KR20240031983A - Method and apparatus for predicting the drop point of a golf ball - Google Patents

Abstract

Obtaining input information including golf club information and golf course information; Obtaining a set of images in which the swing scene is captured for a preset time before and after the moment of impact; generating an expected trajectory of a golf ball based on the input information and the image set; and generating expected falling point information of the golf ball based on the expected trajectory.

Description

Method and apparatus for predicting the drop point of a golf ball}

The present disclosure relates to a method and device for predicting the falling point of a golf ball. More specifically, it relates to a method and device for predicting the falling point of a golf ball by generating an expected trajectory based on golf club information, golf course information, and a set of images taken at the moment of impact.

Golf is a sport that involves hitting a golf ball with a golf club and putting it into a hole on a course. Recently, interest in golf among the general public in Korea is rapidly increasing due to the increase in national income, spread of well-being culture, globalization of sports exchange, and prominence in the PGA and LPGA.

A golf course is also referred to as a field, and when playing golf in a field, if the flying ball does not enter the hole, it is essential to find the landing point of the golf ball for the next hit.

However, it is difficult to find the location of a golf ball that has flown in the field with the human eye, and even if the approximate location is determined, finding the location of the golf ball specifically is a great inconvenience.

Therefore, there was a need to solve the inconvenience of finding a golf ball by analyzing the trajectory of the golf ball flew by hitting and predicting the falling point.

The present disclosure provides a method and device for predicting the falling point of a golf ball. The problem to be solved by the present disclosure is not limited to the problems mentioned above, and other problems and advantages of the present disclosure that are not mentioned can be understood through the following description and can be understood more clearly through the examples of the present disclosure. It will be. In addition, it will be appreciated that the problems and advantages to be solved by the present disclosure can be realized by the means and combinations thereof indicated in the patent claims.

As a technical means for achieving the above-described technical problem, a first aspect of the present disclosure includes the steps of acquiring input information including golf club information and golf course information; Obtaining a set of images in which the swing scene is captured during a preset time before and after the moment of impact; generating an expected trajectory of a golf ball based on the input information and the image set; and generating expected falling point information of the golf ball based on the expected trajectory. A method of predicting the falling point of the golf ball including a step may be provided.

A second aspect of the present disclosure includes a memory storing at least one program; and a processor that operates by executing the at least one program, wherein the processor acquires input information including golf club information and golf course information, and a set of images in which the swing scene is captured during a preset time before and after the moment of impact. A device for predicting the falling point of a golf ball, generating an expected trajectory of the golf ball based on the input information and the image set, and generating expected falling point information of the golf ball based on the expected trajectory. can be provided.

A third aspect of the present disclosure may provide a computer-readable recording medium on which a program for executing the method of the first aspect of the present disclosure on a computer is recorded.

Other aspects, features and advantages in addition to those described above will become apparent from the following drawings, claims and detailed description of the invention.

According to the problem-solving means of the present disclosure described above, the inconvenience of finding a golf ball with the human eye can be resolved by predicting the falling point by analyzing the trajectory of the golf ball flying by hitting.

In addition, according to another problem-solving method of the present disclosure, various necessary information can be provided to golf players or people in related industries by estimating the final position of the golf ball based on the predicted falling point.

In addition, according to another problem solving means of the present disclosure, various information necessary for golf players or related industry workers can be provided in real time by displaying information generated in relation to the predicted falling point on the display of the user terminal.

1 is a system diagram including a fall point prediction device according to an embodiment.
Figure 2 is a block diagram of a fall point prediction device according to an embodiment.
Figure 3 is a diagram for explaining the steps of acquiring an image set according to one embodiment.
Figure 4 is a diagram for explaining a set of images taken of golf clubs according to an embodiment.
Figure 5 is a diagram for explaining a set of images taken of a golf ball according to an embodiment.
Figure 6 is a diagram for explaining a set of images taken of a player's swing posture according to an embodiment.
FIG. 7 is a diagram illustrating the steps of acquiring golf club information according to an embodiment.
FIG. 8 is a diagram illustrating the steps of acquiring player information according to an embodiment.
Figure 9 is a diagram for explaining 3D terrain information according to an embodiment.
Figure 10 is a diagram for explaining the step of generating tee shot location information according to an embodiment.
FIG. 11A is a diagram illustrating the step of generating final expected location information using a virtual space reproduced in one embodiment.
FIG. 11B is a diagram for explaining an interface displayed on a user terminal according to an embodiment.
FIG. 12 is a diagram illustrating the step of generating a recommended movement path for a golf cart according to an embodiment.
Figure 13 is a flowchart of a method for predicting the falling point of a golf ball according to an embodiment.

The present disclosure can be implemented in various ways and can have various embodiments, and specific embodiments are illustrated in the drawings and described in the detailed description. The effects and features of the present disclosure and methods for achieving them will become clear with reference to the embodiments described in detail below along with the drawings.

However, the present disclosure is not limited to the embodiments disclosed below and may be implemented in various forms. In the following embodiments, terms such as first and second are used not in a limiting sense but for the purpose of distinguishing one component from another component. Additionally, singular expressions include plural expressions unless the context clearly dictates otherwise. In addition, terms such as include or have mean that the features or components described in the specification exist, and do not preclude the possibility of adding one or more other features or components.

Additionally, in the drawings, the sizes of components may be exaggerated or reduced for convenience of explanation. For example, the size and thickness of each component shown in the drawings are arbitrarily shown for convenience, and the present disclosure is not necessarily limited to what is shown.

Hereinafter, embodiments of the present disclosure will be described in detail with reference to the accompanying drawings. When describing with reference to the drawings, identical or corresponding components will be assigned the same reference numerals and redundant description thereof will be omitted. do.

Hereinafter, the present disclosure will be described in detail with reference to the attached drawings.

1 is a system diagram including a fall point prediction device according to an embodiment.

Referring to FIG. 1, a system according to one embodiment may include a fall point prediction device 110 and a user terminal 120.

The falling point prediction device 110 may refer to any type of server that manages web and/or apps that can provide a service for predicting the falling point of a golf ball, and a server that manages the homepage of various management platforms, etc. It can mean. However, it is not limited to this. A camera (not shown) may be included as part of the fall point prediction device 110, or may communicate with the fall point prediction device 110 outside of the fall point prediction device 110 using a network.

The user terminal 120 includes a smartphone, a tablet PC, a PC, a smart TV, a mobile phone, a personal digital assistant (PDA), a laptop, a media player, a micro server, a global positioning system (GPS) device, an e-book reader, and a digital broadcasting terminal. , navigation devices, kiosks, MP3 players, digital cameras, home appliances, devices equipped with cameras, and other mobile or non-mobile computing devices. Additionally, the user terminal 120 may be a wearable device such as a watch, glasses, hair band, or ring equipped with a communication function and data processing function. However, it is not limited to this.

Meanwhile, users include all people involved in playing golf, such as golf players, caddies, or golf course managers. There may be a plurality of users, and therefore, there may also be a plurality of terminals used by the user. The falling point prediction device 110 may create an interface that displays the falling point prediction information to be provided to the user, and the created interface may be provided to the user through the user terminal 120.

