WO2014109544A1 - 운동하는 볼에 대한 센싱장치 및 센싱방법과, 운동하는 볼의 스핀 산출을 위한 볼 이미지의 이미지 처리방법 - Google Patents
운동하는 볼에 대한 센싱장치 및 센싱방법과, 운동하는 볼의 스핀 산출을 위한 볼 이미지의 이미지 처리방법 Download PDFInfo
- Publication number
- WO2014109544A1 WO2014109544A1 PCT/KR2014/000197 KR2014000197W WO2014109544A1 WO 2014109544 A1 WO2014109544 A1 WO 2014109544A1 KR 2014000197 W KR2014000197 W KR 2014000197W WO 2014109544 A1 WO2014109544 A1 WO 2014109544A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- image
- ball
- extracting
- feature
- spin
- Prior art date
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/246—Analysis of motion using feature-based methods, e.g. the tracking of corners or segments
-
- A—HUMAN NECESSITIES
- A63—SPORTS; GAMES; AMUSEMENTS
- A63B—APPARATUS FOR PHYSICAL TRAINING, GYMNASTICS, SWIMMING, CLIMBING, OR FENCING; BALL GAMES; TRAINING EQUIPMENT
- A63B69/00—Training appliances or apparatus for special sports
- A63B69/36—Training appliances or apparatus for special sports for golf
-
- G—PHYSICS
- G03—PHOTOGRAPHY; CINEMATOGRAPHY; ANALOGOUS TECHNIQUES USING WAVES OTHER THAN OPTICAL WAVES; ELECTROGRAPHY; HOLOGRAPHY
- G03B—APPARATUS OR ARRANGEMENTS FOR TAKING PHOTOGRAPHS OR FOR PROJECTING OR VIEWING THEM; APPARATUS OR ARRANGEMENTS EMPLOYING ANALOGOUS TECHNIQUES USING WAVES OTHER THAN OPTICAL WAVES; ACCESSORIES THEREFOR
- G03B39/00—High-speed photography
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/254—Analysis of motion involving subtraction of images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
- G06V10/757—Matching configurations of points or features
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/20—Movements or behaviour, e.g. gesture recognition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20212—Image combination
- G06T2207/20224—Image subtraction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30221—Sports video; Sports image
- G06T2207/30224—Ball; Puck
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/09—Recognition of logos
Definitions
- the present invention provides a sensing device and a sensing method for a moving ball to obtain a spin of the ball by acquiring an image of the ball moving and predetermined processing and analyzing the image, and an image of the ball image for calculating the spin of the moving ball. It relates to a treatment method.
- the spin of the ball blown by the blow is rotated at a very high speed around the axis in three-dimensional space, so it is very difficult to measure it, and also requires expensive equipment for accurate measurement.
- Representative methods for measuring the spin of the ball such as using a radar sensor (Radar Sensor) and a method of analyzing the image acquired using a high-speed or high-speed camera, of which the movement using a high-speed or high-speed camera
- the method of calculating the spin of a ball is performed by displaying a specific pattern on the ball and calculating the spin axis and the amount of spin of the moving ball by analyzing a change of the specific pattern displayed on the ball in an image acquired by a high speed or ultra high speed camera. .
- the specific pattern displayed on the ball is a very simple shape, so that the spin calculation is performed by using a specific size and color or by displaying a pattern using a photosensitive material to clearly distinguish the image on the image. do.
- the spin calculation method of displaying a specific pattern on the ball and analyzing the image causes a problem of inconvenience and inconvenience of displaying a specific pattern on the ball, and is also displayed on the ball due to repeated measurements. There is a problem that the pattern may become impossible to measure as the pattern is gradually blurred or deleted.
- the present invention relates to measuring the spin by acquiring an image of a ball moving by hitting and analyzing the ball, and not displaying a specific pattern for only the spin measurement, but a logo of a ball manufacturer already displayed on the ball itself. Unspecified marks such as marks, scratches, and stains on the ball, i.e., extract the features quickly and accurately by a simple method, and use them to accurately calculate the spin axis and the amount of spin for the ball's rotation.
- the present invention provides a sensing device and a sensing method for a moving ball, and an image processing method of a ball image for calculating a spin of the moving ball.
- a sensing device for a moving ball that calculates a spin for a moving ball by acquiring and analyzing an image of a moving ball includes: Image acquisition means for acquiring a continuous image thereof; Image processing means for extracting a feature on the ball image by extracting a ball image which is an image of a ball portion from each image acquired by the image acquiring means, and removing dimples and various noise portions on the ball image; And spin calculation means for calculating the spin axis and the spin amount of the ball by analyzing the change in the position of the extracted feature on each of two successive ball images.
