KR101147873B1 - Screen-golf system using face recognition and control method of the same - Google Patents

Abstract

The present invention discloses a screen golf system using face recognition and a control method thereof. The present invention captures an image of a torso of a user, extracts a face region from the torso image, and analyzes the same to recognize a change in face direction and a change in size of the user. In addition, the present invention may change the direction of the image displayed on the screen to correspond to the recognized direction of the user's face, measure the distance between the user and the screen by using the size change of the user's face, the screen to correspond You can zoom in or out the video displayed on the screen. Accordingly, according to the present invention, the user can easily change the direction of the screen image by simply moving the direction of the face at the turn at the turn, without the inconvenience of manipulating the computer keyboard and returning to the turn at turn. Reduction can be performed.

Description

Screen-golf system using face recognition and control method of the same}

The present invention relates to a screen golf system and a control method thereof, and more particularly, to a screen golf system using face recognition and a control method thereof.

In recent years, with the improvement of living standards, golf has become a popular sport, and the screen golf course which is available to citizens who cannot find a golf course far from the city is rapidly spreading in the city center. The screen golf market is entering maturity beyond growth.

Such a screen golf course displays an image of a golf course as it is in a room of a certain size on a screen installed in the front of the room, and when a user hits a golf ball toward the screen using a golf club, the speed, direction, and rotation of the golf ball. It detects the movement of the golf ball on the screen and displays the expected path and distance of the golf ball in three-dimensional space to proceed with the game.

In the beginning, a series of devices installed in such a screen golf course was referred to as a tangible golf demonstration system, a virtual golf simulation system, and the like. Hereinafter, the present invention will be referred to as a screen golf system, which is called by the general public.

1 is a view showing the configuration of a conventional screen golf system.

Referring to FIG. 1, in the conventional screen golf system, the projector 12 is installed on the ceiling, and the golf course image and the golf ball are displayed on the screen 11 installed at the front.

The swing plate 14 (hereinafter, abbreviated as “at batting”) is provided with a sensor module 15 for measuring the rotation, speed, and direction of a golf ball, and the sensor values measured by the sensor module 15 are computer 16. ) Is entered.

In addition, the front of the plate 14 is installed with a camera 13 to take a picture of the user swings to display the user after the end of the shot.

The computer 16 outputs the golf course image stored therein through the projector 11, and calculates a moving direction and a path of the golf ball hit by the user using the sensor values input from the sensor module 15. It is displayed on the screen 11 through.

However, in this conventional screen golf system, the direction of movement of the golf ball is calculated and displayed with reference to the front face currently displayed on the screen 11, and unlike an open outdoor golf course, an indoor screen golf course has a narrow space due to a narrow screen ( The area displayed in 11) is limited.

Therefore, when the user changes the direction of the ball he is hitting, or wants to change the view he or she is looking at, or to zoom in or out of the image displayed on the current screen, he comes down from the turn at bat 14 The keyboard 17 and the mouse 18 connected to the computer 16 must be operated manually to change the image displayed on the screen.

In addition, if you do not like the direction of the changed image once, you have to come back from the turn at the turn and to change the image displayed on the screen by manipulating the keyboard and mouse, causing a lot of inconvenience.

An object of the present invention is to provide a screen golf system and a method of controlling the same, which allows a user to freely change a direction of an image displayed on a screen at a turn at bat, and freely zoom in or zoom out a desired image.

Screen golf system using the face recognition of the present invention for solving the above problems, the screen installed on the front; A projector for outputting a golf course image on the screen; Sensor module for measuring the speed and direction of the golf ball hit by the user; A camera for photographing an upper body image of the user; And a batting analyzer for analyzing a moving distance and a moving direction of the golf ball using the measurement result input from the sensor module, extracting a face region from an upper body image photographed by the camera, and analyzing the extracted face region. A face recognition unit for generating an image control signal instructing to change the image output on the screen to determine the face direction and corresponding to the face direction, reading graphic data stored in a graphic DB, and outputting a golf course image to the projector; And an image processing unit for synthesizing the golf ball moving image data input from the control unit with the golf course image and changing the image displayed on the screen according to a control signal input from the control unit, and an analysis result input from the batting analysis unit. According to the golf ball moving image data generated Output to the image processing unit, and according to the image control signal received from the face recognition unit and a control apparatus including a control unit for changing the image displayed on the screen by controlling the image processor.

The face recognizing unit may detect the positions of two eyes in the face region of the user and determine the direction of the user's face using the position of the eyes.

In addition, the face recognition unit detects the positions of the two eyes in the face region of the user, and if the center point of the two eyes is outside the center range of the face image, the center point of the eyes is out of the center range of the face image. The direction of can be determined.

