WO2020150993A1 - 一种击球类运动的计分系统及计分方法 - Google Patents

一种击球类运动的计分系统及计分方法 Download PDF

Info

Publication number
WO2020150993A1
WO2020150993A1 PCT/CN2019/073140 CN2019073140W WO2020150993A1 WO 2020150993 A1 WO2020150993 A1 WO 2020150993A1 CN 2019073140 W CN2019073140 W CN 2019073140W WO 2020150993 A1 WO2020150993 A1 WO 2020150993A1
Authority
WO
WIPO (PCT)
Prior art keywords
ball
scoring
sports
collision
sound
Prior art date
Legal status (The legal status 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 status listed.)
Ceased
Application number
PCT/CN2019/073140
Other languages
English (en)
French (fr)
Inventor
伍楷舜
陈孟奇
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shenzhen University
Original Assignee
Shenzhen University
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 Shenzhen University filed Critical Shenzhen University
Priority to PCT/CN2019/073140 priority Critical patent/WO2020150993A1/zh
Publication of WO2020150993A1 publication Critical patent/WO2020150993A1/zh
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • 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

Definitions

  • the invention relates to the field of sound information processing, in particular to a scoring system and a scoring method for ball hitting sports.
  • batting sports are internationally recognized sports, such as table tennis.
  • the basic rules of the game are to separate the two ends of the table, and then the two sides take turns to serve to the opponent to receive back.
  • the serve must touch one's own side in sequence
  • To return the ball to the opponent’s table wait for the table tennis ball to touch your table before returning the table tennis to the opponent’s table. If your side fails to hit the table tennis back to the opponent’s table, it will be considered as a loss for the opponent to score a point.
  • there are other rules in the table tennis game For example, if the serve is completed by touching the net, it needs to be re-sent. The two sides take turns to serve five goals.
  • Party B must win by two points before winning. Since the aforementioned table tennis only needs to set up a net with a proper height between the two tabletops, and then the players each hold a racket to match the table tennis, the space required is not large, and the competition is It's a high level of sports value and fun, so it has been widely loved by the public.
  • the scoring of table tennis is mainly performed by a number of referees visually observing the game process, and then scoring the results of visual observations.
  • the above-mentioned table tennis scoring method has been followed for a long time. Although this method is feasible, it requires manpower. There are many, and the objectivity of artificial judgment is still insufficient. Especially in ordinary practice, there is often the problem of lack of referees. At this time, the players can only score by themselves. This scoring method is likely to affect the game due to subjective judgments. Actually, if you use the scoreboard to score, it takes time to record with the players and interrupts the game, so it is not ideal. If you score based on memory, it will be troublesome and easy to cause such shortcomings as forgetting and miscalculation.
  • the trajectory of the sphere is mainly recorded by a video camera.
  • This recording method is expensive and requires image processing technology to obtain the trajectory of the ball, which requires a lot of calculation. Therefore, there is an urgent need for an accurate and convenient scoring scheme for batting sports.
  • the present invention proposes an acoustic-based method and system for recording and scoring ball hitting movement tracks.
  • the present invention uses a microphone array to realize the location of the ball launch collision sound to record the trajectory and scoring of the ball.
  • a scoring system for batting sports including:
  • Microphone array module It has two or more microphones, used to collect and record the sound signals of the ball colliding with different planes in ball sports;
  • Positioning module According to the sound signal collected by the microphone array, extract the time difference and the angle of arrival of the sound signal to different microphones, so as to locate the ball in real time;
  • Collision type recognition module used to identify the type of collision between the ball and the plane through the classification method
  • Scoring module According to the rules and collision type recognition of batting sports and the position of the ball, score the game process.
  • the sound signal is the sound of hitting the ball, the sound of colliding with the tabletop, and/or the sound of colliding with the ground.
  • the microphone array is two microphones on a smart phone, and the recording start time of the microphone array is controlled by programming to obtain sound data of multiple channels.
  • the positioning module reduces the noise of the recorded sound signal, filters the environmental noise, and only retains the impulse sound when the ball collides with different planes.
  • the positioning module tracks the movement trajectory of the ball by recording the position of the collision point.
  • the classification method is a SVM or DNN machine learning algorithm.
  • S1 Place the microphone array in the center of the court, start the system, and the microphone array starts to collect and record the sound signals of the ball colliding with different planes in ball sports;
  • S2 Process each fixed-length recording data acquired while recording, including:
  • S2.1 Perform noise reduction on the recorded sound signal, filter environmental noise, and only retain the pulse data when the ball collides with different planes;
  • the collision type recognition module uses machine learning classification algorithms to classify the segmented pulse data to identify different collision planes
  • Scoring module Score the game process according to the rules and collision type recognition of batting sports and the position of the ball.
  • the positioning module tracks the movement trajectory of the ball by recording the position of the collision point.
  • the present invention uses the characteristics of different time differences between collision sounds to reach the microphone array to propose a scoring system, and uses an improved algorithm and correction module to more accurately locate the ball;
  • the processing process of the sound signal in the present invention firstly performs denoising processing on the sound signal at the receiving end, and positioning by positioning models such as AoA and TDOA to achieve more accurate positioning. Therefore, the present invention can meet the requirements of accurate positioning of the trajectory of the ball hitting movement, and the positioning accuracy is high.
  • Fig. 1 is a schematic diagram of a scoring system and method for ball hitting sports of the present invention
  • FIG. 2 is a block diagram of the scoring system of the present invention.
  • FIG. 3 is a flow chart of the scoring method of the present invention.
  • Figure 4 is a schematic diagram of the AOA positioning algorithm.
  • a scoring system for batting sports includes:
  • Microphone array module It has two or more microphones to collect and record the sound signals of the ball colliding with different planes in ball sports; the sound signals are the sound of hitting the ball, the sound of colliding with the table and/or the ball The sound of collision with the ground; the distance between the above two or more microphones is a known quantity.
  • the microphone array is two microphones on the smart phone, and the recording start time of the microphone array is controlled by programming to obtain sound data of multiple channels.
  • Positioning module According to the sound signal collected by the microphone array, the time difference and angle of arrival of the sound signal to different microphones are extracted, so as to locate the ball in real time; the positioning module reduces the noise of the recorded sound signal, filters the environmental noise, and only keeps the ball Impulsive sound when colliding with different planes.
  • the positioning module calculates the angle of arrival and the time of arrival according to the time difference of the sound when the ball collides with the face to each microphone in the microphone array, and then confirms the location of the collision point, and tracks the position of the collision point by recording The trajectory of the ball.
  • TDOA Time Difference of Arrival
  • time difference of arrival measures the time difference between a mobile terminal and different sending ends to estimate the distance to different terminals for positioning. Since there is no need to detect the signal transmission time, the system's requirements for time synchronization are greatly reduced.
  • the coordinates of the point MS are (x, y, 0), which is the case of two-dimensional positioning on the ground.
  • the unknown node obtains the direction of arrival of the wireless signal at the transmitter of the reference node through an antenna array or other receiving device, and calculates the relative direction angle between nodes to obtain the location information of the unknown node. It is defined that the angle between the direction vector projected from the transmitting end on the receiving plane to the receiving end and the x axis is the direction angle, and the angle between the direction vector from the receiving end to the transmitting end and the z axis is the elevation angle.
  • the position coordinates (x, y) of the unknown node can be obtained according to the above two formulas.
  • Collision type recognition module It is used to identify the type of collision between the ball and the plane through the classification method; the CFAR segmentation algorithm is used to segment the starting point and the end point of the pulse data generated when the ball collides with different planes, and the sound of the ball colliding with different planes is collected through a large number of Samples are used as training data sets and test data sets, and artificial neural networks are used for training and classification of classification models. Artificial Neural Networks (Artificial Neural Network, or ANN) are currently popular classification methods. It abstracts the human brain neuron network from the perspective of information processing, establishes a certain simple model, and forms different networks according to different connection methods. In engineering and academia, it is often referred to as neural network or quasi-neural network.
  • a neural network is a computing model, which is composed of a large number of nodes (or neurons) interconnected. Each node represents a specific output function, called an activation function. Each connection between two nodes represents a weighted value for the signal passing through the connection, called the weight, which is equivalent to the memory of an artificial neural network.
  • the artificial neural network can automatically mark the characteristics of the data. Then generate a suitable classification model for practical applications.
  • Scoring module According to the rules and collision type recognition of batting sports and the position of the ball, score the game process.
  • table tennis in table tennis, the ball falls off the table and collides with the floor, it is determined that the round is over, and the scorer is recorded according to the rules.
  • a scoring method for batting sports includes the following steps:
  • S1 Place the microphone array in the center of the court, start the system, and the microphone array starts to collect and record the sound signals of the ball colliding with different planes in ball sports;
  • S2 Process each fixed-length recording data acquired while recording, including:
  • S2.1 Perform noise reduction on the recorded sound signal, filter environmental noise, and only retain the pulse data when the ball collides with different planes;
  • the collision type recognition module uses machine learning classification algorithms to classify the segmented pulse data to identify different collision planes
  • Scoring module Score the game process according to the rules and collision type recognition of batting sports and the position of the ball.
  • the positioning module tracks the movement trajectory of the ball by recording the position of the collision point.

Landscapes

  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Physical Education & Sports Medicine (AREA)
  • Circuit For Audible Band Transducer (AREA)

Abstract

本发明公开了一种击球类运动计分系统，包括：麦克风阵列模块：具有两个或两个以上的麦克风，用于采集在球类运动中球与不同平面碰撞的声音信号并录音；定位模块：根据麦克风阵列采集到的声音信号，提取声音信号到达不同麦克风的时间差及到达角度，从而对球进行实时定位；碰撞类型识别模块：通过分类法用于识别球与平面的碰撞类型；计分模块：根据击球类运动的规则和碰撞类型识别及球的位置对比赛过程进行计分。还相应公开了其计分方法。本发明利用碰撞声音到达麦克风时间上的差异计算球的位置进而记录球的轨迹，通过区别不同的碰撞声区分运动员的得分，实现记录运动轨迹和计分的目的。

Description

一种击球类运动的计分系统及计分方法 技术领域
本发明涉及声音信息处理领域，具体涉及一种击球类运动的计分系统及计分方法。
背景技术
大部分击球类运动为国际供认之体育项目，例如乒乓球，其比赛基本规则系由算发放分离球桌两端，再由双方轮流发球予对方接回，比赛中发球需依序碰触己方及对方两桌面，回球则需等乒乓球触碰己桌面后，再将桌球回击到对方桌面，若己方未能将乒乓球回击至对方桌面，即算失球令对方取得一分，比赛以先到达二十一分为胜。此外，乒乓球比赛还有其他规则，如发球若触网才能完成则需重发，双方轮流发五球，若比分达到二十比二十则需乙方胜出两分才获胜等。前述乒乓球运动由于仅需于两球桌面间架设一具有适当高度之球网，再由比赛者各执一球拍，配合乒乓球即可进行，所需场地空间不大，而且该比赛除已于进行外，并具有高度运动价值与趣味性，故现今已广受大众喜爱。
目前，乒乓球运动计分主要都是由若干裁判目视比赛过程，然后再将目视观测所得加以计分显示，上述乒乓球计分方式沿袭已久，然该方式虽然可行，但所需人力较多，且人为判断客观性仍嫌不足，特别是在平常练习时，经常有欠缺裁判的困扰，此时，仅能由打球者自行计分，该计分方式一则易因主观判断影响比赛实况，再则，若以计分板计分时，与实赛者往来记录既费时又会中断比赛，故不理想，若凭记忆计分则于费神之外又易产生遗忘误算等缺点。
目前，乒乓球运动记录球体运动轨迹主要都是由摄像机记录，该记录方式成本高昂，需要图像处理技术获取球的移动轨迹，计算量大。因此，击球类运动急需一种准确、方便的计分方案。
发明内容
为了解决以上技术问题，本发明提出了一种基于声学的击球类运动轨迹记录及计分方法及系统。为了解决上述球类运动轨迹记计分方法及系统的问题，本发明使用麦克风阵列，实现对球类发车碰撞声音的位置进行定位，以记录击球轨迹以及计分，具体技术方案如下：
一种击球类运动计分系统，包括：
麦克风阵列模块：具有两个或两个以上的麦克风，用于采集在球类运动中球与不同平面碰撞的声音信号并录音；
定位模块：根据麦克风阵列采集到的声音信号，提取声音信号到达不同麦克风的时间差及到达角度，从而对球进行实时定位；
碰撞类型识别模块：通过分类法用于识别球与平面的碰撞类型；
计分模块：根据击球类运动的规则和碰撞类型识别及球的位置对比赛过程进行计分。
进一步，声音信号为击球声球、与桌面碰撞的声音和/或球与地面碰撞的声音。
进一步，所述的麦克风阵列为智能手机上的两个麦克风，通过编程控制麦克风阵列的录音开始时间, 得到多个声道的声音数据。
进一步，定位模块对录制到的声音信号进行降噪，过滤环境噪音，只保留球与不同平面碰撞时的脉冲声。
进一步，定位模块通过记录碰撞点的位置跟踪球的运动轨迹。
进一步，所述分类法为SVM或DNN机器学习算法。
一种击球类运动计分方法，其特征在于，包括以下步骤：
S1：将麦克风阵列摆放到球场正中央，启动系统，麦克风阵列开始采集在球类运动中球与不同平面碰撞的声音信号并录音；
S2：录音的同时对每获取到的固定长度的录音数据进行处理，包括：
S2.1：对录制到的声音信号进行降噪，过滤环境噪音，只保留球与不同平面碰撞时的脉冲数据；
S2.2：使用CFAR分割算法分割出球与不同平面碰撞时产生的脉冲数据；
S2.3：碰撞类型识别模块对分割出的脉冲数据使用机器学习分类算法进行分类，识别不同的碰撞平面；
S3：计分模块：根据击球类运动的规则和碰撞类型识别及球的位置对比赛过程进行计分。
进一步，定位模块通过记录碰撞点的位置跟踪球的运动轨迹。
与现有技术相比，本发明具有以下有益的技术效果：本发明利用碰撞声音到达麦克风阵列时间差不同的特性提出计分系统，并使用改进的算法和校正模块能够更准确对球类进行定位；本发明对声音信号的处理过程，首先根据将接收端的声音信号进行去噪处理，AoA,TDOA等定位模型定位，达到更为精确的定位。因此，本发明可以满足对击球类运动轨迹轨迹准确定位，定位精确度高。
附图说明
图1为本发明的一种击球类运动的计分系统及方法的原理图；
图2为本发明的计分系统的模块框图；
图3为本发明计分方法的流程图；
图4为AOA定位算法示意图。
具体实施方式
为了使本发明的目的、技术方案及优点更加清楚明白，以下结合附图及实施例，对本发明进行进一步详细说明。应当理解，此处所描述的具体实施例仅仅用以解释本发明，并不用于限定本发明。
结合附图2，一种击球类运动计分系统，其包括：
麦克风阵列模块：具有两个或两个以上的麦克风，用于采集在球类运动中球与不同平面碰撞的声音信号并录音；声音信号为击球声球、与桌面碰撞的声音和/或球与地面碰撞的声音；上述两个或两个以上的麦克风之间的距离为已知量。所述的麦克风阵列为智能手机上的两个麦克风，通过编程控制麦克风阵列的录音开始时间,得到多个声道的声音数据。
定位模块：根据麦克风阵列采集到的声音信号，提取声音信号到达不同麦克风的时间差及到达角度，从而对球进行实时定位；定位模块对录制到的声音信号进行降噪，过滤环境噪音，只保留球与不同平面碰撞时的脉冲声。通过AoA、TDOA，见图1所述，定位模块根据球与碰面碰撞时的声音到达麦克风阵列中各麦克风的时间差求出到达角度和到达时间进而确认碰撞点的位置，通过记录碰撞点的位置跟踪球的运动轨迹。
TDOA(Time Difference of Arrival),又称到达时间差，通过测量移动终端到不同发送端的时间差从而估计到不同终端的距离之差进而进行定位。由于不需要检测信号传输时间，因此系统对时间同步的要求大大降低。
设定为点MS的坐标为(x，y，0)，即位于地面的二维定位的情况。发送端的位置坐标为(x i,y i,z i)，i＝1,2,3…M，其中M为参与定位的发送端数量。若测得第s个信号与第一个信号(作为基准信号的时间差为τ s1，则第s个发端与第1个发端到MS的传输距离差为R s1＝R s-R 1(s＝2,3…M)。利用传输距离差可列方程求MS位置坐标(x,y)。
Figure PCTCN2019073140-appb-000001
将
Figure PCTCN2019073140-appb-000002
代入上式，令
Figure PCTCN2019073140-appb-000003
x si＝x s-x i，化简得
Figure PCTCN2019073140-appb-000004
当M＝3时，有如下：
Figure PCTCN2019073140-appb-000005
式中
Figure PCTCN2019073140-appb-000006
利用上式求解出x，y，将其带入R 1中，便可求出R 1的值，剔除不符合物理意义的负数结果，把正值带入式(3.12)中即可得到MS坐标。
AoA(Angle of Arrival)到达角度
参见图4，在AOA定位算法中，未知节点通过天线阵列或者其他接收设备获取参考节点发送端无线信号的到达方向，计算节点间的相对方向角获取未知节点的位置信息。定义发送端在接受平面上的投影到接收端的方向向量与x轴的夹角为方向角，接受端到发射端的方向向量与z轴的夹角为仰角。
途中
Figure PCTCN2019073140-appb-000007
和
Figure PCTCN2019073140-appb-000008
分别为两个方位角，ψ 1和ψ 2为两个仰角。一般在二维平面定位时，只需测得接受到信号的两个方位角即可实现定位。假设令两个发送端的坐标分别为A(x 1,y 1),B(x 2,y 2)，未知节点的坐标为(x,y)，测得的方位角为
Figure PCTCN2019073140-appb-000009
和
Figure PCTCN2019073140-appb-000010
对于发送端A有
Figure PCTCN2019073140-appb-000011
化简可得
Figure PCTCN2019073140-appb-000012
同理，对于发送端B，有
Figure PCTCN2019073140-appb-000013
据此可以根据以上两式求出未知节点的位置坐标(x,y)。
碰撞类型识别模块：通过分类法用于识别球与平面的碰撞类型；使用CFAR分割算法分割出球与不同平面碰撞时产生的脉冲数据的起始点和结束点，通过大量收集球体碰撞不同平面声音的样本作为训练数据集合和测试数据集，使用人工神经网络进行分类模型的训练和分类，人工神经网络(Artificial Neural Network，即ANN)，是一种目前流行的分类方法。它从信息处理角度对人脑神经元网络进行抽象，建立某种简单模型，按不同的连接方式组成不同的网络。在工程与学术界也常直接简称为神经网络或类神经网络。神经网络是一种运算模型，由大量的节点(或称神经元)之间相互联接构成。每个节点代表一种特定的输出函数，称为激励函数(activationfunction)。每两个节点间的连接都代表一个对于通过该连接信号的加权值，称之为权重，这相当于人工神经网络的记忆，通过输入大量的训练数据，人工神经网络可以自动标记数据的特征，进而生成合适的分类模型用于实际应用。
计分模块：根据击球类运动的规则和碰撞类型识别及球的位置对比赛过程进行计分。
以乒乓球为例，在乒乓球运动中球跌落到桌面外与地板碰撞，则判定本回合结束，按照规则记录得分方。
一种击球类运动计分方法，包括以下步骤：
S1：将麦克风阵列摆放到球场正中央，启动系统，麦克风阵列开始采集在球类运动中球与不同平面碰撞的声音信号并录音；
S2：录音的同时对每获取到的固定长度的录音数据进行处理，包括：
S2.1：对录制到的声音信号进行降噪，过滤环境噪音，只保留球与不同平面碰撞时的脉冲数据；
S2.2：使用CFAR分割算法分割出球与不同平面碰撞时产生的脉冲数据；
S2.3：碰撞类型识别模块对分割出的脉冲数据使用机器学习分类算法进行分类，识别不同的碰撞平面；
S3：计分模块：根据击球类运动的规则和碰撞类型识别及球的位置对比赛过程进行计分。
进一步，定位模块通过记录碰撞点的位置跟踪球的运动轨迹。
以上内容是结合具体的优选方式对本发明所作的进一步详细说明，不应认定本发明的具体实施只局限于以上说明。对于本技术领域的技术人员而言，在不脱离本发明构思的前提下，还可以作出若干简单推演或替换，均应视为由本发明所提交的权利要求确定的保护范围之内。

Claims (8)

  1. 一种击球类运动计分系统，其特征在于，包括：
    麦克风阵列模块：具有两个或两个以上的麦克风，用于采集在球类运动中球与不同平面碰撞的声音信号并录音；
    定位模块：根据麦克风阵列采集到的声音信号，提取声音信号到达不同麦克风的时间差及到达角度，从而对球进行实时定位；
    碰撞类型识别模块：通过分类法用于识别球与平面的碰撞类型；
    计分模块：根据击球类运动的规则和碰撞类型识别及球的位置对比赛过程进行计分。
  2. 如权利要求1所述的计分系统，其特征在于：声音信号为击球声球、球与桌面碰撞的声音和/或球与地面碰撞的声音。
  3. 如权利要求1所述的计分系统，其特征在于：所述的麦克风阵列为智能手机上的两个麦克风，通过编程控制麦克风阵列的录音开始时间,得到多个声道的声音数据。
  4. 如权利要求1所述的计分系统，其特征在于：定位模块对录制到的声音信号进行降噪，过滤环境噪音，只保留球与不同平面碰撞时的脉冲数据。
  5. 如权利要求1所述的计分系统，其特征在于：定位模块通过记录碰撞点的位置跟踪球的运动轨迹。
  6. 如权利要求1所述的计分系统，其特征在于：所述分类法为SVM或DNN机器学习算法。
  7. 一种击球类运动计分方法，其特征在于，包括以下步骤：
    S1：将麦克风阵列摆放到球场正中央，启动系统，麦克风阵列开始采集在球类运动中球与不同平面碰撞的声音信号并录音；
    S2：录音的同时对每获取到的固定长度的录音数据进行处理，包括：
    S2.1：对录制到的声音信号进行降噪，过滤环境噪音，只保留球与不同平面碰撞时的脉冲数据；
    S2.2：使用CFAR分割算法分割出球与不同平面碰撞时产生的脉冲数据；
    S2.3：碰撞类型识别模块对分割出的脉冲数据使用机器学习分类算法进行分类，识别不同的碰撞平面；
    S3：计分模块：根据击球类运动的规则和碰撞类型识别及球的位置对比赛过程进行计分。
  8. 如权利要求1所述的计分方法，其特征在于：定位模块通过记录碰撞点的位置跟踪球的运动轨迹。
PCT/CN2019/073140 2019-01-25 2019-01-25 一种击球类运动的计分系统及计分方法 Ceased WO2020150993A1 (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
PCT/CN2019/073140 WO2020150993A1 (zh) 2019-01-25 2019-01-25 一种击球类运动的计分系统及计分方法

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2019/073140 WO2020150993A1 (zh) 2019-01-25 2019-01-25 一种击球类运动的计分系统及计分方法

Publications (1)

Publication Number Publication Date
WO2020150993A1 true WO2020150993A1 (zh) 2020-07-30

Family

ID=71735971

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/073140 Ceased WO2020150993A1 (zh) 2019-01-25 2019-01-25 一种击球类运动的计分系统及计分方法

Country Status (1)

Country Link
WO (1) WO2020150993A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116380050A (zh) * 2023-04-17 2023-07-04 上海创屹科技有限公司 乒乓球的落点区域检测方法、回合计算方法及乒乓球桌

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103888580A (zh) * 2014-03-31 2014-06-25 宇龙计算机通信科技(深圳)有限公司 一种终端录音过程中降噪处理方法及终端
US9084057B2 (en) * 2011-10-19 2015-07-14 Marcos de Azambuja Turqueti Compact acoustic mirror array system and method
CN106226740A (zh) * 2016-08-04 2016-12-14 北京地平线信息技术有限公司 远场声源定位系统和方法
CN109164414A (zh) * 2018-09-07 2019-01-08 深圳市天博智科技有限公司 基于麦克风阵列的定位方法、装置和存储介质

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9084057B2 (en) * 2011-10-19 2015-07-14 Marcos de Azambuja Turqueti Compact acoustic mirror array system and method
CN103888580A (zh) * 2014-03-31 2014-06-25 宇龙计算机通信科技(深圳)有限公司 一种终端录音过程中降噪处理方法及终端
CN106226740A (zh) * 2016-08-04 2016-12-14 北京地平线信息技术有限公司 远场声源定位系统和方法
CN109164414A (zh) * 2018-09-07 2019-01-08 深圳市天博智科技有限公司 基于麦克风阵列的定位方法、装置和存储介质

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116380050A (zh) * 2023-04-17 2023-07-04 上海创屹科技有限公司 乒乓球的落点区域检测方法、回合计算方法及乒乓球桌

Similar Documents

Publication Publication Date Title
CN102221369B (zh) 一种球类运动的动作识别方法、装置和动作辅助设备
CN107050803A (zh) 一种羽毛球训练监控评估系统
CN107392939A (zh) 基于体感技术的室内运动观测装置、方法及存储介质
KR100907704B1 (ko) 인공지능형 캐디를 이용한 골퍼자세교정시스템 및 이를이용한 골퍼자세교정방법
CN114037928B (zh) 基于边缘计算的球类运动分析方法、装置和系统
KR102226623B1 (ko) 실내 스포츠를 위한 카메라를 이용한 운동량 산출 시스템
CN111184994B (zh) 击球训练方法、终端设备及存储介质
CN108671505B (zh) 一种羽毛球运动辅助系统及其控制方法
JP2020500489A (ja) ゴルフ競技を撮影するためのカメラシステムおよびその方法
CN109663325B (zh) 一种击球类运动的计分系统及计分方法
CN116688473A (zh) 拳击比赛评判方法及电子设备
CN108905182B (zh) 一种智能眼镜和台球摄像定位瞄准方法
CN115188078A (zh) 一种基于语音交互和姿态估计的乒乓球智能动作训练方法
CN102944180B (zh) 一种基于图像处理的乒乓球抛球高度检测系统及方法
CN118675102A (zh) 一种基于视觉技术判断羽毛球击球训练的方法及装置
WO2020150993A1 (zh) 一种击球类运动的计分系统及计分方法
CN110929595A (zh) 一种基于人工智能的有球无球训练或娱乐系统及方法
CN107899225B (zh) 一种基于运动轨迹的乒乓球发球得分识别方法
CN120586364A (zh) 基于ai智能识别的台球桌响袋及球杆打感精准反馈系统
Zheng et al. A method for table tennis bat trajectories reconstruction with the fusion of human keypoint information
CN119810925A (zh) 一种计算机视觉的匹克球运动员动作分析方法
CN113209597A (zh) 一种线下台球击球辅助方法、装置、终端及存储介质
CN114788951A (zh) 手持运动分析系统与方法
CN105879350A (zh) 一种高尔夫球评分方法及其系统
CN112007340B (zh) 基于加速度传感器的乒乓球比赛裁判和球员训练系统及方法

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 19911942

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 19911942

Country of ref document: EP

Kind code of ref document: A1

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 10/11/2021)

122 Ep: pct application non-entry in european phase

Ref document number: 19911942

Country of ref document: EP

Kind code of ref document: A1