CN109961039A - A kind of individual's goal video method for catching and system - Google Patents
A kind of individual's goal video method for catching and system Download PDFInfo
- Publication number
- CN109961039A CN109961039A CN201910213895.XA CN201910213895A CN109961039A CN 109961039 A CN109961039 A CN 109961039A CN 201910213895 A CN201910213895 A CN 201910213895A CN 109961039 A CN109961039 A CN 109961039A
- Authority
- CN
- China
- Prior art keywords
- goal
- sportsman
- moment
- basketball
- video
- 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.)
- Granted
Links
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
Abstract
The present invention relates to a kind of personal goal video method for catching and systems, wherein method includes: after identifying goal, the position 3D of all moment basketballs is obtained, and constrains to obtain goal track according to the position 3D of each moment basketball and basketry position, moment of scoring, motion state；It obtains determining that this scores based on obtained goal track and sells moment and out hand position, and based on the position of each sportsman of each moment according to the time and out hand position determines goal sportsman of selling, and export goal video.Compared with prior art, the present invention passes through the position 3D of each moment basketball, and basketry position, moment, the motion state of scoring constrain to obtain goal track, it is then based on goal track and obtains goal sportsman, it can be realized using the simple mature equipment such as common monitor camera and common computer, therefore cost of implementation is low, high reliablity, the installation suitable for common court.
Description
Technical field
The present invention relates to a kind of computer technologies, more particularly, to a kind of personal goal video method for catching and system.
Background technique
With the development of sports industry, computer science is used in basketball field, such as real-time tracking ball more and more
Member, programming count and analysis competition data, prediction result of the match etc..In such applications, it identifies sportsman's identity, tracks court
The movement of upper sportsman identifies that the movement of sportsman is most important some technologies.In recent years with the development of hardware-software, these skills
Art become it is more mature quick and precisely.
Sportsman's goal video can be captured in current Basketball Match and identifies that the technology of shooting sportsman's identity mainly has
Following several types:
1. shooting match picture, real-time Transmission by the other video camera of more synchronous technical grades in basketball occupation match
Picture identifies sportsman's identity to processor, by the uniform number of sportsman, then is collected in match with computer image processing technology
Shooting picture, be used widely in American-European occupation match.The disadvantage is that complete equipment is expensive, tens are generally reached
Ten thousand dollars, hardware device requires relatively high, it is often more important that it can be used only in sportsman and all wears in the formal competition of football shirt, cannot
It applies in ordinary populace basketball movement.
2. by wearable device, such as wrist, wrist-watch, the act of shooting of the chip sensor identification sportsman in basketball system
Or identified and scored according to the motion profile that the chip inside ball obtains ball, the disadvantage is that needing additional hardware device.
3. then doing computer picture with cell phone processor by setting up smart phone captured in real-time match picture outside the court
The operation of identification is presented in the form of mobile phone application.The disadvantage is that this kind of application is typically only capable to identify that the shooting of single training is dynamic
Make, does not have the function that more people take part in the match and distinguish sportsman's identity in the case where not wearing unified football shirt.
4. passing through on-site data gathering person, judge's manual record.The disadvantage is that a large amount of human costs are needed, subsequent statistical stream
Journey is cumbersome, can only use in more regular race.And it is difficult to obtain out hand position, runs distance, range of running etc. more
The data of high-order.
Summary of the invention
It is an object of the present invention to overcome the above-mentioned drawbacks of the prior art and provide one kind can be in common field
The personal goal video method for catching and system realized under scape.
The purpose of the present invention can be achieved through the following technical solutions:
A kind of individual's goal video method for catching characterized by comprising
After identifying goal, the position 3D of all moment basketballs is obtained, and according to the position 3D of each moment basketball, and
Basketry position, moment of scoring, motion state constrain to obtain goal track；
Obtain determining that this scores based on obtained goal track and sell moment and out hand position, and it is each to be based on each moment
The position of sportsman exports goal video according to the time and out hand position determines goal sportsman of selling.
The motion state constrains
The movement velocity of basketball is less than setting maximum speed；
The maximum height of the goal track of basketball is greater than setting minimum altitude；
The vertical direction acceleration of basketball is the acceleration of gravity of setting；
The position 3D of goal moment basketball and basketry distance are less than setting maximum distance.
The method also includes: obtained goal video is sent to the corresponding user with goal sportsman.
It is described based on obtained goal track to obtain determining that this scores and sell moment and out hand position, and when being based on each
The position of each sportsman is carved according to the time and out hand position determines goal sportsman of selling, is specifically included:
A1: sportsman of the moment at position of selling that sell is obtained；
A2: one sportsman of selection identifies that lid sportsman is going out by the inclusion of the neural network algorithm of human body critical point detection
Video flowing obtains corresponding posture track in the initial setting period before the hand moment；
A3: inputting the shot and long term memory network containing convolution algorithm for obtained posture track, if output result is to lay up
Or shooting, then identify that current sportsman is goal sportsman, it is on the contrary then select return step A2 after another sportsman.
Realize being connected with each other with the system of real-time capture individual subscriber goal video, including photographic device for the above method
Upper host, the upper host includes memory, processor, and storage is executed in memory and by the processor
Program, the processor performs the steps of when executing described program
After identifying goal, the position 3D of all moment basketballs is obtained, and according to the position 3D of each moment basketball, and
Basketry position, moment of scoring, motion state constrain to obtain goal track；
Obtain determining that this scores based on obtained goal track and sell moment and out hand position, and it is each to be based on each moment
The position of sportsman exports goal video according to the time and out hand position determines goal sportsman of selling.
The photographic device includes imaging in unit and two fields to image unit under two baskets,
Video camera group is located at below two basketrys under two baskets, and two video cameras in unit are imaged under same basket
Line relative to two basketrys is symmetrical arranged,
Video camera group is located at the both ends of court middle line in two fields, and two camera shootings in unit are imaged in same field
Machine is symmetrical arranged relative to court middle line.
It is described to obtain the position 3D of all moment basketballs after identifying goal, specifically: pass through video camera in two fields
After the picture of group acquisition identifies goal, the position 3D of basketball is identified according to the picture for imaging unit acquisition in field.
In the step A1, specifically: based on the picture for imaging unit acquisition under the corresponding basket of ball frame according to goal, obtain
To the position in the goal sportsman picture that video camera acquires under basket, and obtain sportsman of the moment at position of selling that sell.
Compared with prior art, the invention has the following advantages:
1) it constrains to obtain goal rail by the position 3D of each moment basketball and basketry position, moment of scoring, motion state
Mark is then based on goal track and obtains goal sportsman, can be simple mature using common monitor camera and common computer etc.
Equipment realize that therefore cost of implementation is low, high reliablity, the installation suitable for common court.
2) due to realizing sportsman's identification and tracking by human body key point, the unified number of being printed on of players' dress is not needed
The team uniform of code.
3) since whole system is based on image recognition and machine learning algorithm, any additional wearable device is not needed
With expensive external sensor, and the extra data that the sensors such as human body attitude can not obtain can be obtained.
4) it due to the algorithm and multi-cam structure in system, beats and can also accurately identify simultaneously even if the more balls of more people
The people for scoring and shooting, and can accomplish in real time.
Detailed description of the invention
Fig. 1 is place equipment arrangement schematic diagram of the invention；
Fig. 2 is the flow chart of system in the embodiment of the present invention.
Specific embodiment
The present invention is described in detail with specific embodiment below in conjunction with the accompanying drawings.The present embodiment is with technical solution of the present invention
Premised on implemented, the detailed implementation method and specific operation process are given, but protection scope of the present invention is not limited to
Following embodiments.
The application realize key be to provide a kind of computer program, in addition there are corresponding hardware systems, such as Fig. 1 institute
Show, a holonomic system includes photographic device upper host interconnected, photographic device include under two baskets camera shooting unit and
Image unit in two fields, each camera shooting unit contains two video cameras, uses POE video camera in the present embodiment, in this way can be with
Power over Ethernet is directly used, assembling is more convenient, is not limited by the socket position in place, in addition to eight common POE monitor cameras
Outside the upper host equipped with GPU, there are also interchanger, one is furnished with the host of GPU.Video camera group is located at two under two baskets
Two video cameras imaged in unit below a basketry, and under same basket are symmetrical arranged relative to the line of two basketrys, and two
Video camera group is located at the both ends of court middle line in, and two video cameras in unit are imaged in same field relative to court
Middle line is symmetrical arranged.In Fig. 1, a c0 and c1 under same basketry are constituted and are imaged unit under a basket, and two c2 constitute one
Unit is imaged in, two c3, which are constituted, images unit in another, imaging unit in field can be complete from farther away angle shot
Whole half-court picture after video camera is set up, needs to demarcate the internal matrix of video camera and external matrix.Based on normal
The size in court, the focal length of camera under basket are 4mm, and the focal length of camera in field is 6mm.All video cameras are connected to interchanger,
Upper host is given by interchanger for video camera power supply and picture data real-time Transmission, the algorithm in upper host can identify
Shooting tracks sportsman, identifies the identity of goal people, generates segmenting video, and uploads in Cloud Server, then pushes to pair
The user mobile phone answered is using upper.
In the present embodiment, the size (long 28m, wide 15m) on standard basketball court ground, c0, c1 use the 4k of 4mm focal length, POE prison
Control video camera, pixel is tuned into 3840*2160, c2, c3 need to cover entire half-court thus using 6mm focal length 1080p, POE prison
Control video camera, pixel 1920*1080.All cameras are all tuned into 25 frames/second rate, and it is same to carry out the time using ntp server
Step, cable is powered simultaneously and transmission data.
Specific program is as follows:
After identifying goal, the position 3D of all moment basketballs is obtained, and according to the position 3D of each moment basketball, and
Basketry position, moment of scoring, motion state constrain to obtain goal track；
Obtain determining that this scores based on obtained goal track and sell moment and out hand position, and it is each to be based on each moment
The position of sportsman exports goal video according to the time and out hand position determines goal sportsman of selling.
After identifying goal, the position 3D of all moment basketballs is obtained, specifically: it is adopted by imaging unit in two fields
It is fixed by triangle according to the camera matrix of calibration according to the picture for imaging unit acquisition in field after the picture of collection identifies goal
Identify the position 3D of basketball in position.
Wherein, motion state constraint includes four: the movement velocity of basketball is less than setting maximum speed；Basketball into
The maximum height of sphere path curve is greater than setting minimum altitude；The vertical direction acceleration of basketball is the acceleration of gravity of setting；It scores
The position 3D of moment basketball and basketry distance are less than setting maximum distance.
In the present embodiment, specifically: ball movement velocity<8.0m/s, ball motion profile maximum height>3.0m, ball Vertical Square
It is approximately equal to 9.8m/s to acceleration2, score moment ball position and basketry distance < 0.2m.
It is above-mentioned based on obtained goal track to obtain determining that this scores and sell moment and out hand position, and based on respectively
The position of moment each sportsman is specifically included according to the time and out hand position determines goal sportsman of selling:
A1: obtaining sportsman of the moment at position of selling that sell, specifically: based under the corresponding basket of ball frame according to goal
The picture for imaging unit acquisition obtains the position in the goal sportsman picture that video camera acquires under basket, and obtains and sell the moment
Sportsman at hand position out；
A2: one sportsman of selection identifies that lid sportsman is going out by the inclusion of the neural network algorithm of human body critical point detection
Video flowing obtains corresponding posture track in the initial setting period before the hand moment,
Specifically, utilizing Tensorflow, version 1.2.0 to build the 25 of neural network recognization sportsman in the present embodiment
A body key point, key point include: 1. noses, and 2. necks, 3. right shoulders, 4. right elbows, 5. right wrists, 6. left shoulders, 7 left elbows, 8. is left
Wrist, 9. butt cracks, 10. right sterns, 11. right knees, 12. right ankles, 13 left sterns, 14. left knees, 15. left ankles, 16. right eyes, 17.
Left eye, 18. auris dextras, 19. left ears, 20. left foot big toes, the small toe of 21. left foots, 22. left heels, 23. right big toes,
24. the small toe of right crus of diaphragm, 25. right crus of diaphragm heels identify that lid sportsman initially sets video flowing in the period before the moment of selling and obtains
Corresponding posture track；
A3: inputting the shot and long term memory network containing convolution algorithm for obtained posture track, if output result is to lay up
Or shooting, then identify that current sportsman is goal sportsman, it is on the contrary then select return step A2 after another sportsman.
Specifically, the present embodiment utilizes Tensorflow, version 1.2.0, builds one and contain 32 layers of convolution algorithm
Shot and long term memory network.
As shown in Fig. 2, the application method further include:
(1) obtained goal video is sent to the corresponding user with goal sportsman, specifically by APP and small routine
Etc. modes.
(2) user identity identification, comprising:
It needs to upload head portrait when user registers for the first time, is used for face alignment；
Sportsman needs barcode scanning to march into the arena, leave the theatre, and can be used for the identification of sportsman's identity in this way.
Claims (10)
1. a kind of individual's goal video method for catching characterized by comprising
After identifying goal, the position 3D of all moment basketballs is obtained, and according to the position 3D of each moment basketball and basketry
Position, moment of scoring, motion state constrain to obtain goal track；
Obtain determining that this scores based on obtained goal track and sell moment and out hand position, and based on each sportsman of each moment
Position according to the time and out hand position determines goal sportsman of selling, and export goal video.
2. a kind of personal goal video method for catching according to claim 1, which is characterized in that the motion state constraint
Include:
The movement velocity of basketball is less than setting maximum speed；
The maximum height of the goal track of basketball is greater than setting minimum altitude；
The vertical direction acceleration of basketball is the acceleration of gravity of setting；
The position 3D of goal moment basketball and basketry distance are less than setting maximum distance.
3. a kind of personal goal video method for catching according to claim 1, which is characterized in that the method also includes:
Obtained goal video is sent to the corresponding user with goal sportsman.
4. a kind of personal goal video method for catching according to claim 1, which is characterized in that it is described based on obtain into
Sphere path curve, which obtains determining that this scores, sells moment and hand position out, and when the position based on each sportsman of each moment is according to selling
Between and hand position determines goal sportsman out, specifically include:
A1: sportsman of the moment at position of selling that sell is obtained；
A2: one sportsman of selection identifies lid sportsman when selling by the inclusion of the neural network algorithm of human body critical point detection
Video flowing obtains corresponding posture track in the initial setting period before carving；
A3: by obtained posture track input the shot and long term memory network containing convolution algorithm, if output result be lay up or
Shooting then identifies that current sportsman is goal sportsman, on the contrary then select return step A2 after another sportsman.
5. a kind of system of real-time capture individual subscriber goal video, including photographic device upper host interconnected, special
Sign is that the upper host includes the journey executed in memory, processor, and storage and memory and by the processor
Sequence, the processor perform the steps of when executing described program
After identifying goal, the position 3D of all moment basketballs is obtained, and according to the position 3D of each moment basketball and basketry
Position, moment of scoring, motion state constrain to obtain goal track；
Obtain determining that this scores based on obtained goal track and sell moment and out hand position, and based on each sportsman of each moment
Position according to the time and out hand position determines goal sportsman of selling, and export goal video.
6. system according to claim 5, which is characterized in that the photographic device includes imaging unit and two under two baskets
Unit is imaged in a field,
Video camera group is located at below two basketrys under two baskets, and two video cameras imaged in unit under same basket are opposite
It is symmetrical arranged in the line of two basketrys,
Video camera group is located at the both ends of court middle line in two fields, and two video camera phases in unit are imaged in same field
Court middle line is symmetrical arranged.
7. system according to claim 6, which is characterized in that it is described after identifying goal, obtain all moment basketballs
The position 3D, specifically: by two fields image unit acquisition picture identify goal after, according in field image unit adopt
The picture of collection identifies the position 3D of basketball.
8. system according to claim 5, which is characterized in that the motion state, which constrains, includes:
The movement velocity of basketball is less than setting maximum speed；
The maximum height of the goal track of basketball is greater than setting minimum altitude；
The vertical direction acceleration of basketball is the acceleration of gravity of setting；
The position 3D of goal moment basketball and basketry distance are less than setting maximum distance.
9. system according to claim 6, which is characterized in that it is described based on obtained goal track obtain determining this into
Sell moment and the hand position out of ball, and based on the position of each sportsman of each moment according to the time and out hand position is determined and scored of selling
Sportsman specifically includes:
A1: sportsman of the moment at position of selling that sell is obtained；
A2: one sportsman of selection identifies lid sportsman when selling by the inclusion of the neural network algorithm of human body critical point detection
Video flowing obtains corresponding posture track in the initial setting period before carving；
A3: by obtained posture track input the shot and long term memory network containing convolution algorithm, if output result be lay up or
Shooting then identifies that current sportsman is goal sportsman, on the contrary then select return step A2 after another sportsman.
10. system according to claim 9, which is characterized in that in the step A1, specifically: based on according to goal
The picture that unit acquisition is imaged under the corresponding basket of ball frame obtains the position in the goal sportsman picture that video camera acquires under basket,
And obtain sportsman of the moment at position of selling that sell.
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 true CN109961039A (en) | 2019-07-02 |
| CN109961039B 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) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110472561A (en) * | 2019-08-13 | 2019-11-19 | 新华智云科技有限公司 | Soccer goal kind identification method, device, system and storage medium |
| CN110543856A (en) * | 2019-09-05 | 2019-12-06 | 新华智云科技有限公司 | Football shooting time identification method and device, storage medium and computer equipment |
| CN110796085A (en) * | 2019-10-29 | 2020-02-14 | 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 |
| CN111539294A (en) * | 2020-04-17 | 2020-08-14 | 广东世宇科技股份有限公司 | Shooting detection method and device, electronic equipment and computer readable storage medium |
| CN113537168A (en) * | 2021-09-16 | 2021-10-22 | 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 |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101794384A (en) * | 2010-03-12 | 2010-08-04 | 浙江大学 | Shooting action identification method based on human body skeleton map extraction and grouping motion diagram inquiry |
| CN101826155A (en) * | 2010-04-02 | 2010-09-08 | 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 |
| CN103310191A (en) * | 2013-05-30 | 2013-09-18 | 上海交通大学 | Human body action identification method for motion information imaging |
| CN106131469A (en) * | 2016-06-24 | 2016-11-16 | 北京天天乐动科技有限公司 | Ball intelligent robot based on machine vision coach and judgment system |
| 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 |
| CN108697933A (en) * | 2015-11-10 | 2018-10-23 | 投篮追踪公司 | Positioning for sports tournament and event tracking system |
| 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
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101794384A (en) * | 2010-03-12 | 2010-08-04 | 浙江大学 | Shooting action identification method based on human body skeleton map extraction and grouping motion diagram inquiry |