- the sensing method for the movement ball to calculate the spin for the movement ball by acquiring and analyzing the image of the movement ball, the ball with a predetermined feature on the surface movement Acquiring successive images thereof; Extracting a ball image which is an image of a ball portion from each of the acquired images; Extracting features on the ball image by removing dimples and various noise portions on the extracted ball image; And calculating the spin axis and the amount of spin of the ball by analyzing the change in position of the extracted feature on each of two successive ball images.
- the image processing method of the ball image for the calculation of the spin of the moving ball to obtain the image of the movement of the ball marked with a predetermined feature on the surface to calculate the spin of the ball therefrom
- An image processing method of a ball image extracted from the acquired image comprising: rotating the ball on the original image at an angle using the ball image as an original image; Extracting an n-th order difference image obtained by subtracting the original image from the rotated image of the ball; Extracting an n-th cumulative image by accumulating the n-th order difference image on an n-th order difference image or an n-1th order cumulative image; And extracting a feature on the ball from the image by performing a binarization process on the nth cumulative image according to a predetermined reference value.
- n is a natural number equal to or greater than 2.
- the sensing device and the sensing method for the ball moving in accordance with the present invention and the image processing method of the ball image for calculating the spin of the moving ball to measure the spin by acquiring an image of the ball moving by hitting, etc. and analyzing it Rather than displaying a specific pattern for spin measurements only, the ball manufacturer's logo already displayed on the ball itself or any unspecified markings such as trademarks, scratches, or stains on the ball, i.
- the sensing device and the sensing method for the ball moving in accordance with the present invention and the image processing method of the ball image for calculating the spin of the moving ball to measure the spin by acquiring an image of the ball moving by hitting, etc. and analyzing it Rather than displaying a specific pattern for spin measurements only, the ball manufacturer's logo already displayed on the ball itself or any unspecified markings such as trademarks, scratches, or stains on the ball, i.
- FIG. 1 is a block diagram briefly showing a configuration of a sensing device for a ball moving in accordance with an embodiment of the present invention.
- FIG. 2 is a diagram for explaining the function of each component from the image acquisition to the spin calculation of the ball using the configuration shown in FIG.
- FIG. 4 is an enlarged view of a ball part in FIG. 3A.
- 5A to 5C are views for explaining a process of extracting a ball part from each source image shown in FIGS. 3A to 3C.
- 6 (a) to 6 (c) show normalized images of the extracted ball images, respectively, as shown in FIGS. 5 (a) to 5 (c).
- 7 (a) to 7 (f) are time-series diagrams illustrating a process of extracting ball features from an image shown in FIG. 6 (a).
- FIG. 8 is a diagram for explaining the spin calculation of a moving ball.
- FIGS. 9 (a) and 9 (b) show normalized images of a ball image extracted from two consecutive source images, respectively.
- FIGS. 9 (c) and 9 (d) show FIGS. 9 (a) and 9 (b).
- Figures show feature images from which features are extracted from the image shown in the figure.
- the present invention basically calculates the spin of the hit ball by shooting with a predetermined camera a user hitting a golf ball (hereinafter referred to as a "ball") with a golf club and analyzing the captured image.
- a predetermined camera a user hitting a golf ball (hereinafter referred to as a "ball") with a golf club and analyzing the captured image.
- the configuration is such that a stereo camera or a 3D camera composed of a plurality of cameras can convert coordinates on a two-dimensional image of a ball into three-dimensional coordinates or vice versa.
- the sensing device and the sensing method for the movement of the ball according to the present invention and the image processing method of the ball image for calculating the spin of the movement of the ball using the analysis of the ball hitting or virtual reality based on the golf swing of the user It can be applied to various fields such as virtual golf.
- FIGS. 1 and 2 First, a sensing device for a moving ball according to an embodiment of the present invention will be described with reference to FIGS. 1 and 2.
- the sensing device for a moving ball includes an image acquisition means 100, image processing means 200 and spin calculation means 300 It is composed.
- the image acquiring means 100 may be implemented as a camera apparatus of a stereo system or a 3D camera apparatus as described above.
- FIG. 1 illustrates a case where the image acquisition means 100 is implemented as a stereo camera apparatus by the first camera 110 and the second camera 120.
- the image processing means 200 extracts a ball image, which is an image of a ball portion, from each image acquired by the image acquiring means 100, and removes dimples and various noise portions on the ball image. It is a component that extracts unspecified features such as trademarks, logos, scratches, etc., displayed on the features.
- the image processing means 200 preferably comprises a ball image extraction means 210, a ball image normalization means 220, and a ball feature extraction means 230.
