WO2022062153A1 - 一种高尔夫球落地式检测方法、系统及存储介质 - Google Patents

一种高尔夫球落地式检测方法、系统及存储介质 Download PDF

Info

Publication number
WO2022062153A1
WO2022062153A1 PCT/CN2020/131288 CN2020131288W WO2022062153A1 WO 2022062153 A1 WO2022062153 A1 WO 2022062153A1 CN 2020131288 W CN2020131288 W CN 2020131288W WO 2022062153 A1 WO2022062153 A1 WO 2022062153A1
Authority
WO
WIPO (PCT)
Prior art keywords
golf ball
camera
picture
golf
positioning
Prior art date
Application number
PCT/CN2020/131288
Other languages
English (en)
French (fr)
Inventor
王继军
王清华
Original Assignee
深圳市衡泰信科技有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 深圳市衡泰信科技有限公司 filed Critical 深圳市衡泰信科技有限公司
Priority to CA3131155A priority Critical patent/CA3131155C/en
Priority to EP20923691.8A priority patent/EP4009276A4/en
Priority to KR1020217030580A priority patent/KR102603819B1/ko
Priority to AU2020449438A priority patent/AU2020449438B2/en
Priority to JP2021556386A priority patent/JP7214006B2/ja
Priority to US17/499,883 priority patent/US12011652B2/en
Publication of WO2022062153A1 publication Critical patent/WO2022062153A1/zh

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/70—Determining position or orientation of objects or cameras
    • G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
    • 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
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T3/00—Geometric image transformations in the plane of the image
    • G06T3/04—Context-preserving transformations, e.g. by using an importance map
    • G06T3/047—Fisheye or wide-angle transformations
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/12—Edge-based segmentation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/181—Segmentation; Edge detection involving edge growing; involving edge linking
    • 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
    • G06T2207/30204—Marker
    • 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
    • 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
    • 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
    • G06T2207/30241—Trajectory