The face recognition unit may compare the center of the user's face area with the center of the skin color area of the user's face area to determine whether the user faces upward or downward.

The face recognizing unit generates and outputs the image control signal to the controller to control an area corresponding to the direction of the user's face among the images displayed on the screen to move toward the screen center, and the controller controls the image. The image processor may be moved according to a signal to move an image displayed on the screen.

In addition, the facial recognition unit checks the face direction of the user with respect to each image frame input from the camera, and generates a direction change preliminary event corresponding to the face direction of the user when the face direction of the user faces the side. The image control signal is generated to correspond to the preliminary redirection event when the similarity is greater than or equal to a predetermined threshold by comparing the face area of the video frame where the redirection preliminary event is generated with the face area of the post-predetermined number of video frames. It can be output to the control unit.

In addition, the face recognizing unit may compare the size of the face area between the image frames while the face area faces the front, and enlarge (zoom in) or reduce the image displayed on the screen according to the change of the size of the face area. The image control signal indicating the zoom out) may be output to the controller.

The face recognition unit may enlarge (zoom in) an image displayed on the screen according to a change in the size of the face region between each image frame and a change in the position of the face region in the upper torso image while the face region faces the front. Alternatively, an image control signal indicating reduction (zoom out) may be output to the controller.

In addition, the camera, the position between the batter hit the golf ball and the screen, can be taken in the receiving groove formed from the ground inwardly to take a photograph of the upper body of the user located at the batter.

On the other hand, the control method of the screen golf system using the face recognition of the present invention for solving the above problems, (a) the screen golf system displaying a golf course image on the screen; (b) the screen golf system photographing a torso image of a user located at the turn at bat and extracting a face region from the torso image; (c) the screen golf system analyzing the face area to determine a face direction; And (d) the screen golf system moving and displaying an image of an area corresponding to the face direction toward the center of the screen.

In addition, in step (c), the position of the two eyes may be detected in the user face image, and the direction of the user face may be determined using the position of the eyes.

Also, in the step (c), when the positions of the two eyes are detected in the face region of the user and the center point of the two eyes is outside the center range of the face image, the center point of the eyes is out of the center range of the face image. The direction of the user's face may be determined.

In addition, in the step (c), it may be determined whether the user faces the face up or down by comparing the center of the user's face area with the center of the skin color area of the user's face area.

In addition, in the step (c), the direction of the face of the user is irradiated with respect to each image frame input from the camera, and the direction change preliminary event corresponding to the direction of the face of the user when the direction of the face of the user faces the side And a face area of the image frame in which the direction change preliminary event is generated and a face area of the image frame after a predetermined number, and determine a direction corresponding to the preliminary direction change event when the similarity is greater than or equal to a predefined threshold. The user may determine the direction of the face moved to control the screen image.

In addition, when the direction of the face image determined in the step (c) is directed to the front, the step (d) is to compare the size of the face region between each image frame in a state that the face area is facing to the front, As the size of the face area changes, the image displayed on the screen may be enlarged (zoom in) or reduced (zoom out).

In addition, when the direction of the face image determined in the step (c) is directed to the front, the step (d) is to compare the size of the face region between each image frame in a state that the face area is facing to the front, The image displayed on the screen may be enlarged (zoom in) or reduced (zoom out) according to a change in the size of the face area and a change in the position of the face area in the upper body image.

The present invention captures an image of a torso of a user, extracts a face region from the torso image, and analyzes the same to recognize a change in face direction and a change in size of the user. In addition, the present invention may change the direction of the image displayed on the screen to correspond to the recognized direction of the user's face, measure the distance between the user and the screen by using the size change of the user's face, the screen to correspond You can zoom in or out the video displayed on the screen.

Accordingly, according to the present invention, the user can easily change the direction of the screen image by simply moving the direction of the face at the turn at the turn, without the inconvenience of manipulating the computer keyboard and returning to the turn at turn. Reduction can be performed.

1 is a view showing the configuration of a conventional screen golf system.
2 is a diagram showing the configuration of a screen golf system according to a preferred embodiment of the present invention.
3 is a diagram illustrating an example in which a second camera for photographing a user's face is installed between a screen and a turn at bat.
Figure 4 is a block diagram functionally showing the structure of a screen golf system according to a preferred embodiment of the present invention.
5 is a flowchart illustrating a control method of a screen golf system according to a preferred embodiment of the present invention.
6 is a diagram illustrating a process of a user zooming in and out of a screen screen.
7A to 7C are diagrams illustrating an image processing process when a user rotates a face from side to side.
8 and 9 illustrate a method of determining whether a user looks left or right.
10 is a diagram illustrating an image processing process when a user faces a face up and down.
FIG. 11 is a diagram illustrating an example of a method of determining whether a user raises or lowers his head.