- the ball image extracting means 210 is configured to extract a ball image, which is an image of a ball portion, from a source image, which is an image acquired by the image acquiring means 100, and extract a center coordinate of the ball portion. Details thereof will be described later.
- the ball image normalization means 220 normalizes the size and brightness information of each of the ball images extracted by the ball image extracting means 210, so that the ball image is changed on the source image according to the position of the ball in space. It is configured to normalize size and brightness. Details thereof will be described later.
- the ball feature extraction means 230 is a feature of the ball appearing on the image from the image that is normalized by the ball image normalization means 220 with respect to the ball image extracted by the ball image extraction means 210 It is a component that extracts parts (unspecified marks such as trademarks, logos, scratches, etc.). To this end, only the feature portion is extracted while repeating the predetermined angle rotation, difference image, and accumulation method a predetermined number of times with respect to the original image in which the image is normalized by the ball image normalization means 220. Details of this will be described later. .
- the spin calculation means 300 is configured to calculate the spin axis and the amount of spin of the ball by analyzing the change in the position of the extracted feature on each of two consecutive ball images, which will be described later.
- 3 (a) to 3 (c) illustrate the image of the ball moving in the field of view by a fixed camera at a predetermined time interval, and then removes the background portion and the like through the difference image. 22, 23) shows only the remaining state.
- the ball is flying in the left diagonal direction through (a), (b) and (c) of FIG. 3.
- the ball 21 is large as shown in (a) of FIG. 3.
- the balls 22 and 23 appear smaller as shown in FIGS. 3B and 3C.
- the image shown in (a), (b) and (c) of FIG. 3, i.e., the background part and various noise parts are removed from the first acquired image through the difference image, and only the ball part, which is the moving part, remains. This is called the source image.
- the dimple portion DP covering the surface of the ball and the feature F displayed on one side of the ball are shown.
- noises such as so-called salt and pepper noises that appear to be partially sprayed with salt or pepper, or fixed pattern noises that always appear in a fixed position.
- the bright part B1 and the darkest part D1 appear as gradations.
- 5 (a) to 5 (c) show extracting only a ball portion from each source image.
- the ball portions 21, 22, and 23 are found in the source image, and the center point of the ball portion is extracted. It is preferable that the center point becomes the center point so that the outline of the ball portion is substantially in contact with the outline of the image to be extracted so as to accurately extract it.
- the image obtained by extracting only the ball portions 21, 22, and 23 from each source image that is, the ball images 211, 212, and 213 has different sizes because they correspond to the size of the ball on each source image. Since the ball portions 21, 22, and 23 appearing on each source image have different influences of lighting depending on the distance from the camera, the brightness is also different for each ball image.
- FIGS. 5 (a) to 5 (c) show an image in which size and brightness of the ball image corresponding to FIGS. 5 (a) to 5 (c) are normalized by the ball image normalization means.
- the size of the ball image is the same by normalizing the respective ball images.
- normalization is performed by using an average value of all pixels constituting the ball portion for each ball image so that the overall brightness of each ball image is the same.
- the extraction process of the ball feature F by the ball feature extraction means is performed for each normalized ball image as shown in FIG. 7. .
- FIG. 7 (a) is a normalized ball image, which will be referred to as an original image.
- (B), (c), (d), and (e) of FIG. 7 respectively illustrate images of sequentially accumulating a difference image image obtained by subtracting the original image from an image of rotating the ball on the original image at an arbitrary angle.
- FIG. 7F is an image subjected to binarization processing for the cumulative image shown in FIG. 7E.
- the ball is rotated with respect to the original image as shown in FIG. 7 (a) by a predetermined angle or a randomly selected random angle about the center point of the ball. Extracting the difference image minus the image comes out as shown in (b) of FIG.
- the image of FIG. 7B is called a primary difference image, and the degree is increased by one so that the number of times of the difference image may be repeated.
- the portions of the two images that are changed with each other appear bright and the portions with no change appear black, so that the feature portion F is mainly bright and the remaining portions are almost black.
- the dimple Since the ball is rotated but the dimple is almost the same after the rotation, the dimple is almost unchanged (blacked out) and the gradation and various noises on the original image are also removed.
- the feature part may not be clearly displayed in one difference image, when the difference image for different angles is extracted and accumulated with the previously extracted difference image, the brighter part of the image appears brighter. It will appear bright and clear.
- FIG. 7C illustrates a difference image obtained by subtracting the original image, that is, the secondary difference image, from the image in which the ball on the original image is rotated at another preset angle or a randomly selected random angle.
