WO2021145653A1 - 공의 회전을 측정하기 위한 방법, 시스템 및 비일시성의 컴퓨터 판독 가능 기록 매체 - Google Patents
공의 회전을 측정하기 위한 방법, 시스템 및 비일시성의 컴퓨터 판독 가능 기록 매체 Download PDFInfo
- Publication number
- WO2021145653A1 WO2021145653A1 PCT/KR2021/000420 KR2021000420W WO2021145653A1 WO 2021145653 A1 WO2021145653 A1 WO 2021145653A1 KR 2021000420 W KR2021000420 W KR 2021000420W WO 2021145653 A1 WO2021145653 A1 WO 2021145653A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- dimple
- dimples
- image
- ball
- pair
- 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
- 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
- A63B24/00—Electric or electronic controls for exercising apparatus of preceding groups; Controlling or monitoring of exercises, sportive games, training or athletic performances
- A63B24/0003—Analysing the course of a movement or motion sequences during an exercise or trainings sequence, e.g. swing for golf or tennis
- A63B24/0006—Computerised comparison for qualitative assessment of motion sequences or the course of a movement
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/211—Selection of the most significant subset of features
- G06F18/2113—Selection of the most significant subset of features by ranking or filtering the set of features, e.g. using a measure of variance or of feature cross-correlation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/24—Aligning, centring, orientation detection or correction of the image
- G06V10/242—Aligning, centring, orientation detection or correction of the image by image rotation, e.g. by 90 degrees
-
- 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
- G06V10/751—Comparing pixel values or logical combinations thereof, or feature values having positional relevance, e.g. template matching
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
-
- G—PHYSICS
- G09—EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
- G09B—EDUCATIONAL OR DEMONSTRATION APPLIANCES; APPLIANCES FOR TEACHING, OR COMMUNICATING WITH, THE BLIND, DEAF OR MUTE; MODELS; PLANETARIA; GLOBES; MAPS; DIAGRAMS
- G09B19/00—Teaching not covered by other main groups of this subclass
- G09B19/003—Repetitive work cycles; Sequence of movements
- G09B19/0038—Sports
-
- A—HUMAN NECESSITIES
- A63—SPORTS; GAMES; AMUSEMENTS
- A63B—APPARATUS FOR PHYSICAL TRAINING, GYMNASTICS, SWIMMING, CLIMBING, OR FENCING; BALL GAMES; TRAINING EQUIPMENT
- A63B24/00—Electric or electronic controls for exercising apparatus of preceding groups; Controlling or monitoring of exercises, sportive games, training or athletic performances
- A63B24/0021—Tracking a path or terminating locations
- A63B2024/0028—Tracking the path of an object, e.g. a ball inside a soccer pitch
-
- A—HUMAN NECESSITIES
- A63—SPORTS; GAMES; AMUSEMENTS
- A63B—APPARATUS FOR PHYSICAL TRAINING, GYMNASTICS, SWIMMING, CLIMBING, OR FENCING; BALL GAMES; TRAINING EQUIPMENT
- A63B71/00—Games or sports accessories not covered in groups A63B1/00 - A63B69/00
- A63B71/06—Indicating or scoring devices for games or players, or for other sports activities
- A63B71/0619—Displays, user interfaces and indicating devices, specially adapted for sport equipment, e.g. display mounted on treadmills
- A63B71/0622—Visual, audio or audio-visual systems for entertaining, instructing or motivating the user
- A63B2071/0638—Displaying moving images of recorded environment, e.g. virtual environment
-
- A—HUMAN NECESSITIES
- A63—SPORTS; GAMES; AMUSEMENTS
- A63B—APPARATUS FOR PHYSICAL TRAINING, GYMNASTICS, SWIMMING, CLIMBING, OR FENCING; BALL GAMES; TRAINING EQUIPMENT
- A63B2220/00—Measuring of physical parameters relating to sporting activity
- A63B2220/80—Special sensors, transducers or devices therefor
- A63B2220/806—Video cameras
-
- A—HUMAN NECESSITIES
- A63—SPORTS; GAMES; AMUSEMENTS
- A63B—APPARATUS FOR PHYSICAL TRAINING, GYMNASTICS, SWIMMING, CLIMBING, OR FENCING; BALL GAMES; TRAINING EQUIPMENT
- A63B2220/00—Measuring of physical parameters relating to sporting activity
- A63B2220/80—Special sensors, transducers or devices therefor
- A63B2220/807—Photo cameras
-
- A—HUMAN NECESSITIES
- A63—SPORTS; GAMES; AMUSEMENTS
- A63B—APPARATUS FOR PHYSICAL TRAINING, GYMNASTICS, SWIMMING, CLIMBING, OR FENCING; BALL GAMES; TRAINING EQUIPMENT
- A63B2225/00—Miscellaneous features of sport apparatus, devices or equipment
- A63B2225/74—Miscellaneous features of sport apparatus, devices or equipment with powered illuminating means, e.g. lights
-
- 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
-
- 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
- A63B69/3623—Training appliances or apparatus for special sports for golf for driving
- A63B69/3655—Balls, ball substitutes, or attachments on balls therefor
-
- A—HUMAN NECESSITIES
- A63—SPORTS; GAMES; AMUSEMENTS
- A63B—APPARATUS FOR PHYSICAL TRAINING, GYMNASTICS, SWIMMING, CLIMBING, OR FENCING; BALL GAMES; TRAINING EQUIPMENT
- A63B71/00—Games or sports accessories not covered in groups A63B1/00 - A63B69/00
- A63B71/02—Games or sports accessories not covered in groups A63B1/00 - A63B69/00 for large-room or outdoor sporting games
- A63B71/022—Backstops, cages, enclosures or the like, e.g. for spectator protection, for arresting balls
-
- 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
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30221—Sports video; Sports image
- G06T2207/30224—Ball; Puck
Definitions
- the present invention relates to a method, system and non-transitory computer-readable recording medium for measuring the rotation of a ball.