Hereinafter, preferred embodiments of the present invention will be described with reference to the accompanying drawings.

2 is a diagram showing the configuration of a screen golf system according to a preferred embodiment of the present invention.

Referring to FIG. 2, the screen golf system according to the present invention includes a screen 210, a swing plate 240 (abbreviated as “at batting”), a sensor module 250, a projector 220, a first camera 230, and a first one. 2 includes a camera 290, a user sensor (not shown) and the control device 260. Hereinafter, each component is demonstrated.

First, the screen 210 is installed in front of the screen golf course, the projector 220 for outputting the golf course image and the moving image of the golf ball on the front screen 210 is installed on the ceiling.

At a certain distance from the screen 210, a plate at bat 240 is installed to allow the user to hit the golf ball with a golf club. The speed, direction, and direction of the golf ball are around the plate at bat 240 where the user hits the golf ball. Sensor module 250 for detecting the rotation and the like is installed.

In addition, the first camera 230 for capturing the swing state of the user is installed on the front of the user standing on the turn at bat 240 for the swing.

Since the above-described configuration is very similar to that of the conventional screen golf system, a detailed description thereof will be omitted.

On the other hand, the screen golf system according to a preferred embodiment of the present invention is provided between the screen 210 and the plate at bat 240, the second camera 290 that can photograph the user's face located on the plate at bat 240, In the vicinity of the turn at bat, a user detector (not shown) for detecting whether the user is located in an area for screen control (screen control area) and outputting it to the control device 260 is installed.

The user sensor may be implemented as a pressure sensor installed under the screen control area, which is the front of the turn at bat 240, and may detect a pressure when the user is located in the screen control area to output a user detection signal to the control device 260.

In addition, the user detection unit is implemented as a distance measuring sensor (implemented by an ultrasonic sensor, etc.) installed in front of the turn at bat 240 to measure the distance between the user and the user detection unit to detect whether the user is located in the screen control area, the user The detection signal may be output to the control device 260.

3 is a diagram illustrating an example in which a second camera 290 for photographing a user's face is installed between the screen and the turn at bat 240.

Referring to FIG. 3, in a preferred embodiment of the present invention, the second camera 290 photographing the user's face is located inside the receiving groove 291 formed therein from the ground between the plate at bat 240 and the screen 210. Are accepted. In addition, the receiving groove 291 and the surface of the ground is provided with a transparent plate 292 for blocking the golf ball from entering the receiving groove 291, the second camera 290 through the transparent plate 292 The image of the face of the user is photographed and transmitted to the control device 260.

The transparent plate 292 prevents a golf ball from flowing into the receiving groove 291, such as a tempered glass plate or a reinforced plastic material, and the first camera 230 inside the receiving groove 291 passes through the transparent plate 292. If the configuration can shoot the user, the material is not limited.

Referring back to FIG. 2, the control device 260 may be implemented as a computer in which software for implementing the screen golf system of the present invention is installed. The control device 260 uses a sensor value input from the sensor module 250. Then, the movement direction, distance, etc. of the golf ball hit by the user is calculated and displayed on the screen 210. The configuration other than the configuration for controlling the image by detecting the face of the user, which will be described later, such as the configuration for displaying the swing image of the user, is very similar to the prior art, and thus a detailed description thereof will be omitted.

On the other hand, when the control device 260 of the present invention receives a signal from the user sensor (not shown) that the user is located in the screen control area, the control device 260 is a user in the image of the user input from the second camera 290 Detects the face and eyes of the user, detects the direction in which the user moves the face, and changes the image displayed on the screen 210 according to the direction in which the user moves.

That is, when the user turns his head to the left, the control device 260 changes the displayed image so that the image displayed on the left is moved to the center of the screen 210 based on the current user, and the user turns the head to the right. The image displayed on the right side of the user is moved to the center of the screen 210 to change the image.

In addition, the control device 260 examines the size of the user's face area in the image captured by the second camera 290 to investigate whether the user moves forward or backward in the turn at bat 240, so that the user moves forward. When the face area is detected to be larger than the previously photographed image, the image displayed on the screen 210 is zoomed-in and displayed. When the user moves backward, the face area is detected to be smaller than the previously photographed image. The image displayed on the screen 210 is zoomed out and displayed.

Figure 4 is a block diagram functionally showing the structure of a screen golf system according to a preferred embodiment of the present invention.

