KR20230086063A - Apparatus and method for providing surrounding information on a flagstick - Google Patents

Abstract

The present invention relates to an apparatus and method for providing information around a Flagstick, which provides distance information to a Flagstick located in a hall without installing a separate sensor, and provides distance to and surrounding information from a Flagstick through a smartphone image. it's about
Flagstick surrounding information providing device of the present invention is an image acquiring unit for acquiring an image from a camera attached to the flagstick (flagstick) surrounding information providing device, an object recognizing unit for recognizing an object from the image, and information around the object from the image Includes an object surrounding information provider to provide.

Description

Apparatus and method for providing surrounding information on a flagstick based on AI {Apparatus and method for providing surrounding information on a flagstick}

The present invention relates to an apparatus and method for providing information around Flagstick, and more particularly, to providing information on a distance to Flagstick by photographing Flagstick with a smartphone. That is, the present invention relates to an apparatus and method for providing surrounding information on a Flagstick capable of providing surrounding information and a distance to a Flagstick regardless of camera performance of a smartphone.

In a golf course, a golfer needs to grasp the distance, direction, etc. between a golf ball and a hole with the naked eye, but it is difficult to intuitively grasp this related information in a golf course with a large area.

Therefore, in a golf course, in order to measure the distance between a golfer and a hole, a distance sensor is placed at an arbitrary location (mainly the center of the green) of the golf course around each hole of the golf course, and when the golfer carries the distance measurer, the data between the distance sensor and the distance measurer The distance was measured through transmission and reception and provided to the golfer. However, since the hole is not installed at one point on the green, but its location is changed according to the course change of the golf course, there is a limitation in that it is difficult to accurately measure the distance between the golf course hole and the golfer, and efforts have been made to solve this problem.

For example, in Korean Patent Registration Publication No. 10-1848892, a sensor is added to a stick fixed to a hole to measure the distance between a golfer and a hole at a golf course, thereby measuring the location of the hole on the green. A golfer's real-time accurate distance measurement system is presented even if the position is changed.

However, even in this case, since a position measurement sensor is additionally inserted to perform positioning, there is a disadvantage in that use is complicated.

Patent Registration Publication No. 10-1848892 (2018.04.09.)

An object of the present invention is to provide an apparatus and method for providing nearby information on a flagstick that provides distance information to a flagstick located in a hall without installing a separate sensor.

Another object of the present invention is to provide an apparatus and method for providing nearby information on a flagstick that provides information on a distance to and around a flagstick from an image of a smartphone.

The problems to be solved by the present invention are not limited to the problems mentioned above, and other problems not mentioned will be clearly understood by those skilled in the art from the description below.

Flagstick surrounding information providing device according to the present invention includes an image acquiring unit acquiring an image from a camera attached to the flagstick surrounding information providing device, an object recognizing unit recognizing an object from the image, and information around the object from the image. It may include an object surrounding information providing unit that provides.

Here, the image acquisition unit may obtain a 3D image of the surroundings of the flagstick including the flagstick from a device for providing information around the flagstick to which a 3D camera is attached.

In addition, the image acquisition unit may obtain a 2D left image and a 2D right image around the flagstick including the flagstick from a device for providing information around the flagstick to which the 2D camera is attached.

Here, the object recognition unit may recognize a flagstick as an object in the learned AI model.

In addition, the AI model may use a recurrent neural network that stores a state inside the neural network so that connections between units, which are processing units, have a circular structure and can model time-varying dynamic characteristics.

Here, learning may be performed based on an object image generated by a generative adversarial neural network that automatically creates an object close to a real object while competing with a generative model and a discrimination model.

In addition, the object surrounding information providing unit provides distance information between the flagstick surrounding information providing device and the flagstick, flagstick length information, green shape information, hole height At least one of information, green slope information, and wind information around a flagstick may be provided.

Here, the distance information, length information, and shape information are converted based on the actual size per pixel according to the distance from the flagstick surrounding information providing device from the image obtained in 3D from the flagstick surrounding information providing device can provide

In addition, the height information is obtained from the image obtained in 3D by the flagstick surrounding information providing device, and the actual size per pixel according to the distance to the flagstick surrounding information providing device and the flagstick surrounding information providing device. The built-in gravitational acceleration sensor can detect and provide the direction of the image relative to gravity.