Meanwhile, the fall point prediction device 110 may communicate with the user terminal 120 through a network. According to one embodiment, the falling point prediction device 110 may obtain input information including golf club information, golf course information, and player information by communicating with the user terminal 120 through a network. In addition, the falling point prediction device 110 communicates with the user terminal 120 through a network to provide expected trajectory, expected falling point information, tee shot location information for each player, player posture analysis information, reproduced virtual space, and recommended movement. An interface displaying at least one of a route and a strategy may be provided to the user.

The fall point prediction device 110 and the user terminal 120 may communicate using a network. For example, networks include Local Area Network (LAN), Wide Area Network (WAN), Value Added Network (VAN), mobile radio communication network, satellite communication network, and their It is a comprehensive data communication network that includes mutual combinations and allows each of the network configurations 110 and 120 shown in FIG. 1 to communicate smoothly with each other, and may include wired Internet, wireless Internet, and mobile wireless communication networks. You can. In addition, wireless communications include, for example, wireless LAN (Wi-Fi), Bluetooth, Bluetooth low energy, ZigBee, WFD (Wi-Fi Direct), UWB (ultra-wideband), infrared communication (IrDA, Infrared Data Association), NFC (Near Field Communication), etc., but are not limited to these.

Figure 2 is a block diagram of a fall point prediction device according to an embodiment.

Referring to FIG. 2 , the fall point prediction device 200 may include a processor 210, a memory 220, and a communication module 230. In the fall point prediction device 200 of FIG. 2, only components related to the embodiment are shown. Accordingly, those skilled in the art can understand that other general-purpose components may be included in addition to the components shown in FIG. 2. Additionally, the falling point prediction device 200 of FIG. 2 may correspond to the falling point prediction device 110 of FIG. 1 .

The processor 210 controls the overall operation of the fall point prediction device 200. For example, the processor 210 executes programs stored in the memory 220 to operate the input unit (not shown), display (not shown), camera (not shown), memory 220, communication module 230, etc. Overall control is possible, and the operation of the fall point prediction device 200 can be controlled. The processor 210 may control at least some of the operations of the falling point prediction device 200 described in FIGS. 1 to 13 .

The processor 210 includes application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, and microcontrollers. It may be implemented using at least one of micro-controllers, microprocessors, and other electrical units for performing functions.

The memory 220 is hardware that stores various data processed within the fall point prediction device 200, and can store a program for processing and control of the processor 210.

The memory 220 includes random access memory (RAM) such as dynamic random access memory (DRAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), CD- It may include ROM, Blu-ray or other optical disk storage, a hard disk drive (HDD), a solid state drive (SSD), or flash memory.

The communication module 230 may include one or more components that enable wired/wireless communication with an external server or external device. For example, the communication module 230 may include at least one of a short-range communication unit (not shown), a mobile communication unit (not shown), and a broadcast receiver (not shown).

Figure 3 is a diagram for explaining the steps of acquiring an image set according to one embodiment.

Referring to FIG. 3, the camera 310 may be a part of the fall point prediction device, or may be a device that generates a set of images outside the fall point prediction device and provides them to the fall point prediction device. The camera 310 may be installed on the front and/or side of the player by the user before the player hits the golf ball 331 with the golf club 321.

The camera 310 may generate image sets by photographing the golf club 321, the golf ball 331, and the player's swing posture 341. The camera 310 may include any device that generates an image using visible light reflected by a subject, but may also include a camera that generates an image using invisible electromagnetic waves including infrared, ultraviolet, and X-rays. there is.

According to one embodiment, the camera 310 may include a high-speed camera capable of continuous shooting at detailed frame intervals, and may include a high-resolution camera capable of checking the degree of movement and rotation of the subject when shooting at detailed frame intervals. can do.

According to one embodiment, the camera 310 may generate sets of images by including at least one photographing unit, a photographing unit for photographing a golf club 322, a photographing unit for photographing a golf ball 332, and a player's swing. It may include a photographing unit for posture photographing (342). Alternatively, a plurality of cameras 310 may be positioned in front and on the side of the player to capture images, thereby creating sets of images.

According to one embodiment, only a set of images taken together of the golf club 321, the golf ball 331, and the player's swing posture 341 may be generated. In this case, images of each subject are processed from the set of images taken together. Thus, a step of generating each image set can be further performed.

According to one embodiment, the falling point prediction device may use an artificial intelligence neural network model learned using images of golf clubs and golf balls as learning data. The falling point prediction device inputs a set of images taken together with the golf club 321 and the golf ball 331 as input data to a previously learned artificial intelligence neural network model, and inputs a set of images for the golf club 321 and the golf ball 331 A set of images for can be obtained as output data.

According to one embodiment, the camera 310 may generate image sets by photographing the golf club 321, the golf ball 331, and the player's swing posture 341 for a preset time before and after the moment of impact. An image set may consist of a few images to hundreds of thousands of images, but is not limited to this.

According to one embodiment, the moment of impact may be the moment when the golf club touches the golf ball, and the preset time may be sufficient time to analyze the physical quantities of the subjects. This may correspond to several milliseconds (ms) to several seconds (s), but is not limited thereto.

Figure 4 is a diagram for explaining a set of images taken of golf clubs according to an embodiment.

Referring to FIG. 4, according to one embodiment, a fall point prediction device may use a set of images 400 of golf clubs. The image set 400 shown is a set of images in which the shape of a golf club taken in succession is overlapped, with the shape expressed in a solid line as the final position, and the shape of the golf club approaching it is expressed in a dotted line.

According to one embodiment, the falling point prediction device determines the speed of the golf club head at the time of impact, the angle that the surface of the head in contact with the golf ball has with respect to the ground, and the angle of the head in contact with the golf ball from the image set 400 of the golf club. The angle a plane has with respect to the target direction can be calculated.

According to one embodiment, the falling point prediction device may calculate the speed of the golf club head using the shooting time and position of the golf club head before and after the point of impact according to classical mechanics.

According to one embodiment, the falling point prediction device can receive and use standards for the ground and target direction input by the user, or use 3D terrain information input from the user and location information of the place currently preparing to strike. By doing so, it can be calculated and used in real time, but it is not limited to this.

According to one embodiment, the falling point prediction device may calculate the angle that the head's surface has with respect to the ground using the normal vector of the ground calculated from the ground height information at the position where the strike is currently prepared in the 3D terrain information. Using the position where you prepare to hit and the position of the hole, you can calculate the angle that the head surface has with respect to the target direction.

Figure 5 is a diagram for explaining a set of images taken of a golf ball according to an embodiment.

Referring to FIG. 5, according to one embodiment, a falling point prediction device may use a set of images 500 of golf balls. The image set 500 shown is a set of images in which the shape of a golf ball taken in succession is overlapped, with the shape expressed in a solid line as the final position, and the shape of the golf ball approaching it is expressed in a dotted line.

According to one embodiment, the drop point prediction device determines the speed of the golf ball at the time of impact, the angle that the initial path of the golf ball has with respect to the ground, and the initial path of the golf ball from the image set 500 of the golf ball. The angle with respect to the direction and the rotation rate of the golf ball can be calculated.

According to one embodiment, the drop point prediction device may calculate the speed of the golf ball using the shooting time and position of the golf ball before and after the point of impact according to classical mechanics.