- (d) is a second cumulative image of a difference image, that is, a tertiary difference image obtained by subtracting the original image from an image of rotating the ball on the original image at another preset angle or a randomly selected random angle.
- a third cumulative image accumulated on the image shown in (c) of FIG. 7 is shown.
- FIG. 7E shows a difference image obtained by subtracting the original image, that is, the fourth order image from the image of rotating the ball on the original image at another preset angle or a randomly selected random angle.
- the fourth-order cumulative image accumulated on the image shown in (d) of FIG. 7 is shown.
- the image shown in FIG. 7F is extracted by binarizing the fourth-order cumulative image using a threshold value to extract only the feature part through a threshold process or the like.
- the image shown in FIG. 7F is an image in which only the fully extracted feature FC is shown, which will be referred to as a feature image.
- each feature is extracted to provide a feature image, respectively, and spin calculation of the ball by the spin calculation means is performed using these feature images.
- the spin of the ball is coordinate information for the spin axis in the three-dimensional space according to the i-axis, j-axis and k-axis coordinate system as shown in Figure 8 and the angle rotated about the spin axis, that is, information about the amount of spin It can be calculated by calculating.
- the rotational motion in the three-dimensional space may include pitch, yaw, and roll components, respectively, and the rotational component in the i-axis direction may be rotated in the i- and j-axis directions.
- ⁇ and the rotational component in the k-axis direction ⁇ , the vector ( ⁇ ) of the spin to be obtained can be expressed as shown in [Equation 1] below.
- Equation 2 spin axis information as shown in Equation 2 below and spin amount information as shown in Equation 3 can be calculated.
- ⁇ represents spin amount information.
- the spin axis and spin amount information can be obtained by finding the yaw rotational component ⁇ , the roll rotational component ⁇ , and the pitch rotational component ⁇ with respect to the spin of the moving ball.
- Finding such spin axis and spin amount information can be made from features extracted from the ball image as shown in FIG. 7.
- each of the final extracted features FC1 and FC2 for each of the features F1 and F2 on two consecutive ball images may be included.
- the spin axis and the amount of spin may be extracted using the first feature image (FIG. 9C) and the second feature image (FIG. 9D).
- Three-dimensional position information for each pixel constituting the first feature FC1 on the first feature image (FIG. 9C) may be obtained, and an arbitrary spin axis and spin amount may be obtained in the three-dimensional position information.
- an arbitrary spin axis and spin amount information may be obtained in the three-dimensional position information.
- the spin axis and the spin amount information which is closest to the second feature part FC2 by repeatedly applying arbitrary spin axis and the spin amount information to the first feature FC1 in the final spin axis and the spin.
- the amount information it is possible to calculate the spin information for the ball moving.
- the present invention provides a method capable of quickly and accurately extracting a feature of a ball part from a source image obtained continuously by a simple method, and has the advantage of allowing a quick and accurate calculation of the spin of the ball therefrom. .
- the golf simulation can be used in the so-called screen golf industry, where the user can enjoy a virtual golf game.
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Databases & Information Systems (AREA)
- Computing Systems (AREA)
- Artificial Intelligence (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Psychiatry (AREA)
- Social Psychology (AREA)
- Human Computer Interaction (AREA)
- Physical Education & Sports Medicine (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
- Length Measuring Devices By Optical Means (AREA)
Abstract
Description
Claims (13)
- 운동하는 볼에 대한 이미지를 취득하여 분석함으로써 운동하는 볼에 대한 스핀을 산출하는 운동하는 볼에 대한 센싱장치에 있어서,표면에 소정의 특징부가 표시된 볼이 운동함에 따라 이에 대한 연속적인 이미지를 취득하는 이미지 취득수단;상기 이미지 취득수단에 의해 취득된 각 이미지에서 볼 부분에 대한 이미지인 볼 이미지를 추출하여 상기 볼 이미지 상의 딤플 부분 및 각종 노이즈 부분을 제거함으로써 상기 볼 이미지 상의 특징부를 추출하도록 하는 이미지 처리수단; 및임의의 연속하는 두 볼 이미지상에서 각각 추출된 특징부의 위치 변화를 분석함으로써 볼의 스핀축 및 스핀양을 산출하는 스핀 산출수단;을 포함하는 운동하는 볼에 대한 센싱장치.
