KR20090105031A - Golf clinic system using image processing method and application method thereof - Google Patents

Abstract

PURPOSE: A golf clinic system and an operating method for the same are provided, which achieve performance capability improvement of the golf swing motion. CONSTITUTION: A golf clinic system comprises lots of markers attached to the body of the golf trainee and golf club; plural image cameras collecting the swing operation of the golf trainee; an image analysis machine which analyzes the angle value and each phase data of the human body segments on a real time basis and outputs the clinic result in the report format; and a database in which motion dynamic clinic information about the swing operation is matched for the member information and is stored as digital data.

Description

GOLF CLINIC SYSTEM USING IMAGE PROCESSING METHOD AND APPLICATION METHOD THEREOF

The present invention relates to a golf clinic system using an image processing technique, and more particularly, to golf using an image processing technique that provides a clinic for the swing operation from the medical point of view by analyzing the motion of the golf practitioner's swing motion to three-dimensional data Clinic system and its operation method.

Golf, which used to be a symbol of wealth until the past few years, was a sensational popularity as a future profession for young people and a hobby and social means for middle-aged adults due to several professional golfers who are active in PGA and LPGA. Is causing.

Accordingly, many hobbyists enjoy playing golf and are interested in learning golf at golf driving ranges throughout the city before going to the field.

Since the basics of golf are very important to keep the body balance and posture stable while operating the swing, and to manage the flexibility and dynamics of the body efficiently, golf practitioners swing from professional or semi-professional golfers to learn the basics. Posture diagnosis and correction are necessary.

However, there is a lot of difficulty in systematically correcting a wrong swing posture because of the practical reasons, since a considerable time and economic investment is required to receive systematic guidance from an expert.

Therefore, the golf driving range is trying to secure more golf clubs by securing the expensive lesson fee to pay professional golfers or semi-professional golfers to enjoy golf at a low cost.

As a way to attract a lot of golf lovers who demand such a low lesson fee, a proposal to reduce the lesson fee by reducing the role of experts and to apply a map of the golf practitioner's swing motion in another way is emerging.

Among them, a representative method is to analyze the swing behavior of golf practitioners using a video camera.

A video camera analysis method for analyzing a swing movement of a golf practitioner using a conventionally provided video camera is simply a method using only a video camera and a monitor.

For example, a video camera may be installed around the golf practitioner to continuously record the golf practitioner's swing movements, connect the video camera to a monitor, and then play the recorded film to analyze the swing movement on their own, or It depends on how to get advice.

In addition, this analysis method has a disadvantage that the actual analysis is impossible because the golf practitioner's posture is different every time according to the position of the video camera to shoot the swing movement of the golf practitioner.

Most golf practitioners shoot their own swing motions with only one camera, and when playing back film, only the flat screen is displayed, which gives inaccurate evaluation of swing motions. This causes a problem that the correct swing motion cannot be obtained.

This is a device for diagnosing and correcting golf swing motion. The V1 Golf Swing Analysis software of Interactive Frontiers of USA and Computer Coach Pro of Golf Coach of USA are the one or two general home camcorders (30 ~ 60fps) for swing analysis environment. A method of analyzing a motion by configuring a video screen and displaying a video screen and an acquired image to be compared and acquired images has been applied.

In addition, Motion Clinic of MV Sports Co., Ltd. and My Swing of Pro-Time Co., Ltd. connect a general camcorder (30 ~ 60fps) to a computer to take a swing image of the subject and draw a line on the acquired image. In the analysis method, the motion analysis environment and the analysis method are the same as or similar to those described above.

As described above, the analysis of the swing motion is based on video shooting, and the result of the analysis as the analysis is performed on the two-dimensional, planar screen results in the problem that the subjective opinion of the analyst who analyzes the motion as the two-dimensional element is involved. In addition, there is a disadvantage in that it takes a considerable amount of time to analyze the swing motion, and even the swing motion of the same person has a problem that objective analysis cannot be performed at the same time point in multiple swings.

As shown in FIG. 1, in the conventional swing motion analysis through video shooting, it can be seen that a comparative analysis of angles is performed even though the positions of cameras photographing golf practitioners are different.

FIG. 1 is a photograph of an address posture of a golf practitioner, and the angles of the body joints (B) (B) shown in the two images in the same environment, although the view of the feet (A) and (A ′) is different from the captured camera image. ') Is analyzed, but since the viewpoint is different, the subjective opinion of the analyst is strongly involved, which causes the problem that objective analysis is impossible.

The present invention has been invented to solve the above problems, the object of which is to collect the swing movements of golf practitioners with two or more general cameras, extract them as three-dimensional data including the human joint movement and then analyze the real-time motion From the engineering point of view, provide a clinic for swing motion.

In addition, by obtaining objective and quantitative data for the golfer's swing motion analysis, a model is constructed and applied to a check list to provide an improvement in athletic performance.

Golf clinic system using an image processing technique according to a feature of the present invention for realizing the above object, a plurality of markers attached to the body and golf club of the golf practitioner; A plurality of cameras for collecting the swing motion of the golf practitioner as an image; Reconstruct two-dimensional images collected from the plurality of cameras into three-dimensional images, extract spatial coordinates of markers according to movement, and analyze angular values and data of each phase in real time to report the clinic results in report format. An image analyzer for outputting; Kinematic clinic information on the swing motion includes a database that is matched to the member information and stored as digital data.

In addition, the operating method of the golf clinic system using the image processing method according to the characteristics of the present invention, the process of collecting the image of the golf practitioner swing motions with a plurality of cameras; Separating the human body from the marker by processing the collected image, and reconstructing a two-dimensional image of the marker into a three-dimensional image to extract coordinates in space; The method includes extracting a segment angle value of each phase by calculating coordinate values according to spatial movement of a marker composed of a 3D image and outputting a result of real-time analysis of the swing motion.

By the above-described configuration, the present invention has an effect that can be expected to improve the performance of the golf swing motion by obtaining the quantitative data by analyzing the swing motion of the golf practitioner in three-dimensional data in real time.

In addition, it is easy to determine the motion error by an objective analysis on the swing motion of the golf practitioner, and by providing an appropriate posture correction accordingly, there is an effect that can be expected to improve performance in learning the swing motion.

In addition, the integrated solution analysis is provided through a check list developed for each process, and the swing movements of the golf practitioners are stored in a database and used as learning materials for comparing and analyzing the swing movements before or after.

DETAILED DESCRIPTION Hereinafter, exemplary embodiments of the present invention will be described in detail with reference to the accompanying drawings so that those skilled in the art may easily implement the present invention.

As those skilled in the art would realize, the described embodiments may be modified in various different ways, all without departing from the spirit or scope of the present invention.

In the drawings, parts irrelevant to the description are omitted in order to clearly describe the present invention.

In addition, when a part is said to "include" a certain component, this means that it may further include other components, except to exclude other components unless otherwise stated.

2 is a view showing a schematic configuration of a golf clinic system using an image processing technique according to an embodiment of the present invention.

In order to provide a clinic to the golf practitioner through an image processing technique, as shown in FIG. 3, a plurality of markers P1 to P12 are mounted at respective positions and golf clubs for monitoring the joints and movement of the golf practitioner. .

The markers P1-P12 are markers to which light emission is applied by an electrical method or application of a chemical fluorescent substance.

Each position to which the markers P1-P12 are attached and a name for the position are arbitrarily given names, and may be given different names according to settings, and detailed description thereof will be omitted.

To the position where the markers P1-P12 are attached, preferably the head P1, both shoulders P2, P3, the left elbow inner portion P4, and both waist portions P5, P6 of the golf practitioner. , Left wrist portion P7, both knee portions P8 and P9, both instep portions P10 and P11, and club head portion P12.

However, this position is not limited, but the number of markers may be increased or decreased according to the golfer's swing motion analysis and learning achievement, and the attachment position may be selected as various positions according to the increase or decrease of the markers.

For example, it is obvious that it can be attached to the club shaft instead of the club head portion P12.

In addition, the present invention includes a plurality of cameras 101A-101C, an image analyzer 102 and a database 103, as shown in FIG.

The cameras 101A-101C are general analog or digital cameras capable of capturing moving images. The cameras 101A-101C display the movements of the markers P1-P12 attached to each position of the golfer and the golf club at each set position during the swing operation of the golfer. The data is collected and provided to the image analyzer 102.

The cameras 101A-101C are configured as three in the drawings of the embodiment according to the present invention, but the present invention is not limited thereto. When the camera is applied with a larger number of cameras, the swing motions of the golf practitioners can be collected more precisely. do.

In addition, at least two units are installed in order to realize a 3D image.

The image analyzer 102 processes the information input from the cameras 101A-101C, extracts the movements of the markers P1-P12 attached to each position of the golf practitioner and the golf club, and then matches the spatial coordinates. The angle value of the human segment that changes according to the swing motion, the force and the moment value generated in the human body are extracted, and then digitally digitized and stored in the database 103.

Also, the image analyzer 102 analyzes the analyzed result as kinematic data from a medical point of view, outputs a golf swing abnormality sign result, and simultaneously stores the result in a database 103 to store a previous swing motion or a later swing motion. It is provided as a learning material to be compared and analyzed.

The image analyzer 102 passes a frequency band higher than a set cutoff frequency for each image data input from the three cameras 101A-101C, and attenuates a frequency band lower than the set cutoff frequency. Pass Filter) removes line segments and stains from the image and sharpens edges and contrasts.

In addition, noise may be included in the image data passing through the high pass filter, and since the noise is all detected as a ridge line, the noise included in the image data is removed by passing through a low pass filter.

In the present invention, for example, a Gaussian low pass filter is used to remove noise included in the image data.

In addition, the image analyzer 102 applies a critical region to distinguish regions of the markers attached to the golf practitioner and the golf club.

For example, the image of the human body is set to "0 (white)" based on the critical region, and the image of the marker is processed to "1 (black)" to extract only the image of the marker.

Extracting the image of the marker as "1" may be classified based on the critical region because the image of the marker is higher in brightness than the image of the human body in the image obtained through the cameras 101A-101C.

The width of the area to be included in white and black may be adjusted by adjusting the set value of the critical area.

Calculate the two-dimensional coordinate point that is the center of each marker extracted through the setting of the critical area, and then assign the same marker to each image acquired from three cameras, that is, through the region indexing process. Obtain three-dimensional coordinates of each marker.

Therefore, by analyzing the movement of the marker according to the swing movement of the golf practitioner in three-dimensional coordinates to extract the angle value of the human segment and the force and moment value generated in the human body, thereby providing a clinic.

The database 103 stores, as digital data, kinematic and kinematic clinic information on the comparatively analyzed golf practitioner's swing motions matching each member information.

Referring to the operation method of the golf clinic system according to an embodiment of the present invention including the function as described above are as follows.

In order to provide a golf clinic using the present invention, first, as shown in FIG. 3, a plurality of markers (P1-P12) to which an electrical method or a chemical method is applied to each position and golf club where monitoring of the movement of golf practitioners is required. Attached (S501).

The attachment position of the markers P1-P12 is preferably the head part P1 of the golf practitioner, both shoulder parts P2, P3, the left elbow inner part P4, both waist parts P5, P6, Left wrist part P7, both knee parts P8 and P9, both instep parts P10 and P11 and club head part P12.

However, this position is not limited, but the number of markers may be increased or decreased according to the golfer's swing motion analysis and learning achievement, and the attachment position may be selected as various positions according to the increase or decrease of the markers.

As described above, when the golf practitioner performs a swing operation with the markers P1-P12 attached (S102), the golf practitioner is installed at predetermined positions on the front and left and right sides based on the position of the golf practitioner and is set for the golf practitioner. The plurality of cameras 101A to 101C having angles transmits an image obtained by capturing an image of a golf trainee who is swinging to the image analyzer 102 (S103).

The image analyzer 102 removes line segments and spots by passing the image input from each camera 101A-101C through a high pass filter, and processes sharp changes in corners and contrasts to secure the sharpness of the image.

Then, the image preprocessing is performed to remove the noise that can be detected by the ridge line by passing the low-pass filter of the image secured (S104).

Thereafter, a threshold region is set for the brightness of the image, and the image is divided into "1" and "0" based on the threshold region, and the markers P1-P12 are separated from the region of the human body.

This is because the markers P1-P12 are brighter than the critical region, and thus are separated by "1", and are separated by "0" because the human body is dark with respect to the critical region.

When only the image of the markers P1-P12 is extracted through the setting of the critical region as described above, a two-dimensional coordinate point which is the center in the area of each marker P1-P12 is extracted (S105).

Subsequently, a grouping operation (area index processing) specifying the same markers P1-P12 in each of the images acquired by the three cameras 101A-101C is performed to be reconstructed into a 3D image and rendered as a character (S106). .

Thereafter, spatial coordinate values of the plurality of markers P1-P12 attached to the golf practitioner and the golf club are extracted from the 3D image (S107).

Then, by matching the spatial coordinates according to the swing movement of the golf practitioner to the personal body information of the golf practitioner input by the operator to extract the displacement, the speed, the angle of the center of the joint and each body segment of the golf practitioner (S108), Convert to digital numerical data (S108).

The method of extracting an analysis element necessary for the clinic of the swing motion by the image analyzer 102 from the spatial coordinates of the markers P1-P12 is as follows.

The time of back swing and down swing is extracted from the spatial movement of the marker P12, and the swing tempo is extracted as the ratio of the back swing time to the down swing time. .

The shoulder rotation angle according to the swing motion is extracted by calculating the coordinate values of the spatial movements of the markers P2, P3, P5, and P6.

The hip rotation angle is extracted by calculating the coordinates of the spatial coordinates of the global coordinates Y-axis and the markers P5 and P6 in the forward direction of the golf practitioner's swing posture.

An X-Factor Angle is extracted by analyzing the rotation angle of the shoulder with respect to the rotation angle of the extracted heap.

By calculating the coordinate values of the spatial movements of the markers P2, P3, P5, and P6, a crunch factor, which is the rotational speed of the waist and the side bending angle, is extracted.

Address → Back Swing → Down Swing → Follow Through → Finish (From Displacement of Spatial Movement of Global Coordinates X- and Y-Axis and Marker P1) Extract head translation (Head Translation, Head Up) from the swing motion connected to Finish).

By calculating the coordinate values for the spatial movement of the marker P12, the club speed at impact is extracted.

By calculating the coordinate values of the spatial movements of the markers P4, P7, and P12, a cocking angle, which is the angle of the left lower portion and the club shaft, is extracted.

The uncocking time, which is the time when the caulking angle is released, is extracted by extracting the time when the detected caulking angle becomes the maximum value.

The calculation result of the spatial coordinate values of the markers P2 and P3, the calculation result of the spatial coordinate values of the markers P5 and P6, and the calculation result of the spatial coordinate values of the markers P8 and P9 are indicated by the markers P10 and P11. The alignment state (Aim) of the body in the set-up position is extracted by comparing the result of the calculation of the spatial coordinate value of

The area of the swing surface is extracted by calculating coordinate values for the spatial movement of the markers P7 and P12.

As described above, the results of the clinic are extracted by calculating the coordinate values of the spatial movements of the markers P1-P12, and the result of the swing motion is displayed to the golf practitioner through the monitor as shown in FIG. 5. Simultaneously with the provision to be stored in the database 103 to be used as learning materials (S110).

The image analyzer 102 easily determines the error of the swing movement of the golf practitioner by an objective analysis by using the spatial information of the golf practitioner and the kinematic data obtained through the markers P1-P12, and appropriately Posture correction will be provided.

As shown in FIG. 5, the result of the golf clinic according to the swing analysis provided by the image analyzer 102 is as follows: Address → Back Swing → Down Swing → Impact → Follow Through → Swing Time, Finish, Swing Tempo, Swing Arch, Rotation Angle, Distance Distance, head up, cocking results, angle of impact club face, etc. are provided in the form of a report.

The embodiments of the present invention described above are not only implemented through the apparatus and the method, but may be implemented through a program for realizing a function corresponding to the configuration of the embodiments of the present invention or a recording medium on which the program is recorded.

Although the embodiments of the present invention have been described in detail above, the scope of the present invention is not limited thereto, and various modifications and improvements of those skilled in the art using the basic concepts of the present invention defined in the following claims are also provided. It is included in the scope of rights.

1 is a diagram of a swing motion analysis example to which a conventional video analysis method is applied.

2 is a conceptual diagram of a golf clinic system using an image processing technique according to an embodiment of the present invention.

3 is a diagram illustrating a marker attachment position and an axis applied to a golf clinic system using an image processing technique according to an exemplary embodiment of the present invention.

4 is a flowchart illustrating a method of operating a golf clinic system using an image processing technique according to an exemplary embodiment of the present invention.

5 is a report format for a swing analysis result according to an embodiment of the present invention.