- the present inventor(s) proposes a novel and advanced technology capable of accurately measuring a physical quantity related to rotation of a golf ball by analyzing dimples detected in a plurality of images of a golf ball obtained from a camera.
- An object of the present invention is to solve all the problems of the prior art described above.
- Another object of the present invention is to simply and accurately measure a physical quantity related to the rotation of a ball by analyzing dimples appearing over a plurality of ball images.
- Another object of the present invention is to accurately measure the physical quantity related to the rotation of the ball even if there is no mark or mark on the ball that is the target of the physical quantity measurement.
- a representative configuration of the present invention for achieving the above object is as follows.
- a method for measuring the rotation of a ball comprising: detecting a plurality of dimples in each of a plurality of images obtained by photographing a ball that is a target of physical quantity measurement, and among the plurality of images;
- a method is provided that includes measuring a physical quantity related to rotation of the ball with reference to a correlation between attributes of a plurality of dimples detected in a first image and attributes of a plurality of dimples detected in a second image.
- a dimple detection management unit that detects a plurality of dimples in each of a plurality of images of a ball that is a target of physical quantity measurement, and the plurality of
- a system including a physical quantity measuring unit for measuring a physical quantity related to the rotation of the ball with reference to the correlation between the attributes of the plurality of dimples detected in the first image and the attributes of the plurality of dimples detected in the second image among the images is provided do.
- FIG. 1 is a diagram illustrating in detail an internal configuration of a measurement system according to an embodiment of the present invention.
- FIGS. 2 to 4 are diagrams exemplarily showing a preprocessing process that may be performed on each of a plurality of images in order to detect a dimple of a ball according to an embodiment of the present invention.
- control unit 140 control unit
- FIG. 1 is a diagram illustrating in detail an internal configuration of a measurement system 100 according to an embodiment of the present invention.
- the measurement system 100 may include a dimple detection management unit 110 , a physical quantity measurement unit 120 , a communication unit 130 , and a control unit 140 .
- the dimple detection and management unit 110 , the physical quantity measurement unit 120 , the communication unit 130 , and the control unit 140 are program modules in which at least some of them communicate with an external system (not shown).
- Such a program module may be included in the measurement system 100 in the form of an operating system, an application program module, or other program modules, and may be physically stored in various known storage devices.
- a program module may be stored in a remote storage device capable of communicating with the measurement system 100 .
- such a program module includes, but is not limited to, routines, subroutines, programs, objects, components, data structures, etc. that perform specific tasks or execute specific abstract data types according to the present invention.
- the dimple detection management unit 110 may perform a function of detecting a plurality of dimples in each of a plurality of images obtained by photographing a ball that is a target of physical quantity measurement.
- the dimple detection management unit 110 may perform pre-processing for improving identification of the plurality of dimples on each of the plurality of images taken above, and the plurality of dimples based on the plurality of pre-processed images can be detected.
- the dimple detection manager 110 performs blur, histogram equalization, contrast, adaptive thresholding binarization, and morphology for each of the plurality of images 210 . ), stabilization, noise removal, quality improvement, etc. of the plurality of images above may be performed by performing at least one preprocessing.
- the above pre-processing process may be performed based on a window having the same or similar size as that of the dimple of the ball, for example, at least one window having a size equal to or similar to the size of the dimple of the ball.
- a filter of e.g., a filter for processing at least one of blur, contrast, adaptive threshold binarization, and morphology
- Processing e.g, a convolution operation between the filter and the image
- the dimple detection management unit 110 may Blur processing to reduce noise may be performed on each image of .
- the dimple detection management unit 110 may perform a contrast process on each of the plurality of images to increase the contrast while maintaining the same brightness as the original image ( 220 ). Looking at the above contrast processing in detail with reference to FIG.
- the dimple detection management unit 110 may perform the adaptive threshold binarization process on each of the plurality of images (specifically, centered on each dimple region in each image region) (230) .
- analyzing the pixel brightness with respect to the adjacent area of each dimple eg, calculating the average brightness for each pixel at the adaptive threshold of each dimple specified in each of the plurality of images above
- the threshold value of each dimple is calculated based on the brightness average
- the processing is performed based on information on an accumulation map that can be accumulated and managed for the entire area. By doing so, it is possible to reduce the computational load.
- the dimple detection management unit 110 may perform a morphology operation on each of the plurality of images, so that each dimple region appears more clearly in each of the plurality of images. (5) Then, in each of the plurality of images, the area corresponding to the dimple of the ball by light (eg, infrared LED light or sunlight applied for camera photography) applied to the ball while the ball is being photographed. Since this area appears brighter than other areas, the dimple detection management unit 110 may detect a plurality of dimples (specifically, the position of each dimple in the empty image) based on the bright area in each of the plurality of images ( 240).
- light eg, infrared LED light or sunlight applied for camera photography
- the dimple detection management unit 110 may correct the position of the dimple in each of the plurality of images based on a direction in which light is applied to the ball detected in each of the plurality of images. For example, referring to FIG. 4 , when a plurality of dimples 401 are detected based on a bright area in each of the plurality of images as above, the position 410 of the dimples detected in each of the plurality of images is on the ball. There may be an error compared to the actual position 420 of the dimple due to the shape of the ball (or the dimple 401 ) depending on the direction in which light is applied.
- the dimple detection management unit 110 gives a predetermined offset to the position of the dimple 401 detected as above based on the direction in which the light is applied (specifically, the position of the center of the bright area 403).