According to one embodiment, the drop point prediction device may calculate the rotation rate of the golf ball using the shooting time and rotation degree of the golf ball before and after the point of impact according to classical mechanics.

According to one embodiment, the falling point prediction device can receive and use standards for the ground and target direction input by the user, or use 3D terrain information input from the user and location information of the place currently preparing to strike. By doing so, it can be calculated and used in real time, but it is not limited to this.

According to one embodiment, the drop point prediction device may calculate the angle that the initial path of the golf ball has with respect to the ground using the normal vector of the ground calculated from the ground height information at the position where the current hit is prepared in the 3D terrain information, , the angle that the golf ball's initial path has with respect to the target direction can be calculated using the current hitting preparation position and the hole position.

Figure 6 is a diagram for explaining a set of images taken of a player's swing posture according to an embodiment.

Referring to FIG. 6, according to one embodiment, the falling point prediction device may use a set of images 600 that capture the player's swing posture. The image set 600 shown is expressed by overlapping the player's shape taken in rapid succession. The shape expressed in a solid line is set as the final shape, and the shape of the player approaching it is expressed in a dotted line.

According to one embodiment, the falling point prediction device may obtain physical quantities for each part of the player's body from a set of images 600 that capture the player's swing posture. For example, the speed or angular velocity of a body part such as the player's arm can be obtained.

According to one embodiment, the falling point prediction device may compare the acquired physical quantity for each player's body part with the physical quantity calculated from a preset standard swing image set, and use the difference to generate posture analysis information.

According to one embodiment, the falling point prediction device generates the difference analyzed by comparing the player's swing posture with a preset swing standard image or a method for posture correction selected from a preset database based on such differences as posture analysis information. can do.

According to one embodiment, the falling point prediction device identifies a body part, obtains the speed or angular velocity of the body part, analyzes the differences with a preset swing standard image set, and selects a method for posture correction from a preset database. , a previously learned artificial intelligence neural network model can be used. The artificial intelligence neural network model used may be a model learned using images and videos taken of golf swing posture as learning data, and the artificial intelligence neural network model can be used to determine the shape and movement characteristics of body parts, and the movements of body parts in translational and rotational movements. It is possible to extract and use the characteristics of physical quantities related to . The falling point prediction device inputs a set of images of the player's body parts into a pre-trained artificial intelligence neural network model as input data, identifies the body part's identification information, the speed and angular velocity of the body part, and the differences from the preset standard swing image set. , a method for posture correction selected from a preset database can be obtained as output data.

FIG. 7 is a diagram illustrating the steps of acquiring golf club information according to an embodiment.

Referring to FIG. 7, according to one embodiment, the falling point prediction device can obtain golf club information by receiving it from the user, and the golf club information can be input through the display of the user terminal.

According to one embodiment, the drop point prediction device can receive information on the type of golf club, the manufacturer of the golf club, and the seller of the golf club for each player playing golf, and the display that receives the golf club information selects the player. It may include an area 710 for selecting a type of golf club, an area 720 for selecting a golf club type, an area 730 for selecting a manufacturer or seller of a golf club, and an area 740 for displaying a total list of golf clubs. Additionally, according to one embodiment, the drop point prediction device can obtain driver, wood, iron, wedge, etc. as types of golf clubs.

According to one embodiment, the falling point prediction device may obtain golf club information, including whether the head of the golf club being used is covered.

According to one embodiment, the falling point prediction device can perform the physical quantity calculation described in FIG. 4 by calculating the weight of the golf club and the weight of the golf club head using the input information on the type, manufacturer, and seller of the golf club. there is.

According to one embodiment, the falling point prediction device can obtain golf club information to be used in calculating physical quantities related to the golf club by allowing the user to select the golf club used by the player currently playing golf.

According to one embodiment, the falling point prediction device may determine the weight of the golf club, the weight of the golf club head, and the shape of the golf club from the acquired golf club information. This may be information previously entered to correspond to one golf club specified from golf club information.

Alternatively, according to one embodiment, if there is no corresponding previously input information, the falling point prediction device uses an artificial intelligence neural network model learned using the type and brand of the golf club as learning data to calculate the weight of the golf club, the weight of the golf club head, The shape of a golf club can be estimated. The falling point prediction device can input at least one of the type, manufacturer, and seller of a golf club as input data, and obtain the weight of the golf club, the weight of the golf club head, and the shape of the golf club as output data.

FIG. 8 is a diagram illustrating the steps of acquiring player information according to an embodiment.

Referring to FIG. 8, according to one embodiment, the drop point prediction device can obtain player information by receiving player information input from the user, and the player information can be input through the display of the user terminal.

According to one embodiment, the drop point prediction device can receive information about the player's name, age, and gender for each player playing golf, and the display that receives golf club information can input the player's name. It may include, but is not limited to, an area 810 for selecting the player's gender, an area 820 for selecting the player's gender, and an area 840 for selecting the player's age, but is not limited to this and may include additional information such as the player's height and weight, and the player's skill. More input can be received.

Figure 9 is a diagram for explaining 3D terrain information according to an embodiment.

According to one embodiment, the fall point prediction device may receive input from the user of 3D terrain information, golf course temperature, golf course humidity, golf course wind speed, and golf course wind direction. Meanwhile, temperature, humidity, wind speed, and wind direction can be input to the drop point prediction device in real time from a separate measuring device.

Referring to FIG. 9, according to one embodiment, the 3D terrain information 900 input by the user includes the plane distance of the golf course, height, passageway used by the cart 910, positions of tee boxes 920, fairway area, It may include location information of the rough area, bunker area, green area, fringe area, OB area area, hazard area, and hole, and may include friction coefficient information for each area.

According to one embodiment, the falling point prediction device estimates the final expected position from the expected falling point, which will be explained with reference to FIG. 11A below, by using the plane distance of the golf course, the height, the type of area where the golf ball will be located, and the Friction coefficient information is available. For example, the drop point prediction device can predict the direction the golf ball is heading after the first drop using the normal vector of the ground at the expected drop point, and can predict where the rolling golf ball will stop using the friction coefficient in the corresponding area.

Figure 10 is a diagram for explaining the step of generating tee shot location information according to an embodiment.

A golf tee shot refers to the first shot hit in each hole, and the tee box is the area where the tee shot is performed. Generally, it is divided into four types of tee boxes, and the allocation of tee boxes varies depending on the player's physical ability and skill level. The higher the physical ability and skill level, the farther away the tee box is from the hole. Figure 10 is an enlarged representation of the positions 920 of the tee boxes in Figure 9. In Figure 10, the red tee (1010), yellow tee (1020), white tee (1030), and blue tee (1040) are shown from the closest to the hole. It is assumed to be

According to one embodiment, the falling point prediction device can automatically assign the location of the tee shot for each player according to the player information described in detail in FIG. 8. For example, the drop point prediction device may assign a red tee (1010) if the player currently performing the tee shot is an amateur female in her 20s. Alternatively, if the player performing the tee shot is an amateur male in his 50s, a yellow tee (1020) can be assigned. Alternatively, if the player performing the tee shot is a professional male in his 30s, a blue tee (1040) can be assigned. According to one embodiment, the drop point prediction device may generate tee shot location information based on previously assigned information and display this information on the display of the user terminal.