- 제1항에 있어서, 상기 이미지 처리수단은,상기 이미지 취득수단에 의해 취득된 이미지인 소스 이미지로부터 상기 볼 이미지를 추출하고 그 중심좌표를 추출하는 볼 이미지 추출수단과,상기 볼 이미지 추출수단에 의해 추출된 볼 이미지들의 크기 및 밝기 정보에 대한 노멀라이즈 처리를 함으로써 공간상의 볼의 위치에 따라 소스 이미지 상에서 달라지는 볼의 크기 및 밝기를 정규화 하는 볼 이미지 정규화수단을 포함하여,상기 볼 이미지 정규화수단에 의해 처리된 이미지인 정규화 이미지에 대해 상기 특징부 추출이 이루어지도록 구성되는 것을 특징으로 하는 운동하는 볼에 대한 센싱장치.
- 제1항에 있어서, 상기 이미지 처리수단은,상기 볼 이미지 상의 볼을 미리 설정된 각도로 회전시키고 상기 회전시킨 이미지의 회전시키기 전의 원본 이미지 대한 차영상을 추출하며, 상기 회전 및 차영상 추출을 미리 설정된 횟수만큼 반복하여 각각 누적시킴으로써 상기 볼 이미지상의 특징부를 추출하는 볼 특징부 추출수단을 포함하는 것을 특징으로 하는 운동하는 볼에 대한 센싱장치.
- 제1항에 있어서, 상기 이미지 처리수단은,상기 이미지 취득수단에 의해 취득된 이미지인 소스 이미지로부터 볼 이미지를 추출하고 상기 추출된 볼 이미지의 중심 좌표를 추출하는 볼 이미지 추출수단과,연속하는 소스 이미지에서 각각 추출된 볼 이미지들의 크기 및 밝기 정보에 대한 노멀라이즈 처리를 함으로써 공간상의 볼의 위치에 따라 소스 이미지 상에서 달라지는 볼의 크기 및 밝기를 정규화 하는 볼 이미지 정규화수단과,상기 볼 이미지 정규화수단에 의해 처리된 이미지를 원본 이미지로 하여, 상기 원본 이미지 상의 볼을 미리 설정된 각도로 회전시키고 상기 회전시킨 이미지의 원본 이미지에 대한 차영상을 추출하며, 상기 회전 및 차영상 추출을 미리 설정된 횟수만큼 반복하여 각각 누적시킴으로써 상기 볼 이미지상의 특징부를 추출하는 볼 특징부 추출수단을 포함하는 것을 특징으로 하는 운동하는 볼에 대한 센싱장치.
- 운동하는 볼에 대한 이미지를 취득하여 분석함으로써 운동하는 볼에 대한 스핀을 산출하는 운동하는 볼에 대한 센싱방법에 있어서,표면에 소정의 특징부가 표시된 볼이 운동함에 따라 이에 대한 연속적인 이미지를 취득하는 단계;상기 취득된 각 이미지에서 볼 부분에 대한 이미지인 볼 이미지를 추출하는 단계;상기 추출된 볼 이미지 상의 딤플 부분 및 각종 노이즈 부분을 제거함으로써 상기 볼 이미지 상의 특징부를 추출하는 단계; 및임의의 연속하는 두 볼 이미지상에서 각각 추출된 특징부의 위치 변화를 분석함으로써 볼의 스핀축 및 스핀양을 산출하는 단계;를 포함하는 운동하는 볼에 대한 센싱방법.
- 제5항에 있어서, 상기 볼 이미지를 추출하는 단계는,상기 이미지를 취득하는 단계에서 취득된 이미지인 소스 이미지로부터 볼 부분을 찾는 단계와,상기 볼 부분의 중심이 이미지의 중심이 되도록 상기 볼 부분을 추출함으로써 상기 볼 이미지를 마련하는 단계를 포함하는 것을 특징으로 하는 운동하는 볼에 대한 센싱방법.
- 제5항에 있어서, 상기 볼 이미지 상의 특징부를 추출하는 단계는,연속하는 소스 이미지에서 각각 추출된 볼 이미지들의 크기에 대한 노멀라이즈 처리를 함으로써 공간상의 볼의 위치에 따라 소스 이미지 상에서 달라지는 연속하는 볼의 크기를 정규화하는 단계와,상기 볼 크기의 정규화 단계를 거친 볼 이미지 상에서 각각 특징부를 추출하는 단계를 포함하는 것을 특징으로 하는 운동하는 볼에 대한 센싱방법.
- 제5항에 있어서, 상기 볼 이미지 상의 특징부를 추출하는 단계는,상기 추출된 볼 이미지상의 각 픽셀들의 픽셀값의 평균값을 산출하고 상기 평균값을 기준으로 노멀라이즈 처리를 함으로써 볼의 밝기를 정규화하는 단계와,상기 볼의 밝기에 대한 정규화 단계를 거친 볼 이미지 상에서 각각 특징부를 추출하는 단계를 포함하는 것을 특징으로 하는 운동하는 볼에 대한 센싱방법.
