Ball spin calculation method and device using accumulated difference image

Abstract

The present disclosure relates to a ball spin calculation method and device using an accumulated difference image, wherein the ball spine calculation method and device acquire continuous images of a moving ball, extract a portion of the ball from each of the continuous images as a target image, generate an accumulated difference image by accumulating difference images of the target images, and calculate a spin direction and a spin speed of the moving ball on the basis of the accumulated difference image.

Description

Ball spin calculation method and device using accumulated difference image

[0001] The present disclosure relates to a method and device for calculating ball spin using a cumulative difference image, and more particularly, to a method and device for calculating ball spin using a cumulative difference image of a moving ball.

[0002] In sports involving balls, such as baseball, golf, and basketball, the physical characteristics of the ball in motion are accurately measured. These measurements are then used to calculate the ball's trajectory, or the resulting image is used in simulation devices. In particular, screen golf involves sensing the physical characteristics of a golf ball hit by a player, using these measurements to calculate the ball's trajectory, and then displaying the results on a screen.

[0003] Accurately calculating a ball's trajectory requires precise measurement of its physical characteristics. This includes ball speed, acceleration, launch angle, and directional angle, as well as ball spin. In golf, ball spin is a crucial factor in determining the ball's movement, including its trajectory and trajectory, and therefore must be accurately measured. However, ball spin, a characteristic of the ball's inherent motion, is difficult to measure using simple sensors or cameras compared to other physical characteristics. Accurate measurement requires expensive equipment and complex calculations.

[0004] Conventional methods for measuring ball spin include predicting it from other physical characteristics and information about the ball, utilizing specialized sensors such as Doppler radar sensors, and analyzing multiple images acquired using a high-speed camera (or ultra-high-speed camera). For example, in the field of golf simulation, methods for predicting golf ball spin have been used using basic information about the golf ball, such as ball speed, launch angle, and direction, as well as information about the golf club (such as club path). As another example, conventional methods for measuring ball spin using a high-speed camera mark predetermined patterns or marks on the ball and analyze changes in the patterns or marks from images acquired from the high-speed camera.

[0005] However, existing methods for predicting ball spin from other physical characteristics and information on the ball suffer from significant discrepancies with actual spin. Furthermore, methods utilizing specialized sensors require additional, expensive sensors, and existing methods utilizing high-speed cameras can only provide accurate measurements when using balls with predetermined patterns or marks. Furthermore, considering cases where the ball's marks or patterns are not predetermined, a separate process is required to extract the marks or patterns before measuring spin.

[0006] Ultimately, there has been a demand for a ball spin measurement method and device that can be used even when there is no predetermined pattern or mark on the ball without using a separate sensor and that does not separately extract the mark or pattern on the ball, but there has been a problem that this cannot be provided according to the conventional technology, and the present disclosure is intended to solve this problem.

[0007] The present disclosure is intended to accurately measure the spin of a ball.

[0008] Another object of the present disclosure is to measure the spin of a ball even when the ball does not have a predetermined pattern or mark.

[0009] Another object of the present disclosure is to measure the spin of a ball accurately without separately extracting the pattern or mark of the ball.

[0010] Another purpose of the present disclosure is to calculate an accurate ball spin by accumulating the change values ​​of consecutive ball images.

[0011] Another object of the present disclosure is to calculate ball spin using accumulated difference images.

[0012] Another purpose of the present disclosure is to calculate ball spin using an artificial neural network.

[0013] The purposes of the present disclosure are not limited to those mentioned above, and other purposes and advantages of the present disclosure not mentioned above can be understood through the following description and will be more clearly understood through the embodiments of the present disclosure. Furthermore, it will be readily apparent that the purposes and advantages of the present disclosure can be realized by the means and combinations thereof set forth in the claims.

[0014] One embodiment of the present disclosure provides a method and device for calculating ball spin using a cumulative difference image.

[0015] One embodiment of the present disclosure provides a method for calculating ball spin, which is executed on a computing device. The method may include the steps of: acquiring sequential images of a moving ball; extracting a portion of the ball from each of the sequential images as a target image; accumulating differential images of the target images to generate an accumulated differential image; and calculating a spin direction and spin speed of the moving ball based on the accumulated differential image.

[0016] In one embodiment, the differential image can be obtained by subtracting two consecutive target images.

[0017] In one embodiment, the differential image can be obtained by subtracting the value corresponding to each pixel of one target image from the value corresponding to each pixel of another target image.

