CN106991357A - The shooting of automatic identification Basketball Match and the algorithm scored based on panoramic video - Google Patents
The shooting of automatic identification Basketball Match and the algorithm scored based on panoramic video Download PDFInfo
- Publication number
- CN106991357A CN106991357A CN201610037324.1A CN201610037324A CN106991357A CN 106991357 A CN106991357 A CN 106991357A CN 201610037324 A CN201610037324 A CN 201610037324A CN 106991357 A CN106991357 A CN 106991357A
- Authority
- CN
- China
- Prior art keywords
- basketball
- shooting
- backboard
- track
- region
- 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.)
- Pending
Links
Classifications
-
- 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
-
- 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
- G06V20/46—Extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames
Abstract
The invention discloses a kind of automatic identification Basketball Match shooting based on panoramic video and the algorithm scored, including by generating the markup information of scene, the detection of candidate's basketball, the generation of basketball track, the automatic judgement of shooting, the step of automatic judgement 5 scored.The shooting of the automatic identification Basketball Match based on panoramic video and the algorithm scored that the present invention is provided, so that can carry out automatic identification to shooting and scoring in match, accurately judge, overcome in the prior art because of shooting basketball movement excessive velocities, there is the reasons such as motion blur, diplopia and ghost phenomena so that the phenomenon of shooting and goal difficult judgment.
Description
Technical field
Aphorama is based on the present invention relates to a kind of algorithm of Basketball Match video identification, more particularly to one kind
The automatic identification Basketball Match shooting of frequency and the algorithm scored.
Background technology
Commonly the video of large-scale basketball race is analyzed at present, by using to race video
The middle method for carrying out pitching close-up shot detection, come judgement of being shot and scored.And for using general
When logical camera carries out ball match unsupervised recording, close-up shot, therefore above method are had no in video
Often fail.In addition, under panning mode, because the problem of hoop erection and camera coverage, making
During shooting the area of basketball it is smaller, and shooting when basketball movement velocity it is too fast, be commonly present
The phenomenon of motion blur, diplopia and ghost, this automatic basketball shooting and scored to judge more difficult.
For these defects of the prior art, the present invention proposes a kind of automatic identification based on panoramic video
The algorithm that Basketball Match is shot and scored.
The content of the invention
The present invention is to provide one kind based on panorama to solve the technical scheme that above-mentioned technical problem is used
The automatic identification Basketball Match shooting of video and the algorithm scored, wherein specifically including following steps：
1) markup information of scene is generated；
The method learnt automatically using artificial mark or algorithm, acquires some priori letter of scene
Breath；
According to backboard size and location, and at ground corresponding to backboard position court player height,
The shooting interest region of generation match each side；
2) detection of candidate's basketball；
(1) shooting interest region is taken out from panoramic video, sets up background model, and therefrom divide
The prospect of cutting out；
(2) size is utilized, shape, colouring information obtains the suspicious of candidate to being filtered at prospect
Basketball region；
(3) result being tracked using early stage to basketball, predicts the position of present frame basketball, if
There is prospect on the position, be then added to the suspicious basketball region of candidate；
(4) inspection of basketball is carried out to the basketball model that suspicious ball region is come out using offline machine learning
Survey, regard the region for detecting basketball as candidate's basketball region；
3) generation of basketball track；
(1) using currently detected candidate's basketball as region to be tracked, the region is tracked, will
Result formation track in tracking, with the replacement that predicts the outcome if not tracking；If but continuous one section
Time does not track, then terminates the tracking of the track；
(2) time sequencing and spatial relationship are utilized, short track is connected as long track, is formed more complete
Whole basketball pursuit path；
4) the automatic judgement of shooting；
Basketball track is analyzed, when its y-coordinate is in the up-and-down boundary of backboard, and x coordinate is in basket
When between the right boundary of plate, if meeting, it is using present frame as terminal and in the presence of continuous a few frame y-coordinates
Increasing or decreasing, then be judged to shooting；
5) the automatic judgement scored；
Basketball track is analyzed, when its y-coordinate is below the lower boundary of backboard, and x coordinate exists
When between the right boundary of backboard, make decisions.
