CN107241645A - A kind of method that splendid moment of scoring is automatically extracted by the subtitle recognition to video - Google Patents
A kind of method that splendid moment of scoring is automatically extracted by the subtitle recognition to video Download PDFInfo
- Publication number
- CN107241645A CN107241645A CN201710434108.5A CN201710434108A CN107241645A CN 107241645 A CN107241645 A CN 107241645A CN 201710434108 A CN201710434108 A CN 201710434108A CN 107241645 A CN107241645 A CN 107241645A
- Authority
- CN
- China
- Prior art keywords
- score
- camera lens
- video
- frame
- people
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
- H04N21/44—Processing of video elementary streams, e.g. splicing a video clip retrieved from local storage with an incoming video stream, rendering scenes according to MPEG-4 scene graphs
-
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
- H04N21/44—Processing of video elementary streams, e.g. splicing a video clip retrieved from local storage with an incoming video stream, rendering scenes according to MPEG-4 scene graphs
- H04N21/44008—Processing of video elementary streams, e.g. splicing a video clip retrieved from local storage with an incoming video stream, rendering scenes according to MPEG-4 scene graphs involving operations for analysing video streams, e.g. detecting features or characteristics in the video stream
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/47—End-user applications
- H04N21/472—End-user interface for requesting content, additional data or services; End-user interface for interacting with content, e.g. for content reservation or setting reminders, for requesting event notification, for manipulating displayed content
- H04N21/47217—End-user interface for requesting content, additional data or services; End-user interface for interacting with content, e.g. for content reservation or setting reminders, for requesting event notification, for manipulating displayed content for controlling playback functions for recorded or on-demand content, e.g. using progress bars, mode or play-point indicators or bookmarks
Abstract
The invention discloses a kind of method that splendid moment of scoring is automatically extracted by the subtitle recognition to video, including S1:Score subtitle position is determined, the score captions plate in video pictures is identified by than distributional feature;S2:Score, the picture obtained corresponding to present score of consecutive intervals are monitored, and present score is compared with a preceding score, is ignored if identical, the camera lens for having the splendid moment of goal herein is represented if different;S3:Highlight is extracted, the nearest distant view marked is found forward since the frame that score changes, after remote camera lens is identified, on the basis of remote camera lens end frame, a number of continuous frame of video of interception, is used as goal camera lens before and after it.The present invention application score change before have story board principle to video carry out subtitle recognition extract match goal camera lens, the method improve in the prior art manually get ready shearing Highlight defect, it is possible to increase efficiency.
Description
Technical field
The present invention relates to video extraction technology, and in particular to a kind of to automatically extract goal essence by the subtitle recognition to video
The method of color moment.
Background technology
For now, amalgamation media epoch, broadcasting and TV media and the Internet media are advanced side by side, and are complemented each other.Broadcasting and TV matchmaker
Body possesses abundant resource, such as, has substantial amounts of professional sportses race signal to provide content support for the Internet media, and
Competitive sports are also the topic usually continued saying it with interest during people live, and possess substantial amounts of audient;The Internet media, which has, propagates speed
Degree is fast, it is wide to disseminate, information fragmentation the features such as, can continue to keep temperature, on the one hand, the life of broadcasting and TV media can be promoted
Production, on the other hand, also proposes the requirement of content and efficiency to the existing manufacturing system of broadcasting and TV media.
In existing manufacturing system, following two problems are primarily present:
Content problems, bout typically has one or two hour, and the time span of content is unfavorable in internet, social media biography
Broadcast, the development of internet and amalgamation media so that increasing people adapts to the information with demand " fragmentation ".Therefore, it is just interior
For appearance, the mode that match Highlight is issued for internet again of extracting typically is taken.
Efficiency, the method for existing extraction match Highlight substantially carries out hand after video includes completion
It is dynamic to get ready, manually shear, it is clear that such method not only consumes substantial amounts of manpower and time, and efficiency is very low, can not expire
The ageing demand of foot.
The content of the invention
Carried automatically it is an object of the invention to overcome the deficiencies of the prior art and provide a kind of subtitle recognition by video
Take score splendid moment method, have before changing using score story board principle to video carry out subtitle recognition extract compete
Goal camera lens, the method improve the defect for getting shearing Highlight ready manually in the prior art, it is possible to increase efficiency.
The purpose of the present invention is achieved through the following technical solutions:
A kind of method that splendid moment of scoring is automatically extracted by the subtitle recognition to video, comprises the following steps:
S1:Score subtitle position is determined, the score captions plate in video pictures is identified by than distributional feature;
S2 monitors score, the picture obtained corresponding to present score of consecutive intervals, and present score is entered with a preceding score
Row compares, and ignores if identical, and the camera lens for having the splendid moment of goal herein is represented if different;
S3:Highlight is extracted, the nearest distant view marked is found forward since the frame that score changes, is identifying remote mirror
After head, on the basis of remote camera lens end frame, a number of continuous frame of video of interception, is used as goal camera lens before and after it.
Further, described step S1 determines that the position of score plate specifically includes following sub-step:
S11:Full frame search text subtile, caption character is identified in subregion;
S12:The caption character that will identify that than distributional feature with being contrasted, the position if it can contrast for score captions plate
Put.
Further, the described distributional feature of ratio is the score of 1 title team of team 1:Team 2 is than the title of unit 2 or title team of team 1
1 score-team 2 recognized than the title of unit 2, that is, in captions character ":" or "-".
Further, described step S2 calculates monitoring score and specifically includes following sub-step:
S21:The picture of score position is obtained by the time interval of setting;
S22:Score is recognized by subtitle recognition method;
S23:The score of this identification is contrasted with last score, except the score recognized first, ignored if identical, if
It is different then represent there is the camera lens of the splendid moment of goal herein.
Further, described step S3 extracts Highlight and specifically includes following sub-step:
S31:In units of frame, each frame picture is recognized;
S32:According to number of people number mark close shot, middle scape, distant view or according in camera lens frame way of contrast mark distant view, non-distant view;
S33:After remote camera lens is identified, on the basis of remote camera lens end frame, interception is a number of before and after it continuously regards
Frequency frame, is used as goal camera lens.
Further, it is described to specifically refer to train knowledge using artificial neural network according to number of people number judgment frame picture
The model of others' head number, the number of the number of people in picture is judged by Head recognition technology, if number of people number is less than or equal to 1, the picture
Face is close shot picture;If number of people number is between 2 and the value x of setting, the picture is middle scape;If number of people number is more than x, for distant view
Picture.
Further, frame way of contrast refers to recognize between transition camera lens, two transition camera lenses to be one in described camera lens
Natural camera lens, frame interior paired observation is carried out to each natural camera lens, and it fluctuates situation, and fluctuating range is small for distant view, fluctuation width
Degree it is big for non-distant view, distant view is mainly used during shearing video, therefore without distinguishing close shot and middle scape in detail.
Further, described close shot, middle scape, distant view are defined as follows:
Close shot:It is the camera lens of a people to sportsman, the personal skill of coach, the feature expressed one's feelings after fingering ball or out-of-bounds generation;
Middle scape:Refer to the close up fragmentary to event generating processes such as held ball, foul, be the camera lens of 2-5 people;
Distant view:It is the movable camera lens to whole court, is shot using the motion of ball as clue, is the camera lens of many people, its people
Number is more than the number in middle scape.
The beneficial effects of the invention are as follows:The present invention by recognizing score situation of change in captions, in conjunction with camera lens close shot, in
The analysis of scape, distant view, COMPREHENSIVE CALCULATING finds out the featured videos for moment of scoring, and operation is simple and reliable for this method, can effectively extract body
Educate the excellent goal picture in match video.
Brief description of the drawings
Fig. 1 is the flow chart of the present invention.
Embodiment
1 technical scheme is described in further detail below in conjunction with the accompanying drawings, but protection scope of the present invention is not limited to
In as described below.
Principles and methods:
1st, we are the various shot classifications in ball match, respectively close up shots, medium shot and long shot.By analysis,
We have found that goal camera lens is occurred in remote camera lens
1)Close up shots:It is often referred to after the events such as goal, out-of-bounds occur to sportsman, the personal skill of coach, the feature expressed one's feelings, base
Originally it is the camera lens of a people, this camera lens commonly takes place in match Interruption period between The following article.
2)Medium shot:The close up fragmentary to event generating processes such as held ball, foul is often referred to, usually three or five people's
Camera lens.It is not in this camera lens that this camera lens, which is generally present in before midfield or side, goal,.
3)Long shot:Typically to the movable camera lens in whole court, the typically motion using ball is shot as clue.
Ball occurs in this kind of camera lens to before goal, typically can all be switched to this camera lens, the process of goal.
2nd, in bout, the position of score plate will not change.
3rd, the change flag of score, which herein, before a goal moment, moment of scoring in bout be spectators most concerned about
Key point, can extract and change nearest long shot as Highlight from score and be published to the Internet media.
【Embodiment one】
A kind of method that splendid moment of scoring is automatically extracted by the subtitle recognition to video, applied to football match, including with
Lower step;
S1:Determine score subtitle position
Caption character is identified in full frame search text subtile, subregion, and the caption character that will identify that than distributional feature with carrying out
Contrast, the position if it can contrast for score captions plate;Score template characteristic is:The score of 1 title team of team 1:Team 2 compares unit
2 titles, such as China 00:00 South Korea;
S2:Monitor score
The picture of score position is obtained by the time interval of setting, score is recognized by subtitle recognition method, this is known
Other score is contrasted with last score(Except the score recognized first), ignore if identical, represented herein if different
There is the camera lens of the splendid moment of goal, carry out next step.
S3:Extract Highlight
Find the nearest distant view marked forward since the frame that score changes, the judgement of picture type is same with score monitoring
Shi Jinhang's, the judgement of picture comprises the following steps:
In units of frame, each frame picture is recognized, close shot, middle scape, distant view or according to frame pair in camera lens are marked according to number of people number
Distant view, non-distant view are marked than mode.
Judged by number of people number:
The model of identification number of people number is trained using artificial neural network, Head recognition can be used for by the model, pass through people
Head identification technology judges the number of the number of people in picture, if number of people number is less than or equal to 1, and the picture is close shot picture;If the number of people
Number is between 2 and the value X of setting, then the picture is middle scape;If number of people number is more than X, for distant view picture, wherein X can be according to tool
The video of body is correspondingly arranged.
Frame control methods judges in camera lens:
Recognize between transition camera lens, two transition camera lenses to be a natural camera lens, carrying out frame interior contrast to each natural camera lens sees
Examine its fluctuation situation, fluctuating range is small for distant view, fluctuating range it is big for non-distant view, mainly use distant view during shearing video,
Therefore without distinguishing close shot and middle scape in detail.
Choose goal camera lens
After remote camera lens is identified, on the basis of remote camera lens end frame, a number of continuous frame of video of interception before and after it,
Such as above interception 15 seconds, behind cut 5 seconds, be used as goal camera lens.
【Embodiment two】
A kind of method that splendid moment of scoring is automatically extracted by the subtitle recognition to video, applied to Basketball Match;
S1:Determine score subtitle position
Caption character is identified in full frame search text subtile, subregion, and the caption character that will identify that than distributional feature with carrying out
Contrast, the position if it can contrast for score captions plate;Score template characteristic is:1 title team of team, 1 score-team 2 compares unit
2 titles, such as bull 00-00 rockets;
S2:Monitor score
The picture of score position is obtained by the time interval of setting, score is recognized by subtitle recognition method, this is known
Other score is contrasted with last score(Except the score recognized first), ignore if identical, if 3 points of difference is represented herein
There is the camera lens of the splendid moment of goal(Three-point shot is typically all Highlight in Basketball Match), carry out next step.
S3:Extract Highlight
Find the nearest distant view marked forward since the frame that score changes, the judgement of picture type is same with score monitoring
Shi Jinhang's, the judgement of picture comprises the following steps:
In units of frame, each frame picture is recognized, according to the mode comprehensive descision frame picture such as frame contrast in number of people number and camera lens
Type, and mark:Close shot, middle scape, distant view or distant view, non-distant view.
Judged by number of people number:
The model of identification number of people number is trained using artificial neural network, Head recognition can be used for by the model, pass through people
Head identification technology judges the number of the number of people in picture, if number of people number is less than or equal to 1, and the picture is close shot picture;If the number of people
Number is between 2 and the value X of setting, then the picture is middle scape;If number of people number is more than X, for distant view picture, wherein X can be according to tool
The video of body is correspondingly arranged.
Frame control methods judges in camera lens:
Recognize between transition camera lens, two transition camera lenses to be a natural camera lens, carrying out frame interior contrast to each natural camera lens sees
Examine its fluctuation situation, fluctuating range is small for distant view, fluctuating range it is big for non-distant view, mainly use distant view during shearing video,
Therefore without distinguishing close shot and middle scape in detail.
Choose goal camera lens
After remote camera lens is identified, on the basis of remote camera lens end frame, a number of continuous frame of video of interception before and after it,
Such as above interception 15 seconds, behind cut 5 seconds, be used as goal camera lens.
The present invention is not limited solely in basketball or football match, is equally applicable to other grading scheme sports tournaments, can be with
Standard is changed according to the score value that different game-scoring mechanism formulate Highlight, so as to extract corresponding Highlight.
Described above is only the preferred embodiment of the present invention, it should be understood that the present invention is not limited to described herein
Form, is not to be taken as the exclusion to other embodiment, and available for various other combinations, modification and environment, and can be at this
In the text contemplated scope, it is modified by the technology or knowledge of above-mentioned teaching or association area.And those skilled in the art are entered
Capable change and change does not depart from the spirit and scope of the present invention, then all should appended claims of the present invention protection domain
It is interior.
Claims (8)
1. a kind of method that splendid moment of scoring is automatically extracted by the subtitle recognition to video, it is characterised in that including following step
Suddenly:
S1:Score subtitle position is determined, the score captions plate in video pictures is identified by than distributional feature;
S2:Score, the picture obtained corresponding to present score of consecutive intervals are monitored, and present score is entered with a preceding score
Row compares, and ignores if identical, and the camera lens for having the splendid moment of goal herein is represented if different;
S3:Highlight is extracted, the nearest distant view marked is found forward since the frame that score changes, is identifying remote mirror
After head, on the basis of remote camera lens end frame, a number of continuous frame of video of interception, is used as goal camera lens before and after it.
2. a kind of method that splendid moment of scoring is automatically extracted by the subtitle recognition to video according to claim 1,
It is characterized in that:Described step S1 determines that the position of score plate specifically includes following sub-step:
S11:Full frame search text subtile, caption character is identified in subregion;
S12:The caption character that will identify that than distributional feature with being contrasted, the position if it can contrast for score captions plate
Put.
3. a kind of side that splendid moment of scoring is automatically extracted by the subtitle recognition to video according to claim 1 or 2
Method, it is characterised in that:The described distributional feature of ratio is the score of 1 title team of team 1:Team 2 compares than the title of unit 2 or title team 1 of team 1
Point-team 2 is than the title of unit 2.
4. a kind of method that splendid moment of scoring is automatically extracted by the subtitle recognition to video according to claim 1,
It is characterized in that:Described step S2 calculates monitoring score and specifically includes following sub-step:
S21:The picture of score position is obtained by the time interval of setting;
S22:Score is recognized by subtitle recognition method;
S23:The score of this identification is contrasted with last score, except the score recognized first, ignored if identical, if
It is different then represent there is the camera lens of the splendid moment of goal herein.
5. a kind of method that splendid moment of scoring is automatically extracted by the subtitle recognition to video according to claim 1,
It is characterized in that:Described step S3 extracts Highlight and specifically includes following sub-step:
S31:In units of frame, each frame picture is recognized;
S32:According to number of people number mark close shot, middle scape, distant view or according in camera lens frame way of contrast mark distant view, non-distant view;
S33:After remote camera lens is identified, on the basis of remote camera lens end frame, interception is a number of before and after it continuously regards
Frequency frame, is used as goal camera lens.
6. a kind of method that splendid moment of scoring is automatically extracted by the subtitle recognition to video according to claim 5,
It is characterized in that:Described specifically refers to train the identification number of people using artificial neural network according to number of people number judgment frame picture
Several models, the number of the number of people in picture is judged by Head recognition technology, if number of people number is less than or equal to 1, the picture is near
Scape picture;If number of people number is between 2 and the value x of setting, the picture is middle scape;If number of people number is more than x, for distant view picture.
7. a kind of method that splendid moment of scoring is automatically extracted by the subtitle recognition to video according to claim 5,
It is characterized in that:Frame way of contrast refers to recognize between transition camera lens, two transition camera lenses for a natural mirror in described camera lens
Head, frame interior paired observation is carried out to each natural camera lens, and it fluctuates situation, fluctuating range is small for distant view, and fluctuating range is big
For non-distant view, distant view is mainly used during shearing video, therefore without distinguishing close shot and middle scape in detail.
8. a kind of according to any one of claim 5-7 automatically extracts goal excellent wink by the subtitle recognition to video
Between method, it is characterised in that:Described close shot, middle scape, distant view are defined as follows:
Close shot:It is the camera lens of a people to sportsman, the personal skill of coach, the feature expressed one's feelings after fingering ball or out-of-bounds generation;
Middle scape:Refer to the close up fragmentary to event generating processes such as held ball, foul, be the camera lens of 2-5 people;
Distant view:It is the movable camera lens to whole court, is shot using the motion of ball as clue, is the camera lens of many people, its people
Number is more than the number in middle scape.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710434108.5A CN107241645B (en) | 2017-06-09 | 2017-06-09 | Method for automatically extracting goal wonderful moment through caption recognition of video |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710434108.5A CN107241645B (en) | 2017-06-09 | 2017-06-09 | Method for automatically extracting goal wonderful moment through caption recognition of video |
Publications (2)
Publication Number | Publication Date |
---|---|
CN107241645A true CN107241645A (en) | 2017-10-10 |
CN107241645B CN107241645B (en) | 2020-07-24 |
Family
ID=59986153
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710434108.5A Active CN107241645B (en) | 2017-06-09 | 2017-06-09 | Method for automatically extracting goal wonderful moment through caption recognition of video |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107241645B (en) |
Cited By (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107801106A (en) * | 2017-10-24 | 2018-03-13 | 维沃移动通信有限公司 | A kind of video segment intercept method and electronic equipment |
CN109344292A (en) * | 2018-09-28 | 2019-02-15 | 百度在线网络技术(北京)有限公司 | Generation method, device, server and the storage medium of race score segment |
CN109635707A (en) * | 2018-12-06 | 2019-04-16 | 安徽海豚新媒体产业发展有限公司 | A kind of video lens extracting method based on feature identification |
CN110267116A (en) * | 2019-05-22 | 2019-09-20 | 北京奇艺世纪科技有限公司 | Video generation method, device, electronic equipment and computer-readable medium |
CN110339566A (en) * | 2019-05-29 | 2019-10-18 | 努比亚技术有限公司 | A kind of game Wonderful time recognition methods, terminal and computer readable storage medium |
CN111031384A (en) * | 2019-12-24 | 2020-04-17 | 北京多格科技有限公司 | Video content display method and device |
CN111340837A (en) * | 2020-02-18 | 2020-06-26 | 上海眼控科技股份有限公司 | Image processing method, device, equipment and storage medium |
CN111488847A (en) * | 2020-04-17 | 2020-08-04 | 上海媒智科技有限公司 | System, method and terminal for acquiring sports game video goal segment |
CN111988670A (en) * | 2020-08-18 | 2020-11-24 | 腾讯科技(深圳)有限公司 | Video playing method and device, electronic equipment and computer readable storage medium |
CN113490049A (en) * | 2021-08-10 | 2021-10-08 | 深圳市前海动竞体育科技有限公司 | Sports event video editing method and system based on artificial intelligence |
CN113537052A (en) * | 2021-07-14 | 2021-10-22 | 北京百度网讯科技有限公司 | Video clip extraction method, device, equipment and storage medium |
CN117132925A (en) * | 2023-10-26 | 2023-11-28 | 成都索贝数码科技股份有限公司 | Intelligent stadium method and device for sports event |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP1460835A1 (en) * | 2003-03-19 | 2004-09-22 | Thomson Licensing S.A. | Method for identification of tokens in video sequences |
CN101211460A (en) * | 2006-12-30 | 2008-07-02 | 中国科学院计算技术研究所 | Method and device for automatically dividing and classifying sports vision frequency shot |
CN101604325A (en) * | 2009-07-17 | 2009-12-16 | 北京邮电大学 | Method for classifying sports video based on key frame of main scene lens |
CN102254160A (en) * | 2011-07-12 | 2011-11-23 | 央视国际网络有限公司 | Video score detecting and recognizing method and device |
CN102263907A (en) * | 2011-08-04 | 2011-11-30 | 央视国际网络有限公司 | Play control method of competition video, and generation method and device for clip information of competition video |
CN102393909A (en) * | 2011-06-29 | 2012-03-28 | 西安电子科技大学 | Method for detecting goal events in soccer video based on hidden markov model |
CN103049787A (en) * | 2011-10-11 | 2013-04-17 | 汉王科技股份有限公司 | People counting method and system based on head and shoulder features |
CN105955708A (en) * | 2016-05-09 | 2016-09-21 | 西安北升信息科技有限公司 | Sports video lens classification method based on deep convolutional neural networks |
-
2017
- 2017-06-09 CN CN201710434108.5A patent/CN107241645B/en active Active
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP1460835A1 (en) * | 2003-03-19 | 2004-09-22 | Thomson Licensing S.A. | Method for identification of tokens in video sequences |
CN101211460A (en) * | 2006-12-30 | 2008-07-02 | 中国科学院计算技术研究所 | Method and device for automatically dividing and classifying sports vision frequency shot |
CN101604325A (en) * | 2009-07-17 | 2009-12-16 | 北京邮电大学 | Method for classifying sports video based on key frame of main scene lens |
CN102393909A (en) * | 2011-06-29 | 2012-03-28 | 西安电子科技大学 | Method for detecting goal events in soccer video based on hidden markov model |
CN102254160A (en) * | 2011-07-12 | 2011-11-23 | 央视国际网络有限公司 | Video score detecting and recognizing method and device |
CN102263907A (en) * | 2011-08-04 | 2011-11-30 | 央视国际网络有限公司 | Play control method of competition video, and generation method and device for clip information of competition video |
CN103049787A (en) * | 2011-10-11 | 2013-04-17 | 汉王科技股份有限公司 | People counting method and system based on head and shoulder features |
CN105955708A (en) * | 2016-05-09 | 2016-09-21 | 西安北升信息科技有限公司 | Sports video lens classification method based on deep convolutional neural networks |
Cited By (17)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107801106A (en) * | 2017-10-24 | 2018-03-13 | 维沃移动通信有限公司 | A kind of video segment intercept method and electronic equipment |
CN107801106B (en) * | 2017-10-24 | 2019-10-15 | 维沃移动通信有限公司 | A kind of video clip intercept method and electronic equipment |
CN109344292A (en) * | 2018-09-28 | 2019-02-15 | 百度在线网络技术(北京)有限公司 | Generation method, device, server and the storage medium of race score segment |
CN109635707A (en) * | 2018-12-06 | 2019-04-16 | 安徽海豚新媒体产业发展有限公司 | A kind of video lens extracting method based on feature identification |
CN110267116A (en) * | 2019-05-22 | 2019-09-20 | 北京奇艺世纪科技有限公司 | Video generation method, device, electronic equipment and computer-readable medium |
CN110339566A (en) * | 2019-05-29 | 2019-10-18 | 努比亚技术有限公司 | A kind of game Wonderful time recognition methods, terminal and computer readable storage medium |
CN111031384A (en) * | 2019-12-24 | 2020-04-17 | 北京多格科技有限公司 | Video content display method and device |
CN111340837A (en) * | 2020-02-18 | 2020-06-26 | 上海眼控科技股份有限公司 | Image processing method, device, equipment and storage medium |
CN111488847A (en) * | 2020-04-17 | 2020-08-04 | 上海媒智科技有限公司 | System, method and terminal for acquiring sports game video goal segment |
CN111488847B (en) * | 2020-04-17 | 2024-02-02 | 上海媒智科技有限公司 | Sports game video ball-feeding segment acquisition system, method and terminal |
CN111988670A (en) * | 2020-08-18 | 2020-11-24 | 腾讯科技(深圳)有限公司 | Video playing method and device, electronic equipment and computer readable storage medium |
CN113537052A (en) * | 2021-07-14 | 2021-10-22 | 北京百度网讯科技有限公司 | Video clip extraction method, device, equipment and storage medium |
CN113537052B (en) * | 2021-07-14 | 2023-07-28 | 北京百度网讯科技有限公司 | Video clip extraction method, device, equipment and storage medium |
CN113490049A (en) * | 2021-08-10 | 2021-10-08 | 深圳市前海动竞体育科技有限公司 | Sports event video editing method and system based on artificial intelligence |
CN113490049B (en) * | 2021-08-10 | 2023-04-21 | 深圳市前海动竞体育科技有限公司 | Sports event video editing method and system based on artificial intelligence |
CN117132925A (en) * | 2023-10-26 | 2023-11-28 | 成都索贝数码科技股份有限公司 | Intelligent stadium method and device for sports event |
CN117132925B (en) * | 2023-10-26 | 2024-02-06 | 成都索贝数码科技股份有限公司 | Intelligent stadium method and device for sports event |
Also Published As
Publication number | Publication date |
---|---|
CN107241645B (en) | 2020-07-24 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107241645A (en) | A kind of method that splendid moment of scoring is automatically extracted by the subtitle recognition to video | |
US10758807B2 (en) | Smart court system | |
US9613661B2 (en) | Information processing apparatus, recording medium, and information processing system | |
US8611723B2 (en) | System for relating scoreboard information with event video | |
CN107172487A (en) | A kind of method that Highlight is extracted by camera lens playback feature | |
CN105183849B (en) | A kind of match Video Events detection of Snooker and semanteme marking method | |
CN110012348A (en) | A kind of automatic collection of choice specimens system and method for race program | |
CN101303695B (en) | Device for processing a sports video | |
CN101377852B (en) | Apparatus for determining highlight segments of sport video | |
US9094615B2 (en) | Automatic event videoing, tracking and content generation | |
US7793205B2 (en) | Synchronization of video and data | |
US20150297949A1 (en) | Automatic sports broadcasting system | |
CN201349264Y (en) | Motion image processing device and system | |
US20140282642A1 (en) | Attention estimation to control the delivery of data and audio/video content | |
MX2012000902A (en) | Play sequence visualization and analysis. | |
US20080269924A1 (en) | Method of summarizing sports video and apparatus thereof | |
US9924148B2 (en) | Highlight program | |
CN109672899A (en) | The Wonderful time of object game live scene identifies and prerecording method in real time | |
CN110188241A (en) | A kind of race intelligence manufacturing system and production method | |
CN102393909B (en) | Method for detecting goal events in soccer video based on hidden markov model | |
CN109635707A (en) | A kind of video lens extracting method based on feature identification | |
North et al. | Identifying the critical time period for information extraction when recognizing sequences of play | |
KR20180089977A (en) | System and method for video segmentation based on events | |
Shiiya et al. | A study on automatic display system of the archery score for the visually impaired | |
CN110321766B (en) | Misfiring detection system and method in shooting movement |
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 |