FIG. 11A is a diagram illustrating the step of generating final expected location information using a virtual space reproduced in one embodiment.

According to one embodiment, the falling point prediction device may generate an expected trajectory 1110 based on input information and image sets, and the falling point predicting device may generate the speed of the golf ball at the time of impact, the speed of the golf club head, and the impact. The angle that the side of the head that touches the golf ball has with respect to the ground at the time of impact, the angle that the initial path of the golf ball has with respect to the ground at the time of impact, the angle that the side of the head that touches the golf ball has with respect to the target direction at the time of impact, impact The expected trajectory 1110 can be generated by calculating the angle that the initial path of the golf ball has with respect to the target direction at the time and the rotation rate of the golf ball.

According to one embodiment, the speed of the golf ball and the speed of the golf club head can be used to calculate the distance the golf ball moves in a direction parallel to the ground or in a direction perpendicular to the ground.

According to one embodiment, the angle that the initial path of the golf ball has with respect to the ground at the time of impact and the angle that the surface of the head in contact with the golf ball has with respect to the target direction at the time of impact are the rotation amount of the golf ball and the golf ball with respect to the ground. It can be used to calculate the distance in relation to the vertical movement distance.

According to one embodiment, the angle that the surface of the head that touches the golf ball at the time of impact has with respect to the target direction, and the angle that the initial path of the golf ball has with respect to the target direction at the time of impact calculates the side spin given to the golf ball, , can be used to calculate the angle at which the expected trajectory deviates from the target direction.

According to one embodiment, the total spin rate of the golf ball may be used to calculate fades and slices.

According to one embodiment, when the drop point prediction device generates the expected trajectory 1110 with the calculated value, it additionally considers the influence on the calculated value according to the temperature, humidity, wind direction, and wind speed of the golf course. Trajectories can be created. For example, if the wind direction is opposite to the direction in which the golf ball flies, a different expected trajectory can be generated by calculating the force that air resistance exerts on the golf ball.

According to one embodiment, the falling point prediction device may generate an expected trajectory by inputting a set of images into a previously learned trajectory estimation model and obtaining 3D coordinate information of the golf ball over time. For example, the drop point prediction device inputs a set of images in which the entire swing scene was captured into a previously learned trajectory estimation model, or inputs a set of images of the golf club and/or golf ball extracted from the image set in which the entire swing scene was captured. It can be input into the learned trajectory estimation model.

The previously learned trajectory estimation model according to one embodiment may include a learning model learned using image sets taken before and after the point of impact and the trajectory of a golf ball corresponding to the image sets as learning data. At this time, the expected trajectory may be a trajectory generated according to the 3D coordinate information of the golf ball. For example, in a three-dimensional coordinate space with the golf ball position at the point of impact as the origin, the expected trajectory may be the golf ball's position over time mapped onto the three-dimensional coordinate space.

According to another embodiment, the drop point prediction device uses a set of images to determine the speed of the golf ball at the time of impact, the angle that the initial path of the golf ball has with respect to the ground at the time of impact, and the initial path of the golf ball at the time of impact. Estimation is made by calculating at least one of the angle with respect to the direction, the rotation rate of the golf ball, and the rotation axis of the golf ball, inputting the calculated value into a previously learned trajectory estimation model, and obtaining 3D coordinate information according to time of the golf ball. Trajectories can be created.

The drop point prediction device according to one embodiment uses a set of images to determine the speed of the golf ball at the time of impact, the angle that the initial path of the golf ball has with respect to the ground at the time of impact, and the initial path of the golf ball at the time of impact in the target direction. At least one of various physical quantities related to the trajectory of the golf ball, such as the angle it has, the rotation rate of the golf ball, and the axis of rotation of the golf ball, can be calculated, and the calculated value can be input into a previously learned trajectory estimation model. At this time, the trajectory estimation model according to one embodiment may include a learning model learned using the above-mentioned physical quantity and the corresponding trajectory of the golf ball as learning data.

The previously learned trajectory estimation model uses a set of images and the resulting trajectory of a golf ball as learning data, or uses at least one physical quantity calculated from a set of images and the resulting trajectory of a golf ball as learning data, or both as learning data. Thus, a learning model that infers the expected trajectory target of the golf ball may be included. For example, trajectory estimation models include pre-net, CBHG module, Deep Neural Network (DNN), convolutional neural network (CNN), Recurrent Neural Network (RNN), autoencoder, Generative Adversarial Network (GAN), and LSTM. It may include a learning model that infers the expected trajectory based on at least one or a combination of two or more of various artificial neural network models such as (Long Short-Term Memory Network) and BRDNN (Bidirectional Recurrent Deep Neural Network), but is not limited to these. .

Meanwhile, the falling point prediction device inputs a set of images into a trajectory estimation model and obtains 3D coordinate information about the time of the golf ball, and the first operation unit of the trajectory estimation model according to an embodiment calculates the impact point using the image set. At least one of the speed of the golf ball, the angle that the initial path of the golf ball has with respect to the ground at the time of impact, the angle that the initial path of the golf ball has with respect to the target direction at the time of impact, the rotation rate of the golf ball, and the rotation axis of the golf ball. Calculate, and the second operation unit of the trajectory estimation model can generate 3D coordinate information about the time of the golf ball using the calculated value.

The trajectory estimation model according to one embodiment may include a non-linear regression analysis model, and in this case, the model function may include the expected trajectory itself. For example, a nonlinear function that is a model function may include polynomial functions representing the x, y, and z values of a golf ball, respectively, in a three-dimensional coordinate space with x, y, and z axes. For example, the model function may include “x(t) = ax^4 + bx^3 + cx^2 + dx + e” as a quartic function representing the value of x. The trajectory estimation model according to one embodiment may include a nonlinear regression analysis model that takes as input the image set itself and/or at least one physical quantity calculated based on the image set, and has information about the coefficients of the model function as output. there is.

Meanwhile, when inputting a set of images and/or at least one calculated physical quantity into a previously learned trajectory estimation model, the fall point prediction device may further input at least one of various environmental indicators such as wind speed, wind direction, barometric pressure, humidity, or temperature. You can. At this time, the trajectory estimation model may include a learning model learned using not only a set of images and physical quantities generated based on them, but also environmental indicators and the trajectory of a golf ball as learning data. The falling point prediction device may further input at least one of various environmental indicators into the previously learned trajectory estimation model and obtain 3D coordinate information of the golf ball reflecting the environmental indicators as the expected trajectory.

According to one embodiment, the fall point prediction device can reproduce the input 3D terrain information in a virtual space 1100 using a 3D modeling technique, and the current location and generated prediction are recorded in the reproduced virtual space 1100. Information on the expected falling point 1120 can be generated using the trajectory 1110.

According to one embodiment, the reproduced virtual space 1100 may be reproduced by reflecting the physical laws of real space. After the golf club hits the golf ball, the physical quantities calculated based on the image sets and the physical quantities related to the golf club and golf ball calculated from the input information are reflected in the virtual space to generate an expected trajectory 1110 and the expected falling point. (1120) Information can be generated. For example, when the values of other physical quantities are the same, the falling point prediction device can reproduce the expected trajectory 1110 in the virtual space 1100 so that when the weight of the golf club head is large, it displays a longer plane movement distance.