The above-mentioned shooting of the automatic identification Basketball Match based on panoramic video and the algorithm scored, wherein,
In the markup information step for generating scene, prior information includes extracting hoop and backboard from video,
Mark out the height of court player at the corresponding ground in backboard position place.
The above-mentioned shooting of the automatic identification Basketball Match based on panoramic video and the algorithm scored, wherein,
In the markup information step for generating scene, shooting interest region y directions take the common ball at backboard position
Member the top of the head to backboard top at, x directions are extended centered on backboard.
The above-mentioned shooting of the automatic identification Basketball Match based on panoramic video and the algorithm scored, wherein,
The automatic decision steps scored include：(1) judge within former seconds before present frame, if
Shooting is detected, if not detecting, does not score, otherwise, turns next step；(2) judge current
The basketball track of former frame ins before frame, if intersect with hoop entity, if non-intersect, does not enter
Ball, otherwise it is assumed that scoring.
The present invention has the advantages that relative to prior art：
By generating the markup information of scene, the detection of candidate's basketball, the generation of basketball track, shooting
Automatic judgement, the step of automatic judgement 5 scored realize in match shooting and score it is accurate judge,
Overcome in the prior art because of shooting basketball movement excessive velocities, there is motion blur, diplopia and ghost
The reasons such as phenomenon so that the phenomenon of shooting and goal difficult judgment.
Brief description of the drawings
What Fig. 1 shot and scored for the automatic identification Basketball Match based on panoramic video that the present invention is provided
The schematic diagram of algorithm.
Embodiment
The invention will be further described with reference to the accompanying drawings and examples.
The shooting of the automatic identification Basketball Match based on panoramic video and the algorithm scored that the present invention is provided,
Concrete scheme includes：
First, the markup information of scene is generated.
The method learnt automatically using artificial mark or algorithm, acquires some prior informations of scene
(hoop and backboard are such as extracted from video, is marked out common at the corresponding ground in backboard position place
The height of sportsman).
According to backboard size and location, and at ground corresponding to backboard position court player height,
The shooting interest region (crown of the desirable court player at backboard position in y directions of generation match each side
At locating at the top of backboard, x directions can slightly be extended centered on backboard).
2nd, the detection of candidate's basketball.
(1) shooting interest region is taken out from panoramic video, sets up background model, and therefrom divide
The prospect of cutting out；
(2) size is utilized, shape, the information such as color, to being filtered at prospect, obtains some times
The suspicious basketball region of choosing；
(3) result being tracked using early stage to basketball, predicts the position of present frame basketball, if
There is prospect on the position, be then added to the suspicious basketball region of candidate；
(4) to suspicious ball region, the basketball model come out using offline machine learning carries out basketball
Detection, regard the region for detecting basketball as candidate's basketball region.
3rd, the generation of basketball track.
(1) using currently detected candidate's basketball as region to be tracked, the region is tracked (real
Border tracking go up+detect be combined obtain tracking result), by tracking result formed track.If
Do not track, with the replacement that predicts the outcome；If but continuous a period of time does not track, then terminates this
The tracking of track；
(2) time sequencing and spatial relationship are utilized, short track is connected as long track, is formed more complete
Whole basketball pursuit path.
4th, the automatic judgement of shooting.
Basketball track is analyzed, when its y-coordinate is in the up-and-down boundary of backboard, and x coordinate is in basket
When between the right boundary of plate, if meeting：It is using present frame as terminal and in the presence of continuous a few frame y-coordinates
Increasing or decreasing, then be judged to shooting.
5th, the automatic judgement scored.
Basketball track is analyzed, when its y-coordinate is below the lower boundary of backboard, and x coordinate exists
When between the right boundary of backboard, the judgement followed the steps below：
(1) judge within former seconds before present frame, if detected shooting, if not detecting,
Do not score then, otherwise, turn next step；
(2) the basketball track of former frame ins before present frame is judged, if intersect with hoop entity,
If non-intersect, do not score, otherwise it is assumed that scoring.