- the position of each dimple 401 in each of the plurality of images may be more accurately specified.
- the brightness in each of the plurality of images is centered on the diameter d (or radius) of the dimple 401 and the angle ⁇ formed by the opening surface of the dimple 401 with a predetermined point (eg, the ground).
- a predetermined point eg, the ground.
- the magnitude of such an offset may be specified based on a sin function or a cos function, for example, k ⁇ d ⁇ sin(2 ⁇ )/4 (here, k is a predetermined weight).
- the position of the dimple may be corrected with further reference to the position of the additional light source.
- an additional light source eg, sunlight
- the positions of the dimples detected in the plurality of images may be further corrected.
- the position of the dimple may be corrected in consideration of only the position to which the sunlight is applied.
- At least one mark detected in each of the above plurality of images usually corresponds to a dark color, and unlike dimples, there is little difference in brightness, so it is somewhat difficult to specify as a dimple from the corresponding area, but the at least one mark is a dimple and a dimple. Since it can be utilized in the same way, it is possible to prepare for a situation where the number of dimples detected in the ball is small.
- the physical quantity measuring unit 120 determines the correlation between the attributes of the plurality of dimples detected in the first image among the plurality of images and the attributes of the plurality of dimples detected in the second image.
- the function of measuring the physical quantity related to the rotation of the ball can be performed.
- the attribute of a dimple according to an embodiment of the present invention may be a concept including a distance relation, a position relation, a direction relation, and the like between the dimples.
- the physical quantity related to the rotation of the ball may include information about the rotation direction, rotation speed, rotation acceleration, rotation angular velocity, rotation amount, and the like of the ball.
- the physical quantity related to the rotation of the ball according to the present invention is not necessarily limited to the information listed above, and can be variously changed within the range that can achieve the object of the present invention.
- the relation between the attributes of the plurality of dimples according to an embodiment of the present invention may be a concept indicating to what extent the attributes of the plurality of dimples are physically, spatially, numerically, or logically identical to or similar to each other.
- the degree of matching according to the present invention is not limited to the above-listed methods, and can be variously changed to a score (or weighted score) method, etc. within a range that can achieve the object of the present invention.
- the first linked dimple pair according to an embodiment of the present invention may be configured to include a dimple pair of each of at least two images. For example, the first pair of dimples of the first image based on the above matching degree. and a third pair of dimples of the second image, a second pair of dimples of the first image, and a fifth pair of dimples of the second image may be determined as the above first associated dimple pair, respectively.
- a predetermined rotation (specifically, rotation of a ball) occurs with respect to at least one pair of dimples in the first image (or at least one pair of dimples in the second image) of the physical quantity measuring unit 120 .
- a predetermined number eg, top 10% or 5
- dimple pairs in the first image and dimple pairs in the second image based on the degree of matching may be determined as the first pair of associated dimples above. More specifically, when 10 dimples are specified in the first image, a total of 45 dimple pairs may be specified, and when 10 dimples are specified in the second image, a total of 45 dimple pairs may be specified as in the first image. In this case, the comparison between the attributes of each dimple pair may be performed a total of 2,025 times (ie, 45 X 45 times).
- the physical quantity measuring unit 120 determines a dimple pair having a distance between dimples within a predetermined range among at least one dimple pair specified from each of a plurality of images as a valid dimple pair, and the valid The computational load may be reduced by determining the first associated dimple pair based on the dimple pair.
- the distance between the dimples is equal to or less than the first distance (that is, when the distance between the dimples is close to or less than a predetermined level), the distance between the dimples is quite close, so an error (e.g., each error) is high, and when the distance between the dimples is greater than or equal to the second distance (the second distance is set greater than the first distance above) (that is, when the distance between the dimples is farther than a predetermined level)
- an error e.g., each error
- the distance between the dimples is greater than or equal to the second distance (the second distance is set greater than the first distance above) (that is, when the distance between the dimples is farther than a predetermined level)
- the above predetermined range may be preset or dynamically specified with reference to a probability that a dimple pair is detected in the image of the ball (eg, associated with the surface area of the ball).
- a dimple pair specified from a plurality of images is not necessarily specified in each image as a whole as in the above-listed embodiments, and each image is within a range that can achieve the object of the present invention.
- the predetermined region in the above image may be identical for each image or may be specified in consideration of a range in which the region may be rotated between temporally adjacent images.
- the physical quantity measuring unit 120 specifies a predetermined rotation range rotatable between the dimple pair of the first image and the dimple pair of the second image, and the above predetermined one of the at least one first linked dimple pair determined above.
- a pair of associated dimples existing within the rotation range may be determined as the at least one first pair of associated dimples above.
- the maximum rotation range of the ball per image frame between adjacent images may be calculated with reference to the maximum number of rotations of the ball and the frame rate of a camera photographing the ball. may be, and the above predetermined rotation range may be specified based on this.
- the physical quantity measuring unit 120 in order to more accurately specify the physical quantity related to the rotation of the ball, a plurality of the first image and the second image calculated based on the rotation information of the above at least one first linked dimple pair. At least one second linked dimple pair is determined from among the above at least one first linked dimple pair based on the matching degree between the dimples of , and rotation information of the determined second linked dimple pair is used to rotate the ball. It is also possible to measure physical quantities related to
- the physical quantity measuring unit 120 is configured to rotate the dimple pair of the first image among the at least one first linked dimple pair to the corresponding dimple pair of the second image temporally adjacent to the first image.
- the degree of matching of the plurality of dimples of the first image with the plurality of dimples of the second image is compared and analyzed, and the at least one second image is analyzed based on the degree of matching.