Referring to FIG. 4, the present invention provides a sensor module 250 installed at the batter 240 to measure information such as speed, direction, and rotation of the golf ball hit by the user, and detecting whether the user is located in the screen control area. User detection unit 280, the second camera 290 for photographing the face of the user, the first camera 230 for photographing the swing of the user, input such as a keyboard mouse for inputting information according to the user's operation Means 270, a projector 220 for outputting the video signal input from the control device 260 to the screen 210, and a control device 260 for controlling the configurations and outputting the video signal to the projector 220 It is configured to include.

The control device 260 according to the preferred embodiment of the present invention includes a batting analyzer 261, a face recognition unit 263, a controller 265, a graphic DB 269, and an image processor 267. The face recognition unit 263 includes a face region extractor 263-1, an image analyzer 263-2, and an image control signal generator 263-3.

First, the batting analyzer 261 receives sensor measurement information such as the speed, direction, and rotation of the golf ball hit by the user from the sensor module 250, and analyzes the moving direction and movement of the golf ball in a three-dimensional space. The distance, the movement trajectory, etc. are calculated and output to the control unit 265.

Like the conventional screen golf system, the first camera 230 photographs a swing of the user and outputs the swing to the controller 265, and the controller 265 outputs the swing to the user after the hit is completed.

The input means 270 is implemented with a keyboard and a mouse, so that the user can control each function included in the control device 260 using the input means 270.

Since the structure and functions of the above-described ball analysis unit 261, the first camera 230, the input unit 270, and the like are almost the same as those of the conventional screen golf device, detailed descriptions are omitted and the following description will be omitted. A description will be given focusing on the configuration of the face recognition unit 263 and the control unit 265 linked thereto.

The face recognizing unit 263 outputs the screen to the screen 210 according to the direction of the user's viewing and the distance to the screen 210 using the face image of the user located in the turn at bat 240 input from the second camera 290. The control unit 265 generates an image control signal for controlling the image to be changed in the left and right direction or the vertical direction or zooms in and out.

In detail, the face recognizer 263 includes a face region extractor 263-1, an image analyzer 263-2, and an image control signal generator 263-3.

First, the face region extractor 263-1 extracts a face region from the upper body image of the user photographed by the second camera 290 and outputs the face region to the image analyzer 263-2. As a technique for extracting a face region from a user's torso image, various methods have been introduced in the related art, and various conventional face extraction methods may be applied to the present invention. However, in the preferred embodiment of the present invention, the face region of the user is extracted using a "Viola-Jonse Object Detection" algorithm.

The image analyzer 263-2 may examine whether the face region image of the user is symmetrical to determine whether the user is looking at the front or the side (left, right, up, down). have.

In addition, the image analyzer 263-2 compares the position and size of the face region image of the user with the existing face region image to measure a distance between the user and the screen 210, and the user approaches the screen 210. Whether or not to move back the screen 210.

The image control signal generator 263-3 determines the intention of the user by using the analysis result input from the image analyzer 263-2, and changes the image currently displayed on the screen 210 according to the intention of the user. The control unit 265 generates an image control signal instructing the user to output the image control signal, and the control unit 265 controls the screen 210 screen according to the image control signal.

Hereinafter, the function performed by the face recognition unit 263 will be described in more detail with reference to FIGS. 6 to 8.

First, FIG. 6 is a diagram illustrating a process of a user zooming in and out of a screen 210 screen. Referring to FIG. 6, when the user is located at the turn at bat 240, an image captured by the second camera 290 is input to the face region extractor 263-1, and only the face region is extracted from the upper torso image of the user. It is input to the image analyzer 263-2.

The image analyzer 263-2 analyzes the face image and examines whether the user is looking at the front or the side (up, down, left, right) to generate face direction information (face direction, between two eyes). And distance from the center of the face, distance from the center of the face, the location of the center of the skin color area in the face area, etc., together with information about the size of the user's face area and the location of the face image. The signal generator 263-3 outputs the signal.

In this case, the image analyzer 263-2 may investigate whether the face region image is facing the front side in various ways. For example, when the face of the person faces the front side, it is symmetrical. In general, the face region image is inverted left and right, and compared with the original image, when the similarity of the comparison target image is greater than or equal to a predetermined threshold value, it is determined that the user faces the front face. .

In addition, it is possible to determine whether the user looks at the front using the position of the user's eyes, the center position of the two eyes detected in the face area is the center of the face image (the two eyes with the user looking at the front). The user may determine that the user has turned his or her face in a direction outside the center range of the face image when the center of the eyes is out of the center range within a predetermined distance from the line connecting the line and the center vertical line of the face.

That is, if the center point of the two eyes of the face image is outside the center range of the face image, it is determined that the face is lifted up, if it is down, it is determined that the face is bowed down, and if it is left or right, the face is turned left or right. Judging.

In addition, the degree of the center of the skin color region in the face region may be determined by using the degree of deviation from the center of the face region to determine whether the user lifts the face up, down, or to the left or right.

In addition, there are various methods of determining the direction of the face, and the present invention may apply all of these methods, and thus a detailed description of the method of determining the face direction is omitted.

On the other hand, the information output from the image analyzer 263-2 to the image control signal generator 263-3 includes the above-described face direction information, absolute size information of the face image, the face image of the current frame and the face of the previous frame. It may include change information of a relative size comparing the size of the image, change information of the relative position comparing the position of the face image of the current frame and the face image of the previous frame.

The image control signal generator 263-3 uses only the size of the face image input from the image analyzer 263-2, or the user approaches the screen 210 by comprehensively considering the size and position information of the face image. Determining whether or not the user is moving away from the screen 210, and when approaching the screen 210, zooms-in the screen displayed on the screen 210, and moves away from the screen 210. If the image is lost, an image control signal instructing to zoom out the screen displayed on the screen 210 is output to the controller 265.

In this case, an example of a method of determining the distance between the user and the screen 210 by the image control signal generator 263-3 will be described with reference to FIG. 6. When the user is far from the screen 210, As shown in (a) of FIG. 6, the facial region image is small in size, and its position is located below the upper torso image of the entire user.

On the other hand, when the user approaches the screen 210, as shown in Figure 6 (b), the user's face area is larger, the position also rises upward, the user approaches the screen 210 more 6C, the face area of the user is larger than that shown in FIG. 6B, and the position thereof is located upward.

In this way, the image control signal generator 263-3 compares only the size of the face region in the face image of each frame or compares the size and position of the face region in the face image of each frame to the user in the direction of the screen 210. When approaching, the user zooms in on the screen by determining that the user intends to enlarge and view the screen displayed on the current screen 210, and when the user moves away from the screen 210, the user moves to the current screen 210. Zoom out of the screen to determine that it is intended to be further reduced.

In addition, the image control signal generator 263-3 rotates the head left or right or moves up and down to control the screen by using the information on the series of face images input from the image analyzer 263-2. In response to the determination, the control unit 265 generates an image control signal instructing to control the image displayed on the screen 210 accordingly.

7A to 7C are diagrams illustrating an image processing process when a user turns a face left and right, and FIGS. 8 and 9 are views illustrating a method of determining whether a user looks left or right.

First, referring to FIGS. 7A to 7C, the image control signal generator 263-3 may display a screen by using a face image information input from the image analyzer 263-2 as shown in FIG. 7A. If it is determined that the user looks to the front and turns his head to the right for screen control (seeing the right area), the entire image currently displayed on the screen 210 is fixed as shown in FIG. 7B. By moving the image to the left by the area, the image displayed on the right side is moved to the center by a certain portion, and the area not previously visible is displayed on the right side.

Similarly, if it is determined that the user looks straight ahead and turns his head to the left for screen control (to see more of the left area), the entire image currently displayed on the screen 210 as shown in FIG. By moving it to the right as much as possible, the image displayed on the left side is moved to the center by a certain portion, and an area not previously visible is displayed on the left side.

Referring to FIGS. 8 and 9, a method of determining whether a user looks to the left or the right is described. The image analyzer 263-2 analyzes each frame image input from the face region extractor 263-1. One piece of information is output to the image control signal generator 263-3, and the image control signal generator 263-3 controls the image using a face image of a series of frames as shown in Figs. Determine whether to generate a signal.

For example, when a face region is extracted from the face image displayed on the left side of FIG. 8 and the face image displayed on the right side, analysis is performed on the face image, and the analysis information is inputted, the image control signal generator 263- 3) examines whether each face image faces the front, that is, turned the face.

When face images 810 and 910 having turned faces are input, a direction change preliminary event is generated, and after the predetermined number of face images in which the direction change preliminary event is generated, a direction change preliminary event is generated. The images 810 and 910 are compared again.

Subsequently, as shown in FIG. 8, when the similarity of the face image is equal to or greater than a predetermined threshold value (ie, similar to the preliminary event occurrence image), a direction change event corresponding to the direction change preliminary event is generated, and the area corresponding to the corresponding direction is generated. An image control signal is generated so that the image displayed on the left or right side is moved by a predetermined portion in the center direction.

Meanwhile, as shown in FIG. 9, when the similarity of the face image is less than a predetermined threshold value (that is, when the similarity is not similar to the preliminary event occurrence image), the direction change preliminary event is canceled.

Thus, when the user detects an image in which the user turns the face to the side, the reason for generating the direction change event in comparison with the face image after a predetermined number without generating the direction change event immediately is that the user changes the face in order to control the screen. This is to distinguish the case of turning and turning the face to swing in the plate at 240.

As shown in FIG. 8, when the user turns the face to control the screen, the turning angle of the face is limited. That is, it is difficult to occur when the face is turned over the angle of looking at the edge of the screen 210. Therefore, in the case of controlling the screen, an image after a predetermined number of images in which the preliminary direction change event has occurred is an image in which the face is turned to the side slightly more than the image in which the preliminary direction change event has occurred, or after the face is turned to the side, This image is in the process of turning your face to the center.

However, as shown in FIG. 9, when the user turns his face to swing in the turn at bat 240, the face is turned by about 90 degrees with respect to the second camera 290, in which case the face is input. The image is an image 920 in which only the side of the face is shown. Accordingly, the similarity between the image 910 in which the preliminary direction change event occurs and the image 920 after the predetermined number falls below a predetermined threshold value, and the image control signal generator 263-3 causes the user to turn at bat 240. Recognizing that he turned his head in order to swing on the screen 210 does not move the screen.

In the example shown in FIGS. 8 and 9, a direction change preliminary event has occurred in the third image, and then, the screen image of the screen 210 is changed by comparing the face image (the 23rd face image) after 20 frames. Although it is determined whether or not, the image may be compared with a face image after 10 frames or a face image after 30 frames according to the number of images input to the face recognition unit 263 per second.

FIG. 10 is a diagram illustrating an image processing process when a user faces a face up and down, and FIG. 11 is a diagram illustrating an example of a method of determining whether the user raises or lowers his head.

Referring to FIG. 10, when the image control signal generator 263-3 uses the analysis result input from the image analyzer 263-2 to determine that the user looks up at the top of the screen 210 by lifting his face. By moving the screen displayed on the screen 210 down to generate a control signal so that the above partial image of interest to the user in front of the screen 210, the user bows the face to lower the screen 210 When it is determined that the user is looking at the screen, the screen displayed on the screen 210 is moved upward to generate a control signal such that the lower part image of interest to the user is displayed in front of the screen 210.

Referring to FIG. 11, an example of a method of determining whether the user's face is moved in the vertical direction will be described. The image analyzer 263-2 may detect the face region 1100 from the face region extractor 263-1. The center 1110 of the skin color region is calculated by receiving an input and calculating a region corresponding to the skin color therein.

When the user looks at the front side, as shown in FIG. 11 (b), the background image is evenly distributed in four corner portions of the rectangular area representing the face area, and the center of the skin color area is located within the error range of the center of the face area. do.

However, when the user looks up and faces the face, as shown in (a) of FIG. 11, the background image is increased at the corner near the user's forehead, while the background image is at the corner near the user's chin. As a result, the center of the skin color region is positioned below the center of the facial region than when the user looks straight ahead. That is, the center of the skin color region is located below the center of the facial region.

In addition, when the user looks down with his head down, as shown in FIG. 11 (c), the background image is increased in the corner portion near the user's chin while the background image is in the corner portion near the user's forehead. As a result, the center of the skin color region is positioned above the center of the facial region than when the user faces the front. That is, the center of the skin color region is located above the center of the facial region.

Therefore, through this process, it is possible to determine whether the user is looking upward by lifting his face or looking downward by bowing his head.

Meanwhile, the controller 265 calculates a moving distance, a moving direction, and a moving trajectory of the golf ball by using the batting analysis information input from the batting analyzer 261, as in a conventional screen golf system. ) To display on the screen 210 and to move the image currently displayed on the screen 210 in the left-right direction or the vertical direction, or to zoom in / out according to the image control signal input from the face recognition unit 263. The control signal is output to the image processor 267.

The graphic DB 269 stores a golf course image depicting a golf course selected by the user, and the image processor 267 reads graphic data from the graphic DB 269 according to a control signal of the controller 265 to the projector 220. Output

In particular, the image processing unit 267 may control and zoom in / instruct the control unit 265 to move the image displayed on the screen 210 up, down, left and right according to the image control signal received from the face recognition unit 263. The image displayed on the screen 210 is changed according to a control signal instructing to zoom out.