Here, the slope information is converted based on the actual size per pixel according to the distance from the flagstick surrounding information providing device from the image obtained in 3D from the flagstick surrounding information providing device and expressed as a horizontal grid and a vertical grid. that can be characterized.

In addition, wind information may be provided by an AI model learned based on a shape change of a flagstick according to wind.

Here, the shape change may include any one of the frequency of vibration of a stick and a flag, and an angle at which a flag is blown in the wind.

In addition, the AI model may use a recurrent neural network that stores a state inside the neural network so that connections between units, which are processing units, have a circular structure and can model time-varying dynamic characteristics.

Meanwhile, learning may be performed based on an object image generated by a generative adversarial neural network that automatically creates an object close to a real object while competing with a generative model and a discrimination model.

A method for providing information around Flagstick according to another embodiment of the present invention includes an image acquisition step of obtaining an image from a camera attached to a device for providing information around Flagstick in an image acquisition unit, an object recognition unit in an object recognition unit, and an object from the image. It may include an object recognition step of recognizing , and an object surrounding information providing step of providing information around the object from an image in an object surrounding information providing unit.

In addition to this, another method for implementing the present invention, another system, and a computer readable recording medium recording a computer program for executing the method may be further provided.

An apparatus and method for providing surrounding information on Flagstick according to the present invention has an advantage of providing information on a distance to Flagstick located in a hall without installing a separate sensor.

In addition, the apparatus and method for providing surrounding information on Flagstick according to the present invention has the advantage of providing information on the distance to Flagstick and surrounding information through an image of a smartphone.

1 is a block diagram showing a flagstick peripheral information providing device according to an embodiment of the present invention.
FIG. 2 is a 3D image obtained by the apparatus for providing information around Flagstick of FIG. 1 of Flagstick, green, hole, and surrounding scenery and information around Flagstick. It is a drawing showing the target distance, which is the distance between the providing device and the hole.
FIG. 3 is a 2D left image and a 2D right image and flags obtained by the flagstick peripheral information providing device of FIG. 1 for flagstick, green, hole, and surrounding scenery. It is a diagram showing a target distance, which is the distance between a flagstick peripheral information providing device and a hole.
FIG. 4 is a diagram illustrating a horizontal grid and a vertical grid of green slope information of FIG. 4 .
5 is a flowchart illustrating a method for providing Flagstick surrounding information according to an embodiment of the present invention.

Specific embodiments for carrying out the present invention will be described with reference to the accompanying drawings.

Since the present invention can make various changes and have various embodiments, specific embodiments will be illustrated in the drawings and described in detail in the detailed description. This is not intended to limit the present invention to specific embodiments, and it can be understood to include all modifications, equivalents, and substitutes included in the spirit and scope of the present invention.

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, an apparatus and method for providing information around Flagstick according to the present invention will be described in detail with reference to the accompanying drawings.

1 is a configuration diagram showing a flagstick peripheral information providing apparatus 100 according to an embodiment of the present invention, and FIGS. 2 to 4 are detailed views for explaining FIG. 1 in detail.

Hereinafter, an apparatus for providing Flagstick surrounding information according to an embodiment of the present invention will be described with reference to FIGS. 1 to 4 .

First, referring to FIG. 1, an apparatus for providing information around Flagstick according to an embodiment of the present invention includes an image acquisition unit 110 that acquires an image from a camera attached to the apparatus 100 for providing information around Flagstick. , an object recognizing unit 120 recognizing an object from an image, and an object surrounding information providing unit 130 providing information around the object from an image.

Here, the object recognition unit 120 may recognize the flagstick 200 as an object in the learned AI model.

In addition, the AI model may use a recurrent neural network that stores a state inside the neural network so that connections between units, which are processing units, have a circular structure and can model time-varying dynamic characteristics.

Here, learning may be performed based on an object image generated by a generative adversarial neural network that automatically creates an object close to a real object while competing with a generative model and a discrimination model.

In addition, the object surrounding information providing unit 130 provides distance information between the flagstick surrounding information providing device 100 and the flagstick 200, length information of the flagstick 200, green At least one of shape information of the green 300, height information of the hole 400, slope information of the green 300, and wind information around the flagstick 200 can provide

Here, the distance information, length information, and shape information are actual per pixel according to the distance to the flagstick surrounding information providing device 100 from an image obtained in 3D from the flagstick surrounding information providing device 100. A conversion based on size can be provided.