- a predetermined number (eg, top 10%) of dimple pairs among 1 linked dimple pairs are determined as the above second linked dimple pairs, and rotation information of the determined second linked dimple pairs is referred to for rotation of the ball.
- a physical quantity can be measured.
- control unit 140 may perform a function of controlling the flow of data between the dimple detection management unit 110 , the physical quantity measurement unit 120 , and the communication unit 130 . That is, the control unit 140 controls the data flow to/from the outside of the measurement system 100 or the data flow between each component of the measurement system 100 , thereby controlling the dimple detection management unit 110 and the physical quantity measurement unit 120 . and the communication unit 130 may be controlled to perform a unique function, respectively.
- the virtual golf simulation system 200 includes a striking unit 10
- the lighting device 20 , the photographing device 210 , the simulator 220 , and the display device 230 may be included.
- the simulator 220 according to an embodiment of the present invention may include the measurement system 100 according to the present invention.
- the striking unit 10 may be a part where a golfer puts and hits a golf ball while stepping on their feet when using the virtual golf simulation system 200 .
- the striking unit 10 may include a known swing plate whose inclination angle can be adjusted.
- those skilled in the art can determine the configuration of the striking unit 10, if necessary, along with the configuration of other components interlocking therewith, depending on the characteristics of the sport. You can change it to suit you.
- the lighting device 20 may be a device capable of artificially irradiating light when a golfer enjoys virtual golf indoors or outdoors.
- the lighting device 20 may be turned on and off or its brightness may be adjusted as needed.
- the lighting device 20 may be an infrared light (eg, LED) for preventing the natural deterioration of the golf ball image due to the vibration of light.
- the simulator 220 detects a plurality of dimples in each of a plurality of images obtained by photographing a ball that is a target of physical quantity measurement, and detects a plurality of dimples in the first image among the plurality of images.
- a function of measuring a physical quantity related to the rotation of the ball may be performed by referring to the correlation between the attributes of the plurality of dimples and the attributes of the plurality of dimples detected in the second image.
- the simulator 220 may communicate with the photographing device 210 and the display device 230 , and may include a dedicated processor for the virtual golf simulation 200 .
- a dedicated processor may be provided with a memory means and equipped with numerical arithmetic and graphic processing capabilities.
- a plurality of images of the golf ball hit by the photographing device 210 may be acquired.
- the simulator 220 calculates blur, contrast, and/or contrast for each of the plurality of images above based on at least one filter having a window of a size equal to or similar to the size of the dimple of the ball. At least one of adaptive threshold binarization and morphology may be preprocessed.
- the simulator 220 performs a bright area (ie, five images adjacent in time) specified in each of a plurality of images (eg, temporally adjacent five images) of a ball that is a target of physical quantity measurement.
- a plurality of dimples may be detected based on an area brightly displayed by the light applied by the lighting device 20 above.
- the simulator 220 configures the attribute of at least one dimple pair specified from the plurality of dimples of the first image among the plurality of images and the second image among the plurality of images.
- the simulator 220 By comparing and analyzing the attributes of at least one dimple pair specified from the plurality of dimples of , it is possible to determine a plurality of first linked dimple pairs corresponding to the top 10% based on the matching degree (ie, rough search). (coarse search) to determine the first pair of associated dimples).
- the simulator 220 performs a function between the plurality of dimples of the first image and the second image calculated based on the rotation information of the plurality of first linked dimple pairs. Based on the matching degree, a second linked dimple pair having the highest matching degree may be determined among the plurality of first linked dimple pairs (that is, the second linked dimple pair is determined by a fine search method) ).
- the above first image and the second image may include both images that are temporally adjacent or temporally separated by a predetermined level based on the acquisition time.
- Both the linked dimple pair and the second linked dimple pair between the first image among the plurality of images and the third image separated by a predetermined level in time may be determined, respectively.
- the simulator 220 refers to the rotation information of the second linked dimple pair having the highest matching degree among the above second linked dimple pairs, and the rotation amount and rotation of the ball. direction can be measured.
- FIG. 6 is a view exemplarily illustrating a situation in which a physical quantity related to rotation of a ball is measured according to an embodiment of the present invention.
- a plurality of dimples may be detected in each of a plurality of images (ie, a first image, a second image, and a third image) obtained by photographing a ball that is a target of physical quantity measurement.
- the first to third images may be sequentially acquired and temporally adjacent images, respectively.
- an attribute of the plurality of dimple pairs specified from the plurality of dimples of the first image (eg, 601 ) and an attribute of the plurality of dimple pairs specified from the plurality of dimples of the second image (eg, 602 ) ) by comparing with each other, at least one pair of first associated dimples may be determined based on the matching degree.
- an attribute of a plurality of dimple pairs specified from a plurality of dimples of the second image (eg, 602) and an attribute of a plurality of dimple pairs specified from a plurality of dimples of the third image (eg, 603) By comparing and analyzing each other, at least one pair of first associated dimples may be determined based on the matching degree.
- an attribute of a plurality of dimple pairs specified from a plurality of dimples of the first image (eg, 601) and an attribute of a plurality of dimple pairs specified from a plurality of dimples of the third image (eg, 603) By comparing and analyzing each other, at least one pair of first associated dimples may be determined based on the matching degree.
- the properties of the above dimple pair include a first axis connecting the first dimples of the corresponding dimple pair from a predetermined (or arbitrary) point, and a first axis of the corresponding dimple pair from the above predetermined point. It may be specified based on a second axis connecting the two dimples and a third axis (eg, a normal axis) specified based on the first and second axes.
- a predetermined rotation occurs with respect to a plurality of pairs of dimples of the first image
- the properties of each pair of dimples for the plurality of pairs of dimples of the second image that is, the above three axes are matched with each other
- a predetermined number for example, the top two
- a dimple pair may be determined as the first associated dimple pair above.