- 제5항에 있어서, 상기 볼 이미지 상의 특징부를 추출하는 단계는,상기 추출된 볼 이미지를 원본 이미지로 하여, 상기 원본 이미지 상의 볼을 미리 설정된 각도로 회전시키는 단계와,상기 볼을 회전시킨 이미지의 상기 원본 이미지에 대한 차영상을 추출하여 상기 원본 이미지 상의 특징부를 추출하는 단계를 포함하는 것을 특징으로 하는 운동하는 볼에 대한 센싱방법.
- 제5항에 있어서, 상기 볼 이미지 상의 특징부를 추출하는 단계는,상기 추출된 볼 이미지를 원본 이미지로 하여, 상기 원본 이미지 상의 볼을 미리 설정된 각도 또는 랜덤하게 선택된 임의의 각도로 회전시키고 그 회전시킨 이미지에서 상기 원본 이미지를 뺀 1차 차영상을 추출하는 단계와,상기 원본 이미지 상의 볼을 미리 설정된 다른 각도 또는 랜덤하게 선택된 임의의 각도로 회전시키고 그 회전시킨 이미지에서 상기 원본 이미지를 뺀 2차 차영상을 추출하여 상기 1차 차영상에 누적시킴으로써 누적 이미지를 추출하는 단계와,상기 누적 이미지로부터 특징부를 추출하는 단계를 포함하는 것을 특징으로 하는 운동하는 볼에 대한 센싱방법.
- 제5항에 있어서, 상기 볼 이미지 상의 특징부를 추출하는 단계는,상기 추출된 볼 이미지를 원본 이미지로 하여, 상기 원본 이미지 상의 볼을 임의의 각도로 회전시키는 단계와,상기 볼을 회전시킨 이미지에서 상기 원본 이미지를 뺀 n차 차영상을 추출하는 단계와,상기 n차 차영상을 n-1차 누적 이미지에 누적시킴으로써 n차 누적 이미지를 추출하는 단계와,상기 n차 누적 이미지로부터 특징부를 추출하는 단계를 포함하는 것을 특징으로 하는 운동하는 볼에 대한 센싱방법.여기서 n은 2 이상의 자연수임.
- 제11항에 있어서, 상기 볼 이미지 상의 특징부를 추출하는 단계는,상기 n차 누적 이미지에 대해 소정의 기준값에 따른 이진화 처리하는 단계를 더 포함하는 것을 특징으로 하는 운동하는 볼에 대한 센싱방법.
- 표면에 소정의 특징부가 표시된 볼이 운동하는 것에 대한 이미지를 취득하여 그로부터 볼의 스핀을 산출하기 위한 상기 취득된 이미지로부터 추출된 볼 이미지의 이미지 처리방법에 있어서,상기 볼 이미지를 원본 이미지로 하여, 상기 원본 이미지 상의 볼을 임의의 각도로 회전시키는 단계;상기 볼을 회전시킨 이미지에서 상기 원본 이미지를 뺀 n차 차영상을 추출하는 단계;상기 n차 차영상을 n-1차 차영상 또는 n-1차 누적 이미지에 누적시킴으로써 n차 누적 이미지를 추출하는 단계; 및상기 n차 누적 이미지에 대해 소정의 기준값에 따른 이진화 처리를 함으로써 이미지로부터 볼에 대한 특징부를 추출하는 단계;를 포함하는 운동하는 볼의 스핀 산출을 위한 볼 이미지의 이미지 처리방법.여기서 n은 2 이상의 자연수임.
Priority Applications (5)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
EP14738295.6A EP2945121B1 (en) | 2013-01-08 | 2014-01-08 | Device and method for sensing moving ball and method for processing ball image for spin calculation of moving ball |
JP2015551616A JP6102002B2 (ja) | 2013-01-08 | 2014-01-08 | 運動するボールに対するセンシング装置及びセンシング方法、並びに運動するボールのスピン算出のためのボールイメージのイメージ処理方法 |
US14/759,653 US20150356744A1 (en) | 2013-01-08 | 2014-01-08 | Method and apparatus for sensing moving ball, and image processing method of ball image for calculation of spin of moving ball |
CN201480008284.7A CN104981845B (zh) | 2013-01-08 | 2014-01-08 | 供感测移动球体的装置及方法、及球体影像的影像处理方法 |
AU2014205857A AU2014205857B2 (en) | 2013-01-08 | 2014-01-08 | Method and apparatus for sensing moving ball, and image processing method of ball image for calculation of spin of moving ball |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
KR10-2013-0002202 | 2013-01-08 | ||
KR1020130002202A KR101472275B1 (ko) | 2013-01-08 | 2013-01-08 | 운동하는 볼에 대한 센싱장치 및 센싱방법과, 운동하는 볼의 스핀 산출을 위한 볼 이미지의 이미지 처리방법 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2014109544A1 true WO2014109544A1 (ko) | 2014-07-17 |
Family
ID=51167134
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/KR2014/000197 WO2014109544A1 (ko) | 2013-01-08 | 2014-01-08 | 운동하는 볼에 대한 센싱장치 및 센싱방법과, 운동하는 볼의 스핀 산출을 위한 볼 이미지의 이미지 처리방법 |
Country Status (8)
Country | Link |
---|---|
US (1) | US20150356744A1 (ko) |
EP (1) | EP2945121B1 (ko) |
JP (1) | JP6102002B2 (ko) |
KR (1) | KR101472275B1 (ko) |
CN (1) | CN104981845B (ko) |
AU (1) | AU2014205857B2 (ko) |
TW (1) | TWI534759B (ko) |
WO (1) | WO2014109544A1 (ko) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP3309741A4 (en) * | 2015-06-12 | 2018-12-12 | Golfzon Co., Ltd. | Device and method for sensing moving ball |
Families Citing this family (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR102443281B1 (ko) * | 2016-06-29 | 2022-09-15 | 주식회사 크리에이츠 | 공 이미지의 밝기를 보정하기 위한 방법, 시스템 및 비일시성의 컴퓨터 판독 가능한 기록 매체 |
KR101850139B1 (ko) * | 2016-06-29 | 2018-04-19 | 주식회사 크리에이츠 | 공 이미지의 밝기를 보정하기 위한 방법, 시스템 및 비일시성의 컴퓨터 판독 가능한 기록 매체 |
CN106139542B (zh) * | 2016-08-01 | 2018-11-30 | 深圳市衡泰信科技有限公司 | 高尔夫击打触发器及其感测方法 |
KR101931592B1 (ko) * | 2017-12-12 | 2019-03-13 | 주식회사 골프존 | 운동하는 볼에 대한 센싱장치 및 이를 이용한 볼에 대한 운동 파라미터 산출방법 |
KR102541061B1 (ko) * | 2018-04-02 | 2023-06-13 | 주식회사 크리에이츠 | 공 이미지의 밝기를 보정하기 위한 방법, 시스템 및 비일시성의 컴퓨터 판독 가능한 기록 매체 |
WO2022040796A1 (en) * | 2020-08-25 | 2022-03-03 | Tarkett Sports Canada Inc. | Electronic assessment of playing surface properties |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2000019186A (ja) * | 1998-06-30 | 2000-01-21 | Bridgestone Sports Co Ltd | ゴルフボールの回転運動測定方法 |
JP2005087615A (ja) * | 2003-09-19 | 2005-04-07 | Sumitomo Rubber Ind Ltd | ゴルフのインパクト現象解析システム |
JP2005270500A (ja) * | 2004-03-26 | 2005-10-06 | Sri Sports Ltd | ゴルフスウィング診断システム |
KR20060045366A (ko) * | 2004-03-31 | 2006-05-17 | 요코하마 고무 가부시키가이샤 | 비상체의 비상 거동 측정장치 및 비상체의 비상 거동측정방법 |
KR20120033946A (ko) * | 2010-09-30 | 2012-04-09 | 한국전자통신연구원 | 오브젝트 움직임 계산 장치 및 방법 |
Family Cites Families (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6351265B1 (en) * | 1993-10-15 | 2002-02-26 | Personalized Online Photo Llc | Method and apparatus for producing an electronic image |
EP1509781B1 (en) * | 2002-06-06 | 2015-04-29 | WAWGD, Inc, dba Foresight Sports | Flight parameter measurement system |
US7292711B2 (en) * | 2002-06-06 | 2007-11-06 | Wintriss Engineering Corporation | Flight parameter measurement system |
US7324663B2 (en) * | 2002-06-06 | 2008-01-29 | Wintriss Engineering Corporation | Flight parameter measurement system |