According to one embodiment, the falling point prediction device reflects the height and friction coefficient of the terrain in the reproduced virtual space 1100, the temperature, humidity, wind speed, and wind direction of the golf course in the virtual space 1100, so that the golf ball is expected to fall at the expected falling point. Information on the final expected position 1130 at which the device moves from 1120 and finally stops can be generated. For example, the drop point prediction device can predict the direction the golf ball is heading after the first drop using the normal vector of the ground at the expected drop point, and can predict where the rolling golf ball will stop using the friction coefficient in the corresponding area.

The falling point prediction device can reproduce the golf course in a 3D virtual space based on 3D topographic information. At this time, the falling point prediction device according to one embodiment may generate expected falling point information by mapping the 3D coordinate information of the golf ball estimated by the trajectory estimation model into virtual space. At this time, the 3D coordinate information may include 3D coordinate values for the time of the golf ball that constitute the expected trajectory of the golf ball.

According to one embodiment, the falling point prediction device may map the 3D coordinate information of the golf ball into virtual space based on input information. For example, the falling point prediction device can obtain the location where impact is performed as input information and obtain 3D coordinate information of the golf ball in a 3D coordinate space with this as the origin. At this time, the falling point prediction device can map the 3D coordinate information of the golf ball to the virtual space by overlapping the 3D coordinate space on the reproduced virtual space.

According to another embodiment, the falling point prediction device maps the three-dimensional coordinate information of the golf ball into virtual space using a position sensor provided in the photographing device or a user terminal carried by the player and a posture sensor provided in the photographing device. You can. For example, the falling point prediction device may use the position sensor to determine the location where the impact is performed as a specific location on the golf course, and use the posture sensor to determine the coordinate axis of the three-dimensional coordinate information constituting the expected trajectory. there is. The drop point prediction device can map the 3D coordinate information of the golf ball to the virtual space by applying the determined impact position and the coordinate axis of the 3D coordinate information to the reproduced virtual space.

The drop point prediction device maps 3D coordinate information to virtual space and determines the 3D coordinates of the golf ball corresponding to the time when the golf ball falls and touches the ground as the expected drop point in virtual space to generate expected drop point information. You can.

According to one embodiment, the drop point prediction device may determine a strategy for each terrain from a preset database depending on which area of the golf course the final expected location 1130 is. For example, if the final expected location 1130 is a bunker, the strategy can be determined by how to hold the grip when hitting a bunker shot, how to position the legs when hitting a bunker shot, etc.

According to one embodiment, the fall point prediction device may create an interface that displays the reproduced virtual space 1100. On the interface, one of the expected trajectory 1110, expected falling point 1120, expected final location 1130, and strategy may be displayed along with the virtual space 1100.

According to one embodiment, the falling point prediction device provides an interface displayed on the user terminal, allowing users to check the moving target point using the user terminal while moving for the next shot.

According to one embodiment, the fall point prediction device may determine first interest information for generating a first interface that displays at least one of input information, expected trajectory 1110, and expected fall point 1120 information. At this time, the first interface may include an interface for providing information related to the trajectory of the golf ball to the user, and the first information of interest may be understood as a set of information necessary to create the first interface.

As an example, the falling point prediction device reproduces the virtual space 1100 using 3D terrain information included in the input information, and provides an expected trajectory 1110 and an expected falling point 1120 in the reproduced virtual space 1100. First information of interest for creating a first interface displaying may be determined. At this time, the first information of interest is 3D terrain information, 3D modeling information necessary to display the reproduced virtual space 1100, information about the expected trajectory 1110 on the reproduced virtual space 1100, and the reproduced virtual space. It may include location information of the expected falling point 1120 on 1100.

As another example, the drop point prediction device reproduces the virtual space 1100 using the 3D terrain information included in the input information, and calculates the real-time expected position of the golf ball in the reproduced virtual space 1100 as the expected trajectory 1110. First information of interest for creating the first interface displayed on the screen may be determined. At this time, the first information of interest is 3D terrain information, 3D modeling information necessary to display the reproduced virtual space 1100, information about the expected trajectory 1110 on the reproduced virtual space 1100, and golf according to time. It may include information on the expected position of the ball. Meanwhile, the drop point prediction device can determine the expected position information of the golf ball over time using a set of images.

Additionally, the falling point prediction device may determine second information of interest for creating a second interface that displays comparison information generated based on past swing information and current swing information. Past swing information may be related to swings performed in the past by the player who hit the golf ball, and may include information that is the subject of comparison to the swing currently performed by the player, and current swing information may include input information and images. It can be created based on a set.

Past swing information according to one embodiment may include swing information collected through virtual golf, such as screen golf, performed in the past by the player, or actual golf play performed in the field. At this time, the swing information may include the type of golf club, the type of area where the hitting is performed, the speed of the golf ball, the speed of the golf club, the angle of the golf ball, the hitting angle of the golf club, and/or the rotation amount of the golf ball. For example, past swing information may include pitch quality information, flight distance information, and/or area information of the drop point in the first past swing using a specific golf club. For another example, past swing information may include a specific player's average distance when using a specific golf club. As another example, past swing information may include swing information collected from a virtual golf play reproduced identically to the terrain of an actual golf course where golf is currently played.

Current swing information according to one embodiment may be generated based on at least one of input information and a set of images in which swing scenes are captured. For example, the current swing information may include the area where the current hitting is performed (e.g., rough, bunker, etc.), pitch type, or expected flight distance, etc., which are generated based on at least one of input information and an image set.

As an optional example, the past swing information may include swing information collected from a virtual golf play that is identical to the topography of an actual golf course where golf is currently played. For example, if the player currently performs a tee shot on the first hole, the past swing information may include swing information about the tee shot that the player performed on the first hole in a virtual golf play in which the first hole is reproduced. there is. Alternatively, if the player performs a virtual golf play in which the first hole is reproduced several times, average swing information for a plurality of tee shots performed by the player in the first hole may be included. At this time, the average swing information may include the average of all driving distances among a plurality of driving distances collected through virtual golf play.

Comparison information refers to all information provided so that the user can compare information related to the currently performed swing and the past performed swing. For example, comparative information may be provided by providing current swing information and past swing information together. Alternatively, the comparison information may include characteristics shown by comparing current swing information with past swing information. According to one embodiment, comparative information may be provided by providing both the past average distance and the current expected distance. According to another embodiment, the comparative information may include characteristics of pitches according to the current swing with respect to pitches according to corresponding past swings. At this time, when the pitch quality according to the current swing is straight, the pitch quality according to past corresponding swings may be slice characteristics.

According to one embodiment, at least one of the first interface and the second interface may be displayed on the user terminal. At this time, the user terminal may include at least one of a personal device used by the player and a public device used by a group of players. For example, the first interface and/or the second interface may be displayed on a public device, on a private device, or on both types of devices. Personal devices may include devices that are individually used by individual users, such as golf players. A personal device according to one embodiment may include a wearable device that can be worn on the body. Additionally, the shared device may include a device that is commonly used by a group of players who play golf together and/or employees who provide services for playing golf. A common device according to one embodiment may include a device provided on a golf cart. Meanwhile, the group of players playing golf together may include the player who hit the golf ball.