- the 1-1 dimple 611 ⁇ -> the 1-2 dimple 612 and the 2-2 dimple 622 ⁇ -> the 2-3 dimple ( 623) and the 1-1 dimple 611 ⁇ -> the 1-4 dimple 614 and the 2-1 dimple 621 ⁇ -> the 2-4 dimple 624 are the first linked dimples above, respectively can be determined as a pair.
- the at least one first associated dimple pair At least one second associated dimple pair may be determined among the pairs.
- the degree of matching between the plurality of dimples of the first image and the third image calculated based on the rotation information of the at least one first linked dimple pair among the at least one first linked dimple pair At least one second pair of associated dimples may be determined.
- the 1-1 dimple 611 ⁇ -> the 1-2 dimple 612 is rotated to a certain extent
- the 1-1 dimple 611 ⁇ -> the 1-2 dimple 612 is rotated to a certain extent.
- a first image for each of the at least one first linked dimple pair above with reference to information on whether the attribute and the 2-2 dimple 622 ⁇ -> the attribute of the 2-3 dimple 623 match each other and a degree to which a plurality of dimples of the second image are matched may be calculated.
- the 1-1 dimple 611 ⁇ -> the 1-4 dimple 614 is rotated to a certain extent, the properties of the 1-1 dimple 611 ⁇ -> the 1-4 dimple 614 and With reference to information on whether the properties of the 2-1 dimple 621 ⁇ -> the 2-4 dimple 624 match each other, the first image and the second dimple pair for each of the above at least one first linked dimple pair 2 It is possible to calculate a degree to which a plurality of dimples of an image are matched. According to this process, the 1-1 dimple 611 ⁇ -> the 1-4 dimple 614 and the 2-1 th dimple 614 are calculated to have the highest matching degree of the plurality of dimples of the first image and the second image.
- a physical quantity related to the rotation of the ball may be measured with reference to the above determined rotation information of the second linked dimple pair.
- 1-1 dimple 611 ⁇ -> 1-4 dimple 614 and 2-1 dimple 621 ⁇ -> 2-4 dimple 624 is determined as the second linked dimple pair with the highest matching degree, the 1-1 dimple 611 when the 1-1 dimple 611 ⁇ -> the 1-2 dimple 612 rotates to a certain extent ⁇ -> the rotation speed of the ball with reference to information on whether the properties of the 1-2 dimple 612 and the 2-2 dimple 622 ⁇ -> the properties of the 2-3 dimple 623 match each other;
- a rotation amount, rotational acceleration, etc. may be calculated, and a physical quantity related to the rotation of the ball may be measured based on this.
- the embodiments according to the present invention described above may be implemented in the form of program instructions that can be executed through various computer components and recorded in a computer-readable recording medium.
- the computer-readable recording medium may include program instructions, data files, data structures, etc. alone or in combination.
- the program instructions recorded on the computer-readable recording medium may be specially designed and configured for the present invention, or may be known and available to those skilled in the art of computer software.
- Examples of the computer-readable recording medium include hard disks, magnetic media such as floppy disks and magnetic tapes, optical recording media such as CD-ROMs and DVDs, and magneto-optical media such as floppy disks. medium), and hardware devices specially configured to store and execute program instructions, such as ROM, RAM, flash memory, and the like.
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Data Mining & Analysis (AREA)
- Medical Informatics (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- Computing Systems (AREA)
- Business, Economics & Management (AREA)
- Physical Education & Sports Medicine (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Entrepreneurship & Innovation (AREA)
- Educational Administration (AREA)
- Educational Technology (AREA)
- Image Analysis (AREA)
- Length Measuring Devices By Optical Means (AREA)
- Holo Graphy (AREA)
- Holding Or Fastening Of Disk On Rotational Shaft (AREA)
Abstract
Description
Claims (13)
- 공의 회전을 측정하기 위한 방법으로서,물리량 측정의 대상이 되는 공을 촬영한 복수의 이미지 각각에서 복수의 딤플(dimple)을 검출하는 단계, 및상기 복수의 이미지 중 제1 이미지에서 검출되는 복수의 딤플의 속성 및 제2 이미지에서 검출되는 복수의 딤플의 속성 사이의 연관 관계를 참조하여 상기 공의 회전에 관한 물리량을 측정하는 단계를 포함하는방법.
- 제1항에 있어서,상기 검출 단계에서, 상기 공의 딤플의 크기와 동일하거나 유사한 크기의 윈도우(window)를 갖는 적어도 하나의 필터를 상기 복수의 이미지 각각에 대하여 적용함으로써, 상기 복수의 딤플에 대한 식별력을 향상시키기 위한 전처리를 수행하는방법.
- 제1항에 있어서,상기 검출 단계에서, 가우시안 필터를 기반으로 중심부의 크기를 소정 수준 증가시키고 분포의 평균이 소정 수준으로 유지되도록 오프셋시킨 필터를 적용함으로써, 상기 복수의 이미지의 대비(contrast)를 증가시키는 전처리를 수행하는방법.
- 제1항에 있어서,상기 검출 단계에서, 상기 복수의 이미지 각각에서 상기 공에 대하여 빛이 가해지는 방향을 참조하여 상기 복수의 이미지 각각에서 검출되는 복수의 딤플의 위치를 보정하는방법.
- 제1항에 있어서,상기 측정 단계는,상기 제1 이미지에서 검출되는 복수의 딤플 중 적어도 하나의 딤플 쌍의 속성과 상기 제2 이미지에서 검출되는 복수의 딤플 중 적어도 하나의 딤플 쌍의 속성을 서로 비교하여 그 매칭 정도를 기준으로 적어도 하나의 연계 딤플 쌍을 결정하는 단계, 및상기 적어도 하나의 연계 딤플 쌍의 회전 정보를 참조하여 상기 공의 회전에 관한 물리량을 측정하는 단계를 포함하는방법.
- 제1항에 있어서,상기 측정 단계는,상기 제1 이미지에서 검출되는 복수의 딤플 중 적어도 하나의 딤플 쌍의 속성과 상기 제2 이미지에서 검출되는 복수의 딤플 중 적어도 하나의 딤플 쌍의 속성을 서로 비교하여 그 매칭 정도를 기준으로 적어도 하나의 제1 연계 딤플 쌍을 결정하는 단계, 및상기 적어도 하나의 제1 연계 딤플 쌍의 회전 정보에 기초하여 산출되는 상기 제1 이미지 및 상기 제2 이미지의 복수의 딤플 사이의 매칭 정도를 기준으로 상기 적어도 하나의 제1 연계 딤플 쌍 중에서 적어도 하나의 제2 연계 딤플 쌍을 결정하는 단계, 및상기 적어도 하나의 제2 연계 딤플 쌍의 회전 정보를 참조하여 상기 공의 회전에 관한 물리량을 측정하는 단계를 포함하는방법.
- 제1항에 따른 방법을 실행하기 위한 컴퓨터 프로그램을 기록하는 비일시성의 컴퓨터 판독 가능 기록 매체.
- 공의 회전을 측정하기 위한 시스템으로서,물리량 측정의 대상이 되는 공을 촬영한 복수의 이미지 각각에서 복수의 딤플(dimple)을 검출하는 딤플 검출 관리부, 및상기 복수의 이미지 중 제1 이미지에서 검출되는 복수의 딤플의 속성 및 제2 이미지에서 검출되는 복수의 딤플의 속성 사이의 연관 관계를 참조하여 상기 공의 회전에 관한 물리량을 측정하는 물리량 측정부를 포함하는시스템.
- 제8항에 있어서,상기 딤플 검출 관리부는, 상기 공의 딤플의 크기와 동일하거나 유사한 크기의 윈도우(window)를 갖는 적어도 하나의 필터를 상기 복수의 이미지 각각에 대하여 적용함으로써, 상기 복수의 딤플에 대한 식별력을 향상시키기 위한 전처리를 수행하는시스템.
- 제8항에 있어서,상기 딤플 검출 관리부는, 가우시안 필터를 기반으로 중심부의 크기를 소정 수준 증가시키고 분포의 평균이 소정 수준으로 유지되도록 오프셋시킨 필터를 적용함으로써, 상기 복수의 이미지의 대비(contrast)를 증가시키는 전처리를 수행하는시스템.
- 제8항에 있어서,상기 딤플 검출 관리부는, 상기 복수의 이미지 각각에서 상기 공에 대하여 빛이 가해지는 방향을 참조하여 상기 복수의 이미지 각각에서 검출되는 복수의 딤플의 위치를 보정하는시스템.
- 제8항에 있어서,상기 물리량 측정부는, 상기 제1 이미지에서 검출되는 복수의 딤플 중 적어도 하나의 딤플 쌍의 속성과 상기 제2 이미지에서 검출되는 복수의 딤플 중 적어도 하나의 딤플 쌍의 속성을 서로 비교하여 그 매칭 정도를 기준으로 적어도 하나의 연계 딤플 쌍을 결정하고, 상기 적어도 하나의 연계 딤플 쌍의 회전 정보를 참조하여 상기 공의 회전에 관한 물리량을 측정하는시스템.
- 제8항에 있어서,상기 물리량 측정부는, 상기 제1 이미지에서 검출되는 복수의 딤플 중 적어도 하나의 딤플 쌍의 속성과 상기 제2 이미지에서 검출되는 복수의 딤플 중 적어도 하나의 딤플 쌍의 속성을 서로 비교하여 그 매칭 정도를 기준으로 적어도 하나의 제1 연계 딤플 쌍을 결정하고, 상기 적어도 하나의 제1 연계 딤플 쌍의 회전 정보에 기초하여 산출되는 상기 제1 이미지 및 상기 제2 이미지의 복수의 딤플 사이의 매칭 정도를 기준으로 상기 적어도 하나의 제1 연계 딤플 쌍 중에서 적어도 하나의 제2 연계 딤플 쌍을 결정하며, 상기 적어도 하나의 제2 연계 딤플 쌍의 회전 정보를 참조하여 상기 공의 회전에 관한 물리량을 측정하는시스템.