Although the present invention is disclosed as above with preferred embodiment, so it is not limited to the present invention, appoints
What those skilled in the art, without departing from the spirit and scope of the present invention, when a little modification can be made
With it is perfect, therefore protection scope of the present invention is when by being defined that claims are defined.
Claims (4)
1. a kind of shooting of automatic identification Basketball Match and the algorithm scored based on panoramic video, it is special
Levy and be, comprise the following steps：
1) markup information of scene is generated；
The method learnt automatically using artificial mark or algorithm, acquires some priori letter of scene
Breath；
According to backboard size and location, and at ground corresponding to backboard position court player height,
The shooting interest region of generation match each side；
2) detection of candidate's basketball；
(1) shooting interest region is taken out from panoramic video, sets up background model, and therefrom divide
The prospect of cutting out；
(2) size is utilized, shape, colouring information obtains the suspicious of candidate to being filtered at prospect
Basketball region；
(3) result being tracked using early stage to basketball, predicts the position of present frame basketball, if
There is prospect on the position, be then added to the suspicious basketball region of candidate；
(4) inspection of basketball is carried out to the basketball model that suspicious ball region is come out using offline machine learning
Survey, regard the region for detecting basketball as candidate's basketball region；
3) generation of basketball track；
(1) using currently detected candidate's basketball as region to be tracked, the region is tracked, will
Result formation track in tracking, with the replacement that predicts the outcome if not tracking；If but continuous one section
Time does not track, then terminates the tracking of the track；
(2) time sequencing and spatial relationship are utilized, short track is connected as long track, is formed more complete
Whole basketball pursuit path；
4) the automatic judgement of shooting；
Basketball track is analyzed, when its y-coordinate is in the up-and-down boundary of backboard, and x coordinate is in basket
When between the right boundary of plate, if meeting, it is using present frame as terminal and in the presence of continuous a few frame y-coordinates
Increasing or decreasing, then be judged to shooting；
5) the automatic judgement scored；
Basketball track is analyzed, when its y-coordinate is below the lower boundary of backboard, and x coordinate exists
When between the right boundary of backboard, make decisions.
2. the automatic identification Basketball Match based on panoramic video is shot and entered as claimed in claim 1
The algorithm of ball, it is characterised in that generation scene markup information step in, prior information include from regarding
Hoop and backboard are extracted in frequency, the body of court player at the corresponding ground in backboard position place is marked out
It is high.
3. the automatic identification Basketball Match based on panoramic video is shot and entered as claimed in claim 2
The algorithm of ball, it is characterised in that in the markup information step of generation scene, shoot interest region y side
To taking the top of the head of the court player at backboard position at the top of backboard, x directions are centered on backboard
Extension.
4. the automatic identification Basketball Match based on panoramic video is shot and entered as claimed in claim 3
The algorithm of ball, it is characterised in that the automatic decision steps of goal include：(1) judge in present frame
In former seconds before, if detected shooting, if not detecting, do not scored, otherwise, turn
Next step；(2) the basketball track of former frame ins before present frame is judged, if with hoop entity
It is intersecting, if non-intersect, do not score, otherwise it is assumed that scoring.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610037324.1A CN106991357A (en) | 2016-01-20 | 2016-01-20 | The shooting of automatic identification Basketball Match and the algorithm scored based on panoramic video |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610037324.1A CN106991357A (en) | 2016-01-20 | 2016-01-20 | The shooting of automatic identification Basketball Match and the algorithm scored based on panoramic video |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106991357A true CN106991357A (en) | 2017-07-28 |
Family
ID=59414375
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610037324.1A Pending CN106991357A (en) | 2016-01-20 | 2016-01-20 | The shooting of automatic identification Basketball Match and the algorithm scored based on panoramic video |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106991357A (en) |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109692450A (en) * | 2017-10-23 | 2019-04-30 | 聂怀军 | A kind of hollow sphere judgment method |
| CN109948446A (en) * | 2019-02-20 | 2019-06-28 | 北京奇艺世纪科技有限公司 | A kind of video clip processing method, device and computer readable storage medium |
| CN109961039A (en) * | 2019-03-20 | 2019-07-02 | 上海者识信息科技有限公司 | A kind of individual's goal video method for catching and system |
| CN110032914A (en) * | 2018-01-12 | 2019-07-19 | 北京京东尚科信息技术有限公司 | A kind of method and apparatus marking picture |
| CN110298231A (en) * | 2019-05-10 | 2019-10-01 | 新华智云科技有限公司 | A kind of method and system determined for the goal of Basketball Match video |
| CN110942022A (en) * | 2019-11-25 | 2020-03-31 | 维沃移动通信有限公司 | Shooting data output method and electronic equipment |
| CN111104851A (en) * | 2019-11-05 | 2020-05-05 | 新华智云科技有限公司 | Method and system for automatically generating defense area at basketball goal moment |
| 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 |
| CN114422851A (en) * | 2022-01-24 | 2022-04-29 | 腾讯科技（深圳）有限公司 | Video clipping method, video clipping device, electronic equipment and readable medium |
| CN116109981A (en) * | 2023-01-31 | 2023-05-12 | 北京智芯微电子科技有限公司 | Shooting recognition method, basketball recognition device, electronic equipment and storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2003022369A2 (en) * | 2001-09-12 | 2003-03-20 | Pillar Vision Corporation | Trajectory detection and feedback system |
| US20110090344A1 (en) * | 2009-10-21 | 2011-04-21 | Pvi Virtual Media Services, Llc | Object Trail-Based Analysis and Control of Video |
| CN104043237A (en) * | 2013-03-15 | 2014-09-17 | 威尔逊运动货品公司 | Basketball shot determination system |
| US20140301598A1 (en) * | 2013-04-03 | 2014-10-09 | Pillar Vision, Inc. | True space tracking of axisymmetric object flight using diameter measurement |
| CN104307153A (en) * | 2014-10-09 | 2015-01-28 | 华中科技大学 | Basketball flying trajectory navigation device and method |
| CN105139376A (en) * | 2015-07-16 | 2015-12-09 | 武汉体育学院 | Shooting counting method based on shooting counting device |
-
2016
- 2016-01-20 CN CN201610037324.1A patent/CN106991357A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2003022369A2 (en) * | 2001-09-12 | 2003-03-20 | Pillar Vision Corporation | Trajectory detection and feedback system |
| US20110090344A1 (en) * | 2009-10-21 | 2011-04-21 | Pvi Virtual Media Services, Llc | Object Trail-Based Analysis and Control of Video |
| CN104043237A (en) * | 2013-03-15 | 2014-09-17 | 威尔逊运动货品公司 | Basketball shot determination system |
| US20140301598A1 (en) * | 2013-04-03 | 2014-10-09 | Pillar Vision, Inc. | True space tracking of axisymmetric object flight using diameter measurement |
| CN104307153A (en) * | 2014-10-09 | 2015-01-28 | 华中科技大学 | Basketball flying trajectory navigation device and method |
| CN105139376A (en) * | 2015-07-16 | 2015-12-09 | 武汉体育学院 | Shooting counting method based on shooting counting device |
Non-Patent Citations (4)
| Title |
|---|
| 刘勋: "篮球对象分割和跟踪关键技术研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
| 刘舟槛: "基于背景差分法的篮球投篮自动识别系统设计", 《万方学位论文》 * |
| 姚睿: "《复杂环境下的鲁棒目标检测与跟踪》", 30 June 2015, 徐州：中国矿业大学出版社 * |
| 张有为 等著: "《人机交互》", 30 September 2004, 北京：国防工业出版社 * |
Cited By (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109692450A (en) * | 2017-10-23 | 2019-04-30 | 聂怀军 | A kind of hollow sphere judgment method |
| CN110032914A (en) * | 2018-01-12 | 2019-07-19 | 北京京东尚科信息技术有限公司 | A kind of method and apparatus marking picture |
| CN109948446B (en) * | 2019-02-20 | 2021-07-16 | 北京奇艺世纪科技有限公司 | Video clip processing method and device and computer readable storage medium |
| CN109948446A (en) * | 2019-02-20 | 2019-06-28 | 北京奇艺世纪科技有限公司 | A kind of video clip processing method, device and computer readable storage medium |
| CN109961039A (en) * | 2019-03-20 | 2019-07-02 | 上海者识信息科技有限公司 | A kind of individual's goal video method for catching and system |
| CN110298231A (en) * | 2019-05-10 | 2019-10-01 | 新华智云科技有限公司 | A kind of method and system determined for the goal of Basketball Match video |
| CN110298231B (en) * | 2019-05-10 | 2021-07-27 | 新华智云科技有限公司 | Method and system for judging goal of basketball game video |
| CN111104851A (en) * | 2019-11-05 | 2020-05-05 | 新华智云科技有限公司 | Method and system for automatically generating defense area at basketball goal moment |
| CN111104851B (en) * | 2019-11-05 | 2023-05-12 | 新华智云科技有限公司 | Automatic generation method and system for defending area at basketball goal moment |
| CN110942022A (en) * | 2019-11-25 | 2020-03-31 | 维沃移动通信有限公司 | Shooting data output method and electronic equipment |
| 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 |
| CN114422851A (en) * | 2022-01-24 | 2022-04-29 | 腾讯科技（深圳）有限公司 | Video clipping method, video clipping device, electronic equipment and readable medium |
| CN116109981A (en) * | 2023-01-31 | 2023-05-12 | 北京智芯微电子科技有限公司 | Shooting recognition method, basketball recognition device, electronic equipment and storage medium |
| CN116109981B (en) * | 2023-01-31 | 2024-04-12 | 北京智芯微电子科技有限公司 | Shooting recognition method, basketball recognition device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106991357A (en) | The shooting of automatic identification Basketball Match and the algorithm scored based on panoramic video | |
| CN106991359B (en) | Algorithm for tracking basketball in ball game video in panoramic mode | |
| CN106991358A (en) | The algorithm that automatic identification football match based on panoramic video is scored | |
| US9437012B2 (en) | Multiple-object tracking and team identification for game strategy analysis | |
| US20210264141A1 (en) | Device, System, and Method of Computer Vision, Object Tracking, Image Analysis, and Trajectory Estimation | |
| CN104117202B (en) | Projection type billiard batting intelligent assistance system and method | |
| US8659663B2 (en) | Video tracking of baseball players to determine the start and end of a half-inning | |
| CN108141512A (en) | Flight instruments, mobile device, server and program | |
| CN110929596A (en) | Shooting training system and method based on smart phone and artificial intelligence | |
| WO2018035821A1 (en) | Billiard ball striking assistance method, billiard ball striking assistance system, and portable electronic device | |
| CN111444890A (en) | Sports data analysis system and method based on machine learning | |
| CN110327612B (en) | Golf ball trajectory prediction method based on visual recognition | |
| JP2014508624A (en) | Virtual golf simulation apparatus, and sensing apparatus and sensing method used therefor | |
| KR20190031111A (en) | Virtual tennis simulation system, sensing device and method for sensing process using the same | |
| US20230372803A1 (en) | Tennis self-training system | |
| US20120162434A1 (en) | Video tracking of baseball players which identifies merged participants based on participant roles | |
| US9589332B2 (en) | Camera movement correction apparatus, method and system | |
| CN106991685B (en) | Algorithm for tracking football in ball game video in panoramic mode | |
| US10803598B2 (en) | Ball detection and tracking device, system and method | |
| RU2606583C2 (en) | Method and apparatus for determining position of sporting projectile within scene | |
| KR20230050262A (en) | Tennis self-training system | |
| Hsu et al. | Coachai: A project for microscopic badminton match data collection and tactical analysis | |
| CN103870795A (en) | Automatic detection method and device of video rolling subtitle | |
| JP2004248725A (en) | Analysis device and method of shot ball | |
| CN108269265A (en) | Billiard ball batter's box assay method and its device based on deep learning |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170728 |
|
| RJ01 | Rejection of invention patent application after publication |