drawings. In each drawing, components having equivalent functions are denoted by the same reference numerals, and detailed descriptions of components with the same reference numerals will not be repeated.

[0023] (System Configuration) Next, the configuration of the information processing system 1 will be described. Figure 1 is a diagram showing the schematic configuration of the information processing system 1 according to one embodiment. In this figure, each functional unit that performs a function can be said to be a means for performing that function.

[0024] As shown in Figure 1, the information processing system 1 comprises a terminal device 2 and a server 3. The terminal device 2 and the server 3 are connected to each other via a network 4, such as the Internet, enabling communication. The network 4 may be either a wired or wireless connection, and the type and configuration of the connection are not restricted. At least a portion of the terminal device 2 and the server 3 are implemented by a computer.

[0025] (Functional configuration of terminal devices) First, let's describe terminal device 2. Terminal device 2 is used by the user and is an electronic device such as a mobile device like a smartphone or tablet, a notebook computer, or a desktop computer.

[0026] As shown in Figure 1, the terminal device 2 includes a terminal communication unit 21, a terminal control unit 22, a terminal input unit 23, a terminal output unit 24, an imaging unit 25, and a terminal storage unit 26. Each unit 21 to 26 is connected to the others so as to be able to communicate with each other.

[0027] The terminal communication unit 21 is a communication interface between the terminal device 2 and the network 4. The terminal communication unit 21 sends and receives information between the terminal device 2 and the server 3 via the network 4.

[0028] The terminal control unit 22 is a control means that performs various processes of the terminal device 2. The terminal control unit 22 may be implemented by the processor in the terminal device 2 executing a predetermined program, or it may be implemented in hardware.

[0029] The terminal input unit 23 is an interface for the user to input information into the terminal device 2, and is, for example, a touch panel or microphone in a mobile terminal, or a touchpad, keyboard or mouse in a notebook computer.

[0030] The terminal output unit 24 is an interface that outputs various information from the terminal device 2 to the user, and includes, for example, a video display device (display unit) such as an LCD display and an audio output device such as a speaker. The terminal output unit 24 may display a GUI (Graphical User Interface) to accept operations from the user.

[0031] The imaging unit 25 captures an image of the subject (the person whose golf swing is being evaluated) using an image sensor (not shown). The image data (video data, still image data) captured by the imaging unit 25 is stored in the terminal storage unit 26 of the terminal device 2. The image data captured by the imaging unit 25 is also transmitted to the server 3 via the network 4 by the terminal communication unit 21.

[0032] The terminal storage unit 26 is a data storage device such as internal memory or external memory (SD memory card, etc.). The terminal storage unit 26 stores various data handled by the terminal control unit 22, as well as images captured by the imaging unit 25. The terminal storage unit 26 does not necessarily have to be located within the terminal device 2; part or all of the terminal storage unit 26 may be located in another device that is communicably connected to the terminal device 2 via the network 4.

[0033] (Server Functional Configuration) Next, we will describe server 3. As shown in Figure 1, server 3 has a server communication unit 31, a server control unit 32, and a server storage unit 33. Each of the units 31 to 33 is connected to each other so as to be able to communicate.

[0034] Of these, the server communication unit 31 is the communication interface between the server 3 and the network 4. The server communication unit 31 sends and receives information between the server 3 and the terminal device 2 via the network 4.

[0035] The server storage unit 33 is a fixed data storage device such as a hard disk. Various types of data handled by the server control unit 32 are stored in the server storage unit 33. For example, video data of golf swings to be evaluated, video data of golf swings of professional players used as evaluation criteria, and feature quantities (first feature quantities and second feature quantities) generated from this video data are stored in the server storage unit 33.

[0036] The server storage unit 33 does not necessarily have to be located within the server 3; part or all of the server storage unit 33 may be located in another device that is connected to the server 3 via the network 4 in a manner that allows communication with the server 3.

[0037] The server control unit 32 includes a joint point detection unit 32a, a dominant hand determination unit 32b, an image inversion unit 32c, an image timing correction unit 32d, a first feature generation unit 32e, a second feature generation unit 32f, an evaluation calculation unit 32g, a text generation unit 32h, and an output control unit 32i. Each of these units 32a to 32i may be implemented by a processor in the server 3 executing a predetermined program, or they may be implemented in hardware. Alternatively, each of these units 32a to 32i may be implemented in the terminal device 2 and processed by the terminal device 2.