Priority Applications (7)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
EP21741794.8A EP4091681A4 (en) | 2020-01-16 | 2021-01-12 | METHOD, SYSTEM AND COMPUTER READABLE NON-TRANSITORY RECORDING MEDIA FOR MEASURING BALL ROTATION |
JP2021513915A JP7130118B2 (ja) | 2020-01-16 | 2021-01-12 | ボールの回転を測定するための方法、システムおよび非一過性のコンピュータ読み取り可能記録媒体 |
AU2021208238A AU2021208238A1 (en) | 2020-01-16 | 2021-01-12 | Method, system, and non-transitory computer-readable recording medium for measuring spin of ball |
CN202180000438.8A CN113439288A (zh) | 2020-01-16 | 2021-01-12 | 球旋转的测定方法、系统及非暂时性计算机可读记录介质 |
CA3164629A CA3164629A1 (en) | 2020-01-16 | 2021-01-12 | Method, system, and non-transitory computer-readable recording medium for measuring spin of ball |
US17/204,310 US12008770B2 (en) | 2020-01-16 | 2021-03-17 | Method, system, and non-transitory computer-readable recording medium for measuring ball spin |
AU2024202016A AU2024202016A1 (en) | 2020-01-16 | 2024-03-28 | Method, system, and non-transitory computer-readable recording medium for measuring spin of ball |
Applications Claiming Priority (4)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
KR20200006247 | 2020-01-16 | ||
KR10-2020-0006247 | 2020-01-16 | ||
KR1020200143813A KR102483474B1 (ko) | 2020-01-16 | 2020-10-30 | 공의 회전을 측정하기 위한 방법, 시스템 및 비일시성의 컴퓨터 판독 가능 기록 매체 |
KR10-2020-0143813 | 2020-10-30 |
Related Child Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US17/204,310 Continuation US12008770B2 (en) | 2020-01-16 | 2021-03-17 | Method, system, and non-transitory computer-readable recording medium for measuring ball spin |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2021145653A1 true WO2021145653A1 (ko) | 2021-07-22 |
Family
ID=76864764
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/KR2021/000420 WO2021145653A1 (ko) | 2020-01-16 | 2021-01-12 | 공의 회전을 측정하기 위한 방법, 시스템 및 비일시성의 컴퓨터 판독 가능 기록 매체 |
Country Status (6)
Country | Link |
---|---|
US (1) | US12008770B2 (ko) |
EP (1) | EP4091681A4 (ko) |
JP (1) | JP7130118B2 (ko) |
AU (2) | AU2021208238A1 (ko) |
CA (1) | CA3164629A1 (ko) |
WO (1) | WO2021145653A1 (ko) |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20090112538A (ko) | 2008-04-23 | 2009-10-28 | 김성규 | 조명 제어를 이용한 골프 영상 획득 장치, 및 그를 이용한 영상처리 기반의 골프 연습 시스템 |
US20100210377A1 (en) * | 2007-09-21 | 2010-08-19 | Lock Timothy J | Object location and movement detection system and method |
KR101723432B1 (ko) * | 2015-06-12 | 2017-04-18 | 주식회사 골프존 | 운동하는 볼에 대한 센싱장치 및 센싱방법 |
KR20180138075A (ko) * | 2017-06-20 | 2018-12-28 | 김영준 | 골프공의 속력과 회전각 검출방법 |
JP2019054951A (ja) * | 2017-09-20 | 2019-04-11 | 株式会社ディテクト | ゴルフショット撮影装置、ゴルフショット解析システム及びボールスピン計測装置 |
JP6500598B2 (ja) * | 2015-05-26 | 2019-04-17 | 横浜ゴム株式会社 | 飛翔体測定装置、飛翔体測定方法、及びプログラム |
Family Cites Families (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH0961363A (ja) * | 1995-08-29 | 1997-03-07 | Bridgestone Sports Co Ltd | ゴルフボールの外観検査方法及び該検査方法に用いる照明装置 |
JP2002148269A (ja) * | 2000-11-08 | 2002-05-22 | Sumitomo Rubber Ind Ltd | ボール運動計測装置 |
US7324663B2 (en) * | 2002-06-06 | 2008-01-29 | Wintriss Engineering Corporation | Flight parameter measurement system |
CN103079651B (zh) * | 2010-06-29 | 2016-01-20 | 高尔纵株式会社 | 移动球的感测处理装置及方法以及使用该装置与方法的虚拟高尔夫球模拟装置 |
KR101019829B1 (ko) | 2010-06-29 | 2011-03-04 | (주) 골프존 | 운동하는 볼에 대한 센싱처리장치, 센싱처리방법 및 이를 이용한 가상 골프 시뮬레이션 장치 |
JP5572853B2 (ja) * | 2010-06-29 | 2014-08-20 | ゴルフゾン カンパニー リミテッド | 運動するオブジェクトに対するセンシング装置、センシング処理方法及びそれを用いた仮想ゴルフシミュレーション装置 |
KR101472274B1 (ko) * | 2013-01-08 | 2014-12-12 | (주) 골프존 | 운동하는 볼에 대한 센싱장치 및 센싱방법 |
US9171211B2 (en) * | 2013-09-20 | 2015-10-27 | Rapsodo Pte. Ltd. | Image processing for launch parameters measurement of objects in flight |
WO2017205540A1 (en) * | 2016-05-24 | 2017-11-30 | The Translational Genomics Research Institute | Molecular tagging methods and sequencing libraries |
KR20180002408A (ko) * | 2016-06-29 | 2018-01-08 | 주식회사 크리에이츠 | 공의 회전을 측정하기 위한 방법, 시스템 및 비일시성의 컴퓨터 판독 가능한 기록 매체 |
US11176409B2 (en) * | 2016-12-20 | 2021-11-16 | Sony Depthsensing Solutions Sa/Nv | Distance-independent keypoint detection |