| CN101826155A (en) * | 2010-04-02 | 2010-09-08 | 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 |
| CN103310191A (en) * | 2013-05-30 | 2013-09-18 | 上海交通大学 | Human body action identification method for motion information imaging |
| CN108697933A (en) * | 2015-11-10 | 2018-10-23 | 投篮追踪公司 | Positioning for sports tournament and event tracking system |
| 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 |
| CN106131469A (en) * | 2016-06-24 | 2016-11-16 | 北京天天乐动科技有限公司 | Ball intelligent robot based on machine vision coach and judgment system |
| 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 |
Non-Patent Citations (2)
| Title |
|---|
| HUA-YSUNG CHEN ET AL.: "Physics-based ball tracking and 3D trajectory reconstruction with applications to shooting location estimation in basketball video", 《J.VIS.COMMUN.IMAGE R.》 * |
| 丁万: "基于非场景目标特征的篮球视频事件检测及其体育教学应用的研究", 《中国博士学位论文全文数据库 社会科学Ⅱ辑》 * |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110472561A (en) * | 2019-08-13 | 2019-11-19 | 新华智云科技有限公司 | Soccer goal kind identification method, device, system and storage medium |
| 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 |
| CN110543856A (en) * | 2019-09-05 | 2019-12-06 | 新华智云科技有限公司 | Football shooting time identification method and device, storage medium and computer equipment |
| 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 |
| CN110796085A (en) * | 2019-10-29 | 2020-02-14 | 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 |
| 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 |
| CN111539294A (en) * | 2020-04-17 | 2020-08-14 | 广东世宇科技股份有限公司 | Shooting detection method and device, electronic equipment and computer readable storage medium |
| 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 |
| CN113537168A (en) * | 2021-09-16 | 2021-10-22 | 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 |
| 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 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109961039B (en) | 2020-10-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2021129064A9 (en) | Posture acquisition method and device, and key point coordinate positioning model training method and device | |
| CN109961039A (en) | A kind of individual's goal video method for catching and system | |
| WO2021051579A1 (en) | Body pose recognition method, system, and apparatus, and storage medium | |
| CN107871120B (en) | Sports event understanding system and method based on machine learning | |
| CN110738154A (en) | pedestrian falling detection method based on human body posture estimation | |
| CN110544301A (en) | Three-dimensional human body action reconstruction system, method and action training system | |
| WO2021134178A1 (en) | Video stream processing method, apparatus and device, and medium | |
| CN110084192A (en) | Quick dynamic hand gesture recognition system and method based on target detection | |
| CN110478862A (en) | A kind of exercise guide system and its guidance method | |
| CN101826155B (en) | Method for identifying act of shooting based on Haar characteristic and dynamic time sequence matching | |
| CN111353355A (en) | Motion tracking system and method | |
| Yan et al. | Human-object interaction recognition using multitask neural network | |
| Jiang et al. | Golfpose: Golf swing analyses with a monocular camera based human pose estimation | |
| WO2022032652A1 (en) | Method and system of image processing for action classification | |
| CN210933642U (en) | Body-building guidance system | |
| CN115475373B (en) | Display method and device of motion data, storage medium and electronic device | |
| CN116523962A (en) | Visual tracking method, device, system, equipment and medium for target object | |
| CN110096989A (en) | Image processing method and device | |
| CN116012417A (en) | Track determination method and device of target object and electronic equipment | |
| CN115761901A (en) | Horse riding posture detection and evaluation method | |
| CN111680608B (en) | Intelligent sports auxiliary training system and training method based on video analysis | |
| Almasi | Human movement analysis from the egocentric camera view | |
| Sharshar et al. | MM-DOS: a novel dataset of workout activities | |
| Wang et al. | THE DEVELOPMENT AND CHANGES OF TRIPLE JUMPERS’BALANCE BOARD COMBINED WITH SPECIAL TRAINING BY DEEP LEARNING APPROACH | |
| Murthy et al. | DiveNet: Dive Action Localization and Physical Pose Parameter Extraction for High Performance Training |
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 |