So far, the screen golf system according to the preferred embodiment of the present invention has been described. Hereinafter, the control method of the screen golf system described above will be described with reference to FIG. 5, which is a flowchart illustrating a method of controlling the screen golf system according to an exemplary embodiment of the present invention. However, since each function of the method for controlling the screen golf system according to the preferred embodiment of the present invention overlaps with the detailed description while explaining the function of the screen golf system of the present invention, the following briefly focuses on the overall flow. Explain.

Referring to FIG. 5, first, when the screen golf system of the present invention is operated, the golf course image selected by the user is displayed on the screen 210, the user detector 280 is operated, and the user detector 280 is operated by the user. When S is detected in the screen control area, steps S502 to S560 are performed while the user is located in the screen control area (S501).

When the user is located in the screen control area, the second camera 290 photographs a face on the area (screen control area) in which the user can control the screen with the face at a predetermined time interval and recognizes the face. Output to the unit 263 (S502), the face recognition unit 263 detects the user's face area and eyes from the captured image, and extracts the skin color area (S504). Steps S502 and S504 are continuously repeated while the user is positioned in the screen control area that is in front of the turn at bat 240.

The face recognizing unit 263 analyzes the face image extracted in step S504 to check whether the face direction faces the front (S510), and if the face faces the front, examines the change in the size of the face between the frames (S522). When the face size is changed, the image displayed on the screen 210 is zoomed in or zoomed out in response to the face size change (S524).

In the above-described step S522, it is determined whether to zoom in / out by only changing the size of the face, but as shown in FIG. 6, the face size and the position of the face area may be comprehensively determined.

On the other hand, if there is no change in the size of the face in step S522, if the user has moved the face up and down, that is, whether the head is raised or bowed down to look at the front without moving the face up and down The process proceeds to step S510 (S526).

As described above, the method of determining whether the user moves the face up and down in operation S510 may be variously applied. However, in the preferred embodiment of the present invention, as described with reference to FIG. 11, by comparing the center of the face area and the center of the skin color area to investigate whether the center of the skin color area is moved, whether the user raises or bows his head. Judgment was made.

If it is determined in step S526 that the user has moved the face up and down, the image displayed on the screen is changed according to the direction of the face (S528).

On the other hand, when the face direction is not the front in the step S510 (when the face is turned to the left and right side), as shown in Fig. 9, a direction change preliminary event is generated (S532), and the frame image after the predetermined number Comparison is made (S534).

The face recognition unit 263 determines whether the similarity is greater than or equal to the second threshold as a result of the comparison (S540), and when the similarity is less than the threshold, the user completely turns his face to hit the golf ball. Therefore, the preliminary event for changing the direction is canceled (S550), and the user waits until the user views the front face at the turn at bat 240 to control the image displayed on the screen 210 (S552).

Meanwhile, in operation S540, when the similarity is greater than or equal to the threshold, it is determined that the user moves the face direction to control the image of the screen 210, and the screen 210 is determined according to the face direction of the direction change preliminary event generation frame. By moving the image displayed in the left, right direction by a predetermined portion by the display, the user can freely control the image displayed on the screen 210 by moving the face (S560).

The present invention can also be embodied as computer-readable codes on a computer-readable recording medium. A computer-readable recording medium includes all kinds of recording apparatuses in which data that can be read by a computer system is stored. Examples of computer-readable recording media include ROM, RAM, CD-ROM, magnetic tape, floppy disk, optical data storage, and the like, which are also implemented in the form of a carrier wave (for example, transmission over the Internet). It also includes. The computer readable recording medium can also be distributed over network coupled computer systems so that the computer readable code is stored and executed in a distributed fashion.

So far I looked at the center of the preferred embodiment for the present invention. Those skilled in the art will appreciate that the present invention can be implemented in a modified form without departing from the essential features of the present invention. Therefore, the disclosed embodiments should be considered in an illustrative rather than a restrictive sense. The scope of the present invention is shown in the claims rather than the foregoing description, and all differences within the scope will be construed as being included in the present invention.

210 screen
220 projector
230 first camera
240 swing plate
250 sensor module
260 control unit
261 Batting analysis unit 263 Facial recognition unit
263-1 face region extractor 263-2 image analyzer
263-3 Video Control Signal Generator
265 Control Unit 267 Image Processing Unit
269 graphic DB
270 input means
290 second camera
291 Receiving Groove 292 Transparent Plate

Claims (16)

A front mounted screen;
A projector for outputting a golf course image on the screen;
Sensor module for measuring the speed and direction of the golf ball hit by the user;
A camera for photographing an upper body image of the user; And
A batting analyzer for analyzing the moving distance and the moving direction of the golf ball using the measurement result input from the sensor module,
Extracts a face region from the torso image captured by the camera, analyzes the extracted face region to determine a user's face direction, and outputs an image control signal instructing to change the image output on the screen to correspond to the face direction Facial recognition unit to generate,
Read the graphic data stored in the graphic DB to output the golf course image to the projector, display the golf ball moving image data input from the control unit with the golf course image, and displayed on the screen according to the control signal input from the control unit An image processor for changing an image, and
The golf ball moving image data is generated and output to the image processing unit according to the analysis result input from the batting analysis unit, and the image is displayed on the screen by controlling the image processing unit according to the image control signal input from the face recognition unit. Screen golf system comprising a control device including a control unit for changing the. The method of claim 1, wherein the face recognition unit
Screen golf system, characterized in that for detecting the position of both eyes in the user's face area, the direction of the user's face using the position of the eye. The method of claim 1, wherein the face recognition unit
The position of the two eyes is detected in the user's face area, and when the center point of the two eyes is out of the center range of the face image, the direction of the user's face is determined in a direction out of the center range of the face image. Screen golf system. The method of claim 1, wherein the face recognition unit
And comparing the center of the user's face area with the center of the skin color area of the user's face area to determine whether the user is facing up or down. The method of claim 1,
The face recognizing unit generates and outputs the image control signal for controlling the region corresponding to the direction of the user's face in the image displayed on the screen to move to the screen center direction, and outputs it to the controller.
And the controller controls the image processor to move the image displayed on the screen according to the image control signal. The method of claim 1, wherein the face recognition unit
The direction of the face of the user is examined for each image frame input from the camera, and when the direction of the face of the user faces the side, a direction change preliminary event corresponding to the direction of the user's face is generated, and the direction change preliminary event is generated. Comparing the face region of the generated image frame with the face region of the image frame after a predetermined number and generating an image control signal and outputting the image control signal to the controller when the similarity is equal to or greater than a predetermined threshold Screen golf system. The method of claim 1, wherein the face recognition unit
Image control for instructing enlargement (zoom in) or reduction (zoom out) of an image displayed on the screen according to a change in the size of the face area by comparing the size of the face area between each image frame while the face area faces the front. Screen golf system, characterized in that for outputting a signal to the control unit. The method of claim 1, wherein the face recognition unit
In the state in which the face area faces the front, an enlargement (zoom in) or reduction (zoom out) of an image displayed on the screen is indicated according to a change in the size of the face area between each image frame and a change in the position of the face area in the upper body image. A screen golf system, characterized in that for outputting an image control signal to the control unit. The method of claim 1, wherein the camera
Screen golf system, characterized in that the user shoots the upper body of the user located in the plate is accommodated in the receiving groove formed in the interior from the ground at the position between the batter hit the golf ball and the screen. (a) the screen golf system displaying a golf course image on the screen;
(b) the screen golf system photographing a torso image of a user located at the turn at bat and extracting a face region from the torso image;
(c) the screen golf system analyzing the face area to determine a face direction; And
and (d) the screen golf system moving and displaying an image of an area corresponding to the face direction toward the center of the screen. The method of claim 10, wherein step (c)
A method of controlling a screen golf system, characterized in that the position of two eyes is detected from a user's face image and the direction of the user's face is determined using the position of the eyes. The method of claim 10, wherein step (c)
The position of the two eyes is detected in the user's face area, and when the center point of the two eyes is out of the center range of the face image, the direction of the user's face is determined in a direction out of the center range of the face image. The control method of the screen golf system. The method of claim 10, wherein step (c)
And comparing the center of the user's face area with the center of the skin color area of the user's face area to determine whether the user faces the face up or down. The method of claim 10, wherein step (c)
The direction of the face of the user is examined for each image frame input from the camera, and when the direction of the face of the user faces the side, a direction change preliminary event corresponding to the direction of the user's face is generated, and the direction change preliminary event is generated. The user moves the direction corresponding to the preliminary direction change event when the similarity is more than a predetermined threshold by comparing the face area of the generated image frame with the face area of the image frame after a predetermined number. The control method of the screen golf system, characterized in that judging in the direction of the face. 11. The method of claim 10,
When the direction of the face image determined in the step (c) is directed to the front,
The step (d)
In the state where the face area faces the front side, the size of the face area between the image frames is compared, and the image displayed on the screen is enlarged (zoom in) or reduced (zoom out) according to the change of the size of the face area. Control method of screen golf system. 11. The method of claim 10,
When the direction of the face image determined in the step (c) is directed to the front,
The step (d)
In the state in which the face area faces the front side, the size of the face area between the image frames is compared to enlarge an image displayed on the screen according to the change of the size of the face area and the change of the position of the face area in the upper body image. (Zoom in) or down (zoom out).

Images