US20060029257A1 (en) * | 2004-08-03 | 2006-02-09 | Honda Motor Co., Ltd. | Apparatus for determining a surface condition of an object |
KR100972826B1 (ko) * | 2009-12-31 | 2010-07-28 | (주) 골프존 | 서브 디스플레이를 제공하는 가상 골프 시뮬레이션 장치 |
-
2013
- 2013-01-08 KR KR1020130002202A patent/KR101472275B1/ko active IP Right Grant
-
2014
- 2014-01-08 CN CN201480008284.7A patent/CN104981845B/zh active Active
- 2014-01-08 EP EP14738295.6A patent/EP2945121B1/en active Active
- 2014-01-08 WO PCT/KR2014/000197 patent/WO2014109544A1/ko active Application Filing
- 2014-01-08 AU AU2014205857A patent/AU2014205857B2/en active Active
- 2014-01-08 US US14/759,653 patent/US20150356744A1/en not_active Abandoned
- 2014-01-08 JP JP2015551616A patent/JP6102002B2/ja active Active
- 2014-01-08 TW TW103100788A patent/TWI534759B/zh not_active IP Right Cessation
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2000019186A (ja) * | 1998-06-30 | 2000-01-21 | Bridgestone Sports Co Ltd | ゴルフボールの回転運動測定方法 |
JP2005087615A (ja) * | 2003-09-19 | 2005-04-07 | Sumitomo Rubber Ind Ltd | ゴルフのインパクト現象解析システム |
JP2005270500A (ja) * | 2004-03-26 | 2005-10-06 | Sri Sports Ltd | ゴルフスウィング診断システム |
KR20060045366A (ko) * | 2004-03-31 | 2006-05-17 | 요코하마 고무 가부시키가이샤 | 비상체의 비상 거동 측정장치 및 비상체의 비상 거동측정방법 |
KR20120033946A (ko) * | 2010-09-30 | 2012-04-09 | 한국전자통신연구원 | 오브젝트 움직임 계산 장치 및 방법 |
Non-Patent Citations (1)
Title |
---|
See also references of EP2945121A4 * |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP3309741A4 (en) * | 2015-06-12 | 2018-12-12 | Golfzon Co., Ltd. | Device and method for sensing moving ball |
Also Published As
Publication number | Publication date |
---|---|
EP2945121A1 (en) | 2015-11-18 |
TW201432624A (zh) | 2014-08-16 |
EP2945121A4 (en) | 2016-10-12 |
JP6102002B2 (ja) | 2017-03-29 |
CN104981845B (zh) | 2017-09-08 |
KR101472275B1 (ko) | 2014-12-12 |
EP2945121B1 (en) | 2018-03-14 |
AU2014205857A1 (en) | 2015-07-30 |
US20150356744A1 (en) | 2015-12-10 |
JP2016503928A (ja) | 2016-02-08 |
CN104981845A (zh) | 2015-10-14 |
TWI534759B (zh) | 2016-05-21 |
KR20140090008A (ko) | 2014-07-16 |
AU2014205857B2 (en) | 2017-03-30 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2014109544A1 (ko) | 운동하는 볼에 대한 센싱장치 및 센싱방법과, 운동하는 볼의 스핀 산출을 위한 볼 이미지의 이미지 처리방법 | |
WO2014109545A1 (ko) | 운동하는 볼에 대한 센싱장치 및 센싱방법 | |
WO2016200208A1 (ko) | 운동하는 볼에 대한 센싱장치 및 센싱방법 | |
WO2014109546A1 (ko) | 운동하는 볼에 대한 센싱장치 및 센싱방법 | |
WO2018030673A1 (ko) | 볼의 비행정보 연산장치, 볼의 비행정보 연산방법 및 이를 기록한 컴퓨팅장치에 의해 판독 가능한 기록매체 | |
KR20130058526A (ko) | 회전체의 회전 특성 측정 방법 및 장치 | |
CN109001484A (zh) | 旋转速度的检测方法和装置 | |
WO2018139810A1 (ko) | 운동하는 객체의 위치 정보를 산출하기 위한 센싱장치 및 이를 이용한 센싱방법 | |
JP2016218014A (ja) | 飛翔体測定装置、飛翔体測定方法、及びプログラム | |
WO2018097612A1 (ko) | 사용자의 골프샷에 대한 정보를 산출하기 위한 센싱장치 및 이를 이용한 센싱방법 | |
CN111738093A (zh) | 一种基于梯度特征的冰壶球自动测速方法 | |
KR101551685B1 (ko) | 운동하는 볼에 대한 센싱장치 및 센싱방법 | |
Szép | Ball rotation detection based on arbitrary features |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 14738295 Country of ref document: EP Kind code of ref document: A1 |
|
ENP | Entry into the national phase |
Ref document number: 2015551616 Country of ref document: JP Kind code of ref document: A |
|
WWE | Wipo information: entry into national phase |
Ref document number: 2014738295 Country of ref document: EP |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
WWE | Wipo information: entry into national phase |
Ref document number: 14759653 Country of ref document: US |
|
ENP | Entry into the national phase |
Ref document number: 2014205857 Country of ref document: AU Date of ref document: 20140108 Kind code of ref document: A |