A wearable device that can be worn on the body according to one embodiment may include a watch, a hat, clothing, or glasses. For example, glasses, which are wearable devices, may include a display unit capable of displaying an interface on a lens portion. According to one embodiment, glasses, which are wearable devices, may further include a communication unit that receives information for displaying an interface and a control unit that controls the display unit to display the interface. When the first interface and/or the second interface are displayed on the glasses including the display unit, the user, who is a golf player, can check and analyze his/her expected trajectory 1110 immediately after hitting the golf ball and his/her current swing information. You can compare past swing information.

Meanwhile, according to one embodiment, when the first interface and/or the second interface are displayed on a device provided in a golf cart, the user, who is a golf player, moves for the next hit and checks and analyzes his/her expected trajectory 1110. You can compare your current swing information with your past swing information.

The first interface according to one embodiment may further display the location of the golf ball relative to the location of the user terminal. At this time, the location of the user terminal may be determined based on the user's input or GNSS, and the location of the golf ball may be determined based on the location where the hit was performed and the expected trajectory 1110.

According to one embodiment, the first interface may display the location of the user terminal and the estimated current location of the golf ball. For example, the first interface may display the location of the user terminal as a first icon and display the estimated current location of the golf ball as a second icon. According to an optional embodiment, when the first interface is displayed on glasses that are wearable devices, the user, who is a player, displays a first icon representing his or her location and a second icon representing the estimated current location of the golf ball immediately after hitting the golf ball. You can check it in real time until it falls and stops. Through this, the user, who is a player, can objectively check and analyze the movement of the golf ball according to his or her swing immediately after hitting the golf ball, thereby improving the user experience.

According to another embodiment, the first interface may display the estimated current coordinates of the golf ball with respect to the location of the user terminal. As an example, the first interface may display the expected current plane distance of the golf ball as a first indicator and the expected current height of the golf ball as a second indicator, based on the user terminal. For example, if the planar distance of the golf ball from the user terminal is 150m and the height is +10m, 150m can be displayed as the first indicator and +10m can be displayed as the second indicator. As another example, when the coordinates of the user terminal are set to (0,0,0) and the current coordinates of the golf ball are predicted to be (90m, 120m, 10m), the first interface is (90m, 120m, 10m) Can be displayed as the estimated current coordinates of the golf ball with respect to the location of the user terminal.

Meanwhile, the first interface and the second interface according to one embodiment may be displayed together. For example, the second interface may be displayed overlapping the first interface. As an example, the first interface may display a 3D virtual space 1100 that reproduces the current golf course and display an expected trajectory 1110 on the 3D virtual space 1100. At this time, the second interface may be displayed overlapping with the first interface. The second interface may display the current expected distance and the average distance based on swings performed in the same area (e.g., rough, bunker, etc.) using the same golf club in the past. As another example, the second interface may display the current pitch quality and expected distance, and may display the pitch quality and distance of a swing performed in a past virtual golf play as a past swing corresponding to the current swing.

FIG. 11B is a diagram for explaining an interface displayed on a user terminal according to an embodiment.

Referring to FIG. 11B, the falling point prediction device 1101 may transmit information for displaying the interface to an external device, such as a user terminal, in order to display the first interface and/or the second interface to the external device. Meanwhile, the falling point prediction device 1101 shown in FIG. 11B may correspond to the falling point prediction device 120 shown in FIG. 1, and the first to fourth player personal devices 1111 and 1112 shown in FIG. 11B. , 1113, 1114) and a common device 1121 may be included in the user terminal 110 shown in FIG. 1.

A player's personal device refers to a personal device that is individually used by each player playing golf. For example, when there are four players, the personal device used by the first player, one of the players, refers to the first player personal device 1111.

According to one embodiment, the fall point prediction device 1101 may create a first interface and/or a second interface and transmit it to an external device. The external device may include a user terminal, first to fourth player personal devices 1111, 1112, 1113, and 1114, and a public device 1121. According to another embodiment, the falling point prediction device may determine first interest information and/or second interest information and transmit the determined first interest information and/or second interest information to an external device.

The external device may receive the first interface and/or the second interface and display it through a display unit provided on the external device. Alternatively, the external device receives the first interest information and/or the second interest information, generates the first interface and/or the second interface based on the first interest information and/or the second interest information, and generates the generated first interface and/or the second interface. The first interface and/or the second interface can be displayed through a display unit provided on the external device.

At least one of the first interface and the second interface, when displayed on a personal device, may display information related to the player, and when displayed on the public device 1101, may display information related to each member included in the player group. All can be displayed. For example, when the first interface or the second interface is displayed on the first player's personal device 1111, the displayed first interface or second interface may display only information related to the first player. Alternatively, when the first interface or the second interface is displayed on the second player's personal device 1112, the displayed first interface or second interface may display only information related to the second player. For another example, when the first interface or the second interface is displayed on the public device 1121, the displayed first interface or the second interface may display all information related to each of the first to fourth players.

As an optional embodiment, the first interface may display the virtual space 1100, the player's location in the virtual space 1100, and the expected trajectory 1110. At this time, the first interface displayed on the first player's personal device 1111 may display the virtual space 1100, the location of the first player in the virtual space 1100, and the expected trajectory of the golf ball hit by the first player. . Additionally, the first interface displayed on the second player's personal device 1112 may display the virtual space 1100, the location of the second player in the virtual space 1100, and the expected trajectory of the golf ball hit by the second player. . Meanwhile, the first interface displayed on the public device 1121 displays the virtual space 1100, the positions of each of the first to fourth players on the virtual space 1100, and the golf hit by each of the first to fourth players. All expected trajectories of the ball can be displayed.

As an optional embodiment, the second interface may display comparative information about an expected distance based on the player's current swing and an average distance based on past swing information collected about the player. At this time, the second interface displayed on the first player's personal device 1111 may display comparative information about the expected distance based on the first player's current swing and the average distance based on past swing information collected for the first player. there is. Additionally, the second interface displayed on the second player's personal device 1112 may display comparative information about the expected distance based on the second player's current swing and the average distance based on past swing information collected for the second player. there is. Meanwhile, the second interface displayed on the common device 1121 provides comparison information that compares the expected distance according to the current swing of each of the first to fourth players and the average distance according to past swing information collected for each player. It can be displayed.

According to one embodiment, the drop point prediction device 1101 provides first interest information related to the player corresponding to the personal device and/or second interest information related to the corresponding player to each personal device, such as the first player personal device 1111. Information can be transmitted. Additionally, according to one embodiment, the drop point prediction device 1101 may transmit first interest information related to all players and second interest information related to all players to the public device 1121.

As an example, the first player's personal device 1111 may include glasses, which are wearable devices. The falling point prediction device 1101 may transmit first interest information related to the first player to the glasses worn by the first player, and accordingly, the glasses worn by the first player may be generated using the first interest information. 1 The interface can be displayed. At this time, the first interface may display the virtual space 1100, the location of the first player on the virtual space 1100, and the expected trajectory of the golf ball hit by the first player on the virtual space 1100. Meanwhile, the falling point prediction device 1101 may transmit second interest information related to the first player to the glasses worn by the first player, and accordingly, the glasses worn by the first player are generated using the second interest information. A second interface may be displayed. At this time, the second interface may display comparison information generated using the expected distance according to the first player's current swing and past swing information. Through this, the first player can check and analyze information related to his or her play during play.