[0038] The joint point detection unit 32a detects the joint points (key points) of the subject (user)'s entire body from video data of a golf swing. For example, the joint point detection unit 32a detects the joint points of the user's entire body for each frame of image data using a posture estimation deep-trained model. The coordinate values ​​(x, y, z) or (x, y) of each joint point detected by the joint point detection unit 32a are stored in the server storage unit 33.

[0039] Figure 4 shows an example of joint points detected by the joint point detection unit 32a. As shown in Figure 4, the joint point detection unit 32a detects one or more joint points (key points) from the body contained in the video data.

[0040] Returning to Figure 1, the dominant hand determination unit 32b determines the dominant hand of the body performing the golf swing from the video data. Specifically, the dominant hand determination unit 32b determines the dominant hand by detecting the direction of movement of the joint points of both hands detected by the joint point detection unit 32a.

[0041] The video inversion unit 32c performs left-right inversion processing on the video data according to the determination result by the handedness determination unit 32b. Specifically, it performs left-right inversion on the input video file (video data) as needed so that the evaluation of the golf swing by the evaluation calculation unit described later can be performed appropriately. For example, if the dominant hand of the subject in the video data to be evaluated is the same as the dominant hand of the subject in the video data used as the evaluation standard (for example, video data of a professional golfer's swing), the video inversion unit 32c performs left-right inversion processing on the video data to be evaluated or the video data used as the evaluation standard.

[0042] The video timing correction unit 32d corrects the position (video timing) of the start frame of the video data that captures the golf swing to be evaluated. Specifically, the video timing correction unit 32d uses the center of the shoulders as a reference point at the joint points of both hands detected by the joint point detection unit 32a, and detects the frame in which the lateral movement amount first becomes maximum (for example, the right side is positive when facing) as the start frame of the backswing of the golf swing. Based on the start frame number of the subject in the reference video data (for example, video data capturing the golf swing of a professional golfer) when the subject starts the backswing, the start frame of the video data to be evaluated is corrected.

[0043] Here, an example of the processing of the video timing correction unit 32d will be described while referring to FIG. 4. The video timing correction unit 32d uses, for example, key points 15 and 16 as the joint points of both wrists. Let the respective coordinate values be k 11 , , 12 , , , 12 , , ,

[0046] , 11 , , , 12 ,

[0045] , , (x 15 ,y 15 ), k 16 (x 16 ,y 16 ). Then, the central point coordinate value of the wrist is obtained as follows.

[0044]

Equation

[0045]

Equation

[0046]

Equation

[0047] Then, the video timing correction unit 32d calculates the index I of the first maximum peak value of the lateral movement amount. max We seek.

[0048]

number

[0049] For example, I max An example of correcting video timing based on this was explained, but the index I of the first minimum peak value of the horizontal movement amount is used. min You may adjust the video timing based on this.

[0050] The first feature generation unit 32e generates a first feature from the video data, which is the change in position of one or more joint points of the body. Specifically, the first feature generation unit 32e calculates the Euclidean distance at each joint point using the joint point coordinate data of the current t-th frame and the adjacent previous (t-1)-th frame. This distance, along with the movement angle, is then used as the movement distance change value (first feature). (N-1) movement distance change values ​​are calculated for each joint point from a single video data set. The calculated movement distance change value data is saved as the position change feature of all joint points in the body.

[0051] Here, an example of processing by the first feature generation unit 32e will be explained with reference to Figure 4.

[0052] The first feature generation unit 32e calculates the change in movement distance (Euclidean distance) between frames of the joint point (e.g., right wrist) detected by the joint point detection unit 32a. The coordinate value of the i-th key point of the right wrist is k (i,16) (x (i,16) ,y (i,16) ), the coordinates of the i+1th right wrist keypoint are k (i+1,16) (x (i+1,16) ,y (i+1,16) Assuming this is the case, the change in distance traveled between frames (Euclidean distance) can be calculated as follows:

[0053]

number

[0054] Furthermore, the first feature generation unit 32e determines the movement angle between frames as follows.

[0055]

number

[0056] The first feature generation unit 32e calculates position change features (first features) [d,θ] for both the video data to be evaluated and the video data used as evaluation criteria.