Definitions

  • the present invention relates to the technical field of golf simulation, and in particular, to a method, a system and a storage medium for ground-mounted detection of golf balls.
  • the golf system includes the hitting area, sensors, computing unit and display screen.
  • the golf system can be used for indoor golf or outdoor golf.
  • the sensor collects the hitting information and motion information of the golf ball, and the computing unit simulates the motion trajectory of the golf ball according to the information and displays it on the display screen.
  • the sensor may be an image sensor or a light sensing sensor or the like. When using an image sensor, it is necessary to analyze and process the image information to obtain the motion change information of the golf ball to simulate its motion trajectory.
  • the current golf system processes the pictures collected by the image sensor, it does not perform environmental adaptation processing on the pictures, which affects the positioning accuracy in the golf ball positioning process.
  • the purpose of the present invention is to provide a golf ball landing detection method, system and storage medium, aiming at improving the positioning accuracy of the golf system during the positioning process.
  • the present invention proposes a ground-type detection method for golf balls, which is applied to a golf system equipped with a camera on the side to detect golf balls, the golf balls are provided with marks, and the method includes the following steps:
  • the positioning of the golf ball adopting the dynamic segmentation method based on fuzzy entropy to process the picture collected by the camera after triggering the shot, and locating the processed picture to obtain the coordinate data of the golf ball;
  • parameter calculation substitute the coordinate data of the golf ball obtained by positioning into the world coordinate system to calculate the motion parameters of the golf ball;
  • the present invention provides a golf simulation system, wherein the system includes a memory, a processor, and a computer program stored in the memory and configured to be executed by the processor, the processor executing The computer program implements the aforementioned method.
  • the present invention provides a computer-readable storage medium, wherein a computer program is stored in the computer-readable storage medium, and when the computer program is executed, the aforementioned method is implemented.
  • the golf ball landing type detection method of the present invention adopts the distortion correction of the camera, combined with the dynamic segmentation based on fuzzy entropy used in positioning, so that the image processing can adapt to the change of the ambient light, and the positioning accuracy is improved.
  • the position monitoring is no longer performed, but the real-time monitoring of the pixel change value at the golf ball teeing position is performed. In this way, the change from coordinate positioning to pixel monitoring can improve the response speed of the golf system.
  • FIG. 1 is a schematic flowchart of the first embodiment of the golf ball grounding detection method according to the present invention
  • FIG. 2 is a schematic diagram of the conversion process between the image coordinate system and the world coordinate system of the present invention
  • Fig. 3 is the golf ball motion parameter calculation schematic diagram of the present invention.
  • FIG. 5 is a schematic diagram of the simulated background brightness in the positioning of the present invention.
  • FIG. 6 is a schematic diagram of the process of eliminating simulated background brightness and removing interference background in positioning according to the present invention.
  • FIG. 7 is a schematic diagram of the process of obtaining the target contour after the original image is dynamically divided by fuzzy entropy in the positioning of the present invention.
  • FIG. 8 is a schematic diagram of the screening process of target contour passing area, aspect ratio and brightness in positioning according to the present invention.
  • FIG. 9 is a schematic diagram of the process of fitting and correcting a picture after target screening in the positioning of the present invention.
  • FIG. 10 is a schematic flowchart of the first embodiment of the golf ball rotational speed detection according to the present invention.
  • FIG. 11 is a schematic diagram of simulating and adjusting the illumination distribution in the detection of the rotational speed of the golf ball according to the present invention.
  • Figure 12 is a schematic diagram of the process of obtaining the mark map in the golf ball rotational speed detection of the present invention.
  • the present invention proposes a grounding detection method for golf balls, which is applied to a golf system equipped with a camera on the side of the golf ball to detect the motion state of the golf ball, and the golf ball is provided with a mark.
  • a golf system equipped with a camera on the side is a golf system with a floor-mounted camera, and the pictures collected are the perspective of the side of the golf ball.
  • the golf system with floor-mounted camera is suitable for detecting the motion state of golf balls in low-resolution and low-performance golf systems.
  • the lens of this type of golf system In order to meet the requirements that the floor-mounted camera can capture more data, the lens of this type of golf system generally adopts a wide-angle camera, but the wide-angle camera has fisheye distortion, which must be corrected. At the same time, when the golf ball is shot from a side perspective, the human body and the golf ball will overlap, causing great interference. Therefore, the golf system with a camera on the side of the present invention is suitable for the following method to detect the movement of the golf ball to improve the response speed of the system.
  • the distortion correction of the camera the polar coordinate transformation is used to correct the distorted image coordinate system of the camera.
  • the correction formula used to correct the distorted image coordinate system of the camera by polar coordinate transformation is:
  • phi is the azimuth angle
  • x, y are the coordinates of the image coordinate system
  • DST and dst are the radius lengths on the polar coordinate system of the output plane and the image plane, respectively
  • r is the physical radius of the camera lens
  • L is the zoom factor.
  • the polar coordinate system of the above correction formula can be used to obtain the corrected coordinate system, so as to solve the problem of image distortion and improve the image accuracy.
  • Camera calibration is the process of transforming the mathematical meaning of the real image into a digital implementation process that can be calculated and manipulated.
  • the calibration of the camera can affect the subsequent calculation accuracy and avoid the accumulation of errors in the algorithm. It is the key to achieve efficient computational targets.
  • a fixed number of calibration blocks of different heights and uniform distribution are used at fixed positions.
  • the distribution of the calibration blocks is designed based on experiments with the highest efficiency. Since the calibration blocks contain height information after placement, only one calibration is required.
  • the camera of the present invention can be a monocular camera or a binocular camera, and when a binocular camera is used, each camera is individually calibrated.
  • the process of converting the image coordinate system into the world coordinate system after the correction of the present invention is to first convert the image coordinate system into the image plane coordinate system, then convert the image plane coordinate system into the camera coordinate system, and then convert the camera coordinate system into the camera coordinate system. Convert to world coordinate system.
  • the present invention uses the following conversion formula to convert the corrected image coordinate system into the world coordinate system:
  • M 1 is the internal parameter matrix of the camera
  • M 2 is the external parameter matrix of the camera
  • M 1 ⁇ M 2 M
  • M is the mapping matrix
  • each of the binocular cameras is calibrated to obtain a mapping matrix M , and the coordinates and the matrix of the binocular camera are substituted into the simultaneously to obtain the world coordinates.
  • Triggering batting judgment can avoid positioning processing of each frame of pictures before serving, thereby reducing the image processing capacity of the system and improving the response processing speed of the system.
  • the camera Before hitting the ball, the camera first collects pictures, and performs preliminary positioning from the pictures to obtain the coordinates of the golf ball at the teeing position. After obtaining the coordinates of the golf ball's teeing position, the present invention no longer monitors the change of the golf ball's coordinate position before the ball is served, but instead performs real-time monitoring of the pixel change value at the golf ball's teeing position, because the golf ball's The change monitoring of the coordinate position requires global positioning of the entire picture, while the pixel monitoring only needs to process the picture at the golf ball teeing position, which reduces the processing area and content of the picture. In this way, the change of coordinate positioning to pixel monitoring can improve the response speed of the golf system.
  • the image processing needs to adapt to the changes of the environment, such as changes in the target and changes in the interference, such as changes in brightness and shape.
  • the present invention adopts the dynamic segmentation method based on fuzzy entropy to process the picture, which can well adapt to the environmental changes in the foreground and the background, and can accurately separate the required target and improve the positioning accuracy.
  • the coordinates obtained by the positioning in step S40 are converted into world coordinates to calculate the motion parameters, including parameters such as ball speed, side fly angle, take-off angle, etc., ⁇ is the side fly angle, ⁇ is the take-off angle, and V is the space ball speed .
  • detection of rotational speed of golf ball detection of rotational speed of golf ball: using gradient-based dynamic segmentation method to extract the mark on the golf ball in the picture used for positioning, and obtain the rotational speed through the angle change of the extracted mark in the picture.
  • a mark is preset on the golf ball, so that the rotation speed can be calculated according to the angle change of the mark in the picture.
  • the gradient-based dynamic segmentation rule of the present invention can accurately extract the mark on the golf ball in the lower resolution picture, thereby ensuring the subsequent rotation detection.
  • step S50 Using the parameter calculation in step S50 to convert the coordinates obtained from the positioning into world coordinates, parameters such as ball speed, fly angle, take-off angle can be calculated, and then combined with step S60 to obtain the rotational speed of the golf ball, the golf ball after hitting the ball can be simulated and calculated.
  • the detection and simulation of the present invention are generally carried out separately, and the simulation is generally completed by the client.