In addition, the height information is the actual size per pixel according to the distance to the flagstick surrounding information providing device 100 from the image obtained in 3D from the flagstick surrounding information providing device 100 and the flagstick The gravitational acceleration sensor built into the surrounding information providing device 100 may detect and provide the image relative to gravity direction.

The image acquisition unit 110 may be a 3D camera or a 2D camera depending on circumstances. In the case of a 3D camera, distance information may be converted for each pixel, but in the case of a 2D camera, at least a certain distance It can be converted into a 3D image with two independent images separated from each other.

In the object recognition unit 120, the object may include any one of a flagstick 200, a green 300, and a hole 400, and these objects allow AI to learn. can be recognized through

At this time, AI learning has different recognition accuracy depending on the data provided, and collects images of flagstick 200, green 300, and hole 400 for various learning. thing has limits. On the other hand, learning can be performed very similar to the field by reproducing and learning images similar to the field through simulation.

The generative adversarial neural network reproduces an image to the extent that the image generated by the generative model cannot be distinguished from the real image in the discriminant model, enabling more accurate learning, and has the advantage of being able to artificially learn about rain or fog.

In addition, since the object may change temporally under the influence of wind, object recognition accuracy may be increased by using a recurrent neural network capable of storing a state inside the AI model.

Therefore, the flagstick peripheral information providing device according to the present invention has the advantage of improving object recognition accuracy by performing highly accurate learning through a generative adversarial network and reflecting time-varying dynamic characteristics of an object through a recurrent neural network.

Meanwhile, distance information, length information, shape information, and height information in the object surrounding information providing unit 130 are converted based on the actual size per pixel according to the distance between the flagstick surrounding information providing device 100 and the object. In particular, since the height information differs according to the angle of the gravity contrast image, it can be accurately calculated by including and converting the information of the acceleration of gravity built into the flagstick peripheral information providing device 100.

FIG. 2 shows a flagstick (200), a green (300), a hole (400), and a surrounding landscape (700) It is a diagram showing the target distance 500, which is the distance between the 3D image 600 obtained for , the flagstick nearby information providing device 100, and the hole 400.

As can be seen in FIG. 2, the image acquisition unit 110 captures the flagstick including the flagstick 200 from the flagstick peripheral information providing device 100 to which the 3D camera is attached. A 3D image 600 around 200 may be obtained.

Recently, a 3D camera is basically installed in a smartphone, and it is possible to extract distance information for each pixel. Therefore, after recognizing the flagstick 200 from the image acquired by the image acquisition unit 110, by extracting distance information of the pixel where the flagstick 200 is located, the flagstick 200 ) has the advantage of being able to extract distance information from the hole 400 on which it is mounted.

However, when the distance information is inaccurate, the height information of the flagstick 200 is received separately and the height information of the flagstick 200 is compared with the image size, thereby making the flagstick 200 The distance to the located green 300 may be easily obtained.

FIG. 3 shows a flagstick (200), a green (300), a hole (400), and a surrounding landscape (700) The target distance 500, which is the distance between the 2D left image 610 and the 2D right image 620 obtained for , the flagstick peripheral information providing device 100, and the hole 400 is the drawing shown.

As can be seen in FIG. 3, the image acquisition unit 110 captures the flagstick including the flagstick 200 from the flagstick peripheral information providing device 100 to which the 2D camera is attached. A 2D left image 610 and a 2D right image 620 around (200) may be obtained.

In the case of a smartphone not equipped with a 3D camera, it is possible to extract distance information for each pixel because it can be converted into 3D from two images at least at a certain distance. Therefore, after recognizing the flagstick 200 from the image acquired by the image acquisition unit 110, by extracting distance information of the pixel where the flagstick 200 is located, the flagstick 200 ) has the advantage of being able to extract distance information from the hole 400 in which it is mounted.

However, when the distance information is inaccurate, the height information of the flagstick 200 is received separately and the height information of the flagstick 200 is compared with the image size, thereby making the flagstick 200 The distance to the located green 300 may be easily obtained.

FIG. 4 is a diagram showing a horizontal grid 310 and a vertical grid 320 of slope information of green 300 of FIG. 4 .