[0057] The second feature generation unit 32f generates a second feature, which is the change in evaluation values ​​calculated from the position of one or more body parts from the video data. Specifically, the second feature generation unit 32f generates the body's center of gravity and shoulder movement as features (second features). The body's center of gravity and shoulder movement are areas that are particularly important to evaluate in golf swing evaluation.

[0058] Here, an example of processing by the first feature generation unit 32e will be explained with reference to Figure 4. [Method for calculating centroid change features] The second feature generation unit 32f calculates the center of gravity evaluation value from key points (joint points) of both shoulders, waist, and both knees detected by the joint point detection unit 32a, for example. The coordinate values ​​of the key points of both shoulders (numbers 11 and 12) are k 11 (x 11 ,y 11 ), k 12 (x 12 ,y 12 ), the coordinate values ​​of the waist key points (numbers 23 and 24) 23 (x 23 ,y 23 ), k 24 (x 24 ,y 24 ), the coordinate values ​​of the key points (numbers 25 and 26) on both knees are k 25 (x 25 ,y 25 ), k 26 (x 26 ,y 26 ), if so, the center of gravity evaluation value CG i The answer is as follows:

[0059]

number

[0060] The second feature generation unit 32f generates centroid change feature CG (second feature) (for example, centroid evaluation value CG of the i-th frame) for both the video data to be evaluated and the video data for evaluation criteria. i and the centroid evaluation value CG of the i+nth frame i+n Calculate the difference between the two values. [Method for calculating shoulder movement features] The second feature generation unit 32f generates, for example, the angle (θ) between the left and right arms and the torso detected by the joint point detection unit 32a in each frame. L θ R) is calculated. For example, the angle between the right arm and the torso (θ) is calculated. R ) can be calculated as follows. In Figure 4, find the angle formed by line segments 14-12 and 12-24, which connect the key points. The coordinate values ​​of each key point are k 12 (x 12 ,y 12 ), k 14 (x 14 ,y 14 ), k 24 (x 24 ,y 24 If we assume that θ is the angle between the right arm and the torso in the i-th frame, then θ i, Shoulder right = θ i,R ) can be calculated as follows:

[0061]

number

[0062] The second feature generation unit 32f generates shoulder movement features (second features) (for example, the angle θi of the i-th frame and the angle θ of the i+n-th frame) for both the video data to be evaluated and the video data for the evaluation criteria. i+n Calculate the difference between the two values.

[0063] The evaluation calculation unit 32g calculates the evaluation of a golf swing using the first and second features. Specifically, the evaluation calculation unit 32g evaluates each feature by comparing the first and second features generated from the video data to be evaluated with the first and second features generated from the video data used as the evaluation criteria.

[0064] The evaluation calculation unit 32g calculates the correlation coefficient between the first feature and the first feature that serves as the evaluation criterion for each joint point, sets the average value of these correlation coefficients as the first evaluation, sets the correlation coefficient between the second feature and the second feature that serves as the evaluation criterion as the second evaluation, and then weights each of the first and second evaluations to calculate an overall evaluation score.

[0065] The evaluation calculation unit 32g may also calculate the evaluation score using an estimation model generated by machine learning using the first and second features as training data.

[0066] The text generation unit 32h generates text according to the first feature and / or the second feature. Specifically, it generates text of an advice message to improve the golf swing of the user being evaluated, based on the evaluation calculated according to the first feature and / or the second feature. The text generation unit 32h may also generate text according to the relationship between the evaluation score calculated by the evaluation calculation unit 32g and a predetermined threshold.

[0067] The output control unit 32i outputs the evaluation (first evaluation and / or second evaluation) and evaluation score calculated by the evaluation calculation unit 32g to the display unit (terminal output unit 24) of the terminal device 2. If the evaluation is not a numerical value but a rank such as A, B, C, etc., the output control unit 32i converts the evaluation into an evaluation score and displays it on the display unit of the terminal device 2.

[0068] Furthermore, the output control unit 32i displays the text (advice message) generated by the text generation unit 32h on the display unit of the terminal device 2.

[0069] Furthermore, the output control unit 32i may display an indicator (such as a graph) on the display unit of the terminal device 2 that shows the changes in each feature (first feature and second feature) over time, along with the playback of the video data being evaluated. This allows the user to visually grasp the timing of significant changes in each feature.

[0070] (Hardware configuration) Next, the hardware configuration of the information processing system 1 according to this embodiment will be described. Figure 2 is a block diagram showing an example of the hardware configuration of the terminal device 2 and server 3 included in the information processing system 1 according to this embodiment.

[0071] In terminal device 2, the CPU 201 is a processing unit that controls the operation of the entire terminal device 2. ROM 202 is a non-volatile memory that stores control programs executed by the CPU 201 and various data. RAM 203 is a volatile memory used for the load area and work area of ​​programs executed by the CPU 201. Storage device 204 is a storage means for storing various information, and may be built into the terminal device 2 itself or have a removable storage medium. Input device 205 is a device for the user of terminal device 2 to input information, such as a keyboard, mouse, touch panel, or microphone. Display 206 is a display device that displays various information (user interface, etc.). Image sensor 207 is a photoelectric conversion element that captures an image of a subject. Communication I / F (interface) 208 is an interface for connecting to network 4. Bus 209 is a bus line that connects each of the above components to each other.

[0072] In server 3, the CPU 301 is a processing unit that controls the overall operation of server 3. ROM 302 is a non-volatile memory that stores control programs and various data executed by the CPU 301. RAM 303 is a volatile memory used for the load area and work area of ​​programs executed by the CPU 301. Storage device 304 is a storage means for storing various information, and may be built into the server 3 itself or have a removable storage medium. Communication I / F (interface) 305 is an interface for connecting to network 4. Bus 306 is a bus line that connects each of the above components to each other.

[0073] (An example of operation) Next, an example of the operation of the information processing system 1 will be described. Figure 3 is a flowchart showing the operation in which a user of the information processing system 1 generates content consisting of one or more frames using the user interface displayed on the display unit (output unit 24) of the terminal device 2.

[0074] First, the video timing correction unit 32d of the server control unit 32 corrects the position of the starting frame of the video data of the golf swing to be evaluated (step S1).

[0075] Next, the first feature generation unit 32e of the server control unit 32 generates a first feature from the video data, which is the amount of change in the position of one or more joint points of the body (step S2).

[0076] Next, the second feature generation unit 32f of the server control unit 32 generates a second feature, which is the change in evaluation value calculated from the position of one or more body parts from the video data (step S3).

[0077] Then, the evaluation calculation unit 32g of the server control unit 32 calculates an evaluation of the golf swing using the first feature and the second feature (step S4).

[0078] As described above, according to this embodiment, the information processing system 1 is an information processing system for evaluating a golf swing, and includes a correction means (correction unit 32d) for correcting the position of the starting frame of video data of a golf swing to be evaluated, a first feature generation means (first feature generation unit 32e) for generating a first feature, which is the amount of change in the position of one or more joint points of the body from the video data, a second feature generation means (second feature generation unit 32f) for generating a second feature, which is the amount of change in an evaluation value calculated from the position of one or more parts of the body from the video data, and an evaluation calculation means (evaluation calculation unit 32g) for calculating an evaluation of the golf swing using the first feature and the second feature. Therefore, it is possible to evaluate a golf swing well using information about the joint points of the body.

[0079] Any part or all of the functional components described herein may be implemented by program. The programs referred to herein may be distributed by non-temporarily recording them on a computer-readable recording medium, by distributing them via communication lines such as the Internet (including wireless communication), or by distributing them installed on any terminal.

[0080] Based on the above description, those skilled in the art may be able to conceive of additional effects and various modifications of the present invention, but the embodiments of the present invention are not limited to the individual embodiments described above. Various additions, modifications, and partial deletions are possible without departing from the conceptual idea and spirit of the present invention derived from the claims and their equivalents.

[0081] For example, what is described herein as a single device (or component, hereinafter the same) (including what is depicted as a single device in the drawings) may be implemented by multiple devices. Conversely, what is described herein as multiple devices (including what is depicted as multiple devices in the drawings) may be implemented by a single device. Alternatively, some or all of the means or functions included in one device (e.g., a server) may be included in another device (e.g., a terminal device).

[0082] Furthermore, not all matters described herein are mandatory requirements. In particular, matters described herein but not included in the claims can be considered optional additional matters.

[0083] It should also be noted that the applicant is only aware of the prior art inventions described in the "Prior Art Documents" section of this specification, and the present invention is not necessarily intended to solve the problems described in those prior art inventions. The problems that the present invention aims to solve should be determined by considering this specification as a whole. For example, if this specification describes that a certain effect is achieved by a particular configuration, it can also be said that the problem that is the inverse of that predetermined effect is solved. However, this does not necessarily mean that such a particular configuration is an essential requirement. [Explanation of symbols]

[0084] 1. Information Processing System 2 Terminal devices 21 Terminal Communication Section 22 Terminal Control Unit 23 Terminal Input Section 24 Terminal output section 25 Imaging Department 26 Terminal Storage Unit 3 servers 31 Server Communication Section 32 Server Control Unit 32a Joint point detection unit 32b Handedness determination unit 32c Video Inversion Section 32d Video Timing Correction Unit 32e First Feature Generation Unit 32f Second Feature Generation Unit 32g Evaluation Calculation Unit 32h Text generation unit 32i Output Control Unit 33 Server Storage Unit

Claims

1. An information processing system for evaluating a golf swing, A correction means for correcting the starting frame position of video data of a golf swing to be evaluated, A first feature generation means generates a first feature, which is the amount of change in the position of one or more joint points of the body, from the aforementioned video data. A second feature generation means generates a second feature, which is the amount of change in evaluation values ​​calculated from the position of one or more parts of the body from the aforementioned video data, An evaluation calculation means for calculating an evaluation of a golf swing using the first feature and / or the second feature, An information processing system equipped with the following features.

2. The aforementioned evaluation value is the center of gravity position calculated from the positions of multiple joint points of the body. The information processing system according to claim 1.

3. The aforementioned evaluation value is the angle between the arm and the torso, calculated from the positions of multiple joint points of the body. The information processing system according to claim 1.

4. The evaluation calculation means calculates the evaluation by comparing the first feature and the second feature with the first feature and the second feature which serve as evaluation criteria. The information processing system according to claim 1.

5. The evaluation calculation means is The correlation coefficient between the aforementioned first feature and the first feature that serves as the evaluation criterion is calculated for each joint point, and the average value is taken as the first evaluation. The correlation coefficient between the aforementioned second feature and the second feature that serves as the evaluation criterion is used as the second evaluation. The first evaluation and the second evaluation are weighted, and the evaluation is calculated. The information processing system according to claim 1.

6. The evaluation calculation means calculates an evaluation score using an estimation model generated by machine learning using the first and second features as training data. The information processing system according to claim 1.

7. The correction means corrects the position of the starting frame so that the frame in which the horizontal position of the wrist joint point is at its maximum or minimum becomes the starting frame of the video data. The information processing system according to claim 1.

8. A handedness determination means for determining the dominant hand of the body performing the golf swing from the aforementioned video data, An inversion means that performs left-right inversion processing on the video data according to the determination result by the handedness determination means, The information processing system according to claim 1, further comprising:

9. The system further includes output control means for converting the aforementioned evaluation into an evaluation score and outputting it to a display unit. The information processing system according to claim 1.

10. The text generation means further comprises a means for generating text according to the first feature and / or second feature, The output control means outputs the text to the display unit. The information processing system according to claim 9.

11. The text generation means generates the text according to the relationship between the evaluation score and the threshold. The information processing system according to claim 10.

12. An information processing device for evaluating a golf swing, A correction means for correcting the starting frame position of video data of a golf swing to be evaluated, A first feature generation means generates a first feature, which is the amount of change in the position of one or more joint points of the body, from the aforementioned video data. A second feature generation means generates a second feature, which is the amount of change in evaluation values ​​calculated from the position of one or more parts of the body from the aforementioned video data, An evaluation calculation means for calculating an evaluation of a golf swing using the first feature and / or the second feature, An information processing device equipped with the following features.

13. A method by which a computer evaluates a golf swing, The steps include correcting the starting frame position of the video data of the golf swing to be evaluated, and The steps include generating a first feature quantity from the aforementioned video data, which is the amount of change in the position of one or more joint points of the body, The steps include generating a second feature quantity, which is the amount of change in evaluation values ​​calculated from the position of one or more body parts, from the aforementioned video data, A step of calculating an evaluation of a golf swing using the first feature and / or the second feature, Methods that include...

14. A program for a computer to perform the method described in claim 13.

15. A computer-readable storage medium storing the program described in claim 14.

Images