  • the present invention uses a dynamic segmentation method based on fuzzy entropy to process the pictures collected by the camera after triggering the shot, and locates the processed pictures to obtain the coordinate data of the golf ball, which specifically includes the following steps :
  • the brightness of the ambient background of the picture is simulated, and then the brightness of the simulated background is removed in the original picture.
  • the left is the original image, which has obvious interference background of human legs, and then the image on the right is obtained by excluding the brightness of the simulated background in this figure, and the interference background in the right image has been removed.
  • the brightness of the ball surface shows a large range of changes (about [40-120]), and in the case of dynamic changes in brightness, the dynamic segmentation based on fuzzy entropy can be well adapted to the hit.
  • the change in the picture environment after the distance between the ball and the camera changes, so that the target in the picture can be accurately segmented.
  • the segmentation value of the fuzzy entropy dynamic segmentation of the present invention is calculated by the following formula:
  • u is the degree of membership
  • m is the feature value based on the gray value
  • v is the pixel value
  • entropy is the fuzzy entropy
  • the original image collected by the camera after hitting the ball of the present invention is processed by fuzzy entropy dynamic segmentation to obtain the picture on the right in FIG. 7 .
  • the middle and edge parts of the target are highlighted. Thereby a clear outline of the target is obtained.
  • S403 perform area, aspect ratio, and brightness screening on the binarized target contour, remove non-golf targets, and retain golf targets to obtain a golf target picture.
  • This step is used to remove non-golf debris from the image, such as club heads and other reflective shapes in the image. Because golf balls have specific characteristics such as area, aspect ratio, brightness, etc., these characteristics can be filtered.
  • the left side is the binarized target contour image obtained by dynamic segmentation based on fuzzy entropy.
  • the area, aspect ratio, and brightness are filtered in turn to obtain Figure 8
  • the debris has been removed in the picture at this time.
  • the outline of the golf ball in the golf target image is not a complete circle, as shown in the left part of Figure 9, so it is impossible to locate the center of the golf ball in the image. Therefore, it is necessary to correct the contour of the ball in the target image.
  • a complete circular contour of the golf ball is obtained by fitting and correcting the least squares method.
  • the right part of FIG. 9 is a picture of the complete ball contour after fitting and correction.
  • S405 Acquire the coordinates of the ball center of the golf ball according to the complete golf ball outline picture.
  • the complete golf ball outline picture can accurately locate the center of the ball, and then obtain the ball center coordinates of the golf ball through the pixel coordinates.
  • the present invention uses a gradient-based dynamic segmentation method to extract the marks on the golf ball in the picture used for positioning, and obtains the rotational speed through the angle change of the extracted marks in the picture, which specifically includes the following steps: Describe the steps:
  • a mark is pre-set on the golf ball, so that a mark map can be obtained according to the mark in the picture.
  • the simulated distribution is applicable to a wide range, but its distribution effect is poor. Therefore, the illumination distribution on the spherical surface obtained from the subsequent positioning is added and adjusted to obtain the adjustment on the right.
  • the light distribution map can achieve the best light distribution effect in this environment.
  • a heat energy map is obtained by making a difference between the original image obtained from the positioning and the adjusted illumination distribution map to exclude the influence caused by the brightness change, and the gradients in the x and y axis directions are obtained on the heat energy map and superimposed to obtain the most obvious local change. marker diagram.
  • the brightness distribution of the foreground is uneven, and the brightness of each frame of the picture changes greatly, and the resolution of the obtained picture is low. At this time, it is difficult to obtain the mark on the golf ball clearly and accurately if the gray value segmentation is used.
  • the present invention adopts a gradient-based dynamic segmentation method:
  • the difference between the original image on the left and the adjusted illumination distribution image is obtained first, and then the middle heat energy map is obtained, which excludes the influence caused by the brightness change. Then, the gradients in the x and y axis directions are calculated and superimposed on the heat energy map, and the marked map on the right with the most obvious local changes is obtained.
  • the angular features of the marks (marks) in the mark graph are extracted.
  • the angle sample feature library stores various angles of marks on the golf ball and three-dimensional coordinate information corresponding to various angles. After extracting the angle feature of the mark on the golf ball in the picture, it is matched with the angle sample feature library to obtain the corresponding three-dimensional coordinate information.
  • the angle feature of the mark extracted by the Singular Value Decomposition (SVD) method in the embodiment of the present invention is the case where the mark on the golf ball is fixed.
  • the center of mass of the mark can be found as the target point, and the rotational speed is calculated according to the three-dimensional coordinates corresponding to the spherical surface of the target point.
  • S604 Calculate the rotational speed of the golf ball based on the three-dimensional coordinate information obtained from the marks in two consecutive frames of pictures.
  • the rotation state of the golf ball at each point of the trajectory can be simulated, which improves the realism of the system simulation.
  • the golf ball grounding detection method proposed in the embodiment of the present invention adopts the distortion correction of the camera, combined with the dynamic segmentation based on fuzzy entropy used in positioning, so that the image processing can adapt to changes in ambient light, improve the accuracy of positioning, and at the same time by triggering
  • the position monitoring is no longer carried out, but the real-time monitoring of the pixel change value at the golf ball teeing position is carried out. In this way, the change from coordinate positioning to pixel monitoring can improve the golf system. reaction speed.
  • the gradient-based dynamic segmentation method is used to extract the mark on the golf ball, which can accurately extract the mark on the golf ball in the low-resolution picture, so as to accurately obtain the angle characteristics of the golf ball. to calculate the speed.
  • the present invention also provides a golf simulation system, the system includes a memory, a processor and a computer program stored in the memory and configured to be executed by the processor, when the processor executes the computer program, Implement the above method.
  • the computer program may be divided into one or more modules/units, and the one or more modules/units are stored in the memory and executed by the processor to accomplish the present invention.
  • the one or more modules/units may be a series of computer program instruction segments capable of accomplishing specific functions, and the instruction segments are used to describe the execution process of the computer program in the asynchronous message processing terminal device.
  • the main control module may include, but is not limited to, a processor and a memory. Those skilled in the art can understand that the above components are only examples based on the system, and do not constitute a limitation on the main control module, and may include more or less components than the above, or combine some components, or different components, such as
  • the main control module may also include input and output devices, network access devices, buses, and the like.
  • the processor may be a central processing unit (Central Processing Unit, CPU), or other general-purpose processors, digital signal processors (Digital Signal Processor, DSP), application-specific integrated circuits (Application Specific Integrated Circuit, ASIC), off-the-shelf Programmable Gate Array (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc.
  • the general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc.
  • the processor is the control center of the device, and uses various interfaces and lines to connect various parts of the entire main control module.
  • the memory can be used to store the computer program and/or module, and the processor implements the device by running or executing the computer program and/or module stored in the memory and calling the data stored in the memory various functions.
  • the memory may mainly include a stored program area and a stored data area, wherein the stored program area may store an operating system, an application program required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the storage data area may store The data (such as audio data, phone book, etc.) created according to the usage, etc.
  • the memory may include high-speed random access memory, and may also include non-volatile memory, such as hard disk, internal memory, plug-in hard disk, smart memory card (Smart Media Card, SMC), Secure Digital , SD) card, flash memory card (Flash Card), at least one magnetic disk storage device, flash memory device, or other volatile solid state storage device.
  • non-volatile memory such as hard disk, internal memory, plug-in hard disk, smart memory card (Smart Media Card, SMC), Secure Digital , SD) card, flash memory card (Flash Card), at least one magnetic disk storage device, flash memory device, or other volatile solid state storage device.
  • the present invention also provides a computer-readable storage medium, where a computer program is stored in the computer-readable storage medium, and the above-mentioned method is implemented when the computer program is executed.
  • the integrated modules/units of the golf ball grounding detection method of the present invention are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium.
  • the specific implementation manner of the computer-readable storage medium of the present invention is basically the same as that of the above-mentioned embodiments of the golf ball grounding detection method, and will not be repeated here.
  • the above-described embodiments are only illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units , that is, it can be located in one place, or it can be distributed to multiple network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution in this embodiment.
  • the connection relationship between the modules indicates that there is a communication connection between them, which may be specifically implemented as one or more communication buses or signal lines. Those of ordinary skill in the art can understand and implement it without creative effort.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Multimedia (AREA)
  • Image Analysis (AREA)
  • Length Measuring Devices By Optical Means (AREA)