<Description of Symbols for Main Parts of Drawings>

101A-101C: Image Camera 102: Image Analyzer

103: first database

Claims (14)

A plurality of markers attached to the body and golf club of the golf practitioner; A plurality of cameras for collecting the swing motion of the golf practitioner as an image; Reconstruct two-dimensional images collected from the plurality of cameras into three-dimensional images, extract spatial coordinates of markers according to movements, and analyze angular values and data for each phase in real time to report clinic results in report format. An image analyzer for outputting; A database in which kinematic clinic information on a swing motion is matched with member information and stored as digital data; Golf clinic system using an image processing technique comprising a. The method of claim 1, The marker has a light emitting function by applying an electrical and chemical method, and the golf clinic system using an image processing technique that is attached to the body part and the club that requires the monitoring of movement in the swing motion. The method of claim 1, The markers are the golfer's head (P1), both shoulders (P2) (P3), the left elbow inner (P4), both waist (P5) (P6), left wrist (P7), both knees Golf clinic system using the image processing technique attached to the minute (P8) (P9), both instep (P10) (P11), club head or shaft portion (P12). The method of claim 1, The camera is composed of at least two analog or digital cameras having a video input function, golf clinic system using an image processing method that is installed at a predetermined angle on the front and left and right sides of the golf practitioner. The method of claim 1, The image analyzer uses an image processing technique that removes line segments and stains from an input image using a high pass filter, secures sharpness by processing sudden changes in edges and contrasts, and removes noise using a low pass filter. Golf Clinic System. The method of claim 1, The image analyzer extracts a marker and a region of the human body by setting a threshold region with respect to the brightness of the image, A golf clinic system using an image processing technique that extracts two-dimensional coordinate points of a marker and then groups the same markers collected from each camera and renders them as characters of a three-dimensional image. The method of claim 1, The image analyzer extracts the swing tempo and club speed from the coordinate values of the marker P12 according to the swing movement of the golf practitioner, Extract the shoulder rotation angle from the coordinates of the markers P2, P3, P5 and P6, Extract the rotation angle of the heap from the global coordinate Y-axis and the coordinate values of the markers (P5, P6), Extract the effector from the shoulder rotation angle relative to the hip rotation angle, Extract the crunch factor from the coordinate values of the markers (P2, P3, P5, P6), Head movement is extracted from the coordinates of the global coordinates X and Y axes and the marker (P1), From the coordinate values of the markers P4, P7 and P12, the caulking angle and the uncoking point of time are extracted, Golf clinic system using an image processing technique for extracting the alignment state of the body from the coordinate values of the markers (P2, P3) (P5, P6) (P8, P9) and the coordinates of the markers (P10, P11). The method of claim 1, The image analyzer matches the golfer's body information with the three-dimensional spatial coordinates of the marker and extracts the numerical values of the golfer's body segment, club displacement, velocity, and the center of the joint as numerical data. Golf clinic system using image processing technique that analyzes data and provides clinic about swing motion. Collecting a swing motion of a golf practitioner by capturing an image with a plurality of cameras; Separating the human body from the marker by processing the collected image, and reconstructing a two-dimensional image of the marker into a three-dimensional image to extract coordinates in space; Extracting segment angle values for each phase by calculating coordinate values according to spatial movement of a marker composed of a 3D image and outputting a result of a swing motion in real time; Operation method of a golf clinic system using an image processing technique comprising a. The method of claim 9, High pass filtering of images collected by a plurality of cameras to perform sharpening processing to remove line segments and spots from the image, and low pass filtering to remove the noise contained in the image golf using the image processing technique How to use the clinic system. The method of claim 9, The real-time analysis result of the swing motion is analyzed by the kinematics from the medical point of view to predict the abnormality of the swing motion operation method of the golf clinic system using an image processing method further comprising the step of outputting the result. The method of claim 9, A method of operating a golf clinic system using an image processing technique in which a real time analysis result of the swing motion is stored in a database and used as a learning material for comparison with a previous swing motion. The method of claim 9, Separating the human body from the marker in the collected image is to set the threshold region to the brightness of the image to extract the region of the marker as "1", and to extract the human region as "0" image processing technique to extract only the image of the marker Operation method of used golf clinic system. The method of claim 9, The configuration of the three-dimensional image is a golf clinic operating method using an image processing method for processing through the grouping of the same marker for each of the two-dimensional markers collected and extracted from at least two cameras.

Images