[0018] In one embodiment, the spin direction of the moving ball may be the rotation axis vector of the ball, and the spin speed may be the number of revolutions per minute of the ball.

[0019] In one embodiment, the step of calculating the spin direction and spin speed of the moving ball based on the accumulated difference image may be performed by a machine-learned artificial neural network. The accumulated difference image may include two or more accumulated difference images.

[0020] In one embodiment, the step of acquiring sequential images of the moving ball may be performed by two or more camera devices.

[0021] In one embodiment, the target image may have the center coordinates of the ball image positioned at the center.

[0022] In one embodiment, the target image may be normalized to have the same size as the ball image.

[0023] In one embodiment, the target image may be normalized so that the brightness of the ball image is uniform.

[0024] One embodiment of the present disclosure provides a ball spin calculation device. The device may include a sensor unit that acquires continuous images of a moving ball; a target image extraction unit that extracts a portion of the ball from each of the continuous images as a target image; an image accumulation unit that accumulates differential images of the target images to generate a cumulative differential image; and a spin calculation unit that calculates a spin direction and spin speed of the moving ball based on the cumulative differential image.

[0025] In one embodiment, the image accumulator can obtain the difference image by subtracting two consecutive target images.

[0026] In one embodiment, the image accumulation unit can obtain the subtracted image by subtracting a value corresponding to each pixel of one target image from a value corresponding to each pixel of another target image.

[0027] In one embodiment, the spin direction of the moving ball may be the rotation axis vector of the ball, and the spin speed may be the number of revolutions per minute of the ball.

[0028] In one embodiment, the spin generating unit includes a machine-learned artificial neural network, and the artificial neural network can receive the accumulated difference image as input and output the spin direction and spin speed of the moving ball.

[0029] In one embodiment, the cumulative difference image may include two or more cumulative difference images.

[0030] In one embodiment, the sensor unit may include two or more camera devices.

[0031] In one embodiment, the target image extraction unit can extract the target image such that the center coordinate of the ball image is located at the center of the target image.

[0032] In one embodiment, the image preprocessing unit may further include an image preprocessing unit capable of normalizing the size of the ball image of the target image to be the same.

[0033] In one embodiment, the method further comprises an image preprocessing unit, wherein the image preprocessing unit can normalize the brightness of the ball image of the target image to be uniform.

[0034] One embodiment of the present disclosure includes a program stored on a recording medium to cause a computer to execute a method according to one embodiment of the present disclosure.

[0035] One embodiment of the present disclosure includes a computer-readable recording medium having recorded thereon a program for executing a method according to one embodiment of the present disclosure on a computer.

[0036] One embodiment of the present disclosure includes a computer-readable recording medium having recorded thereon a database used in one embodiment of the present disclosure.

[0037] The method and device according to the present disclosure have the effect of accurately measuring the spin of a ball.

[0038] Additionally, according to the present disclosure, there is an effect that allows for measuring the spin of a ball even when there is no predetermined pattern or mark on the ball.

[0039] In addition, according to the present disclosure, there is an effect of being able to accurately measure the spin of a ball without separately extracting a pattern or mark of the ball.

[0040] In addition, according to the present disclosure, there is an effect of being able to calculate an accurate spin of a ball by accumulating the change values ​​of consecutive ball images.

[0041] In addition, according to the present disclosure, there is an effect of being able to calculate ball spin using an accumulated difference image.

[0042] In addition, according to the present disclosure, there is an effect of being able to calculate ball spin using an artificial neural network.

[0043] In addition to the above, the specific effects of the present disclosure are described together with the specific matters for carrying out the disclosure below.

[0044] FIG. 1 is a conceptual diagram illustrating the configuration of a ball spin generating device according to one embodiment of the present disclosure.

[0045] Figure 2 is an example diagram explaining the spin direction (rotation axis direction) and spin speed of the ball.

[0046] FIG. 3 is a conceptual diagram illustrating the configuration of a sensor unit according to one embodiment of the present disclosure.

[0047] FIG. 4 is a conceptual diagram illustrating the configuration of an image processing unit according to one embodiment of the present disclosure.

[0048] Figures 5a to 5d are exemplary diagrams illustrating a process of obtaining an accumulated difference image from a target image.

[0049] Figure 6 is a conceptual diagram illustrating an embodiment of a spin calculation unit that calculates the spin of a ball from an accumulated difference image.