Abstract

一种高尔夫球落地式检测方法、系统及存储介质，所述方法包括下述步骤：摄像头的畸变修正（S10）；摄像头的标定（S20）；触发击球：对摄像头采集图片中高尔夫球发球位置处的像素变化值进行实时监测，当该位置像素变化值之超过阈值即为触发击球（S30）；高尔夫球的定位：对触发击球后摄像头采集的图片采用基于模糊熵动态分割方式处理图片，并对处理后的图片进行定位获取高尔夫球的坐标数据（S40）；参数计算（S50）；高尔夫球的转速检测：对定位所用图片中的高尔夫球上的标记采用基于梯度的动态分割法进行提取，通过所述提取的标记在图片中的角度变化获取转速（S60）。提升了高尔夫系统在进行定位处理过程的定位准确度。

Description

一种高尔夫球落地式检测方法、系统及存储介质 技术领域
本发明涉及高尔夫模拟技术领域，尤其涉及一种高尔夫球落地式检测方法、系统及存储介质。
 背景技术
高尔夫系统包括击球区，传感器，计算单元和显示屏幕。高尔夫系统可以用在室内高尔夫或者室外高尔夫运动项目。
使用者在击球区击打高尔夫球，传感器采集高尔夫球的击打信息及运动信息，计算单元根据这些信息来模拟高尔夫球的运动轨迹并在显示屏幕上进行显示。传感器可以是图像传感器或者光感应传感器等。当使用图像传感器时，需要对图像信息进行分析处理以得到高尔夫球的运动变化信息以模拟其运动轨迹。
然而，目前的高尔夫系统在对图像传感器采集的图片进行处理时，并没有对图片进行环境适应性处理，这样影响高尔夫球定位过程中的定位准确度。
因此，现有技术还有待发展。
 技术解决方案
鉴于上述现有技术的不足之处，本发明的目的在于提供一种高尔夫球落地式检测方法、系统及存储介质，旨在提升高尔夫系统在进行定位处理过程的定位准确度。
为实现上述目的，本发明采取了以下技术方案：
第一方面，本发明提出了一种高尔夫球落地式检测方法，应用于侧面配置有摄像头的高尔夫系统对高尔夫球进行检测，所述高尔夫球上设置有标记，其中，包括下述步骤：
S10，摄像头的畸变修正：对摄像头的畸变图像坐标系采用极坐标变换修正；
S20，摄像头的标定：将修正后的图像坐标系转换成世界坐标系；
S30，触发击球：对摄像头采集图片中高尔夫球发球位置处的像素变化值进行实时监测, 当该位置像素变化值之超过阈值即为触发击球；
S40，高尔夫球的定位：对触发击球后摄像头采集的图片采用基于模糊熵动态分割方式处理图片,并对处理后的图片进行定位获取高尔夫球的坐标数据；
S50，参数计算：将定位得到高尔夫球的坐标数据代入世界坐标系计算高尔夫球的运动参数；
S60，高尔夫球的转速检测：对定位所用图片中的高尔夫球上的标记采用基于梯度的动态分割法进行提取，通过所述提取的标记在图片中的角度变化获取转速。
第二方面，本发明提出了一种高尔夫模拟系统，其中，所述系统包括存储器、处理器及存储在所述存储器中并被配置为由所述处理器执行的计算机程序，所述处理器执行所述计算机程序时，实现前述的方法。
第三方面，本发明提出了一种计算机可读存储介质，其中，所述计算机可读存储介质中存储有计算机程序，所述计算机程序被执行时实现前述的方法。
 有益效果
本发明的高尔夫球落地式检测方法，采用摄像头的畸变修正，结合定位时采用的基于模糊熵动态分割，使得图片处理能适应环境光的变化，提高定位的准确度，同时通过触发击球判断，在得到高尔夫球发球位置的坐标后，不再进行位置监测，而是改为对高尔夫球发球位置处的像素变化值进行实时监测，这样由坐标定位改为像素监测可以提高高尔夫系统的反应速度。
 附图说明
为了更清楚地说明本发明实施例或现有技术中的技术方案，下面将对实施例或现有技术描述中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图仅仅是本发明的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图示出的结构获得其他的附图。
图1为本发明高尔夫球落地式检测方法第一实施例的流程示意图；
图2为本发明图像坐标系与世界坐标系转换过程示意图；
图3为本发明高尔夫球运动参数计算示意图；
图4为本发明高尔夫球定位第一实施例的流程示意图；
图5为本发明定位中模拟背景亮度示意图；
图6为本发明定位中排除模拟背景亮度去掉干扰背景过程示意图；
图7为本发明定位中原图经过模糊熵动态分割后得到目标轮廓过程示意图；
图8为本发明定位中目标轮廓经过面积，高宽比，亮度筛选过程示意图；
图9为本发明定位中目标筛选后图片经过拟合修正的过程示意图；
图10为本发明高尔夫球转速检测第一实施例的流程示意图；
图11为本发明高尔夫球转速检测中模拟及调整光照分布示意图；
   图12为本发明高尔夫球转速检测中得到mark图的过程示意图。
 本发明的实施方式
下面将结合本发明实施例中的附图，对本发明实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例仅仅是本发明的一部分实施例，而不是全部的实施例。基于本发明中的实施例，本领域普通技术人员在没有作出创造性劳动前提下所获得的所有其他实施例，都属于本发明保护的范围。
本发明提出一种高尔夫球落地式检测方法，应用于侧面配置有摄像头的高尔夫系统对高尔夫球的运动状态进行检测，所述高尔夫球上设置有标记（mark）。
侧面配置有摄像头的高尔夫系统，即为落地式摄像头的高尔夫系统,其采集的图片为高尔夫球侧面的视角。落地式摄像头的高尔夫系统适用于分辨率较低的中低性能高尔夫系统中高尔夫球的运动状态检测。
为满足落地式摄像头能抓取成更多数据, 该类型的高尔夫系统的镜头一般采用广角摄像头, 但是广角摄像头存在鱼眼畸变,必须进行修正。同时，侧面的视角拍摄高尔夫球时，人体和高尔夫球会产生重合,存在较大干扰。故本发明的侧面配置有摄像头的高尔夫系统适用于以下方法对高尔夫球的运动进行检测来提高系统的反应速度。
如图1所示，为本发明高尔夫球落地式检测方法的流程，包括下述步骤：
S10，摄像头的畸变修正：对摄像头的畸变图像坐标系采用极坐标变换修正。
因采用了广角摄像头，存在鱼眼畸变, 根据经验该畸变将使成像不同位置坐标转换世界坐标时的精度不同, 直接表现为长杆球速较实际更慢，故需要进行修正。 由于镜头规格固定, 对此使用固定几何变换快速修正畸变坐标使其回归透视原理。
优选地，本发明实施例对摄像头的畸变图像坐标系采用极坐标变换修正所用的修正公式为：
 