As another example, the shared device 1121 may include a device (eg, tablet PC, etc.) installed in a golf cart. The falling point prediction device 1101 may transmit first interest information related to each of the first to fourth players to a device provided in the golf cart, and accordingly, the device provided in the golf cart generates information using the first interest information. A first interface may be displayed. At this time, the first interface may display the virtual space 1100, the positions of each of the first to fourth players on the virtual space 1100, and the expected trajectory corresponding to each of the first to fourth players on the virtual space 1100. there is. Meanwhile, the falling point prediction device 1101 may transmit second interest information related to each of the first to fourth players to a device provided in the golf cart, and accordingly, the device provided in the golf cart uses the second interest information. The created second interface can be displayed. At this time, the second interface may display comparison information generated using the expected distance according to the current swing of each of the first to fourth players and past swing information for each player. At this time, the comparison information may include information comparing the first player's expected distance and the first player's past average distance, and information comparing the second player's expected distance and the second player's past average distance. Through this, the first to fourth players can board the golf cart and check and analyze information about other players playing golf together and information related to their own play. In addition, the public device 1121 according to one embodiment can display the final expected positions for each of the first to fourth players, and can efficiently display the path of the golf cart along with the final expected positions.

Meanwhile, the first interface may display the location of the golf ball relative to the location of the user terminal. According to one embodiment, after hitting a golf ball, the first player may check the position of the golf ball relative to his or her position through a first interface displayed on the first player's personal device 1111. Through this, each player can immediately check and analyze the movement of the golf ball he or she has hit after hitting it. According to another embodiment, users such as the first to fourth players can check the position of the golf ball relative to the position of the golf cart through the first interface displayed on the common device 1121 provided in the golf cart. Through this, the path of the golf cart can be effectively displayed.

FIG. 12 is a diagram illustrating the step of generating a recommended movement path for a golf cart according to an embodiment.

Referring to FIG. 12, according to one embodiment, the drop point prediction device includes the final expected position of the golf ball hit by the first player (1211), the final expected position of the golf ball hit by the second player (1212), and the final expected position of the golf ball hit by the third player. The cart path location closest to one of the final expected positions of one golf ball (1213) or the final expected position of a golf ball hit by a fourth player (1214) can be selected.

According to one embodiment, the drop point prediction device sets the cart path location closest to the final expected position 1211 of the golf ball hit by the first player as the first position 1221, and sets the final expected position 1211 of the golf ball hit by the second player as the first position 1221. The cart path location closest to location 1212 may be selected as the second location 1222.

According to one embodiment, the falling point prediction device uses the route passing through the closest first location 1221 and the second closest location 1222 based on the current location where the shot was performed as a recommended movement path for the golf cart. It can be created, and an interface to display it can be created and provided to the user.

According to one embodiment, after the cart reaches the first position 1221, the falling point prediction device calculates the distance from the final expected position 1211 of the golf ball hit by the first player to the first position 1221 and the first position 1221. 2 The sum of the distances from the position 1222 to the final expected position 1212 of the golf ball hit by the second player is the final expected position 1211 of the golf ball hit by the first player to the final expected position 1211 of the golf ball hit by the second player. If the distance to the expected location 1212 is greater, a route where the golf cart passes only the first location 1221 and does not pass through the second location 1222 can be generated as a recommended travel path, and the golf cart hit by the first player A message is generated recommending that the method of moving from the final expected position of the ball (1211) to the final expected position (1212) of the golf ball hit by the second player is by walking, and the recommended travel path and message are displayed on the user terminal. You can.

Figure 13 is a flowchart of a method for predicting the falling point of a golf ball according to an embodiment.

Referring to FIG. 13, in step 1310, the falling point prediction device may obtain input information including golf club information and golf course information.

Golf club information may include at least one of the type of golf club, the manufacturer of the golf club, and the seller of the golf club.

Golf course information may include at least one of three-dimensional topographic information of the golf course, temperature, humidity, wind speed, and wind direction of the golf course.

The input information may include player information including at least one of the player's name, age, and gender.

The falling point prediction device may generate tee shot location information for each player based on player information.

In step 1320, the falling point prediction device may acquire a set of images in which the swing scene is captured during a preset time before and after the moment of impact.

The image set may include a first image set of golf clubs and a second image set of golf balls.

The image set may include a third image set that captures the player's swing posture for a preset time before and after the moment of impact.

The falling point prediction device may generate the player's posture analysis information based on the third image set and the preset swing standard image set.

In step 1330, the drop point prediction device may generate an expected trajectory of the golf ball based on the input information and image set.

The drop point prediction device uses a set of images to determine i) the speed of the golf ball and the speed of the golf club head at the time of impact, ii) the angle that the surface of the head that touches the golf ball has with respect to the ground at the time of impact, and the angle of the golf ball at the time of impact. The angle that the initial path has with respect to the ground, iii) the angle that the side of the head that touches the golf ball at the time of impact has with respect to the target direction, and the angle that the initial path of the golf ball has with respect to the target direction at the time of impact, and iv) the angle of the golf ball's At least one of the turnover rates can be calculated.

The fall point prediction device may generate an expected trajectory based on calculations.

According to one embodiment, the falling point prediction device may generate an expected trajectory by inputting a set of images into a previously learned trajectory estimation model and obtaining 3D coordinate information of the golf ball over time.

According to another embodiment, the drop point prediction device uses a set of images to determine the speed of the golf ball at the time of impact, the angle that the initial path of the golf ball has with respect to the ground at the time of impact, and the initial path of the golf ball at the time of impact. Estimation is made by calculating at least one of the angle with respect to the direction, the rotation rate of the golf ball, and the rotation axis of the golf ball, inputting the calculated value into a previously learned trajectory estimation model, and obtaining 3D coordinate information according to time of the golf ball. Trajectories can be created.

In step 1340, the falling point prediction device may generate expected falling point information of the golf ball based on the expected trajectory.

The falling point prediction device can reproduce the golf course in a 3D virtual space based on 3D topographic information.

The falling point prediction device may generate information on the final expected location where the golf ball will stop after falling, based on the reproduced virtual space, golf course information, and expected falling point information.

Meanwhile, the falling point prediction device can generate expected falling point information by mapping the 3D coordinate information of the golf ball into virtual space.

The drop point prediction device may generate a recommended movement path for the golf cart based on the final expected location information and 3D terrain information.

The drop point prediction device may determine a strategy included in a preset strategy database for each terrain based on the final expected location information and 3D terrain information.

The fall point prediction device may determine first interest information for creating a first interface that displays at least one of input information, expected trajectory, and expected fall point information.

The falling point prediction device may determine second information of interest for creating a second interface that displays comparison information generated based on past swing information and current swing information. At this time, the past swing information may be related to the swing performed in the past by the player who hit the golf ball, and may include information that is the subject of comparison with the swing currently performed by the player, and the current swing information may be input information. and may be generated based on the image set.

According to one embodiment, at least one of the first interface and the second interface may be displayed on the user terminal. The user terminal may include at least one of a personal device used by a player and a public device used by a group of players. At this time, the player group may include players. Meanwhile, the first interface may further display the position of the golf ball relative to the position of the user terminal.

A personal device according to an embodiment may include a wearable device that can be worn on the body, and a public device according to an embodiment may include a device installed on a golf cart. At least one of the first interface and the second interface, when displayed on a personal device, may display information related to the player, and when displayed on a public device, may display all information related to each member included in the player group. You can.

Embodiments according to the present disclosure may be implemented in the form of a computer program that can be executed through various components on a computer, and such a computer program may be recorded on a computer-readable medium. At this time, the media includes magnetic media such as hard disks, floppy disks, and magnetic tapes, optical recording media such as CD-ROMs and DVDs, magneto-optical media such as floptical disks, and ROM. , RAM, flash memory, etc., may include hardware devices specifically configured to store and execute program instructions.

Meanwhile, the computer program may be specially designed and configured for the present disclosure, or may be known and usable by those skilled in the computer software field. Examples of computer programs may include not only machine language code such as that created by a compiler, but also high-level language code that can be executed by a computer using an interpreter or the like.

According to one embodiment, methods according to various embodiments of the present disclosure may be included and provided in a computer program product. Computer program products are commodities and can be traded between sellers and buyers. The computer program product may be distributed in the form of a machine-readable storage medium (e.g. compact disc read only memory (CD-ROM)) or through an application store (e.g. Play StoreTM) or between two user devices. It may be distributed in person or online (e.g., downloaded or uploaded). In the case of online distribution, at least a portion of the computer program product may be at least temporarily stored or temporarily created in a machine-readable storage medium, such as the memory of a manufacturer's server, an application store's server, or a relay server.

Unless there is an explicit order or description to the contrary regarding the steps constituting the method according to the present disclosure, the steps may be performed in any suitable order. The present disclosure is not necessarily limited by the order of description of the steps above. The use of any examples or illustrative terms (e.g., etc.) in the present disclosure is merely to describe the present disclosure in detail, and unless limited by the claims, the scope of the present disclosure is limited by the examples or illustrative terms. It doesn't work. Additionally, those skilled in the art will recognize that various modifications, combinations and changes may be made depending on design conditions and factors within the scope of the appended claims or their equivalents.

Therefore, the spirit of the present disclosure should not be limited to the above-described embodiments, and the scope of the patent claims described below as well as all scopes equivalent to or equivalently changed from the claims are within the scope of the spirit of the present disclosure. It will be said to belong to

Claims (21)

Obtaining input information including golf club information and golf course information;
Obtaining a set of images in which the swing scene is captured during a preset time before and after the moment of impact;
generating an expected trajectory of a golf ball based on the input information and the image set; and
generating expected falling point information of the golf ball based on the expected trajectory;
A method for predicting the falling point of a golf ball, including. According to claim 1,
The method of claim 1, wherein the set of images includes a first set of images for golf clubs and a second set of images for golf balls. According to claim 1,
The step of generating the expected trajectory is,
Using the image set, i) the speed of the golf ball at the time of impact, and the speed of the golf club head, ii) the angle that the surface of the head that touches the golf ball has with respect to the ground at the time of impact, and the speed of the golf club head at the time of impact. The angle that the initial path of the golf ball has with respect to the ground, iii) the angle that the surface of the head that touches the golf ball at the time of impact has with respect to the target direction, and the initial path of the golf ball at the time of impact is calculating at least one of an angle with respect to the target direction and iv) a rotation rate of the golf ball; and
generating the expected trajectory based on the calculation;
Method, including. According to claim 1,
The golf club information includes at least one of the type of golf club, the manufacturer of the golf club, and the seller of the golf club. According to claim 1,
The input information further includes player information including at least one of the player's name, age, and gender,
The above method is,
Generating tee shot location information for each player based on the player information;
How to further include . According to claim 1,
The input information further includes player information including at least one of the player's name, age, and gender,
The image set includes a third image set in which the player's swing posture is captured during a preset time before and after the moment of impact,
The above method is,
generating posture analysis information of the player based on the third image set and a preset swing standard image set;
How to further include . According to claim 1,
The golf course information includes at least one of three-dimensional topographic information of the golf course, temperature, humidity, wind speed, and wind direction of the golf course. According to claim 7,
The above method is,
Reproducing the golf course in a 3D virtual space based on the 3D terrain information; and
Based on the reproduced virtual space, the golf course information, and the expected falling point information, generating final expected position information where the golf ball will stop after the falling;
A method further comprising: According to claim 8,
The step of generating the expected trajectory is,
A method of generating the expected trajectory by inputting the image set into a previously learned trajectory estimation model and obtaining 3D coordinate information of the golf ball over time. According to claim 8,
The step of generating the expected trajectory is,
Using the image set, the speed of the golf ball at the time of impact, the angle that the initial path of the golf ball has with respect to the ground at the time of impact, and the initial path of the golf ball at the time of impact with respect to the target direction calculating at least one of an angle, a rotation rate of the golf ball, and an axis of rotation of the golf ball; and
Generating the expected trajectory by inputting the calculated value into a previously learned trajectory estimation model and obtaining 3D coordinate information of the golf ball over time;
Method, including. According to claim 9 or 10,
The step of generating the expected falling point information is,
A method of generating the expected falling point information by mapping the three-dimensional coordinate information to the virtual space. According to claim 8,
The above method is,
generating a recommended movement path for a golf cart based on the final expected location information and the 3D terrain information;
A method further comprising: According to claim 8,
The above method is,
determining a strategy included in a preset strategy database for each terrain based on the final expected location information and the 3D terrain information;
A method further comprising: According to claim 1,
The above method is,
determining first information of interest for creating a first interface displaying at least one of the input information, the expected trajectory, and the expected falling point information;
A method further comprising: According to claim 14,
The above method is,
determining second information of interest to create a second interface displaying comparison information generated based on past swing information and current swing information;
Including more,
The past swing information is related to a swing performed in the past by the player who hit the golf ball and includes information that is the subject of comparison with the swing currently performed by the player,
The method of claim 1, wherein the current swing information is generated based on the input information and the image set. According to claim 15,
At least one of the first interface and the second interface is displayed on the user terminal,
The user terminal includes at least one of a personal device used by the player and a public device used by a group of players,
The method of claim 1, wherein the player population includes the player. According to claim 16,
The personal device includes a wearable device that can be worn on the body,
The method of claim 1, wherein the shared device includes a device mounted on a golf cart. According to claim 16,
The first interface further displays the location of the golf ball relative to the location of the user terminal. According to claim 16,
At least one of the first interface and the second interface,
When displayed on the personal device, display information related to the player,
When displayed on the public device, a method of displaying all information related to each member included in the player group. a memory in which at least one program is stored; and
a processor that operates by executing the at least one program;
Including,
The processor acquires input information including golf club information and golf course information, acquires a set of images in which swing scenes are captured during a preset time before and after the moment of impact, and determines the size of the golf ball based on the input information and the image set. An apparatus for predicting the falling point of a golf ball, generating an expected trajectory and generating expected falling point information of the golf ball based on the expected trajectory. A computer-readable recording medium recording a program for executing the method of claim 1 on a computer.