[0050] FIG. 7 is a block diagram of a ball spin calculation device according to one embodiment of the present disclosure.

[0051] To clarify the technical idea of ​​the present disclosure, embodiments of the present disclosure will be described in detail with reference to the attached drawings. In describing the present disclosure, if a detailed description of a related known function or component is determined to unnecessarily obscure the gist of the present disclosure, the detailed description will be omitted. Components having substantially the same functional configuration among the drawings are given the same reference numbers and symbols as possible even if they are shown in different drawings. For convenience of explanation, devices and methods are described together when necessary. Each operation of the present disclosure does not necessarily have to be performed in the described order and may be performed in parallel, selectively, or individually.

[0052] The terms used in the embodiments of this disclosure have been selected from widely used, current terms, taking into account the functions of the present disclosure. However, these terms may vary depending on the intentions of those skilled in the art, precedents, the emergence of new technologies, etc. Furthermore, in certain cases, the applicant may arbitrarily select terms, and in such cases, their meanings will be described in detail in the description of the relevant embodiments. Therefore, the terms used in this specification should not be defined simply as names of terms, but rather based on their meanings and the overall content of the present disclosure.

[0053] Throughout this disclosure, singular expressions may include plural expressions unless the context clearly dictates otherwise. Terms such as "comprise" or "have" should be understood to indicate the presence of a feature, number, step, operation, component, part, or combination thereof, but do not preclude the presence or addition of one or more other features, numbers, steps, operations, components, parts, or combinations thereof. In other words, when it is said throughout this disclosure that a part "comprises" a certain component, unless specifically stated otherwise, this does not mean that other components may be included, but rather that other components may be excluded.

[0054] Expressions such as "at least one" modify the entire list of elements, not individual elements of the list. For example, "at least one of A, B, and C" and "at least one of A, B, or C" refer to only A, only B, only C, both A and B, both B and C, both A and C, all of A, B, and C, or any combination thereof.

[0055] In addition, terms such as “...part”, “...module”, etc. described in the present disclosure mean a unit that processes at least one function or operation, which may be implemented as hardware or software, or a combination of hardware and software.

[0056] Throughout this disclosure, when a part is said to be "connected" to another part, this includes not only cases where the parts are "directly connected," but also cases where the parts are "electrically connected" with other elements intervening. Furthermore, when a part is said to "include" a component, this does not exclude other components, but rather includes other components, unless otherwise specifically stated.

[0057] The expression "configured to" as used throughout this disclosure can be used interchangeably with, for example, "suitable for," "having the capacity to," "designed to," "adapted to," "made to," or "capable of." The term "configured to" does not necessarily mean something is "specifically designed to" in hardware. Instead, in some contexts, the expression "a system configured to" can mean that the system is "capable of" in conjunction with other devices or components. For example, the phrase "a processor configured to perform A, B, and C" can mean a dedicated processor for performing the operations (e.g., an embedded processor), or a general-purpose processor (e.g., a CPU or application processor) that can perform the operations by executing one or more software programs stored in memory.

[0058] Throughout this disclosure, terms including ordinal numbers, such as "first," "second," etc., may be used to describe various components; however, the components are not limited by the terms. The terms are used solely to distinguish one component from another. For example, without departing from the scope of the present disclosure, a first component could be referred to as a second component, and similarly, a second component could also be referred to as a first component. The term "and / or" includes any combination of multiple related items or any one of multiple related items.

[0059] The present disclosure relates to a method and device for calculating ball spin using a cumulative difference image, and more particularly, to a method and device for calculating ball spin using a cumulative difference image of a moving ball.

[0060] FIG. 1 is a conceptual diagram illustrating the configuration of a ball spin generating device according to one embodiment of the present disclosure.

[0061] A ball spin calculation device according to one embodiment of the present disclosure may include a sensor unit (100), an image processing unit (200), and a spin calculation unit (300). In one embodiment, the sensor unit (100), the image processing unit (200), and the spin calculation unit (300) may be implemented as a single device (not shown). In one embodiment, the image processing unit (200) and the spin calculation unit (300) may be implemented as a single computing device (10). In another embodiment, the image processing unit (200) and the spin calculation unit (300) may be implemented by including a plurality of computing devices.

[0062] The sensor unit (100) is a means for acquiring an image of a moving ball. In one embodiment, the sensor unit (100) is a high-speed camera device capable of acquiring an image of a moving ball, and may include one or more cameras. For example, the sensor unit (100) may be configured as a stereo camera that includes two or more cameras and operates in a stereo manner. As another example, the sensor unit (100) may be configured as a 3D camera capable of recognizing a 2D image of the ball into 3D coordinates. In the present disclosure, the sensor unit (100) is described as a camera device for convenience of explanation, but is not limited thereto, and any technical means capable of acquiring an image of the ball may be used.

[0063] The image processing unit (200) is a means for processing ball images acquired from the sensor unit (100) to calculate the spin of the ball. In one embodiment, the image processing unit (200) may accumulate difference images of consecutive ball images on the same coordinates and input the accumulated difference image generated to the spin calculation unit (300). For example, the image processing unit (200) may accumulate difference images of consecutive images of a moving ball captured by the sensor unit (100) on the same coordinates to generate an image expressing a change due to the spin of the ball and provide the image to the spin calculation unit (300).

[0064] The spin calculation unit (300) can receive a cumulative difference image of a moving ball from the image processing unit (200) and calculate the spin direction and spin speed of the ball. In one embodiment, the spin calculation unit (300) can receive a cumulative difference image of a moving ball and output the spin axis and spin rate of the ball. Referring to FIG. 2, the spin calculation unit (300) can calculate the spin speed of the ball as a vector value (v) representing the rotation axis direction of the ball spin and a scalar value (u) representing the number of rotations per unit time (e.g., RPM).

[0065] In one embodiment, the spin calculation unit (300) is configured as a neural network that machine-learns the spin direction and spin speed of the ball according to the accumulated difference image, so that when the accumulated difference image is input to the neural network, the spin direction and spin speed of the ball corresponding to the input image can be output. For example, the spin calculation unit (300) is implemented based on AI deep learning technology, and can receive the accumulated difference image and output (v, u). Here, v is a vector value indicating the direction of the rotation axis of the ball spin, and u is a scalar value (u) indicating the spin speed of the ball in rotations per unit time (e.g., RPM).

[0066] FIG. 3 is a conceptual diagram illustrating the configuration of a sensor unit according to one embodiment of the present disclosure.

[0067] According to one embodiment of the present disclosure, the sensor unit (100) includes one or more cameras (110) to acquire multiple images of a moving ball. In one embodiment, by using the high-speed camera (110), images of the moving ball at each shooting point can be acquired while the ball moves within the angle of view of the high-speed camera (110). For example, if the high-speed camera (110) operates at 3800 FPS (frames per second), one image is saved per 1 / 3800 second, so multiple consecutive images of the moving ball can be acquired while the ball moves within the angle of view of the camera.

[0068] Referring to FIG. 3, the sensor unit (100) can be implemented as a three-dimensional camera that operates in a stereo manner, including two cameras (110), and can measure the direction and speed of the ball by calculating three-dimensional coordinates for a moving ball.

[0069] FIG. 4 is a conceptual diagram illustrating the configuration of an image processing unit according to one embodiment of the present disclosure.

[0070] According to one embodiment of the present disclosure, the image processing unit (200) may include a target image extraction unit (210) and an image accumulation unit (230).

[0071] In one embodiment, the target image extraction unit (210) is a means for extracting a target image, which is an image of a ball, from each of a plurality of original images acquired by the sensor unit (100). For example, the target image extraction unit (210) may recognize an image of a ball from the original image, and extract a certain area from the center coordinates of the ball as a region of interest, and extract it as a target image. In one embodiment, the target image extraction unit (210) may generate a target image such that the center coordinates of the ball correspond to the center of the target image.

[0072] In one embodiment, the image accumulation unit (230) can accumulate difference images of target images extracted from the target image extraction unit (210) to generate an accumulated difference image for spin calculation. In one embodiment, the image accumulation unit (230) can generate an accumulated difference image by accumulating differences between two consecutive target images of a moving ball. For example, the image accumulation unit (230) can obtain the difference between two consecutive target images as a difference image and accumulate these difference images into one image to generate an accumulated difference image. Here, the difference image of the two target images can be obtained by calculating a difference value of digital numerical values ​​corresponding to pixels constituting the two target images.