Figure 894419dest_path_image001
其中：
 
Figure 980055dest_path_image002
phi为方位角，x, y为图像坐标系坐标， DST和dst分别为输出平面和图像平面极坐标系上的半径长, r为摄像头的镜头物理半径长, L为缩放倍数。
这样可用上面修正公式的极坐标系求出修正后的坐标系，从而解决图像的畸变问题，提高图像精度。
S20，摄像头的标定：将修正后的图像坐标系转换成世界坐标系。
在进行图像处理的过程中，为确定空间物体表面某点的三维几何位置与其在图像中对应点之间的相互关系，必须建立相机成像的几何模型，在大多数条件下这些参数必须通过实验与计算才能得到，这个求解参数的过程就称之为相机标定（或摄像头标定）。相机的标定就是将真实的图像的数学意义转化到可计算可操作的数字化的实现过程。
摄像头的标定能影响后续计算精度，避免误差在算法中逐渐累积增大。它是实现有效计算目标物的关键。
本发明在标定过程中，采用高低不同, 分布均匀的固定数目固定位置的标定块, 标定块分布基于实验为效率最高设计，由于摆放后标定块包含高度信息因此只需标定一次。
本发明的摄像头可以采用单目摄像头或者双目摄像头，采用双目摄像头时，对每一摄像头进行单独标定。
如图2所示，本发明修正后图像坐标系转换成世界坐标系的过程为先将图像坐标系转换为像平面坐标系，然后将像平面坐标系转换为摄像机坐标系，再将摄像机坐标系转换为世界坐标系。
优选地，本发明将修正后的图像坐标系转换成世界坐标系采用下述转换公式：
 
Figure 424943dest_path_image003
其中，M 1为摄像头的内参矩阵，M 2为摄像头的外参矩阵， M 1×M 2= M， M为映射矩阵。
当本发明的摄像头为双目摄像头时，对双目摄像头各自标定得到映射矩阵M ，将双目摄像头的坐标和矩阵代入联立求出世界坐标。
S30，触发击球：对摄像头采集图片中高尔夫球发球位置处的像素变化值进行实时监测, 当该位置像素变化值之超过阈值即为触发击球。
触发击球判断可以避免对发球前的每一帧图片都进行定位处理而减少系统的图片处理量，提高系统的反应处理速度。
在击球前，摄像头先采集图片，并从图片中进行初步定位获取高尔夫球在发球位置的坐标。在得到高尔夫球发球位置的坐标后，本发明在发球前不再对高尔夫球的坐标位置的变化进行监测，而是改为对高尔夫球发球位置处的像素变化值进行实时监测，因为高尔夫球的坐标位置的变化监测需要对整张图进行全局定位，而像素监测只需对高尔夫球发球位置处的图片进行处理，减少了图片的处理面积和内容。这样由坐标定位改为像素监测可以提高高尔夫系统的反应速度。
S40，高尔夫球的定位：对触发击球后摄像头采集的图片采用基于模糊熵动态分割方式处理图片,并对处理后的图片进行定位获取高尔夫球的坐标数据。
因为侧面配置有摄像头的高尔夫系统，人体和高尔夫球会产生重合,干扰大，图片处理时需要适应环境的变化，如目标的变化和干扰物的变化，变化有亮度，形状变化等。
而本发明采用基于模糊熵动态分割方式处理图片能够很好地适应前景及背景中的环境变化，而准确地分离出所需的目标，提高定位的准确度。
S50，参数计算：将定位得到高尔夫球的坐标数据代入世界坐标系计算高尔夫球的运动参数。
如图3所示，利用步骤S40定位得到的坐标转换为世界坐标即可计算运动参数，包括球速, 侧飞角, 起飞角等参数，θ是侧飞角，γ是起飞角，V是空间球速。
S60，高尔夫球的转速检测：高尔夫球的转速检测：对定位所用图片中的高尔夫球上的标记采用基于梯度的动态分割法进行提取，通过所述提取的标记在图片中的角度变化获取转速。
本发明在高尔夫球上预先设置有标记（mark），这样可以根据图片中标记（mark）的角度变化来计算转速。
由于前景亮度分布不均以及每帧亮度变化较大, 在较低分辨率下的图片中提取高尔夫球上的mark具有相当的难度，不适用于灰度值分割。而本发明的基于梯度的动态分割法则能在较低分辨率下的图片中准确地提取高尔夫球上的mark，而保证后续的旋转检测。
利用步骤S50的参数计算将定位得到的坐标转换为世界坐标后即可计算球速, 侧飞角, 起飞角等参数，再结合步骤S60获得高尔夫球的转速，即可模拟计算出在击球后高尔夫球的完整运动轨迹，以及轨迹上高尔夫球的旋转状态。本发明的检测和模拟一般分开进行，模拟一般由客户端完成。
具体地，如图4所示，本发明对触发击球后摄像头采集的图片采用基于模糊熵动态分割方式处理图片,并对处理后的图片进行定位获取高尔夫球的坐标数据，具体包括下述步骤：
S401，获取触发击球后的图片，对该图片采用排除模拟背景亮度的方式去掉干扰背景。
如图5所示，模拟图片环境背景的亮度，然后在原图中用将所述模拟背景亮度去除。如图6中所示，左边为原图，其存在有明显的人体双腿的干扰背景，然后在该图中通过排除模拟背景亮度后得到右边的图，右边的图中干扰背景已经去除。
S402，对去掉干扰背景的图片进行模糊熵动态分割得到清晰的二值化目标轮廓。
在击球后球与摄像头的距离变化下, 球表面的亮度呈现较大区间的变化(大约[40-120]), 而在亮度动态变化的情况下采用基于模糊熵动态分割可以良好地适应击球后球与摄像头距离变化后图片环境中的变化，以能准确地分割出图片中的目标。
优选地，本发明的模糊熵动态分割的分割值采用如下公式计算：
 