US20180353828A1 (en) * | 2017-06-09 | 2018-12-13 | Golftech, Llc | Method and apparatus for ball flight analysis |
-
2021
- 2021-01-12 WO PCT/KR2021/000420 patent/WO2021145653A1/ko unknown
- 2021-01-12 AU AU2021208238A patent/AU2021208238A1/en not_active Abandoned
- 2021-01-12 CA CA3164629A patent/CA3164629A1/en active Pending
- 2021-01-12 EP EP21741794.8A patent/EP4091681A4/en active Pending
- 2021-01-12 JP JP2021513915A patent/JP7130118B2/ja active Active
- 2021-03-17 US US17/204,310 patent/US12008770B2/en active Active
-
2024
- 2024-03-28 AU AU2024202016A patent/AU2024202016A1/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20100210377A1 (en) * | 2007-09-21 | 2010-08-19 | Lock Timothy J | Object location and movement detection system and method |
KR20090112538A (ko) | 2008-04-23 | 2009-10-28 | 김성규 | 조명 제어를 이용한 골프 영상 획득 장치, 및 그를 이용한 영상처리 기반의 골프 연습 시스템 |
JP6500598B2 (ja) * | 2015-05-26 | 2019-04-17 | 横浜ゴム株式会社 | 飛翔体測定装置、飛翔体測定方法、及びプログラム |
KR101723432B1 (ko) * | 2015-06-12 | 2017-04-18 | 주식회사 골프존 | 운동하는 볼에 대한 센싱장치 및 센싱방법 |
KR20180138075A (ko) * | 2017-06-20 | 2018-12-28 | 김영준 | 골프공의 속력과 회전각 검출방법 |
JP2019054951A (ja) * | 2017-09-20 | 2019-04-11 | 株式会社ディテクト | ゴルフショット撮影装置、ゴルフショット解析システム及びボールスピン計測装置 |
Non-Patent Citations (1)
Title |
---|
See also references of EP4091681A4 |
Also Published As
Publication number | Publication date |
---|---|
JP2022520681A (ja) | 2022-04-01 |
US20210220701A1 (en) | 2021-07-22 |
EP4091681A4 (en) | 2023-07-26 |
EP4091681A1 (en) | 2022-11-23 |
US12008770B2 (en) | 2024-06-11 |
CA3164629A1 (en) | 2021-07-22 |
AU2021208238A1 (en) | 2022-08-04 |
JP7130118B2 (ja) | 2022-09-02 |
AU2024202016A1 (en) | 2024-04-18 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109903312B (zh) | 一种基于视频多目标跟踪的足球球员跑动距离统计方法 | |
JP7051315B2 (ja) | ボールの回転を測定するための方法、システム、及び非一時的なコンピュータ読み取り可能な記録媒体 | |
JP4628782B2 (ja) | 飛行パラメータ測定システム | |
WO2013043020A2 (ko) | 복수의 카메라로 운동하는 피사체를 촬영하고 그 촬영 이미지에 기초하여 피사체의 실제의 운동 궤적을 획득하기 위한 방법 및 시스템 | |
JP7076955B2 (ja) | ボールの画像の明るさを補正するための方法、システム、及び非一時的なコンピュータ読み取り可能な記録媒体 | |
US20020022531A1 (en) | Method of measuring rotational motion of a golf ball | |
WO2015080431A1 (ko) | 골프 시뮬레이터, 및 골프 시뮬레이션 방법 | |
WO2016200208A1 (ko) | 운동하는 볼에 대한 센싱장치 및 센싱방법 | |
JP4109075B2 (ja) | 球体の回転特性と飛行特性の測定方法及び球体の回転特性と飛行特性の測定装置 | |
WO2014109544A1 (ko) | 운동하는 볼에 대한 센싱장치 및 센싱방법과, 운동하는 볼의 스핀 산출을 위한 볼 이미지의 이미지 처리방법 | |
WO2018139810A1 (ko) | 운동하는 객체의 위치 정보를 산출하기 위한 센싱장치 및 이를 이용한 센싱방법 | |
WO2021145653A1 (ko) | 공의 회전을 측정하기 위한 방법, 시스템 및 비일시성의 컴퓨터 판독 가능 기록 매체 | |
KR20090112538A (ko) | 조명 제어를 이용한 골프 영상 획득 장치, 및 그를 이용한 영상처리 기반의 골프 연습 시스템 | |
KR102129129B1 (ko) | 공의 회전을 측정하기 위한 방법, 시스템 및 비일시성의 컴퓨터 판독 가능한 기록 매체 | |
WO2023149603A1 (ko) | 다수의 카메라를 이용한 열화상 감시 시스템 | |
WO2021145654A1 (ko) | 골프 클럽과 연관되는 물리량을 측정하기 위한 방법, 시스템 및 비일시성의 컴퓨터 판독 가능 기록 매체 | |
KR20210092659A (ko) | 공의 회전을 측정하기 위한 방법, 시스템 및 비일시성의 컴퓨터 판독 가능 기록 매체 | |
KR20170083788A (ko) | 표적 훈련 시스템 및 이를 이용한 표적 훈련 분석 방법 | |
JP2018000959A (ja) | ボールの画像撮影のために関心領域を決定するための方法、システム、及び非一時的なコンピュータ読み取り可能な記録媒体 | |
CN115248025B (zh) | 一种基于自适应算法的吊车负载摆角测量方法 | |
KR101602222B1 (ko) | 골프 시뮬레이션장치의 골프공 인식방법 | |
WO2023211034A1 (ko) | 골프 공에 관한 구질 정보를 제공하는 방법, 시스템 및 비일시성의 컴퓨터 판독 가능한 기록 매체 | |
KR102443281B1 (ko) | 공 이미지의 밝기를 보정하기 위한 방법, 시스템 및 비일시성의 컴퓨터 판독 가능한 기록 매체 | |
KR20220128599A (ko) | 공 이미지의 밝기를 보정하기 위한 방법, 시스템 및 비일시성의 컴퓨터 판독 가능한 기록 매체 | |
JP2024063521A (ja) | スピン計測システム |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
ENP | Entry into the national phase |
Ref document number: 2021513915 Country of ref document: JP Kind code of ref document: A |
|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 21741794 Country of ref document: EP Kind code of ref document: A1 |
|
ENP | Entry into the national phase |
Ref document number: 3164629 Country of ref document: CA |
|
ENP | Entry into the national phase |
Ref document number: 2021208238 Country of ref document: AU Date of ref document: 20210112 Kind code of ref document: A |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
ENP | Entry into the national phase |
Ref document number: 2021741794 Country of ref document: EP Effective date: 20220816 |