As can be seen in FIG. 4, the inclination information is actual per pixel according to the distance from the flagstick surrounding information providing device 100 from the 3D obtained image in the flagstick surrounding information providing device 100. It may be characterized in that it is converted based on the size and expressed as a horizontal grid 310 and a vertical grid 320.

In addition, the wind information may be provided by the AI model learned based on the shape change of the flagstick 200 according to the wind.

Here, the shape change may include any one of the frequency of vibration of the stick 210 and the flag 220 and the angle at which the flag 220 blows in the wind.

In addition, the AI model may use a recurrent neural network that stores a state inside the neural network so that connections between units, which are processing units, have a circular structure and can model time-varying dynamic characteristics.

Meanwhile, learning may be performed based on an object image generated by a generative adversarial neural network that automatically creates an object close to a real object while competing with a generative model and a discrimination model.

As in FIG. 1, the flagstick 200 can be recognized through AI learning in the object recognition unit 120, and the frequency of the stick 210, the flag ( 220) changes over time. Therefore, learning may be performed very similar to the field by reproducing an image similar to the field through simulation of the effect of the wind and learning it.

The generative adversarial neural network reproduces an image to the extent that the image generated by the generative model cannot be distinguished from the real image in the discriminant model, enabling more accurate learning, and has the advantage of being able to artificially learn about rain or fog.

In addition, since the object may change temporally under the influence of wind, object recognition accuracy may be increased by using a recurrent neural network capable of storing a state inside the AI model.

Therefore, the present invention has the advantage of improving object recognition accuracy by performing highly accurate learning through a generative adversarial neural network and reflecting time-varying dynamic characteristics of an object through a recurrent neural network.

5 is a flowchart illustrating a method for providing Flagstick surrounding information according to an embodiment of the present invention.

As can be seen in FIG. 5, the method for providing information around Flagstick includes acquiring an image from a camera attached to the device 100 for providing information around Flagstick in the image acquisition unit 110 (S100); The object recognizing unit 120 may include recognizing the object from the image (S200), and the object surrounding information providing unit 130 may include providing information around the object from the image (S300).

Here, if the camera is a 3D camera, distance information is converted for each pixel, and in the case of a 2D camera, distance information can be converted for each pixel by converting two independent images separated by at least a certain distance into a 3D image.

In addition, the flagstick 200, green 300, and hole 400 recognized as objects by the object recognition unit 120 may be recognized through AI learning, and simulation Learning can be performed very similar to the field by reproducing images similar to the field through and learning them.

The generative adversarial neural network is characterized by reproducing an image to the extent that the image generated by the generative model cannot be distinguished from the real image in the discrimination model. The Flagstick peripheral information providing method according to the present invention has the advantage of performing high-accuracy learning through a generative adversarial neural network and increasing object recognition accuracy by reflecting the time-varying dynamic characteristics of an object through a recurrent neural network. there is.

As described above, the apparatus and method for providing surrounding information on Flagstick according to the present invention has the advantage of providing information on the distance to Flagstick without installing a separate sensor on Flagstick located in the hall, and provides information on the distance to Flagstick through a smartphone image. It has the advantage of providing distance and surrounding information.

What has been described above includes examples of one or more embodiments. Of course, it is not possible to describe every possible combination of components or methods for purposes of describing the above embodiments, but those skilled in the art will recognize that many additional combinations and permutations of various embodiments are possible. Accordingly, the described embodiments are intended to cover all alternatives, modifications and adaptations falling within the spirit and scope of the appended claims.

The method according to an embodiment of the present invention described above may be implemented as a program (or application) to be executed in combination with a server, which is hardware, and stored in a medium.

The aforementioned program is C, C++, JAVA, machine language, etc. It may include a code coded in a computer language of. These codes may include functional codes related to functions defining necessary functions for executing the methods, and include control codes related to execution procedures necessary for the processor of the computer to execute the functions according to a predetermined procedure. can do. In addition, these codes may further include memory reference related codes for which location (address address) of the computer's internal or external memory should be referenced for additional information or media required for the computer's processor to execute the functions. there is. In addition, when the processor of the computer needs to communicate with any other remote computer or server in order to execute the functions, the code uses the computer's communication module to determine how to communicate with any other remote computer or server. It may further include communication-related codes for whether to communicate, what kind of information or media to transmit/receive during communication, and the like.

The storage medium is not a medium that stores data for a short moment, such as a register, cache, or memory, but a medium that stores data semi-permanently and is readable by a device. Specifically, examples of the storage medium include ROM, RAM, CD-ROM, magnetic tape, floppy disk, optical data storage device, etc., but are not limited thereto. That is, the program may be stored in various recording media on various servers accessible by the computer or various recording media on the user's computer. In addition, the medium may be distributed to computer systems connected through a network, and computer readable codes may be stored in a distributed manner.

Steps of a method or algorithm described in connection with an embodiment of the present invention may be implemented directly in hardware, implemented in a software module executed by hardware, or implemented by a combination thereof. A software module may include random access memory (RAM), read only memory (ROM), erasable programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), flash memory, hard disk, removable disk, CD-ROM, or It may reside in any form of computer readable recording medium well known in the art to which the present invention pertains.

Although the embodiments of the present invention have been described with reference to the accompanying drawings, those skilled in the art to which the present invention pertains can be implemented in other specific forms without changing the technical spirit or essential features of the present invention. you will be able to understand Therefore, it should be understood that the embodiments described above are illustrative in all respects and not restrictive.

Claims (15)

An image acquiring unit acquiring an image from a camera attached to a flagstick peripheral information providing device;
an object recognizing unit recognizing an object from the image; and
Flagstick surrounding information providing device comprising a; object surrounding information providing unit for providing information around the object from the image. According to claim 1,
The image acquisition unit acquires a three-dimensional image of the surroundings of the flagstick including the flagstick from the information providing device around the flagstick to which the three-dimensional camera is attached. information provision device. According to claim 1,
The image obtaining unit acquires a 2D left image and a 2D right image around the flagstick including the flagstick from the device for providing information around the flagstick to which the 2D camera is attached. Flagstick peripheral information providing device characterized by. According to claim 1,
The object recognition unit recognizes a flagstick as an object in the learned AI model. According to claim 4,
The AI model uses a recurrent neural network that stores states inside the neural network so that connections between units, which are processing units, have a cyclic structure and can model time-varying dynamic characteristics. Flagstick peripheral information providing device. According to claim 4,
The learning is performed based on an object image generated by a generative adversarial neural network that automatically creates an object close to the real while the generative model and the discrimination model compete. Flagstick peripheral information providing device. According to claim 1,
The object surrounding information providing unit may provide distance information between the flagstick surrounding information providing device and the flagstick, length information of the flagstick, green shape information, and hole information. An apparatus for providing information around a flagstick, characterized in that for providing at least one of height information of the green, slope information of the green, and wind information around the flagstick. According to claim 7,
The distance information, the length information, and the shape information are actual per pixel according to the distance to the flagstick surrounding information providing device from the image obtained in 3D by the flagstick surrounding information providing device. A flagstick peripheral information providing device characterized in that it is converted and provided based on the size. According to claim 7,
The height information includes the actual size per pixel according to the distance from the flagstick surrounding information providing device and the surroundings of the flagstick from the image obtained in 3D by the flagstick surrounding information providing device. Flagstick peripheral information providing device, characterized in that for detecting and providing the gravity contrast direction of the image with a gravitational acceleration sensor built into the information providing device. According to claim 7,
The tilt information is converted based on the actual size per pixel according to the distance from the flagstick surrounding information providing device from the image obtained in 3D by the flagstick surrounding information providing device, and the horizontal grid and vertical Flagstick peripheral information providing device, characterized in that displayed in a grid. According to claim 7,
The wind information is provided by an AI model learned based on a shape change of the flagstick according to the wind. According to claim 11,
The shape change includes any one of the frequency of a stick and a flag, and an angle at which the flag blows in the wind. According to claim 11,
The AI model uses a recurrent neural network that stores states inside the neural network so that connections between units, which are processing units, have a cyclic structure and can model time-varying dynamic characteristics. Flagstick peripheral information providing device. According to claim 11,
The learning is performed based on an object image generated by a generative adversarial neural network that automatically creates an object close to the real while the generative model and the discrimination model compete. Flagstick peripheral information providing device. An image acquisition step of obtaining an image from a camera attached to a flagstick peripheral information providing device in an image acquisition unit;
an object recognizing step of recognizing an object from the image in an object recognizing unit; and
A flagstick surrounding information providing method comprising: providing information around the object from the image in an object surrounding information providing unit.

Images