Figure 231225dest_path_image004
其中，u为隶属度, m为基于灰度值的特征值, v为像素值，entropy为模糊熵；
将符合上式像素范围内的每一个像素分别代入上式求其前景和背景的模糊熵, 并选择最小值做为最佳分割值。最后得到目标轮廓清晰的二值化图片。
如图7所示，本发明击球后摄像头采集的原图经过模糊熵动态分割处理后的得到图7中右边的图片，此时的目标物的中间和边缘各部分均以呈高亮显示，从而得到了目标的清晰轮廓。
S403，对该二值化目标轮廓进行面积，高宽比，亮度筛选后去掉非高尔夫球的目标，保留高尔夫球目标得到高尔夫球目标图片。
该步骤用于去除图片中的非高尔夫球杂物，如去掉图片中的杆头及其他反光等形状。因为高尔夫球有特定的面积、宽高比、亮度等特征，故可以这些特征进行筛选。
如图8所示，左边为经过基于模糊熵动态分割得到的二值化目标轮廓图片，该图片中存在非高尔夫球形状的杂物，然后依次经过面积，高宽比，亮度筛选后得到图8中右边的图片，此时杂物在图片中已经被去除。
S404，对筛选后高尔夫球目标图片中的球轮廓用最小二乘法拟合修正, 得到完整的高尔夫球轮廓图片。
由于阴影等因素影响，高尔夫球目标图片中的高尔夫球的轮廓并不是一个完整的圆形，如图9中的左边部分所示，这样就没法在图片中定位出高尔夫球的中心。故需要对目标图片中的球轮廓修正。本发明实施例采用最小二乘法拟合修正得到高尔夫球的完整圆形轮廓，如图9右边部分所示为拟合修正后的完整球轮廓的图片。
S405，依据所述完整的高尔夫球轮廓图片获取高尔夫球的球中心坐标。
完整的高尔夫球轮廓图片能够准确地定位出球的中心，然后通过像素点坐标来得到高尔夫球的球中心坐标。
具体地，如图10所示，本发明对定位所用图片中的高尔夫球上的标记采用基于梯度的动态分割法进行提取，通过所述提取的标记在图片中的角度变化获取转速，具体包括下述步骤：
S601，以摄像头发出的红外平行光为基础模拟球面的光照分布得到模拟光照分布图，将后续定位所得图片中的球表面光照分布加入该模拟光照分布图进行光照分布调整得到调整光照分布图。
如图12中左边的图所示，本发明在高尔夫球上预先设置有标记（mark），这样可以根据图片中标记（mark）得到标记图。
如图11中左边所示，先对球表面的光照进行模拟分布，该模拟分布适用范围较广，但是其分布效果较差，故将后续定位得到球表面光照分布加入后进行调整得到右边的调整光照分布图，可达到该环境下最佳光照分布效果。
S602，将定位所得的原图与该调整光照分布图做差得到热能图以排除亮度变化造成的影响，在所述热能图上求取x、y轴方向上的梯度并叠加得到局部变化最明显的标记图。
前景亮度分布不均，同时每帧图片的亮度变化较大,得到图片的分辨率较低，此时如果采用灰度值分割难以清晰准确地获得高尔夫球上的标记（mark）。本发明采用了基于梯度的动态分割法：
如图12中所示，先将左边的原图与调整光照分布图做差后得到中间的热能图，该热能图排除了亮度变化造成的影响。然后在该热能图上求取x、y轴方向上的梯度并叠加，即得到了右边的局部变化最明显的标记图。
S603，对所述标记图采用向量奇异值分解方式提取标记的角度特征，对比预先建立的角度样本特征库，获取该角度特征在角度样本特征库中匹配的三维坐标信息。
用奇异值分解(SVD)，提取标记图中标记（mark）的角度特征。角度样本特征库存储高尔夫球上标记（mark）的各种角度，及各种角度对应的三维坐标信息。提取出高尔夫球上标记（mark）在图片中的角度特征后，与角度样本特征库进行匹配得到对应的三维坐标信息。
本发明实施例的奇异值分解(SVD) 方式提取标记的角度特征是对高尔夫球上标记（mark）固定的情形。在其他实施例中，当高尔夫球上标记（mark）不固定时，可以采用寻找标记（mark）的质心做目标点, 根据目标点的球面对应的三维坐标计算转速。
S604，以连续两帧图片中的标记所获得的三维坐标信息计算高尔夫球的转速。
得到高尔夫球的转速后，结合定位得到的坐标信息，可以模拟出以高尔夫球在轨迹各点的旋转状态，提高系统模拟的真实感。
本发明实施例提出的高尔夫球落地式检测方法，采用摄像头的畸变修正，结合定位时采用的基于模糊熵动态分割，使得图片处理中能适应环境光的变化，提高定位的准确度，同时通过触发击球判断，在得到高尔夫球发球位置的坐标后，不再进行位置监测，而是改为对高尔夫球发球位置处的像素变化值进行实时监测，这样由坐标定位改为像素监测可以提高高尔夫系统的反应速度。并且在转速检测过程中采用基于梯度的动态分割法进行提取高尔夫球上的标记（mark），能够在低分辨图片中准确提取高尔夫球上的标记（mark），以准确地获得高尔夫球的角度特征来计算转速。
本发明还提出一种高尔夫模拟系统，所述系统包括存储器、处理器及存储在所述存储器中并被配置为由所述处理器执行的计算机程序，所述处理器执行所述计算机程序时，实现上述的方法。
示例性的，所述计算机程序可以被分割成一个或多个模块/单元，所述一个或者多个模块/单元被存储在所述存储器中，并由所述处理器执行，以完成本发明。所述一个或多个模块/单元可以是能够完成特定功能的一系列计算机程序指令段，该指令段用于描述所述计算机程序在所述异步消息处理终端设备中的执行过程。
所述主控模块可包括但不仅限于处理器、存储器。本领域技术人员可以理解，上述部件仅仅是基于系统的示例，并不构成对主控模块的限定，可以包括比上述更多或更少的部件，或者组合某些部件，或者不同的部件，例如主控模块还可以包括输入输出设备、网络接入设备、总线等。
所称处理器可以是中央处理单元(Central Processing Unit，CPU)，还可以是其他通用处理器、数字信号处理器(Dig ita l Sig na l Processor，DSP) 、专用集成电路(Application Specific Integrated Circuit，ASIC)、现成可编程门阵列(Field-Programmable Gate Array，FPGA)或者其他可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件等。通用处理器可以是微处理器或者该处理器也可以是任何常规的处理器等，所述处理器是所述设备的控制中心，利用各种接口和线路连接整个主控模块的各个部分。
所述存储器可用于存储所述计算机程序和/或模块，所述处理器通过运行或执行存储在所述存储器内的计算机程序和/或模块，以及调用存储在存储器内的数据，实现所述设备的各种功能。所述存储器可主要包括存储程序区和存储数据区，其中，存储程序区可存储操作系统、至少一个功能所需的应用程序(比如声音播放功能、图像播放功能等)等；存储数据区可存储根据使用所创建的数据(比如音频数据、电话本等)等。此外，存储器可以包括高速随机存取存储器，还可以包括非易失性存储器，例如硬盘、内存、插接式硬盘，智能存储卡(Smart Media Card ,SMC)，安全数字(Secure Digital ,SD)卡，闪存卡(Flash Card)、至少一个磁盘存储器件、闪存器件、或其他易失性固态存储器件。
本发明还提出一种计算机可读存储介质，所述计算机可读存储介质中存储有计算机程序，所述计算机程序被执行时实现上述的方法。
本发明的高尔夫球落地式检测方法集成的模块/单元如果以软件功能单元的形式实现并作为独立的产品销售或使用时，可以存储在一个计算机可读取存储介质中。本发明计算机可读存储介质具体实施方式与上述用于高尔夫球落地式检测方法各实施例基本相同，在此不再赘述。
需说明的是，以上所描述的实施例仅仅是示意性的，其中所述作为分离部件说明的单元可以是或者也可以不是物理上分开的，作为单元显示的部件可以是或者也可以不是物理单元，即可以位于一个地方，或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部模块来实现本实施例方案的目的。另外，本发明提供的实施例附图中，模块之间的连接关系表示它们之间具有通信连接，具体可以实现为一条或多条通信总线或信号线。本领域普通技术人员在不付出创造性劳动的情况下，即可以理解并实施。
以上所述仅为清楚地说明本发明所作的举例，并非因此限制本发明的专利范围，这里无法对所有的实施方式予以穷举，凡是在本发明的构思下，利用本发明技术方案中的内容所作的等效结构变换，或直接/间接运用在其他相关的技术领域均包括在本发明的专利保护范围内。

Claims (8)

  1. 一种高尔夫球落地式检测方法，应用于侧面配置有摄像头的高尔夫系统对高尔夫球进行检测，所述高尔夫球上设置有标记，其特征在于，包括下述步骤：
    S10，摄像头的畸变修正：对摄像头的畸变图像坐标系采用极坐标变换修正；
    S20，摄像头的标定：将修正后的图像坐标系转换成世界坐标系；
    S30，触发击球：对摄像头采集图片中高尔夫球发球位置处的像素变化值进行实时监测, 当该位置像素变化值之超过阈值即为触发击球；
    S40，高尔夫球的定位：对触发击球后摄像头采集的图片采用基于模糊熵动态分割方式处理图片,并对处理后的图片进行定位获取高尔夫球的坐标数据；
    S50，参数计算：将定位得到高尔夫球的坐标数据代入世界坐标系计算高尔夫球的运动参数；
    S60，高尔夫球的转速检测：对定位所用图片中的高尔夫球上的标记采用基于梯度的动态分割法进行提取，通过所述提取的标记在图片中的角度变化获取转速。
  2. 根据权利要求1所述的方法，其特征在于，所述对摄像头的畸变图像坐标系采用极坐标变换修正所用的修正公式为：
    Figure 23352dest_path_image001
     
    其中：
     
    Figure 219978dest_path_image002
        phi为方位角，x, y为图像坐标系坐标， DST和dst分别为输出平面和图像平面极坐标系上的半径长, r为摄像头的镜头物理半径长, L为缩放倍数。
  3. 根据权利要求1所述的方法，其特征在于，所述将修正后的图像坐标系转换成世界坐标系采用下述转换公式：
     
    Figure 630100dest_path_image003
    其中，M 1为摄像头的内参矩阵，M 2为摄像头的外参矩阵， M 1×M 2= M，M为映射矩阵。
  4. 根据权利要求1所述的方法，其特征在于，所述对触发击球后摄像头采集的图片采用基于模糊熵动态分割方式处理图片,并对处理后的图片进行定位获取高尔夫球的坐标数据，具体包括下述步骤：
    S401，获取触发击球后的图片，对该图片采用排除模拟背景亮度的方式去掉干扰背景；
    S402，对去掉干扰背景的图片进行模糊熵动态分割得到清晰的二值化目标轮廓；
    S403，对该二值化目标轮廓进行面积，高宽比，亮度筛选后去掉非高尔夫球的目标，保留高尔夫球目标得到高尔夫球目标图片；
    S404，对筛选后高尔夫球目标图片中的球轮廓用最小二乘法拟合修正, 得到完整的高尔夫球轮廓图片；
    S405，依据所述完整的高尔夫球轮廓图片获取高尔夫球的球中心坐标。
  5. 根据权利要求1所述的方法，其特征在于，所述模糊熵动态分割的分割值采用如下公式计算：
     
    Figure 898270dest_path_image004
    其中，u为隶属度, m为基于灰度值的特征值, v为像素值，entropy为模糊熵；
    将符合上式像素范围内的每一个像素分别代入上式求其前景和背景的模糊熵, 并选择最小值做为最佳分割值。
  6. 根据权利要求1所述的方法，其特征在于，对定位所用图片中的高尔夫球上的标记采用基于梯度的动态分割法进行提取，通过所述提取的标记在图片中的角度变化获取转速，具体包括下述步骤：
    S601，以摄像头发出的红外平行光为基础模拟球面的光照分布得到模拟光照分布图，将后续定位所得图片中的球表面光照分布加入该模拟光照分布图进行光照分布调整得到调整光照分布图；
    S602，将定位所得的原图与该调整光照分布图做差得到热能图以排除亮度变化造成的影响，在所述热能图上求取x、y轴方向上的梯度并叠加得到局部变化最明显的标记图；
    S603，对所述标记图采用向量奇异值分解方式提取标记的角度特征，对比预先建立的角度样本特征库，获取该角度特征在角度样本特征库中匹配的三维坐标信息；
    S604，以连续两帧图片中的标记所获得的三维坐标信息计算高尔夫球的转速。
  7. 一种高尔夫模拟系统，其特征在于，所述系统包括存储器、处理器及存储在所述存储器中并被配置为由所述处理器执行的计算机程序，所述处理器执行所述计算机程序时，实现如权利要求1-6中任一项所述的方法。
  8. 一种计算机可读存储介质，其特征在于，所述计算机可读存储介质中存储有计算机程序，所述计算机程序被执行时实现如权利要求1-6任一项所述的方法。
PCT/CN2020/131288 2020-09-22 2020-11-25 一种高尔夫球落地式检测方法、系统及存储介质 WO2022062153A1 (zh)

Priority Applications (6)

Application Number Priority Date Filing Date Title
CA3131155A CA3131155C (en) 2020-09-22 2020-11-25 Floor-type golf ball detection method, system and storage medium
EP20923691.8A EP4009276A4 (en) 2020-09-22 2020-11-25 GOLF BALL FLOOR TYPE DETECTION METHOD, SYSTEM AND STORAGE HOLDER
KR1020217030580A KR102603819B1 (ko) 2020-09-22 2020-11-25 골프공 착지형 검출방법, 시스템 및 저장매체
AU2020449438A AU2020449438B2 (en) 2020-09-22 2020-11-25 Floor-type golf ball detection method, system and storage medium
JP2021556386A JP7214006B2 (ja) 2020-09-22 2020-11-25 ゴルフボールオンフロア式検出方法、システム及び記憶媒体
US17/499,883 US12011652B2 (en) 2020-09-22 2021-10-13 Floor-type golf ball detection method, system and storage medium

