CN108509931A - Football featured videos method for catching and system - Google Patents
Football featured videos method for catching and system Download PDFInfo
- Publication number
- CN108509931A CN108509931A CN201810318626.5A CN201810318626A CN108509931A CN 108509931 A CN108509931 A CN 108509931A CN 201810318626 A CN201810318626 A CN 201810318626A CN 108509931 A CN108509931 A CN 108509931A
- Authority
- CN
- China
- Prior art keywords
- video frame
- proportion
- video
- thresholding
- frame
- 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
- 238000000034 method Methods 0.000 title claims abstract description 28
- 230000008859 change Effects 0.000 claims abstract description 49
- 238000010801 machine learning Methods 0.000 claims description 6
- 230000000386 athletic effect Effects 0.000 abstract 2
- 230000006870 function Effects 0.000 description 5
- 238000004458 analytical method Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 230000000712 assembly Effects 0.000 description 1
- 238000000429 assembly Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000009189 diving Effects 0.000 description 1
- 238000003708 edge detection Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 239000002360 explosive Substances 0.000 description 1
- 210000002683 foot Anatomy 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
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
Landscapes
- Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Television Signal Processing For Recording (AREA)
- Image Analysis (AREA)
Abstract
The present invention provides a kind of football featured videos method for catching, including:Capture the first brightness change of football video;When the first brightness change is more than preset first threshold value, start to extract one or more video frame after the first brightness change;Image procossing is carried out to video frame, obtains the video frame after image procossing;Based on the video frame after image procossing, the characteristic information in one or more video frame is obtained;It presets multiple video frame and judges threshold value;Determine the classification of excellent event;The video after the first brightness change is recorded, and captures the second brightness change in the video after recording the first brightness change;And the stop recording video when the second brightness change is more than preset second threshold value.The football featured videos method of the present invention can reduce Computing amount, and video is with strong points, highlight the peculiar glamour of Football Athletic fortune work(, the promotion and popularization for contributing to Football Athletic to move.
Description
Technical field
The present invention relates to sports intelligent apparatus fields, more particularly to football featured videos method for catching and system.
Background technology
Sport is a kind of Social Culture phenomenon of complexity, it gives birth to using body and intellection as basic means according to human body
The rules such as long development, technical ability are formed and function improves, reach promote full development, improve fitness and overall education level,
It builds up health and improves locomitivity, mode of making the life better and improve the quality of living a kind of conscious, purposeful, organized
Social activities.With the expansion of international association, the scale and level of sports business development have been to weigh country, a social development
A progressive important symbol also becomes the important means of diplomacy and cultural exchanges between country.Currently, football has become one kind
Worldwide sports, the good reputation with " the first in the world movement ", is the most influential individual event body of global sporting world
Educate movement.
Past tradition is all to watch sports tournament by television relay, however as multimedia technology and internet
The demand of fast development, multimedia messages also increasingly increases, and integrates the multi-medium data of image, audio and text message
With geometric progression explosive growth, traditional information processing method and technology can not cope with the massive video of this sustainable growth
Data.Multimedia video is as main medium type, and the influence to the education, life, amusement of people etc. is increasingly
Prominent, Video Applications of novel functions at present, such as DTV, video on demand, video conference, long-distance education have been dissolved into
In daily life.Since the data format of video is unstructured, data volume is huge and the abundant in content factors such as various of performance are deposited
, how effectively organization and management mass data, and valuable or user sense how is excavated from massive video data
The information of interest becomes the problem studied with searching field scholars for current video analysis to meet users ' individualized requirement.
Sports video is liked by spectators deeply, and possesses huge commercial value, receives the wide of various circles of society and researcher
General concern.An important branch of the Sports Video Analysis with retrieval as field of video retrieval, primarily directed to all kinds of sport ratios
Video is matched, video low-level feature is analyzed, realizes the detection of certain semantic event, and creates video frequency abstract.Sports video have as
Lower feature:(1) video genre is complicated, is related to a variety of racing tips such as basketball, football, table tennis, baseball, tennis, diving;
(2) video content is rich and varied, includes the contents such as match carry out situation, player information, Studio and advertisement;(3) it regards
The frequency duration is longer, and data volume is huge;(4) sports video type is different, and technical term and rule difference are regarded for different
Frequency type needs to carry out specific structure and rule defines.
Being disclosed in the information of the background technology part, it is only intended to increase understanding of the overall background of the invention, without answering
It has been the prior art well known to persons skilled in the art when being considered as recognizing or imply that the information is constituted in any form.
Invention content
The purpose of the present invention is to provide a kind of football featured videos method for catching and systems, to overcome the prior art
Disadvantage.
The present invention provides a kind of football featured videos method for catching, include the following steps:It is bright to capture football video first
Degree variation;When the first brightness change is more than preset first threshold value, start to extract one after the first brightness change
A or multiple video frame;Image procossing is carried out to video frame, obtains the video frame after image procossing;After image procossing
Video frame, obtain the characteristic information in one or more video frame;It presets multiple video frame and judges threshold value;Based on spy
Reference ceases and multiple video frame judge the comparison between threshold value, determines the classification of excellent event;Record the first brightness change
Video after change, and capture the second brightness change in the video after recording the first brightness change;And when the second brightness
When variation is more than preset second threshold value, stop recording video.
Preferably, in above-mentioned technical proposal, the characteristic information in one or more video frame includes:Place is in the video frame
Proportion, sportsman proportion, referee proportion, forbidden zone region institute in the video frame in the video frame in the video frame
Accounting example, middle field areas proportion, corner-kick region proportion and frame exercise intensity in the video frame in the video frame.
Preferably, in above-mentioned technical proposal, video frame judges that threshold value is the machine learning method via supervised learning
It generates, wherein video frame judges that threshold value includes:Multiple places in the video frame proportion thresholding, multiple sportsmen regarding
Proportion thresholding, multiple referees proportion thresholding, multiple forbidden zone regions institute in the video frame in the video frame in frequency frame
Accounting example thresholding, multiple middle field areas proportion thresholding, multiple corner-kick regions proportion in the video frame in the video frame
Thresholding and frame exercise intensity thresholding.
Preferably, in above-mentioned technical proposal, feature based information and multiple video frame judge that the comparison between threshold value is closed
System, determines that the classification of excellent event specifically includes:If proportion is more than the first corner-kick region in the video frame in corner-kick region
Proportion thresholding in the video frame, and proportion is less than field one institute's accounting in the video frame in the video frame in place
Example thresholding, then be judged as corner-kick event by excellent event;If proportion is more than the first referee to referee in the video frame
Proportion thresholding in the video frame, and frame exercise intensity is more than frame exercise intensity thresholding, then by the excellent event criminal of being judged as
Rule event.
Preferably, in above-mentioned technical proposal, feature based information and multiple video frame judge that the comparison between threshold value is closed
System, determines that the classification of excellent event further includes specifically:If middle field areas in the video frame proportion be less than first in place
Domain proportion thresholding in the video frame, and proportion is more than the first forbidden zone region in video in the video frame in forbidden zone region
Proportion thresholding in frame, and proportion is more than sportsman's proportion thresholding in the video frame to sportsman in the video frame, then
Excellent event is judged as penalty kick event.
The present invention also provides a kind of football featured videos to capture system, including:For capturing the first brightness of football video
The unit of variation;For when the first brightness change is more than preset first threshold value, starting to extract the first brightness change
The unit of one or more video frame later;For carrying out image procossing to video frame, the video after image procossing is obtained
The unit of frame;For based on the video frame after image procossing, obtaining the unit of the characteristic information in one or more video frame;
The unit of threshold value is judged for presetting multiple video frame;Judge threshold value for feature based information and multiple video frame
Between comparison, determine the unit of the classification of excellent event;For recording the video after the first brightness change, and capture
Record the unit of the second brightness change in the video after the first brightness change;And for being more than in advance when the second brightness change
When the second threshold value first set, the unit of stop recording video.
Preferably, in above-mentioned technical proposal, the characteristic information in one or more video frame includes:Place is in the video frame
Proportion, sportsman proportion, referee proportion, forbidden zone region institute in the video frame in the video frame in the video frame
Accounting example, middle field areas proportion, corner-kick region proportion and frame exercise intensity in the video frame in the video frame.
Preferably, in above-mentioned technical proposal, video frame judges that threshold value is the machine learning method via supervised learning
It generates, wherein video frame judges that threshold value includes:Multiple places in the video frame proportion thresholding, multiple sportsmen regarding
Proportion thresholding, multiple referees proportion thresholding, multiple forbidden zone regions institute in the video frame in the video frame in frequency frame
Accounting example thresholding, multiple middle field areas proportion thresholding, multiple corner-kick regions proportion in the video frame in the video frame
Thresholding and frame exercise intensity thresholding.
Preferably, in above-mentioned technical proposal, judge the ratio between threshold value for feature based information and multiple video frame
Compared with relationship, determine that the specific unit of the classification of excellent event is additionally configured to:If corner-kick region proportion in the video frame
More than the first corner-kick region proportion thresholding in the video frame, and proportion is less than field one in the video frame in place
Excellent event is then judged as corner-kick event by proportion thresholding in the video frame;And if referee institute in the video frame
Accounting example is more than the first referee proportion thresholding in the video frame, and frame exercise intensity is more than frame exercise intensity thresholding,
Excellent event is then judged as foul event.
Preferably, in above-mentioned technical proposal, judge the ratio between threshold value for feature based information and multiple video frame
Compared with relationship, determine that the specific unit of the classification of excellent event is additionally configured to:If middle field areas proportion in the video frame
Field areas proportion thresholding in the video frame in less than first, and proportion is more than first in the video frame in forbidden zone region
Forbidden zone region proportion thresholding in the video frame, and proportion is more than sportsman institute in the video frame to sportsman in the video frame
Accounting example thresholding, then be judged as penalty kick event by excellent event.
Compared with prior art, the present invention has the advantages that:Current video method for catching is opened from video
Begin to terminate up to video, capture analysis is carried out to video frame at any time.In this way to a head up to 90 minutes or more foots
Ball match video is analyzed, and every game may need the frame number analyzed to be up to 130,000 or more, and for each video
Frame carries out the processing of a series of complex such as image procossing, transformation, edge detection and analysis, statistics again.This for computer and
Speech will be very big calculation amount, if corporate user wants to analyze football video with the method for the prior art, due to
The problem of calculation amount, each computer same time can only handle 1-3 video, if user is this ultra-large type of central station
Entity, then it wishes that the video handled may be thousands of, this means that if it is desired to handle all videos in a short time,
It so just needs to put into substantial contribution outfit thousands of computers.It is this input even for for central station be also be difficult to receive
's.In order to solve problems in the prior art, the present invention proposes a kind of method reducing Computing amount, and computer is not right
Each video frame is handled, and the brightness change of each video is recorded simply by sensor, is then judged by computer
Whether brightness change is more than thresholding, and only when brightness change is more than thresholding, just beginning video frame is handled, and the processing of this process
Amount can be ignored.The method of the present invention fundamentally solves the excessive defect of prior art calculation amount.
Description of the drawings
Fig. 1 is the flow chart of video method for catching according to the present invention.
Specific implementation mode
The illustrative embodiments of the disclosure are more fully described below with reference to accompanying drawings.Although showing this public affairs in attached drawing
The illustrative embodiments opened, it being understood, however, that may be realized in various forms the disclosure without the reality that should be illustrated here
The mode of applying is limited.It is to be able to be best understood from the disclosure on the contrary, providing these embodiments, and can be by this public affairs
The range opened completely is communicated to those skilled in the art.
Embodiment 1
Fig. 1 is the flow chart of video method for catching according to the present invention.As shown in Figure 1, according to preferred implementation side of the invention
The video method for catching of formula includes:Step 101:Capture the first brightness change of football video;Step 102:When the first brightness change
When more than preset first threshold value, start to extract one or more video frame after the first brightness change;Step
103:Image procossing is carried out to video frame, obtains the video frame after image procossing;Step 104:After image procossing
Video frame obtains the characteristic information in one or more video frame;Step 105:It presets multiple video frame and judges threshold value;
Step 106:Feature based information and multiple video frame judge the comparison between threshold value, determine the classification of excellent event;
Step 107:The video after the first brightness change is recorded, and is captured second bright in the video after the first brightness change of record
Degree variation;And step 108:When the second brightness change is more than preset second threshold value, stop recording video.
Embodiment 2
In a preferred embodiment, the characteristic information in one or more video frame includes:Place is shared in the video frame
Ratio, sportsman proportion, referee proportion, forbidden zone region institute's accounting in the video frame in the video frame in the video frame
Example, middle field areas proportion, corner-kick region proportion and frame exercise intensity in the video frame in the video frame.Video frame
Judge that threshold value is generated via the machine learning method of supervised learning, wherein video frame judges that threshold value includes:It is multiple
Place in the video frame proportion thresholding, multiple sportsmen in the video frame proportion thresholding, multiple referees in video frame
Proportion thresholding, multiple middle field areas are shared in the video frame in the video frame for middle proportion thresholding, multiple forbidden zone regions
Ratio thresholding, multiple corner-kick regions proportion thresholding and frame exercise intensity thresholding in the video frame.
Embodiment 3
In an additional preferred embodiment, feature based information and multiple video frame judge that the comparison between threshold value is closed
System, determines that the classification of excellent event specifically includes:If proportion is more than the first corner-kick region in the video frame in corner-kick region
Proportion thresholding in the video frame, and proportion is less than field one institute's accounting in the video frame in the video frame in place
Example thresholding, then be judged as corner-kick event by excellent event;If proportion is more than the first referee to referee in the video frame
Proportion thresholding in the video frame, and frame exercise intensity is more than frame exercise intensity thresholding, then by the excellent event criminal of being judged as
Rule event.Feature based information and multiple video frame judge the comparison between threshold value, determine the classification tool of excellent event
Body further includes:If middle field areas field areas proportion door in the video frame during proportion is less than first in the video frame
Limit, and proportion is more than the first forbidden zone region proportion thresholding in the video frame in the video frame in forbidden zone region, and
Proportion is more than sportsman's proportion thresholding in the video frame to sportsman in the video frame, then excellent event is judged as penalty kick thing
Part.
Embodiment 4
The present invention also provides a kind of football featured videos to capture system comprising:It is bright for capturing football video first
Spend the unit of variation;For when the first brightness change is more than preset first threshold value, starting to extract the first brightness change
The unit of one or more video frame after change;For carrying out image procossing to video frame, regarding after image procossing is obtained
The unit of frequency frame;For based on the video frame after image procossing, obtaining the list of the characteristic information in one or more video frame
Member;The unit of threshold value is judged for presetting multiple video frame;Judge door for feature based information and multiple video frame
Comparison between limit value determines the unit of the classification of excellent event;For recording the video after the first brightness change, and
Capture the unit of the second brightness change in the video after recording the first brightness change;And it is big for working as the second brightness change
When preset second threshold value, the unit of stop recording video.
Embodiment 5
In a preferred embodiment, the characteristic information in one or more video frame includes:Place is shared in the video frame
Ratio, sportsman proportion, referee proportion, forbidden zone region institute's accounting in the video frame in the video frame in the video frame
Example, middle field areas proportion, corner-kick region proportion and frame exercise intensity in the video frame in the video frame.Video frame
Judge that threshold value is generated via the machine learning method of supervised learning, wherein video frame judges that threshold value includes:It is multiple
Place in the video frame proportion thresholding, multiple sportsmen in the video frame proportion thresholding, multiple referees in video frame
Proportion thresholding, multiple middle field areas are shared in the video frame in the video frame for middle proportion thresholding, multiple forbidden zone regions
Ratio thresholding, multiple corner-kick regions proportion thresholding and frame exercise intensity thresholding in the video frame.
Embodiment 6
In an additional preferred embodiment, it is used for feature based information and multiple video frame judges the comparison between threshold value
Relationship determines that the specific unit of the classification of excellent event is additionally configured to:If proportion is big in the video frame in corner-kick region
In the first corner-kick region proportion thresholding in the video frame, and proportion exists less than field one in the video frame in place
Excellent event is then judged as corner-kick event by proportion thresholding in video frame;If referee's proportion in the video frame
More than the first referee proportion thresholding in the video frame, and frame exercise intensity is more than frame exercise intensity thresholding, then will be smart
Color event is judged as foul event.Judge the comparison between threshold value for feature based information and multiple video frame, really
The specific unit of classification of fixed excellent event is additionally configured to:If proportion is less than in first middle field areas in the video frame
Field areas proportion thresholding in the video frame, and proportion exists more than the first forbidden zone region in the video frame in forbidden zone region
Proportion thresholding in video frame, and proportion is more than sportsman's proportion door in the video frame to sportsman in the video frame
Limit, then be judged as penalty kick event by excellent event.
Embodiment 7
By the various elements including block, module, component, circuit, step, process, algorithm etc. in specific embodiment party
It is described in formula and device and method is shown in the accompanying drawings.Electronic hardware, computer software or its any group can be used
It closes and comes individually or realize these elements or its any part in combination with other elements and/or function.These elements are implemented as
The design constraint that hardware or software depend on specific application and applies to whole system.In one aspect, as made herein
Term " component " can be one of component of composition system and can be divided into other assemblies.
For example, any portion of element or element can be realized with " system " including one or more processors
Point or element arbitrary combination.Processor may include general processor, digital signal processor (DSP), special integrated electricity
It is road (ASIC), field programmable gate array (FPGA) or other programmable logic components, discrete gate or transistor logic, discrete hard
Part component, or any combination thereof, or be designed as executing any other suitable component of function described herein.General processor
Can be microprocessor, but alternatively, processor can be any traditional processor, controller, microcontroller or shape
State machine.Processor is also implemented as the combination of computation module, for example, the combination of DSP and microprocessor, multi-microprocessor,
One or more microprocessors combination DSP or any other such configuration.
One or more of system processor can execute software.Software should be broadly interpreted as indicating instruction, refer to
Enable collection, code, code segment, program code, program, subprogram, software module, application program, software application, software package,
Routine, subroutine, object, executable program, the thread of execution, process, function etc., no matter be known as software, firmware, in
Between part, microcode, hardware description language or other.The software may reside within temporary or non-transitory computer-readable medium
On.As an example, non-transitory computer-readable medium may include magnetic storage facilities (for example, hard disk, floppy disk, magnetic stripe), light
Disk (for example, compact disk (CD), digital versatile disc (DVD)), smart card, flash memory device (for example, card, stick, key drive), with
Machine accesses memory (RAM), static state RAM (SRAM), dynamic ram (DRAM), synchronous dynamic ram (SDRAM);Double Data Rate
RAM (DDRAM), read-only memory (ROM), programming ROM (PROM), erasable PROM (EPROM), electric erasable PROM
(EEPROM), general register or any other suitable non-state medium for storing software.
The foregoing is only a preferred embodiment of the present invention, but scope of protection of the present invention is not limited thereto,
Any one skilled in the art in the technical scope disclosed by the present invention, the change or replacement that can be readily occurred in,
It should be covered by the protection scope of the present invention.Therefore, protection scope of the present invention answers the protection model with claim
Subject to enclosing.
Claims (10)
1. a kind of football featured videos method for catching, it is characterised in that:The football featured videos method for catching includes following step
Suddenly:
Capture the first brightness change of football video;
When first brightness change is more than preset first threshold value, start to extract one after the first brightness change
A or multiple video frame;
Image procossing is carried out to the video frame, obtains the video frame after image procossing;
Based on the video frame after described image processing, the characteristic information in one or more of video frame is obtained;
It presets multiple video frame and judges threshold value;
Judge the comparison between threshold value based on the characteristic information and the multiple video frame, determines the class of excellent event
Not;
Record the video after first brightness change, and capture in the video after recording first brightness change the
Two brightness changes;And
When second brightness change is more than preset second threshold value, stop recording video.
2. football featured videos method for catching as described in claim 1, it is characterised in that:In one or more of video frame
Characteristic information include:Proportion, referee be in the video frame in the video frame by proportion, sportsman in the video frame in place
Proportion, forbidden zone region in the video frame proportion, middle field areas in the video frame proportion, corner-kick region in video
Proportion and frame exercise intensity in frame.
3. football featured videos method for catching as claimed in claim 2, it is characterised in that:The video frame judges that threshold value is
It is generated via the machine learning method of supervised learning, wherein the video frame judges that threshold value includes:Multiple places regarding
Proportion thresholding, multiple sportsmen proportion thresholding, multiple referees institute's accounting in the video frame in the video frame in frequency frame
Example thresholding, multiple forbidden zone regions in the video frame proportion thresholding, multiple middle field areas in the video frame proportion thresholding,
Multiple corner-kick regions proportion thresholding and frame exercise intensity thresholding in the video frame.
4. football featured videos method for catching as claimed in claim 3, it is characterised in that:Based on the characteristic information with it is described
Multiple video frame judge the comparison between threshold value, determine that the classification of excellent event specifically includes:
If proportion is more than the first corner-kick region proportion thresholding in the video frame in the video frame in the corner-kick region,
And proportion is less than field one proportion thresholding in the video frame in the video frame in the place, then by excellent event
It is judged as corner-kick event;And
If proportion is more than the first referee proportion thresholding in the video frame to the referee in the video frame, and
The frame exercise intensity is more than the frame exercise intensity thresholding, then excellent event is judged as foul event.
5. football featured videos method for catching as claimed in claim 4, it is characterised in that:Based on the characteristic information with it is described
Multiple video frame judge the comparison between threshold value, determine that the classification of excellent event further includes specifically:If the midfield
Region in the video frame proportion be less than first in field areas proportion thresholding, and the forbidden zone region in the video frame
Proportion is more than the first forbidden zone region proportion thresholding in the video frame in the video frame, and the sportsman is in video frame
Middle proportion is more than sportsman proportion thresholding in the video frame, then excellent event is judged as penalty kick event.
6. a kind of football featured videos capture system, it is characterised in that:The football featured videos capture system:
Unit for capturing the first brightness change of football video;
For when first brightness change be more than preset first threshold value when, start extract the first brightness change after
One or more video frame unit;
For carrying out image procossing to the video frame, the unit of the video frame after image procossing is obtained;
For the video frame after being handled based on described image, the list of the characteristic information in one or more of video frame is obtained
Member;
The unit of threshold value is judged for presetting multiple video frame;
For judging the comparison between threshold value based on the characteristic information and the multiple video frame, excellent event is determined
Classification unit;
For recording the video after first brightness change, and capture in the video after recording first brightness change
The second brightness change unit;And
For when second brightness change be more than preset second threshold value when, the unit of stop recording video.
7. football featured videos method for catching as claimed in claim 6, it is characterised in that:In one or more of video frame
Characteristic information include:Proportion, referee be in the video frame in the video frame by proportion, sportsman in the video frame in place
Proportion, forbidden zone region in the video frame proportion, middle field areas in the video frame proportion, corner-kick region in video
Proportion and frame exercise intensity in frame.
8. football featured videos method for catching as claimed in claim 7, it is characterised in that:The video frame judges that threshold value is
It is generated via the machine learning method of supervised learning, wherein the video frame judges that threshold value includes:Multiple places regarding
Proportion thresholding, multiple sportsmen proportion thresholding, multiple referees institute's accounting in the video frame in the video frame in frequency frame
Example thresholding, multiple forbidden zone regions in the video frame proportion thresholding, multiple middle field areas in the video frame proportion thresholding,
Multiple corner-kick regions proportion thresholding and frame exercise intensity thresholding in the video frame.
9. football featured videos method for catching as claimed in claim 8, it is characterised in that:For be based on the characteristic information with
The multiple video frame judges the comparison between threshold value, determines that the specific unit of the classification of excellent event is also configured
For:
If proportion is more than the first corner-kick region proportion thresholding in the video frame in the video frame in the corner-kick region,
And proportion is less than field one proportion thresholding in the video frame in the video frame in the place, then by excellent event
It is judged as corner-kick event;And
If proportion is more than the first referee proportion thresholding in the video frame to the referee in the video frame, and
The frame exercise intensity is more than the frame exercise intensity thresholding, then excellent event is judged as foul event.
10. football featured videos method for catching as claimed in claim 9, it is characterised in that:For being based on the characteristic information
Judge the comparison between threshold value with the multiple video frame, determines that the specific unit of the classification of excellent event is also configured
For:If middle field areas field areas proportion thresholding in the video frame during proportion is less than first in the video frame,
And proportion is more than the first forbidden zone region proportion thresholding in the video frame in the video frame in the forbidden zone region, and
Proportion is more than sportsman proportion thresholding in the video frame to the sportsman in the video frame, then judges excellent event
For penalty kick event.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810318626.5A CN108509931B (en) | 2018-04-11 | 2018-04-11 | Football wonderful video capturing method and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810318626.5A CN108509931B (en) | 2018-04-11 | 2018-04-11 | Football wonderful video capturing method and system |
Publications (2)
Publication Number | Publication Date |
---|---|
CN108509931A true CN108509931A (en) | 2018-09-07 |
CN108509931B CN108509931B (en) | 2021-06-01 |
Family
ID=63381337
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810318626.5A Active CN108509931B (en) | 2018-04-11 | 2018-04-11 | Football wonderful video capturing method and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108509931B (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110688498A (en) * | 2019-09-27 | 2020-01-14 | 北京奇艺世纪科技有限公司 | Information processing method and device, electronic equipment and storage medium |
CN111001149A (en) * | 2019-12-10 | 2020-04-14 | 苏宁智能终端有限公司 | Position positioning method and system based on video playback |
CN111510668A (en) * | 2019-01-30 | 2020-08-07 | 原盛科技股份有限公司 | Motion detection method for motion sensor |
CN111787338A (en) * | 2020-03-09 | 2020-10-16 | 北京理工大学 | Auxiliary design method for sports event live broadcast scheme |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1645357A (en) * | 2004-01-20 | 2005-07-27 | 日本先锋公司 | Apparatus, method and computer product for recognizing video contents and for video recording |
CN1738433A (en) * | 2004-03-05 | 2006-02-22 | 三星电子株式会社 | Method that video lens changes in the detection moving image and the equipment that uses this method |
CN101420579A (en) * | 2007-10-22 | 2009-04-29 | 皇家飞利浦电子股份有限公司 | Method, apparatus and system for detecting exciting part |
CN103262169A (en) * | 2010-12-14 | 2013-08-21 | 高通股份有限公司 | Video editing device for deleting failed frames |
US20140270500A1 (en) * | 2013-03-15 | 2014-09-18 | General Instrument Corporation | Playfield detection and shot classification in sports video |
CN105678732A (en) * | 2014-11-18 | 2016-06-15 | 北京数码视讯科技股份有限公司 | Penalty kick, corner kick and free kick key frame detection method and device |
US9752875B2 (en) * | 2011-09-23 | 2017-09-05 | Creatz Inc. | Virtual sport system for acquiring good image of ball by controlling camera according to surrounding brightness |
CN107360474A (en) * | 2017-08-18 | 2017-11-17 | 电子科技大学 | Video sluggishness frame detection method based on Local textural feature and global brightness |
-
2018
- 2018-04-11 CN CN201810318626.5A patent/CN108509931B/en active Active
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1645357A (en) * | 2004-01-20 | 2005-07-27 | 日本先锋公司 | Apparatus, method and computer product for recognizing video contents and for video recording |
CN1738433A (en) * | 2004-03-05 | 2006-02-22 | 三星电子株式会社 | Method that video lens changes in the detection moving image and the equipment that uses this method |
CN101420579A (en) * | 2007-10-22 | 2009-04-29 | 皇家飞利浦电子股份有限公司 | Method, apparatus and system for detecting exciting part |
CN103262169A (en) * | 2010-12-14 | 2013-08-21 | 高通股份有限公司 | Video editing device for deleting failed frames |
US9752875B2 (en) * | 2011-09-23 | 2017-09-05 | Creatz Inc. | Virtual sport system for acquiring good image of ball by controlling camera according to surrounding brightness |
US20140270500A1 (en) * | 2013-03-15 | 2014-09-18 | General Instrument Corporation | Playfield detection and shot classification in sports video |
CN105678732A (en) * | 2014-11-18 | 2016-06-15 | 北京数码视讯科技股份有限公司 | Penalty kick, corner kick and free kick key frame detection method and device |
CN107360474A (en) * | 2017-08-18 | 2017-11-17 | 电子科技大学 | Video sluggishness frame detection method based on Local textural feature and global brightness |
Non-Patent Citations (5)
Title |
---|
BO YIN 等: "Global Motion Video Segmentation Based on the Change of Integral Brightness in Rows (Columns)", 《2012 5TH INTERNATIONAL CONGRESS ON IMAGE AND SIGNAL PROCESSING》 * |
J. ASSFULG 等: "Automatic extraction and annotation of soccer video highlights", 《PROCEEDINGS 2003 INTERNATIONAL CONFERENCE ON IMAGE PROCESSING》 * |
张晓丽 等: "网球视频中慢镜头的自适应阈值探测法", 《计算机工程与科学》 * |
文军 等: "足球比赛视频中的精彩镜头分析方法", 《计算机工程》 * |
陈剑赟: "体育视频语义内容分析技术研究", 《中国优秀博硕士学位论文全文数据库(博士) 信息科技辑》 * |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111510668A (en) * | 2019-01-30 | 2020-08-07 | 原盛科技股份有限公司 | Motion detection method for motion sensor |
CN111510668B (en) * | 2019-01-30 | 2021-10-19 | 原相科技股份有限公司 | Motion detection method for motion sensor |
CN113992887A (en) * | 2019-01-30 | 2022-01-28 | 原相科技股份有限公司 | Motion detection method for motion sensor |
US11336869B2 (en) | 2019-01-30 | 2022-05-17 | Pixart Imaging Inc. | Motion detection methods and motion sensors capable of more accurately detecting true motion event |
CN113992887B (en) * | 2019-01-30 | 2024-05-17 | 原相科技股份有限公司 | Motion detection method for motion sensor |
CN110688498A (en) * | 2019-09-27 | 2020-01-14 | 北京奇艺世纪科技有限公司 | Information processing method and device, electronic equipment and storage medium |
CN110688498B (en) * | 2019-09-27 | 2022-07-22 | 北京奇艺世纪科技有限公司 | Information processing method and device, electronic equipment and storage medium |
CN111001149A (en) * | 2019-12-10 | 2020-04-14 | 苏宁智能终端有限公司 | Position positioning method and system based on video playback |
CN111001149B (en) * | 2019-12-10 | 2021-06-04 | 苏宁智能终端有限公司 | Position positioning method and system based on video playback |
CN111787338A (en) * | 2020-03-09 | 2020-10-16 | 北京理工大学 | Auxiliary design method for sports event live broadcast scheme |
Also Published As
Publication number | Publication date |
---|---|
CN108509931B (en) | 2021-06-01 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US11556743B2 (en) | Learning highlights using event detection | |
Giancola et al. | Soccernet: A scalable dataset for action spotting in soccer videos | |
CN108509931A (en) | Football featured videos method for catching and system | |
Yao et al. | Highlight detection with pairwise deep ranking for first-person video summarization | |
Zhu et al. | Event tactic analysis based on broadcast sports video | |
Merler et al. | Automatic curation of sports highlights using multimodal excitement features | |
Lanagan et al. | Using Twitter to detect and tag important events in sports media | |
Xu et al. | Using webcast text for semantic event detection in broadcast sports video | |
CN104021140B (en) | A kind of processing method and processing device of Internet video | |
CN103200463A (en) | Method and device for generating video summary | |
CN101894125A (en) | Content-based video classification method | |
Jiang et al. | A new method to segment playfield and its applications in match analysis in sports video | |
Merler et al. | Automatic curation of golf highlights using multimodal excitement features | |
Zhou et al. | Actionhub: a large-scale action video description dataset for zero-shot action recognition | |
CN108647789A (en) | A kind of intelligent body deep value function learning method based on the sampling of state distributed awareness | |
Tong et al. | A unified framework for semantic shot representation of sports video | |
Chu et al. | Explicit semantic events detection and development of realistic applications for broadcasting baseball videos | |
Chen | [Retracted] Semantic Analysis of Multimodal Sports Video Based on the Support Vector Machine and Mobile Edge Computing | |
Choroś | Automatic playing field detection and dominant color extraction in sports video shots of different view types | |
Faulkner et al. | Tenniset: a dataset for dense fine-grained event recognition, localisation and description | |
Narwal et al. | A novel multi-modal neural network approach for dynamic and generic sports video summarization | |
Godi et al. | Indirect match highlights detection with deep convolutional neural networks | |
Choroś et al. | Content-based scene detection and analysis method for automatic classification of TV sports news | |
Chen et al. | Event mining and indexing in basketball video | |
Zhang et al. | Unsupervised sports video scene clustering and its applications to story units detection |
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 | ||
TR01 | Transfer of patent right | ||
TR01 | Transfer of patent right |
Effective date of registration: 20231011 Address after: 1st Floor, Unit 3, Building 9, No. 1, Huazhong Park Road, No. 258, South Section of Labor Road, Xiangyang Community, Hongqi District, Xinxiang City, Henan Province, 453000 Patentee after: Henan Zebra Sports Service Co.,Ltd. Address before: No. 699, plain road, Xinxiang, Henan, Henan Patentee before: HENAN INSTITUTE OF TECHNOLOGY |