[0073] In one embodiment, the accumulated difference image generated by the image accumulation unit (230) can accumulate and display changes in patterns, markers, etc. located on the surface of the ball. In one embodiment, the pattern or marker on the ball may not be predetermined or may be irregular. However, this is not limited thereto, and one embodiment of the present disclosure can also be applied even when a predetermined or regular pattern or marker is used. In one embodiment, if there is no special pattern or marker on the surface of the ball, the shape of the ball itself can be used. For example, if there is no special pattern or marker displayed on the golf ball, changes in dimples on the surface of the golf ball can be generated as an accumulated difference image.

[0074] According to one embodiment of the present disclosure, the image processing unit (200) may further include an image preprocessing unit (220).

[0075] In one embodiment, the image preprocessing unit (220) may be a means for preprocessing the target images prior to differentiating and accumulating the target images. In one embodiment, the image preprocessing unit (220) may normalize the target images. For example, the target images may be captured with different sizes of balls depending on how close the moving ball is to the camera. Since the target images are images of the same ball, the target images may be normalized so that the sizes of the balls included in the target images are constant prior to differentiating and accumulating the target images. In addition, since the target images are affected by ambient lighting differently depending on the position of the ball, the brightness of the target images may vary, either entirely or partially. Prior to differentiating and accumulating the target images, the brightness of the target images may be adjusted and normalized.

[0076] In one embodiment, the image preprocessing unit (220) can remove background portions or various noise portions from the target image in advance. For example, the image preprocessing unit (220) can compare a base image containing only the background portion, but not the ball, with the target image to remove the background portion in advance. For example, the image preprocessing unit (220) can recognize and remove noise portions of the target image in advance using a noise filter.

[0077] In the embodiment described above, the image preprocessing unit (220) is described as preprocessing target images, but the present invention is not limited thereto, and for example, the image preprocessing unit (220) may be used as a means for preprocessing a plurality of original images acquired from the sensor unit (100). In addition, the functions of the image preprocessing unit (220) described in the embodiment described above may not be implemented separately as the image preprocessing unit (220), but may be implemented as a function of the target image extraction unit (210) and may be directly applied in the process of extracting the target image. For example, the target image extraction unit (210) may obtain the target image by normalizing the size and brightness of the ball image in the process of extracting the ball image.

[0078] Figures 5a to 5d are exemplary diagrams illustrating a process of obtaining an accumulated difference image from a target image.

[0079] In FIGS. 5A to 5D, images (1) to (20) are target images obtained by sequentially capturing images of a moving ball, and images (A) to (T) illustrate a process in which a cumulative difference image is generated by sequentially accumulating differences between two consecutive target images.

[0080] According to one embodiment of the present disclosure, the image processing unit (200) can generate an accumulated difference image for calculating the spin direction and spin speed of the ball from the target image. Referring to FIG. 5A, the image processing unit (200) calculates the difference between image (1) and image (2) in image (2), accumulates the difference, and stores it in the accumulated image. For example, if the value corresponding to each pixel of image (2) is subtracted from the value corresponding to each pixel of image (1), the same pixel becomes '0' and only the pixels corresponding to the difference between image (2) and image (1) have a value. For example, when comparing images (1) and (2) of FIG. 4, the background and the golf ball are almost identical, and only the change in marking according to spin can be recognized as the main difference, and image (B), expressed as the difference between images (1) and (2), shows the change in marking. Ultimately, the difference image, which is the difference between images (2) and (1), can be stored as image (B).

[0081] According to one embodiment, the image processing unit (200) calculates the difference between image (2) and image (3) again, and accumulates and stores the difference in the accumulated image. That is, the difference between image (3) and image (2) can be calculated, and the difference can be added to image (B) and stored as image (C). For example, if the value corresponding to each pixel of image (3) is subtracted by the value corresponding to each pixel of image (2), the same pixel becomes '0' and only the pixels corresponding to the difference between image (3) and image (2) have a value, and if this result is added pixel-to-pixel with image (B), an accumulated difference image such as image (C) can be stored. Ultimately, the difference image of image (2) and image (1) and the difference image of image (3) and image (2) can be accumulated and stored as image (C).

[0082] According to one embodiment, the image processing unit (200) can generate accumulated difference images (B) to (T) by repeatedly performing this process to calculate and sequentially accumulate difference images of target images (1) to (20).

[0083] Figure 6 is a conceptual diagram illustrating an embodiment of a spin calculation unit that calculates the spin of a ball from an accumulated difference image.

[0084] According to one embodiment of the present disclosure, the spin calculation unit (300) may receive a cumulative difference image from the image processing unit (200) and calculate the spin of the ball. According to one embodiment, the spin calculation unit (300) may receive at least one cumulative difference image and output the spin direction and spin speed of the moving ball detected by the sensor unit (100). For example, the spin calculation unit (300) may receive a cumulative difference image and output (v, u). Here, v is a vector value representing the direction of the rotation axis of the ball spin, and u is a scalar value (u) representing the spin speed of the ball in rotations per unit time (e.g., RPM).

[0085] In one embodiment, the spin calculation unit (300) may receive an accumulated difference image generated by accumulating difference images of target images captured at predetermined time intervals for a predetermined period of time among target images captured continuously with images of a moving ball. For example, image (J), which is an accumulated difference image generated by accumulating difference images of images (1) to (10) of FIG. 4, may be selected as an input. As another example, image (T), which is an accumulated difference image generated by accumulating difference images of images (1) to (20) of FIG. 4, may be selected as an input. As another example, an accumulated difference image (not shown) generated by accumulating difference images of images (1), (3), (5), ..., and (19) of FIG. 4 may be selected as an input.

[0086] In one embodiment, the spin calculation unit (300) may calculate the spin of a ball by receiving a plurality of accumulated difference images from among the accumulated difference images of target images that are sequentially captured images of a moving ball. For example, images (E), (J), (O), and (T) of FIG. 4 may be input to the spin calculation unit (300).

[0087] According to one embodiment, the spin calculation unit (300) may include an artificial neural network (350) capable of machine learning. The spin calculation unit (300) may be trained by training data that inputs cumulative spin images and outputs the spin direction and spin speed of the ball. The artificial neural network (350) may be trained to output the spin direction and spin speed of the ball that are already known by inputting cumulative spin images of the training data. Although the learning of the artificial neural network (350) has been described above using supervised learning as an example, it is not limited thereto, and unsupervised learning, semi-supervised learning, or reinforcement learning may be used alone or in combination. In addition, gradient / gradient descent, regression techniques, probability-based methods, geometric-based methods, or ensemble-based methods may be used for machine learning, but are not limited thereto.

[0088] According to one embodiment, the artificial neural network (350) of the spin generating unit (300) may be composed of a convolutional neural network, a recurrent neural network, a deep neural network, etc. However, the present invention is not limited thereto, and any type of artificial neural network may be used as long as it can infer the spin direction and spin speed of the ball by inputting a cumulative difference image.

[0089] FIG. 7 is a block diagram of a ball spin calculation device according to one embodiment of the present disclosure.

[0090] Referring to FIG. 7, the ball spin calculating device (700) may include a transceiver (710), a memory (720), and a processor (730). In addition, the processor (730) may be implemented as a software module. However, not all of the components illustrated in FIG. 7 are essential components of the ball spin calculating device (700). The ball spin calculating device (700) may be implemented with more components than the components illustrated in FIG. 7, or may be implemented with fewer components than the components illustrated in FIG. 7. In addition, the transceiver (710), the memory (720), and the processor (730) may be implemented in the form of a single chip.

[0091] In one embodiment, the transceiver (710) may communicate with a terminal, server, or other electronic device connected wired or wirelessly to the ball spin calculation device (700). For example, the transceiver (710) may receive images of a moving ball from the sensor unit and transmit the spin direction and spin speed of the moving ball to another server.

[0092] Various types of data, such as programs and files, such as applications, can be installed and stored in the memory (720). The processor (730) can access and use data stored in the memory (720), or store new data in the memory (720).

[0093] The processor (730) controls the overall operation of the ball spin calculation device (700) and may include at least one processor, such as a CPU or a GPU. The processor (730) may control other components included in the ball spin calculation device (700) to perform operations for operating the ball spin calculation device (700). For example, the processor (730) may execute a program stored in the memory (720), read a stored file, or store a new file. In one embodiment, the processor (730) may perform operations for operating the ball spin calculation device (700) by executing a program stored in the memory (720).

[0094] An embodiment of the present disclosure may also be implemented in the form of a recording medium containing computer-executable instructions, such as program modules, executed by a computer. Computer-readable media may be any available media that can be accessed by a computer, and includes both volatile and nonvolatile media, removable and non-removable media. Furthermore, computer-readable media may include both computer storage media and communication media. Computer storage media includes both volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storing information, such as computer-readable instructions, data structures, program modules, or other data. Communication media typically contains computer-readable instructions, data structures, or program modules, and includes any information delivery media.

[0095] The above description of the present disclosure is provided for illustrative purposes only, and those skilled in the art will readily appreciate that the present disclosure can be readily modified into other specific forms without altering the technical spirit or essential characteristics of the present invention. Therefore, the embodiments described above should be understood as illustrative in all respects and not restrictive. For example, components described as being single may be implemented in a distributed manner, and similarly, components described as being distributed may be implemented in a combined manner.

[0096] The scope of the present disclosure is indicated by the claims described below rather than the detailed description above, and all changes or modifications derived from the meaning and scope of the claims and their equivalent concepts should be interpreted as being included in the scope of the present disclosure.

[0097] [Explanation of symbols]

[0098] 10: Computing devices

[0099] 20: Ball

[0100] 100: Sensor section

[0101] 110: High-speed camera

[0102] 200: Image Processing Unit

[0103] 210: Target image extraction unit

[0104] 220: Image preprocessing unit

[0105] 230: Image accumulation section

[0106] 300: Spin generator

[0107] 350: Artificial Neural Network

Claims

1. In the method of calculating ball spin, A step of acquiring sequential images of a moving ball; A step of extracting a portion of a ball from each of the above consecutive images as a target image; A step of generating an accumulated difference image by accumulating the difference images of the above target images; and Comprising a step of calculating the spin direction and spin speed of the moving ball based on the accumulated difference image. How to calculate ball spin.

2. In paragraph 1, The above difference image is obtained by subtracting two consecutive target images. How to calculate ball spin.

3. In paragraph 2, The above difference image is obtained by subtracting the value corresponding to each pixel of one target image from the value corresponding to each pixel of another target image. How to calculate ball spin.

4. In paragraph 1, The spin direction of the above moving ball is the rotation axis vector of the ball, and the spin speed is the number of rotations per minute of the ball. How to calculate ball spin.

5. In paragraph 1, The step of calculating the spin direction and spin speed of the moving ball based on the above accumulated difference image is performed by a machine-learned artificial neural network. How to calculate ball spin.

6. In paragraph 1, The above cumulative difference image includes two or more cumulative difference images. How to calculate ball spin.

7. In paragraph 1, The step of acquiring successive images of the above moving ball is performed by two or more camera devices. How to calculate ball spin.

8. In paragraph 1, The above target image is located at the center of the center coordinate of the ball image. How to calculate ball spin.

9. In paragraph 1, The above target image is normalized to have the same size as the ball image. How to calculate ball spin.

10. In paragraph 1, The above target image is normalized so that the brightness of the ball image is uniform. How to calculate ball spin.

11. In the ball spin generating device, A sensor unit that acquires successive images of a moving ball; A target image extraction unit that extracts a portion of a ball from each of the above consecutive images as a target image; An image accumulation unit for generating an accumulated difference image by accumulating the difference images of the above target images; and A spin calculation unit that calculates the spin direction and spin speed of the moving ball based on the accumulated difference image. Ball spin generating device.

12. In paragraph 11, The above image accumulation unit obtains the difference image by subtracting two consecutive target images. Ball spin generating device.

13. In paragraph 12, The image accumulation unit obtains the subtraction image by subtracting the value corresponding to each pixel of one target image from the value corresponding to each pixel of another target image. Ball spin generating device.

14. In paragraph 11, The spin direction of the above moving ball is the rotation axis vector of the ball, and the spin speed is the number of rotations per minute of the ball. Ball spin generating device.

15. In paragraph 11, The above spin generating unit includes a machine-learned artificial neural network, The above artificial neural network receives the accumulated difference image as input and outputs the spin direction and spin speed of the moving ball. Ball spin generating device.

16. In paragraph 11, The above cumulative difference image includes two or more cumulative difference images. Ball spin generating device.

17. In paragraph 11, The above sensor unit includes two or more camera devices, Ball spin generating device.

18. In paragraph 11, The above target image extraction unit extracts the target image so that the center coordinate of the ball image is located at the center of the target image. Ball spin generating device.

19. In paragraph 11, Including more image preprocessing, The above image preprocessing unit normalizes the size of the ball image of the target image to be the same. Ball spin generating device.

20. In paragraph 11, Including more image preprocessing, The above image preprocessing unit normalizes the brightness of the ball image of the target image so that it is uniform. Ball spin generating device.

21. A program stored on a computer-readable recording medium that causes a computer to execute any one of the methods of clauses 1 to 10.

Images