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202010999663.4 2020-09-22
CN202010999663.4A CN112184807B (zh) 2020-09-22 2020-09-22 一种高尔夫球落地式检测方法、系统及存储介质

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US17/499,883 Continuation US12011652B2 (en) 2020-09-22 2021-10-13 Floor-type golf ball detection method, system and storage medium

Publications (1)

Publication Number Publication Date
WO2022062153A1 true WO2022062153A1 (zh) 2022-03-31

Family

ID=73956422

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/131288 WO2022062153A1 (zh) 2020-09-22 2020-11-25 一种高尔夫球落地式检测方法、系统及存储介质

Country Status (2)

Country Link
CN (1) CN112184807B (zh)
WO (1) WO2022062153A1 (zh)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113171597A (zh) * 2021-05-10 2021-07-27 海口美视国际高尔夫俱乐部有限公司 综合高尔夫练习场和综合房
CN113538550A (zh) * 2021-06-21 2021-10-22 深圳市如歌科技有限公司 高尔夫球感测方法、系统及存储介质

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103442773A (zh) * 2011-03-22 2013-12-11 高夫准株式会社 虚拟高尔夫模拟装置及其使用的感测装置与感测方法
US20150356748A1 (en) * 2013-01-08 2015-12-10 Golfzon Co., Ltd. Method and apparatus for sensing moving ball
CN107239748A (zh) * 2017-05-16 2017-10-10 南京邮电大学 基于棋盘格标定技术的机器人目标识别与定位方法
CN107543530A (zh) * 2016-06-29 2018-01-05 可利爱驰有限公司 用于测量球的旋转的方法、系统及非暂时性计算机可读记录介质
CN110787433A (zh) * 2018-08-03 2020-02-14 深圳市衡泰信科技有限公司 一种用于高尔夫模拟器的高尔夫球感测系统
CN111097155A (zh) * 2018-10-29 2020-05-05 可利爱驰有限公司 用于测定球的旋转的方法、系统及存储介质

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2007146621A2 (en) * 2006-06-12 2007-12-21 Wintriss Engineering Corporation Method and apparatus for detecting the placement of a golf ball for a launch monitor
KR101862145B1 (ko) * 2016-11-23 2018-05-29 주식회사 골프존 사용자의 골프샷에 대한 정보를 산출하기 위한 센싱장치 및 이를 이용한 센싱방법
CN106780620B (zh) * 2016-11-28 2020-01-24 长安大学 一种乒乓球运动轨迹识别定位与跟踪系统及方法

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103442773A (zh) * 2011-03-22 2013-12-11 高夫准株式会社 虚拟高尔夫模拟装置及其使用的感测装置与感测方法
US20150356748A1 (en) * 2013-01-08 2015-12-10 Golfzon Co., Ltd. Method and apparatus for sensing moving ball
CN107543530A (zh) * 2016-06-29 2018-01-05 可利爱驰有限公司 用于测量球的旋转的方法、系统及非暂时性计算机可读记录介质
CN107239748A (zh) * 2017-05-16 2017-10-10 南京邮电大学 基于棋盘格标定技术的机器人目标识别与定位方法
CN110787433A (zh) * 2018-08-03 2020-02-14 深圳市衡泰信科技有限公司 一种用于高尔夫模拟器的高尔夫球感测系统
CN111097155A (zh) * 2018-10-29 2020-05-05 可利爱驰有限公司 用于测定球的旋转的方法、系统及存储介质

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
See also references of EP4009276A4 *
WU, TENGTENG : "Application of Minimum Fuzzy Entropy Segmentation Method to Oil Spill Detection in SAR Imagery", REMOTE SENSING INFORMATION, vol. 30, no. 2, 30 April 2015 (2015-04-30), pages 89 - 93,98, XP055859641, ISSN: 1000-3177, DOI: 10.3969/j.issn.100-3177.2015.02.016 *

Also Published As

Publication number Publication date
CN112184807A (zh) 2021-01-05
CN112184807B (zh) 2023-10-03

Similar Documents

Publication Publication Date Title
CN107507235B (zh) 一种基于rgb-d设备采集的彩色图像和深度图像的配准方法
CN110111248B (zh) 一种基于特征点的图像拼接方法、虚拟现实系统、照相机
CN113255486B (zh) 一种基于高位视频监控的车位占用检测方法
CN107145224B (zh) 基于三维球面泰勒展开的人眼视线跟踪方法和装置
WO2022062153A1 (zh) 一种高尔夫球落地式检测方法、系统及存储介质
CN107330942A (zh) 一种标定模板、标定方法、标定操作方法及标定系统
CN106408551A (zh) 一种监控装置控制的方法及装置
CN115201883B (zh) 一种运动目标视频定位测速系统及方法
CN106886976B (zh) 一种基于内参数修正鱼眼像机的图像生成方法
CN113763478B (zh) 无人车相机标定方法、装置、设备、存储介质及系统
US20220088455A1 (en) Golf ball set-top detection method, system and storage medium
CN115830135A (zh) 一种图像处理方法、装置及电子设备
TW202247108A (zh) 視覺定位方法、設備及電腦可讀儲存媒體
CN116977449B (zh) 一种基于闪烁棋盘格的复眼事件相机主动标定方法
CN110910489B (zh) 一种基于单目视觉的智能球场运动信息采集系统与方法
CN110340901B (zh) 一种控制方法、控制装置及终端设备
WO2022062152A1 (zh) 一种高尔夫球置顶式检测方法、系统及存储介质
US12011652B2 (en) Floor-type golf ball detection method, system and storage medium
CN215954346U (zh) 一种篮球比赛自动生成运动员点位图的视频拍摄装置
CN113506210A (zh) 一种篮球比赛自动生成运动员点位图的方法和视频拍摄装置
CN107086033B (zh) 云计算系统
CN108108694A (zh) 一种人脸特征点定位方法及装置
CN113674145B (zh) Ptz运动图像的球面拼接与实时对准方法
TWI755250B (zh) 植物生長曲線確定方法、裝置、電子設備及存儲媒體
CN112070846A (zh) 基于视频的实时人体动作跟踪方法和系统

Legal Events

Date Code Title Description
ENP Entry into the national phase

Ref document number: 2021556386

Country of ref document: JP

Kind code of ref document: A

ENP Entry into the national phase

Ref document number: 2020923691

Country of ref document: EP

Effective date: 20210916

ENP Entry into the national phase

Ref document number: 2020449438

Country of ref document: AU

Date of ref document: 20201125

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: 20923691

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE