CN109961039B - Personal goal video capturing method and system - Google Patents
Personal goal video capturing method and system Download PDFInfo
- Publication number
- CN109961039B CN109961039B CN201910213895.XA CN201910213895A CN109961039B CN 109961039 B CN109961039 B CN 109961039B CN 201910213895 A CN201910213895 A CN 201910213895A CN 109961039 B CN109961039 B CN 109961039B
- Authority
- CN
- China
- Prior art keywords
- goal
- hand
- basketball
- players
- player
- 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.)
- Active
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
- A63B71/02—Games or sports accessories not covered in groups A63B1/00 - A63B69/00 for large-room or outdoor sporting games
-
- 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
-
- A—HUMAN NECESSITIES
- A63—SPORTS; GAMES; AMUSEMENTS
- A63B—APPARATUS FOR PHYSICAL TRAINING, GYMNASTICS, SWIMMING, CLIMBING, OR FENCING; BALL GAMES; TRAINING EQUIPMENT
- A63B71/00—Games or sports accessories not covered in groups A63B1/00 - A63B69/00
- A63B71/06—Indicating or scoring devices for games or players, or for other sports activities
- A63B71/0619—Displays, user interfaces and indicating devices, specially adapted for sport equipment, e.g. display mounted on treadmills
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items
- G06V20/42—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items of sport video content
-
- A—HUMAN NECESSITIES
- A63—SPORTS; GAMES; AMUSEMENTS
- A63B—APPARATUS FOR PHYSICAL TRAINING, GYMNASTICS, SWIMMING, CLIMBING, OR FENCING; BALL GAMES; TRAINING EQUIPMENT
- A63B71/00—Games or sports accessories not covered in groups A63B1/00 - A63B69/00
- A63B71/06—Indicating or scoring devices for games or players, or for other sports activities
- A63B71/0619—Displays, user interfaces and indicating devices, specially adapted for sport equipment, e.g. display mounted on treadmills
- A63B2071/0647—Visualisation of executed movements
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Physical Education & Sports Medicine (AREA)
- General Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Software Systems (AREA)
- Computational Linguistics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Human Computer Interaction (AREA)
- Testing, Inspecting, Measuring Of Stereoscopic Televisions And Televisions (AREA)
- Processing Or Creating Images (AREA)
Abstract
The invention relates to a method and a system for capturing personal goal video, wherein the method comprises the following steps: when goal is identified, the 3D positions of the basketballs at all moments are obtained, and goal tracks are obtained according to the 3D positions of the basketballs at all moments, the positions of the basketballs, the goal moments and the motion state constraints; and determining the hand-out time and the hand-out position of the goal based on the obtained goal track, determining the goal players based on the positions of the players at all times according to the hand-out time and the hand-out position, and outputting a goal video. Compared with the prior art, the goal track is obtained through the 3D position of the basketball at each moment, the position of the basket, the goal moment and the motion state constraint, then the goal players are obtained based on the goal track, and the goal players can be achieved through simple and mature equipment such as a common monitoring camera and a common computer, so that the goal track is low in implementation cost and high in reliability, and is suitable for installation of a common court.
Description
Technical Field
The invention relates to a computer technology, in particular to a personal goal video capturing method and system.
Background
With the development of the sports industry, computer science is increasingly applied to the field of basketball, such as real-time tracking of players, automatic statistics and analysis of game data, prediction of game results, and the like. In these applications, identifying the identity of a player, tracking the movement of the player on a court, and identifying the actions of the player are some of the most important techniques. In recent years, with the development of hardware and software, the technologies become more mature, rapid and accurate.
The current technology for capturing the goal video of a basketball player and identifying the identity of the basketball shooting player in the basketball game is mainly of the following types:
1. in the basketball professional competition, a plurality of synchronous industrial-grade cameras are used for shooting competition pictures, the pictures are transmitted to a processor in real time, the identities of players are identified through the coat numbers of the players, shooting pictures in the competition are collected through a computer image processing technology, and the basketball professional competition is widely applied to European and American professional competitions. The disadvantages are that the whole set of equipment is expensive, usually reaches hundreds of thousands of dollars, the requirement on hardware equipment is high, and more importantly, the set of equipment can only be used in a regular game with players wearing ball covers and cannot be applied to common mass basketball games.
2. The chip sensor on the wearable device, such as a wrist, a watch and basketball equipment, identifies the shooting action of a player or acquires the motion track of a ball according to the chip in the ball to identify a goal, and the defect of the chip sensor is that an additional hardware device is required.
3. The intelligent mobile phone is erected at the field side to shoot the match picture in real time, and then a mobile phone processor is used for performing computer image recognition operation, so that the match picture is presented in a mobile phone application form. The disadvantage is that such applications typically only recognize the shooting motion of a single person training and do not have the ability to distinguish the identity of players in a multi-player game and without a uniform jersey.
4. And manually recording by field data collectors and referees. The method has the disadvantages of large labor cost, complex subsequent statistical process and capability of being used only in more regular events. And it is difficult to obtain higher-order data such as hand position, running distance, running range, etc.
Disclosure of Invention
The present invention aims to overcome the defects of the prior art and provide a method and a system for capturing a personal goal video, which can be realized in a common scene.
The purpose of the invention can be realized by the following technical scheme:
a method for personal goal video capture, comprising:
when goal is identified, the 3D positions of the basketballs at all moments are obtained, and goal tracks are obtained according to the 3D positions of the basketballs at all moments, the positions of the basketballs, the goal moments and the motion state constraints;
and determining the hand-out time and the hand-out position of the goal based on the obtained goal track, determining the goal players based on the positions of the players at all times according to the hand-out time and the hand-out position, and outputting a goal video.
The kinematic state constraints include:
the movement speed of the basketball is less than the set maximum speed;
the maximum height of the basketball goal track is greater than the set minimum height;
the acceleration of the basketball in the vertical direction is set gravity acceleration;
the distance between the 3D position of the basketball at the goal moment and the basket is smaller than the set maximum distance.
The method further comprises the following steps: and sending the obtained goal video to the user corresponding to the goal player.
The goal time and the goal position of this goal are determined based on the obtained goal track, and the goal players are determined according to the goal time and the goal position based on the positions of the players at all times, and the method specifically comprises the following steps:
a1: acquiring a player with a hand-out time at a hand-out position;
a2: selecting a player, and identifying a video stream of the player covered in the initial set time period before the hand-out time to obtain a corresponding posture track through a neural network algorithm including human body key point detection;
a3: inputting the obtained posture track into a long-short term memory network containing convolution operation, if the output result is a shot or a shot, identifying that the current player is a goal player, otherwise, selecting another player and returning to the step A2.
The system for capturing the personal goal video of the user in real time for realizing the method comprises an upper host computer and a processor, wherein the upper host computer is connected with the camera device, the upper host computer comprises a memory, the processor and a program which is stored in the memory and executed by the processor, and the processor realizes the following steps when executing the program:
when goal is identified, the 3D positions of the basketballs at all moments are obtained, and goal tracks are obtained according to the 3D positions of the basketballs at all moments, the positions of the basketballs, the goal moments and the motion state constraints;
and determining the hand-out time and the hand-out position of the goal based on the obtained goal track, determining the goal players based on the positions of the players at all times according to the hand-out time and the hand-out position, and outputting a goal video.
The camera device comprises two camera groups under the basket and two camera groups in the field,
the two under-basket camera sets are respectively positioned below the two baskets, and two cameras in the same under-basket camera set are symmetrically arranged relative to the connecting line of the two baskets,
the two camera groups in the field are respectively positioned at two ends of the midline of the court, and the two cameras in the camera group in the same field are symmetrically arranged relative to the midline of the court.
After identifying the goal, acquiring the 3D positions of the basketball at all moments, specifically: after the goal is identified through the pictures collected by the two camera groups in the field, the 3D position of the basketball is identified according to the pictures collected by the camera groups in the field.
In the step a1, the method specifically includes: the positions of the goal players in the pictures collected by the camera under the basket are obtained based on the pictures collected by the camera set under the basket corresponding to the goal frames, and the players with the hands at the positions of the hands are obtained.
Compared with the prior art, the invention has the following beneficial effects:
1) the goal track is obtained through the 3D position of the basketball at each moment, the basket position, the goal moment and the motion state constraint, then the goal players are obtained based on the goal track, and the goal players can be achieved through simple and mature equipment such as a common monitoring camera and a common computer, so that the goal track is low in cost and high in reliability, and is suitable for installation of a common court.
2) Because the identification and tracking of the players are realized through the key points of the human body, the players do not need to wear uniform uniforms printed with numbers.
3) Because the whole set of system is based on image recognition and machine learning algorithm, no extra wearing equipment and expensive external sensors are needed, and extra data which cannot be obtained by sensors such as human body postures and the like can be obtained.
4) Due to the algorithm and the multi-camera structure in the system, people who enter the ball and shoot the basket can be accurately identified even if multiple people play multiple balls at the same time, and real-time effect can be achieved.
Drawings
FIG. 1 is a schematic view of a field device layout of the present invention;
FIG. 2 is a flow chart of the system in an embodiment of the invention.
Detailed Description
The invention is described in detail below with reference to the figures and specific embodiments. The present embodiment is implemented on the premise of the technical solution of the present invention, and a detailed implementation manner and a specific operation process are given, but the scope of the present invention is not limited to the following embodiments.
The key that this application realized lies in providing a computer program, corresponding hardware system in addition, as shown in fig. 1, a complete system includes camera device interconnect's host computer on higher level, camera device includes camera group and two camera groups in the field under two baskets, every camera group contains two cameras, adopt the POE camera in this embodiment, can directly use the ethernet power supply like this, more convenient equipment, do not receive the socket position restriction in field, except that eight ordinary POE surveillance camera machine and the host computer that is furnished with GPU, there is the switch in addition, a host computer that is furnished with GPU. The two camera groups under the basketball are respectively positioned below the two basketries, the two cameras in the same camera group under the basketball are symmetrically arranged relative to the connecting line of the two basketries, the two camera groups in the court are respectively positioned at two ends of the center line of the court, and the two cameras in the camera group in the same court are symmetrically arranged relative to the center line of the court. In fig. 1, one c0 and c1 under the same basket form a basket camera group, two c2 form a field camera group, and two c3 form another field camera group, the field camera group can shoot a complete half field picture from a far angle, and after the camera is erected, the internal matrix and the external matrix of the camera need to be calibrated. Based on the size of a normal court, the focal length of the camera under the basket is 4mm, and the focal length of the camera in the field is 6 mm. All cameras are connected to the switch, power is supplied to the cameras through the switch, and picture data are transmitted to the upper host in real time, an algorithm in the upper host can identify shooting, track players, identify the identities of the players, generate segmented videos, upload the segmented videos to the cloud server, and then push the segmented videos to corresponding user mobile phone applications.
In this embodiment, the standard basketball court size (28 m long and 15m wide), c0 and c1 use 4k with 4mm focal length, POE surveillance camera, and the pixels are adjusted to 3840 × 2160, c2 and c3, so that 1080p with 6mm focal length, POE surveillance camera, and the pixels are 1920 × 1080, are used. All cameras were tuned to a rate of 25 frames/second, time synchronized using an ntp server, and the network cable powered and transmitting data simultaneously.
The specific procedure is as follows:
when goal is identified, the 3D positions of the basketballs at all moments are obtained, and goal tracks are obtained according to the 3D positions of the basketballs at all moments, the positions of the basketballs, the goal moments and the motion state constraints;
and determining the hand-out time and the hand-out position of the goal based on the obtained goal track, determining the goal players based on the positions of the players at all times according to the hand-out time and the hand-out position, and outputting a goal video.
After identifying the goal, acquiring the 3D positions of the basketball at all moments, specifically: after the goal is identified through the pictures collected by the two camera groups in the field, the 3D position of the basketball is identified through triangular positioning according to the pictures collected by the camera groups in the field and the calibrated camera matrix.
Wherein the motion state constraint comprises the following four terms: the movement speed of the basketball is less than the set maximum speed; the maximum height of the basketball goal track is greater than the set minimum height; the acceleration of the basketball in the vertical direction is set gravity acceleration; the distance between the 3D position of the basketball at the goal moment and the basket is smaller than the set maximum distance.
In this embodiment, the following concrete steps are performed: speed of ball movement<8.0m/s, maximum height of ball motion trajectory>3.0m, acceleration in the vertical direction of the ball equal to about 9.8m/s2The distance between the ball position and the basket at the time of ball-in<0.2m。
The above-mentioned play moment and play position based on the goal orbit that obtains confirming this goal to each sportsman's position according to the time of playing and play position confirms the sportsman of goal based on each sportsman's position at every moment, specifically include:
a1: obtain the sportsman of hand-out position department at the hand-out time, specifically be: obtaining the position of a goal player in the picture collected by the under-basket camera based on the picture collected by the under-basket camera set corresponding to the goal frame, and obtaining the player with the hand at the hand-out position at the hand-out time;
a2: selecting a player, identifying a video stream of the player covered in the initial set time period before the hand-out time to obtain a corresponding posture track through a neural network algorithm including human body key point detection,
specifically, utilize Tensorflow, version 1.2.0 to build neural network discernment sportsman's 25 body key points in this embodiment, the key point includes: 1. the video stream of the hoodie player is recognized to obtain a corresponding posture track in an initial set time period before the hand-out time;
a3: inputting the obtained posture track into a long-short term memory network containing convolution operation, if the output result is a shot or a shot, identifying that the current player is a goal player, otherwise, selecting another player and returning to the step A2.
Specifically, in this embodiment, a long-term and short-term memory network including 32 layers of convolution operations is built by using Tensorflow and version 1.2.0.
As shown in fig. 2, the method of the present application further includes:
(1) and sending the obtained goal video to a user corresponding to the goal player, specifically through modes such as APP and small program.
(2) User identification, including:
when a user registers for the first time, a head portrait needs to be uploaded for face comparison;
the player needs to sweep the code to go on and off, so that the player can be used for identifying the identity of the player.
Claims (7)
1. A method for personal goal video capture, comprising:
when the goal is identified, the 3D positions of the basketball at all moments are obtained, the goal track is obtained according to the 3D positions of the basketball at all moments and the constraints of the position of the basketball, the goal moment and the motion state,
determining the hand-out time and the hand-out position of the goal based on the obtained goal track, determining goal players based on the positions of the players at all times according to the hand-out time and the hand-out position, and outputting a goal video;
the goal time and the goal position of this goal are determined based on the obtained goal track, and the goal players are determined according to the goal time and the goal position based on the positions of the players at all times, and the method specifically comprises the following steps:
a1: the player whose hand is at the hand-out position at the moment of hand-out is acquired,
a2: selecting a player, identifying a video stream of the player in an initial set time period before the hand-out time to obtain a corresponding posture track through a neural network algorithm comprising human body key point detection,
a3: inputting the obtained posture track into a long-short term memory network containing convolution operation, if the output result is a shot or a shot, identifying that the current player is a goal player, otherwise, selecting another player and returning to the step A2.
2. The method of claim 1, wherein the motion state constraint comprises:
the movement speed of the basketball is less than the set maximum speed;
the maximum height of the basketball goal track is greater than the set minimum height;
the acceleration of the basketball in the vertical direction is set gravity acceleration;
the distance between the 3D position of the basketball at the goal moment and the basket is smaller than the set maximum distance.
3. The method of claim 1, wherein the method further comprises: the resulting goal video is sent to the user corresponding to the goal player.
4. A system for capturing a user's personal goal video in real time, comprising a host computer connected with each other by a camera device, wherein the host computer comprises a memory, a processor, and a program stored in the memory and executed by the processor, and the processor executes the program to realize the following steps:
when the goal is identified, the 3D positions of the basketball at all moments are obtained, the goal track is obtained according to the 3D positions of the basketball at all moments and the constraints of the position of the basketball, the goal moment and the motion state,
determining the hand-out time and the hand-out position of the goal based on the obtained goal track, determining goal players based on the positions of the players at all times according to the hand-out time and the hand-out position, and outputting a goal video;
the camera device comprises two camera groups under the basket and two camera groups in the field,
the two under-basket camera sets are respectively positioned below the two baskets, and two cameras in the same under-basket camera set are symmetrically arranged relative to the connecting line of the two baskets,
the two camera groups in the field are respectively positioned at two ends of the center line of the court, and the two cameras in the camera group in the same field are symmetrically arranged relative to the center line of the court;
the goal time and the goal position of this goal are determined based on the obtained goal track, and the goal players are determined according to the goal time and the goal position based on the positions of the players at all times, and the method specifically comprises the following steps:
a1: the player whose hand is at the hand-out position at the moment of hand-out is acquired,
a2: selecting a player, identifying a video stream of the player in an initial set time period before the hand-out time to obtain a corresponding posture track through a neural network algorithm comprising human body key point detection,
a3: inputting the obtained posture track into a long-short term memory network containing convolution operation, if the output result is a shot or a shot, identifying that the current player is a goal player, otherwise, selecting another player and returning to the step A2.
5. The system of claim 4, wherein the 3D position of the basketball at all times is obtained when the goal is identified, specifically: after the goal is identified through the pictures collected by the two camera groups in the field, the 3D position of the basketball is identified according to the pictures collected by the camera groups in the field.
6. The system of claim 4, wherein the kinematic state constraints comprise:
the movement speed of the basketball is less than the set maximum speed;
the maximum height of the basketball goal track is greater than the set minimum height;
the acceleration of the basketball in the vertical direction is set gravity acceleration;
the distance between the 3D position of the basketball at the goal moment and the basket is smaller than the set maximum distance.
7. The system according to claim 4, wherein in the step A1, specifically: the positions of the goal players in the pictures collected by the camera under the basket are obtained based on the pictures collected by the camera set under the basket corresponding to the goal frames, and the players with the hands at the positions of the hands are obtained.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910213895.XA CN109961039B (en) | 2019-03-20 | 2019-03-20 | Personal goal video capturing method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910213895.XA CN109961039B (en) | 2019-03-20 | 2019-03-20 | Personal goal video capturing method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109961039A CN109961039A (en) | 2019-07-02 |
| CN109961039B true CN109961039B (en) | 2020-10-27 |
Family
ID=67024633
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910213895.XA Active CN109961039B (en) | 2019-03-20 | 2019-03-20 | Personal goal video capturing method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109961039B (en) |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110472561B (en) * | 2019-08-13 | 2021-08-20 | 新华智云科技有限公司 | Football goal type identification method, device, system and storage medium |
| CN110543856B (en) * | 2019-09-05 | 2022-04-22 | 新华智云科技有限公司 | Football shooting time identification method and device, storage medium and computer equipment |
| CN110796085B (en) * | 2019-10-29 | 2022-04-22 | 新华智云科技有限公司 | Method for automatically distinguishing basketball goal segment AB team based on deep learning object detection algorithm |
| CN111539294B (en) * | 2020-04-17 | 2022-11-15 | 广东世宇科技股份有限公司 | Shooting detection method and device, electronic equipment and computer readable storage medium |
| CN113537168B (en) * | 2021-09-16 | 2022-01-18 | 中科人工智能创新技术研究院(青岛)有限公司 | Basketball goal detection method and system for rebroadcasting and court monitoring scene |
| CN113989725B (en) * | 2021-11-09 | 2024-11-08 | 新华智云科技有限公司 | Ball feeding segment classification method based on neural network |
Family Cites Families (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101794384B (en) * | 2010-03-12 | 2012-04-18 | 浙江大学 | Shooting action identification method based on human body skeleton map extraction and grouping motion diagram inquiry |
| CN101826155B (en) * | 2010-04-02 | 2012-07-25 | 浙江大学 | Method for identifying act of shooting based on Haar characteristic and dynamic time sequence matching |
| US20120004951A1 (en) * | 2010-06-30 | 2012-01-05 | International Business Machines Corporation | Tracking metrics, goals and personal accomplishments using electronic messages |
| CN103310191B (en) * | 2013-05-30 | 2016-12-28 | 上海交通大学 | The human motion recognition method of movable information image conversion |
| JP6813762B2 (en) * | 2015-11-10 | 2021-01-13 | ディーディースポーツ，インコーポレイテッド | Position and event tracking system for sports matches |
| CN106991357A (en) * | 2016-01-20 | 2017-07-28 | 上海慧体网络科技有限公司 | The shooting of automatic identification Basketball Match and the algorithm scored based on panoramic video |
| CN107303428A (en) * | 2016-04-20 | 2017-10-31 | 李斌 | Basketball goal decision method and system based on image procossing |
| CN107305138A (en) * | 2016-04-20 | 2017-10-31 | 李斌 | Basketball action identification method and system based on wrist attitude detection |
| CN106131469B (en) * | 2016-06-24 | 2019-06-28 | 北京狂跑者科技有限公司 | Ball intelligent robot coach and judgment system based on machine vision |
| CN109145733A (en) * | 2018-07-17 | 2019-01-04 | 焦点科技股份有限公司 | A kind of artificial intelligence explanation method and system of Basketball Match |
-
2019
- 2019-03-20 CN CN201910213895.XA patent/CN109961039B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN109961039A (en) | 2019-07-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109961039B (en) | Personal goal video capturing method and system | |
| CN107871120B (en) | Sports event understanding system and method based on machine learning | |
| US20180137363A1 (en) | System for the automated analisys of a sporting match | |
| US20080192116A1 (en) | Real-Time Objects Tracking and Motion Capture in Sports Events | |
| WO2017011817A1 (en) | Integrated sensor and video motion analysis method | |
| US20070064975A1 (en) | Moving object measuring apparatus, moving object measuring system, and moving object measurement | |
| US9087380B2 (en) | Method and system for creating event data and making same available to be served | |
| WO2007035878A2 (en) | Method and apparatus for determining ball trajectory | |
| CN111866575B (en) | Real-time motion video intelligent capturing and feedback method and system | |
| Zhang et al. | MV-Sports: a motion and vision sensor integration-based sports analysis system | |
| CN111860418A (en) | Intelligent video examination and consultation system, method, medium and terminal for athletic competition | |
| Pers et al. | A low-cost real-time tracker of live sport events | |
| CN108970091B (en) | Badminton action analysis method and system | |
| CN110213611A (en) | A kind of ball competition field camera shooting implementation method based on artificial intelligence Visual identification technology | |
| CN209865244U (en) | Goal video capture device | |
| CN112057833A (en) | Badminton forehand high-distance ball flapping motion identification method | |
| WO2023130696A1 (en) | Smart system for automatically tracking-photographing sports events, and control method therefor | |
| CN115845349A (en) | General training method for ball game items for moving target detection based on deep learning technology and auxiliary referee system | |
| CN117593784A (en) | Badminton player batting action posture evaluation system based on 3D digital person | |
| KR101094137B1 (en) | Motion capture system | |
| KR102256260B1 (en) | Smart camera sensor for screen golf | |
| CN115475373A (en) | Motion data display method and device, storage medium and electronic device | |
| CN114241602A (en) | Multi-purpose rotational inertia measuring and calculating method based on deep learning | |
| CN207545784U (en) | A kind of smart motion trap setting and system | |
| KR101971060B1 (en) | Module type high speed photographing apparatus, apparatus and method for sensing of ball motion based on high speed photographing |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |