CN102819749A - Automatic identification system and method for offside of football based on video analysis - Google Patents
Automatic identification system and method for offside of football based on video analysis Download PDFInfo
- Publication number
- CN102819749A CN102819749A CN2012102538081A CN201210253808A CN102819749A CN 102819749 A CN102819749 A CN 102819749A CN 2012102538081 A CN2012102538081 A CN 2012102538081A CN 201210253808 A CN201210253808 A CN 201210253808A CN 102819749 A CN102819749 A CN 102819749A
- Authority
- CN
- China
- Prior art keywords
- football
- image
- offside
- court
- video
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Landscapes
- Image Analysis (AREA)
Abstract
The invention discloses an automatic identification system and an automatic identification method for offside of a football based on video analysis. The method is characterized by comprising the steps of: collecting an image in a video, extracting a football field and detecting athletes and the football; extracting characteristic lines of the football field and rebuilding a coordinate of a plane of the football field; and finishing identification of the offside in the football match video automatically. The automatic identification system and the automatic identification method disclosed by the invention identify the offside behaviors through image processing of a computer, have the advantages that the identification speed is quick and the result is accurate, the workload and the error of an assistant referee can be reduced to a large extent, artificial factors for controlling the match are greatly removed and the reliability of penalties is improved. The designed offside detecting algorithm is based on plane coordinate scores of the athlete, so that the plane coordinates of the football field can be recovered by shooting with a single camera and solving a projection matrix, and further the lengthy computations on analysis of a plurality of cameras can be saved. According to the method, the offside condition of international football matches can be monitored in a better way, and the purposes of assisting the penalties and reducing the workload and error of the referee are realized.
Description
Technical field
The invention belongs to the Motion Technology field, relate in particular to offside automatic judgement system of a kind of football and method based on video analysis.
Background technology
In football match, whether offsidely mainly judge by the linesman.On to offside differentiation be with pass moment be foundation, be not to judge that time that football lands.Artificial judge receives the restriction of self notice, reaction capacity, physical function, individual quality each side; Only depending on artificial judge not accomplish objective and fair to offside judgement, is very necessary so utilize computer technology to design the offside algorithm of corresponding automatic differentiation.
At present, most of in the world sports video frequency content analytic system concentrates on tennis, basketball and baseball field, and the color identification that more personnel hanker after analyzing intelligent robot aspect football is implemented with strategy.Domestic main research focus concentrates on the extraction of video semanteme object, comprises detection, ball and the sportsman's in court detection and the three-dimensional reconstruction of scene, and these technology all concentrate on video analysis and are not embodied in the penalty match.
Summary of the invention
The purpose of the embodiment of the invention is to provide offside automatic judgement system of a kind of football based on video analysis and method; Be intended to solve most of in the world at present sports video frequency content analytic system and concentrate on tennis, basketball and baseball field, and the color identification that more personnel hanker after analyzing intelligent robot aspect football is implemented with strategy.Domestic main research focus concentrates on the extraction of video semanteme object, comprises detection, ball and the sportsman's in court detection and the three-dimensional reconstruction of scene, and these technology all concentrate on video analysis and are not embodied in the problem in the penalty match.
The embodiment of the invention is achieved in that a kind of method of the offside automatic differentiation of football based on video analysis, and this method comprises:
At first gather the image in the video, extract the pitch and carry out the detection of sportsman and football;
Extract the court characteristic curve, coordinate is carried out on the plane, court rebuild;
Accomplish offside automatic differentiation in the section of football match video.
Further, gather video image, extract the pitch and carry out the sportsman following with the implementation method of football detection:
Through the pitch specific algorithm that extracts, obtain the place image of football;
Through regional analysis the zone beyond the court is removed, under this background model, carry out sportsman's extraction;
Method with similar sportsman extracts is extracted the football image.
Further, the method for extracting with similar sportsman is extracted the implementation method of football image:
At first design Gauss's template of a 5*5, draw an evaluation function that football is estimated, extract the football candidate region.Be defined as:
R＝A(i，j)/B(i，j)+k
Wherein (i is with Gauss's template image to be sued for peace j) to A, and its value shows that more greatly this target might be a football; (i j) is defined as the goodness of fit evaluation function of football to B, serves as that size is asked variance to each pixel of image with Gauss's template, and difference shows that more greatly target is not football more; K is a constant term.Target through in this football evaluation function evaluate image is a football.Last algorithm carries out normalization to image.
Further, the implementation method that coordinate is rebuild is carried out on the plane, court:
Uncalibrated image to collecting carries out pre-service, utilizes court Detection Techniques back projection to extract the pitch, and disturb in other places, filtering court;
Utilize the Canny rim detection, strengthen boundary line, forbidden zone and these court characteristic curves of sideline, court in the image through image processing methods such as expansion, closures.
Utilize Hough change detection straight line, obtain the intersecting point coordinate that straight-line equation is found the solution the boundary line, be the image coordinate of court unique point.
Utilize the camera marking method of line style camera model to find the solution projection matrix.
Further, the implementation method of offside automatic differentiation comprises:
Information in each moment competition field is preserved, and information comprises: 22 sportsmen's of two teams position, the position and the ownership of ball;
According to the definition combination court areal model of International Football Union, obtain judgment rule to offside position:
Suppose blue side team member attack left, red is the defender, and greater than center line x coordinate, then this team member is not in offside position, promptly offside will the generation at opponents' half as if ordering array medium blue side team member coordinate; If there are two or more defenders the blue side team member front of attack in the ordering array, then this team member is not in offside position; If attacker's coordinate of the most forward sportsman equates that with two above defence members' coordinate then this team member is not in offside position yet; On position of Player of attacker, be in offside position,, comprise the attack or the shooting that do not have " being involved in " one's own side, do not have the interfering with an opponent goalkeeper if do not obtain interests, then not very offside.
Based on above-mentioned offside rule and algorithm, use the model of setting up, the programming of being open to the custom realizes offside detection algorithm.
Further, the implementation method of the extraction in place, court is following:
Read in video image, choose key frame, the RGB color space conversion is become the HSV model;
Extract the H component of image, obtain the histogram of H component;
In histogram, seek the position of peak point, the value of its peak point is M
1
Around peak point, inquire about numerical value greater than k*M
1Pixel, k is a scale factor, calculates this part, and this part is removed from histogram, then seeks next peak point and carries out similar operation;
These peak values of removing are partly compared, and the vector of getting largest portion carries out back projection's conversion, and rebuilding with RGB is the image of color model, has finally obtained the place image of football.
Further, the method that the sportsman extracts, this method comprises:
Read in video image, the operation court is detected and the algorithm that extracts, and obtains behind the pitch its binaryzation;
Binary image to the pitch carries out the morphology processing, and noise is eliminated in closed operation, and opening operation extracts the court;
Utilize the method for regional analysis that zone, non-court is removed, bianry image and original image that the court that obtains is regional multiply each other, and obtain the RGB image in zone, court;
The image in the figure image subtraction Performance Area territory that the court is regional;
Remove non-sportsman zone, the result who obtains can contain some non-sportsmen zones, establish the length of holding in the zone and wide be respectively H and W, the number of pixels in the zone is S, if satisfy H/W＞5 or H/W＜0.5 and S/ (H*W)＜0.3, then should the deletion zone; For sportsman's occlusion issue, set each sportsman's parameter W (width), H (highly); S (sportsman's area pixel number), setting threshold T is when S then is a noise during less than certain value; Remove, S then blocks during greater than certain value, and occlusion area is carried out level and vertical segmentation.
Another purpose of the embodiment of the invention is to provide a kind of football based on video analysis offside automatic judgement system, it is characterized in that this judgement system comprises:
Video camera is used to take the video of football match;
Main control computer is used for receiving the video information that camera acquisition arrives through data connecting line;
Further; Main control computer is provided with memory module and image information processing module; The scene and the offside differentiation result of the video that this memory module is used for transmitting video camera store; This image information processing module has been accomplished the detection to court line, football and sportsman, and coordinate is carried out in whole court rebuild, and carries out offside position judgement and the judgement of offside participation sense of attack through the offside automatic differentiation algorithm of football then.
The present invention is to be the image source with the section of football match video, and image-pickup method is simply effective, is easy to real-time processing; Carry out Flame Image Process by computing machine and judge offside behavior, speed is fast, the result is accurate, has largely alleviated linesman's workload and error, and has got rid of the factor of artificial control match greatly, has improved penalty result's confidence level; Image has been transformed into the HSV spatial model by RGB, has more met the mode of people's description and explain color, and the HSV model has the advantage of separating monochrome information and colouring information; The offside detection algorithm of design is based on sportsman's planimetric coordinates branch, finds the solution the planimetric coordinates that projection matrix just can recover the court so utilize single camera to take, and has saved the miscellaneous calculating that a plurality of video cameras are analyzed.
The method can better be monitored the offside situation in the international soccer match, reaches the purpose of assisting penalty, reducing judge's workload and error.
Description of drawings
Fig. 1 is the offside automatic judgement system of the football based on video analysis that provides of the embodiment of the invention and the process flow diagram of method;
Fig. 2 is the collection video image that the embodiment of the invention provides, and extracts the pitch and carries out the sportsman and the method flow diagram of football detection;
Fig. 3 be the embodiment of the invention provide the method flow diagram that coordinate is rebuild is carried out on the plane, court;
Fig. 4 is the method flow diagram of the offside automatic differentiation that provides of the embodiment of the invention;
Fig. 5 is the method for distilling process flow diagram in the place, court that provides of the embodiment of the invention;
Fig. 6 is the sportsman's that provides of the embodiment of the invention a method for distilling process flow diagram.
Embodiment
In order to make the object of the invention, technical scheme and advantage clearer,, the present invention is further elaborated below in conjunction with accompanying drawing and embodiment.Should be appreciated that specific embodiment described herein only in order to explanation the present invention, and be not used in qualification the present invention.
The method that Fig. 1 shows that case study on implementation of the present invention provides based on the offside automatic differentiation of football of video analysis, this method comprises:
In step S101, at first gather the image in the video, extract the pitch and carry out the detection of sportsman and football.
In step S102, extract the court characteristic curve, coordinate is carried out on the plane, court rebuild.
In step S103, accomplish offside automatic differentiation in the section of football match video.
Fig. 2 has gone out the collection video image that case study on implementation of the present invention provides, and extracts the pitch and carries out the sportsman and the method for football detection, and this method comprises:
In step S1011,, obtain the place image of football through the pitch specific algorithm that extracts.
In step S1012, through regional analysis the zone beyond the court is removed, under this background model, carry out sportsman's extraction.
In step S1013, extract the football image with the method that similar sportsman extracts.
At first design Gauss's template of a 5*5, draw an evaluation function that football is estimated, extract the football candidate region.Be defined as:
R＝A(i，j)/B(i，j)+k
Wherein (i is with Gauss's template image to be sued for peace j) to A, and its value shows that more greatly this target might be a football; (i j) is defined as the goodness of fit evaluation function of football to B, serves as that size is asked variance to each pixel of image with Gauss's template, and difference shows that more greatly target is not football more; K is a constant term.Target through in this football evaluation function evaluate image is a football.Last algorithm carries out normalization to image.
What Fig. 3 showed that case study on implementation of the present invention provides carries out the method that coordinate is rebuild to the plane, court, and this method comprises:
In step S1021, the uncalibrated image that collects is carried out pre-service, utilize court Detection Techniques back projection to extract the pitch, disturb in other places, filtering court.
In step S1022, utilize the Canny rim detection, strengthen boundary line, forbidden zone and these court characteristic curves of sideline, court in the image through image processing methods such as expansion, closures.
In step S1023, utilize Hough change detection straight line, obtain the intersecting point coordinate that straight-line equation is found the solution the boundary line, be the image coordinate of court unique point.
In step S1024, utilize the camera marking method of line style camera model to find the solution projection matrix.Fig. 4 shows the method for the offside automatic differentiation that case study on implementation of the present invention provides, and this method comprises:
In step S1031, the information in each moment competition field to be preserved, information comprises: 22 sportsmen's of two teams position, the position and the ownership of ball.
In step S1032,, obtain judgment rule according to the definition combination court areal model of International Football Union to offside position.
Suppose blue side team member attack left, red is the defender, and greater than center line x coordinate, then this team member is not in offside position, promptly offside will the generation at opponents' half as if ordering array medium blue side team member coordinate; If there are two or more defenders the blue side team member front of attack in the ordering array, then this team member is not in offside position; If attacker's coordinate of the most forward sportsman equates that with two above defence members' coordinate then this team member is not in offside position yet; On position of Player of attacker, be in offside position,, comprise the attack or the shooting that do not have " being involved in " one's own side, do not have the interfering with an opponent goalkeeper if do not obtain interests, then not very offside.
In step S1033, based on above-mentioned offside rule and algorithm, use the model of setting up, the programming of being open to the custom realizes offside detection algorithm.
Fig. 5 shows the method for distilling in the place, court that case study on implementation of the present invention provides, and this method comprises:
In step S10111, read in video image, choose key frame, the RGB color space conversion is become the HSV model.
In step S10112, extract the H component of image, obtain the histogram of H component.
In step S10113, in histogram, seek the position of peak point, the value of its peak point is M
1.
In step S10114, around peak point, inquire about numerical value greater than k*M
1Pixel (k is a scale factor), calculate this part, this part is removed from histogram, then seek next peak point and carry out similar operation.
In step S10115, these peak values of removing are partly compared, the vector of getting largest portion carries out back projection's conversion, and rebuilding with RGB is the image of color model, has finally obtained the place image of football.
The method that the sportsman that Fig. 6 shows case study on implementation of the present invention to be provided extracts, this method comprises:
In step S10121, read in video image, the operation court is detected and the algorithm that extracts, and obtains behind the pitch its binaryzation.
In step S10122, the binary image of pitch to be carried out morphology handle, noise is eliminated in closed operation, and opening operation extracts the court.
In step S10123, utilize the method for regional analysis that zone, non-court is removed, bianry image and original image that the court that obtains is regional multiply each other, and obtain the RGB image in zone, court.
In step S10124, the image in the figure image subtraction Performance Area territory that the court is regional.
In step S10125, remove non-sportsman zone.
The result who obtains can contain some non-sportsmen zones, establish the length of holding in the zone and wide be respectively H and W, the number of pixels in the zone is S, if satisfy H/W＞5 or H/W＜0.5 and S/ (H*W)＜0.3, then should the deletion zone; For sportsman's occlusion issue, set each sportsman's parameter W (width), H (highly); S (sportsman's area pixel number), setting threshold T is when S then is a noise during less than certain value; Remove, S then blocks during greater than certain value, and occlusion area is carried out level and vertical segmentation.
Two important concept are arranged: offside position and offside during football is offside.In defender's half-court, when the attacker plays or touch ball in an instant, more near the opponents' goal line, and between he and opponents' goal line, defender team member's less than two man-hours are called this team member and are in offside position than ball in teammate.Except the scenario;
1. this team member is in our half-court;
2. have at least opposing players two people more to approach the other side's goal line (be any part of finger, trunk and pin than ball and the other side's the second last name sportsman more near goal line, in arm is not included in) than this team member because only arm preceding can not made a profit;
When the team member plays or touch ball in a flash, when teammate is in offside position, following behavior is arranged as if this team member, then be judged to offside:
1. interfering with play or interfering with an opponent;
2. thereby attempt is acquired an advantage from offside position and is got the ball attack.
Scenario, the team member should not be judged to offside:
1. the team member only is in offside position and is not involved in match, is involved in match and is meant that the sportsman who is on the offside position participates in attack and touches the football that the team member transmits, and perhaps makes the judge and thinks that significantly moving or the posture interfering with an opponent of misconduct arranged;
The team member directly receive goal kick, corner-kick or when out-of-bounds delivering the referee also need not to judge offside.
Regulation was judged with the moment in an instant that teammate passes the ball to the attacker; Rather than he is when receiving; For example the team member is in on-side position, and when teammate spread out of or kicks out of free kick to him, this team member went to the place ahead and also do not constitute offside when ball flies.
In sum, whether offside penalty is:
1. must take place at opponents' half;
2. the position of attacker, whether pass in an instant near opponents' goal, two of defender's less thaies between he and the goal end line (one or nobody are two of less thaies, no matter and this sportsman whether be goalkeeper);
3. even be in offside position on position of Player of attacker, if do not obtain interests, comprise the attack or the shooting that do not have " being involved in " one's own side, there is not the interfering with an opponent goalkeeper, then not very offside.
At first gather the image in the section of football match video, from football video, be partitioned into zone, non-lawn, find out football impact point in the multiple image, extract sportsman's impact point; Unique points such as place, court, goal are detected and extract, and disturb in other places, filtering court; Obtain the projection matrix of contact image coordinate system and Euclidean world coordinate system,, obtain football and sportsman's Euclidean world coordinates football and the coordinate substitution projection matrix of sportsman under image coordinate system; Preserve each moment 22 sportsman's of two teams position, the position and the ownership of ball;
The certain proportion convergent-divergent is carried out in actual court obtain the court two dimension and overlook model, square and triangle are represented indigo plant side and red team member respectively; Obtain sportsman's coordinate and store according to the court rule with the one-dimension array form; X coordinate figure according to the team member sorts, and x changes along with the variation of fixture; Carry out offside position judgement in the image according to rule; According to offside rule and algorithm, use the model of setting up at last, realize offside detection algorithm through programming.
Offside automatic judgement system of the football that the embodiment of the invention provides and method based on video analysis; At first gather the image in the section of football match video; From football video, be partitioned into zone, non-lawn, find out football impact point in the multiple image, extract sportsman's impact point; Unique points such as place, court, goal are detected and extract, and disturb in other places, filtering court; Obtain the projection matrix of contact image coordinate system and Euclidean world coordinate system,, obtain football and sportsman's Euclidean world coordinates football and the coordinate substitution projection matrix of sportsman under image coordinate system; Preserve each moment 22 sportsman's of two teams position, the position and the ownership of ball;
The certain proportion convergent-divergent is carried out in actual court obtain the court two dimension and overlook model, square and triangle are represented indigo plant side and red team member respectively; Obtain sportsman's coordinate and store according to the court rule with the one-dimension array form; X coordinate figure according to the team member sorts, and x changes along with the variation of fixture; Carry out offside position judgement in the image according to rule; According to offside rule and algorithm, use the model of setting up at last, realize offside detection algorithm through programming.
Be to realize above-mentioned purpose, judgement system of the present invention comprises: video camera and main control computer, and wherein video camera is the video that is used to take football match, the video information that collects through the data connecting line handle then is transferred in the middle of the main control computer;
In the main control computer; Be provided with memory module and image information processing module; The scene and the offside differentiation result of the video that this memory module is used for transmitting video camera store; This image information processing module has been accomplished the detection to court line, football and sportsman, and coordinate is carried out in whole court rebuild, and carries out offside position judgement and the judgement of offside participation sense of attack through the offside automatic differentiation algorithm of football then.
The present invention is to be the image source with the section of football match video, and image-pickup method is simply effective, is easy to real-time processing; Carry out Flame Image Process by computing machine and judge offside behavior, speed is fast, the result is accurate, has largely alleviated linesman's workload and error, and has got rid of the factor of artificial control match greatly, has improved penalty result's confidence level; Image has been transformed into the HSV spatial model by RGB, has more met the mode of people's description and explain color, and the HSV model has the advantage of separating monochrome information and colouring information; The offside detection algorithm of design is based on sportsman's planimetric coordinates branch, finds the solution the planimetric coordinates that projection matrix just can recover the court so utilize single camera to take, and has saved the miscellaneous calculating that a plurality of video cameras are analyzed.
The method can better be monitored the offside situation in the international soccer match, reaches the purpose of assisting penalty, reducing judge's workload and error.
The above is merely preferred embodiment of the present invention, not in order to restriction the present invention, all any modifications of within spirit of the present invention and principle, being done, is equal to and replaces and improvement etc., all should be included within protection scope of the present invention.
Claims (9)
1. method based on the offside automatic differentiation of football of video analysis is characterized in that this method comprises:
At first gather the image in the video, extract the pitch and carry out the detection of sportsman and football;
Extract the court characteristic curve, coordinate is carried out on the plane, court rebuild;
Accomplish offside automatic differentiation in the section of football match video.
2. the method for claim 1 is characterized in that, gathers video image, extracts the pitch and carry out the sportsman following with the implementation method of football detection:
Through the pitch specific algorithm that extracts, obtain the place image of football;
Through regional analysis the zone beyond the court is removed, under this background model, carry out sportsman's extraction;
Method with similar sportsman extracts is extracted the football image.
3. method as claimed in claim 2 is characterized in that, extracts the implementation method of football image with the method for similar sportsman's extraction:
At first design Gauss's template of a 5*5, draw an evaluation function that football is estimated, extract the football candidate region.Be defined as:
R＝A(i，j)/B(i，j)+k
Wherein (i is with Gauss's template image to be sued for peace j) to A, and its value shows that more greatly this target might be a football; (i j) is defined as the goodness of fit evaluation function of football to B, serves as that size is asked variance to each pixel of image with Gauss's template, and difference shows that more greatly target is not football more; K is a constant term.Target through in this football evaluation function evaluate image is a football.Last algorithm carries out normalization to image.
4. the method for claim 1 is characterized in that, the implementation method that coordinate is rebuild is carried out on the plane, court:
Uncalibrated image to collecting carries out pre-service, utilizes court Detection Techniques back projection to extract the pitch, and disturb in other places, filtering court;
Utilize the Canny rim detection, strengthen boundary line, forbidden zone and these court characteristic curves of sideline, court in the image through image processing methods such as expansion, closures.
Utilize Hough change detection straight line, obtain the intersecting point coordinate that straight-line equation is found the solution the boundary line, be the image coordinate of court unique point.
Utilize the camera marking method of line style camera model to find the solution projection matrix.
5. the method for claim 1 is characterized in that, the implementation method of offside automatic differentiation comprises:
Information in each moment competition field is preserved, and information comprises: 22 sportsmen's of two teams position, the position and the ownership of ball;
According to the definition combination court areal model of International Football Union, obtain judgment rule to offside position:
Suppose blue side team member attack left, red is the defender, and greater than center line x coordinate, then this team member is not in offside position, promptly offside will the generation at opponents' half as if ordering array medium blue side team member coordinate; If there are two or more defenders the blue side team member front of attack in the ordering array, then this team member is not in offside position; If attacker's coordinate of the most forward sportsman equates that with two above defence members' coordinate then this team member is not in offside position yet; On position of Player of attacker, be in offside position,, comprise the attack or the shooting that do not have " being involved in " one's own side, do not have the interfering with an opponent goalkeeper if do not obtain interests, then not very offside.
Based on above-mentioned offside rule and algorithm, use the model of setting up, the programming of being open to the custom realizes offside detection algorithm.
6. the method for claim 1 is characterized in that, the implementation method of the extraction in place, court is following:
Read in video image, choose key frame, the RGB color space conversion is become the HSV model;
Extract the H component of image, obtain the histogram of H component;
In histogram, seek the position of peak point, the value of its peak point is M
1
Around peak point, inquire about numerical value greater than k*M
1Pixel, k is a scale factor, calculates this part, and this part is removed from histogram, then seeks next peak point and carries out similar operation;
These peak values of removing are partly compared, and the vector of getting largest portion carries out back projection's conversion, and rebuilding with RGB is the image of color model, has finally obtained the place image of football.
7. the method for claim 1 is characterized in that, the method that the sportsman extracts, and this method comprises:
Read in video image, the operation court is detected and the algorithm that extracts, and obtains behind the pitch its binaryzation;
Binary image to the pitch carries out the morphology processing, and noise is eliminated in closed operation, and opening operation extracts the court;
Utilize the method for regional analysis that zone, non-court is removed, bianry image and original image that the court that obtains is regional multiply each other, and obtain the RGB image in zone, court;
The image in the figure image subtraction Performance Area territory that the court is regional;
Remove non-sportsman zone, the result who obtains can contain some non-sportsmen zones, establish the length of holding in the zone and wide be respectively H and W, the number of pixels in the zone is S, if satisfy H/W＞5 or H/W＜0.5 and S/ (H*W)＜0.3, then should the deletion zone; For sportsman's occlusion issue, set each sportsman's parameter W (width), H (highly); S (sportsman's area pixel number), setting threshold T is when S then is a noise during less than certain value; Remove, S then blocks during greater than certain value, and occlusion area is carried out level and vertical segmentation.
8. offside automatic judgement system of the football based on video analysis is characterized in that this judgement system comprises:
Video camera is used to take the video of football match;
Main control computer is used for receiving the video information that camera acquisition arrives through data connecting line.
9. judgement system as claimed in claim 8; It is characterized in that; Main control computer is provided with memory module and image information processing module, and the scene and the offside differentiation result of the video that this memory module is used for transmitting video camera store, and this image information processing module has been accomplished the detection to court line, football and sportsman; And coordinate is carried out in whole court rebuild, carry out offside position judgement and the judgement of offside participation sense of attack through the offside automatic differentiation algorithm of football then.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210253808.1A CN102819749B (en) | 2012-07-23 | 2012-07-23 | A kind of football offside automatic discrimination system and method based on video analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210253808.1A CN102819749B (en) | 2012-07-23 | 2012-07-23 | A kind of football offside automatic discrimination system and method based on video analysis |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN102819749A true CN102819749A (en) | 2012-12-12 |
| CN102819749B CN102819749B (en) | 2016-08-03 |
Family
ID=47303857
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201210253808.1A Expired - Fee Related CN102819749B (en) | 2012-07-23 | 2012-07-23 | A kind of football offside automatic discrimination system and method based on video analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102819749B (en) |
Cited By (30)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103617644A (en) * | 2013-12-03 | 2014-03-05 | 西安电子科技大学 | Badminton side boundary crossing distinguishing method based on machine vision |
| CN104680560A (en) * | 2015-02-28 | 2015-06-03 | 东华大学 | Fast sports venues detection method based on image line element correspondence |
| CN104811592A (en) * | 2014-01-23 | 2015-07-29 | 卡西欧计算机株式会社 | Imaging apparatus, imaging control method and storage medium |
| CN104998394A (en) * | 2015-06-18 | 2015-10-28 | 深圳市润安科技发展有限公司 | Athletic competition auxiliary judgment system and judgment method thereof |
| CN105288957A (en) * | 2015-11-27 | 2016-02-03 | 河南科技学院 | Physical ability comprehensive training apparatus and evaluation system thereof |
| CN106492455A (en) * | 2016-09-30 | 2017-03-15 | 深圳前海万动体育智能科技有限公司 | A kind of football electronic interaction systems |
| CN106606856A (en) * | 2016-02-04 | 2017-05-03 | 简极科技有限公司 | Football data intelligent statistical method |
| CN106989674A (en) * | 2017-04-28 | 2017-07-28 | 北京瑞盖科技股份有限公司 | A kind of place scaling method and the device for implementing this method |
| CN106991685A (en) * | 2016-01-20 | 2017-07-28 | 上海慧体网络科技有限公司 | A kind of algorithm being tracked under panning mode to football in ball match video |
| CN107240111A (en) * | 2017-06-14 | 2017-10-10 | 郑州天迈科技股份有限公司 | Edge connection segmentation passenger flow statistical method |
| CN107510928A (en) * | 2016-06-16 | 2017-12-26 | 江剑华 | A kind of football real-time monitoring system |
| CN108654059A (en) * | 2018-04-23 | 2018-10-16 | 宁波市鄞州乐可机电科技有限公司 | A kind of device to the movement of specification short-track speeding skating |
| CN109101911A (en) * | 2018-07-31 | 2018-12-28 | 浙江大学 | A kind of visual analysis method of pair of football match formation variation and flow of personnel |
| CN109330431A (en) * | 2018-12-04 | 2019-02-15 | 余姚市腾翔电子科技有限公司 | Automate ceramic bathtub |
| CN109432752A (en) * | 2017-07-03 | 2019-03-08 | 罗继伟 | A kind of perimeter security appraisal procedure for ice and snow sports |
| CN109483540A (en) * | 2018-11-21 | 2019-03-19 | 南京邮电大学 | Anthropomorphic robot based on Gauss punishment is layered the optimization method for Optimized model of playing football |
| CN109567846A (en) * | 2018-12-05 | 2019-04-05 | 宁波耀通管阀科技有限公司 | Reaction type tomoscan platform |
| CN109731304A (en) * | 2018-12-06 | 2019-05-10 | 浙江大学 | A kind of rhythmic gymnastics individual clubs instrument difficulty space utilization detection method |
| CN109847292A (en) * | 2019-01-18 | 2019-06-07 | 昆明理工大学 | A kind of tennis Shou Qiu robot with visual identity function |
| CN110135308A (en) * | 2019-04-30 | 2019-08-16 | 天津工业大学 | A kind of direct free kick type identification method based on video analysis |
| 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 |
| CN111228777A (en) * | 2020-02-27 | 2020-06-05 | 东北石油大学 | Intelligent basketball referee processing method and device |
| CN111275021A (en) * | 2020-03-17 | 2020-06-12 | 淮安信息职业技术学院 | Automatic football offside line scribing method based on computer vision |
| CN111901516A (en) * | 2019-12-30 | 2020-11-06 | 蒋梅 | Switch control system of half-field capturing mechanism |
| CN111936212A (en) * | 2018-01-21 | 2020-11-13 | 斯塔特斯公司 | Method for detecting events in sports using convolutional neural networks |
| CN112528785A (en) * | 2020-11-30 | 2021-03-19 | 联想(北京)有限公司 | Information processing method and device |
| CN113082680A (en) * | 2021-04-09 | 2021-07-09 | 谢弘毅 | Automatic judgment system for ball out of bound of ball game based on machine vision |
| CN113476815A (en) * | 2021-05-17 | 2021-10-08 | 张昌昊 | Intelligent sports auxiliary training method and system based on E-ink |
| CN113780181A (en) * | 2021-09-13 | 2021-12-10 | 浙江大学 | Football match offside judgment method and device based on unmanned aerial vehicle and electronic equipment |
| US11935298B2 (en) | 2020-06-05 | 2024-03-19 | Stats Llc | System and method for predicting formation in sports |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107137886B (en) * | 2017-04-12 | 2019-07-05 | 国网山东省电力公司 | A kind of football technique blank model and its construction method and application based on big data |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2002263363A (en) * | 2001-03-09 | 2002-09-17 | Square Co Ltd | Soccer video game program, recording medium recorded soccer video game program, offside judging method in soccer video game, game device, and soccer video game system |
| JP2002346221A (en) * | 2001-05-30 | 2002-12-03 | Square Co Ltd | Soccer video program, recording medium with the program recorded thereon, displaying method in soccer video game and game machine |
| US20090298588A1 (en) * | 2008-05-31 | 2009-12-03 | Venkatesh P. Gopinath | Method of automatically detecting offside in Soccer using fixed and wireless sensors and central server |
| CN101686352A (en) * | 2008-09-22 | 2010-03-31 | 索尼株式会社 | Display control apparatus, display control method, and program |
| CN102118567A (en) * | 2009-12-30 | 2011-07-06 | 新奥特（北京）视频技术有限公司 | Virtual sports system in split mode |
-
2012
- 2012-07-23 CN CN201210253808.1A patent/CN102819749B/en not_active Expired - Fee Related
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2002263363A (en) * | 2001-03-09 | 2002-09-17 | Square Co Ltd | Soccer video game program, recording medium recorded soccer video game program, offside judging method in soccer video game, game device, and soccer video game system |
| JP2002346221A (en) * | 2001-05-30 | 2002-12-03 | Square Co Ltd | Soccer video program, recording medium with the program recorded thereon, displaying method in soccer video game and game machine |
| US20090298588A1 (en) * | 2008-05-31 | 2009-12-03 | Venkatesh P. Gopinath | Method of automatically detecting offside in Soccer using fixed and wireless sensors and central server |
| CN101686352A (en) * | 2008-09-22 | 2010-03-31 | 索尼株式会社 | Display control apparatus, display control method, and program |
| CN102118567A (en) * | 2009-12-30 | 2011-07-06 | 新奥特（北京）视频技术有限公司 | Virtual sports system in split mode |
Non-Patent Citations (2)
| Title |
|---|
| TIZIANA D"ORAZIO等: "An Investigation into the Feasibility of Real-Time Soccer Offside Detection From a Multiple Camera System", 《IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY》 * |
| 王志芳: "足球比赛视频中越位检测关键技术研究", 《中国优秀硕士学位论文全文数据库（电子期刊）》 * |
Cited By (39)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103617644B (en) * | 2013-12-03 | 2016-08-17 | 西安电子科技大学 | Cross the border method of discrimination in a kind of shuttlecock sideline based on machine vision |
| CN103617644A (en) * | 2013-12-03 | 2014-03-05 | 西安电子科技大学 | Badminton side boundary crossing distinguishing method based on machine vision |
| CN104811592A (en) * | 2014-01-23 | 2015-07-29 | 卡西欧计算机株式会社 | Imaging apparatus, imaging control method and storage medium |
| CN104811592B (en) * | 2014-01-23 | 2018-07-06 | 卡西欧计算机株式会社 | Photographic device and camera shooting control method |
| CN104680560B (en) * | 2015-02-28 | 2017-10-24 | 东华大学 | Based on the corresponding sports place quick determination method of image line element |
| CN104680560A (en) * | 2015-02-28 | 2015-06-03 | 东华大学 | Fast sports venues detection method based on image line element correspondence |
| CN104998394A (en) * | 2015-06-18 | 2015-10-28 | 深圳市润安科技发展有限公司 | Athletic competition auxiliary judgment system and judgment method thereof |
| CN105288957B (en) * | 2015-11-27 | 2017-11-14 | 河南科技学院 | A kind of physical efficiency combined training apparatus and its evaluation system |
| CN105288957A (en) * | 2015-11-27 | 2016-02-03 | 河南科技学院 | Physical ability comprehensive training apparatus and evaluation system thereof |
| CN106991685A (en) * | 2016-01-20 | 2017-07-28 | 上海慧体网络科技有限公司 | A kind of algorithm being tracked under panning mode to football in ball match video |
| CN106991685B (en) * | 2016-01-20 | 2020-09-25 | 上海慧体网络科技有限公司 | Algorithm for tracking football in ball game video in panoramic mode |
| CN106606856A (en) * | 2016-02-04 | 2017-05-03 | 简极科技有限公司 | Football data intelligent statistical method |
| CN107510928A (en) * | 2016-06-16 | 2017-12-26 | 江剑华 | A kind of football real-time monitoring system |
| CN106492455A (en) * | 2016-09-30 | 2017-03-15 | 深圳前海万动体育智能科技有限公司 | A kind of football electronic interaction systems |
| CN106989674A (en) * | 2017-04-28 | 2017-07-28 | 北京瑞盖科技股份有限公司 | A kind of place scaling method and the device for implementing this method |
| CN106989674B (en) * | 2017-04-28 | 2019-06-28 | 北京瑞盖科技股份有限公司 | A kind of place scaling method and the device for implementing this method |
| CN107240111A (en) * | 2017-06-14 | 2017-10-10 | 郑州天迈科技股份有限公司 | Edge connection segmentation passenger flow statistical method |
| CN109432752A (en) * | 2017-07-03 | 2019-03-08 | 罗继伟 | A kind of perimeter security appraisal procedure for ice and snow sports |
| CN111936212A (en) * | 2018-01-21 | 2020-11-13 | 斯塔特斯公司 | Method for detecting events in sports using convolutional neural networks |
| CN108654059A (en) * | 2018-04-23 | 2018-10-16 | 宁波市鄞州乐可机电科技有限公司 | A kind of device to the movement of specification short-track speeding skating |
| CN109101911A (en) * | 2018-07-31 | 2018-12-28 | 浙江大学 | A kind of visual analysis method of pair of football match formation variation and flow of personnel |
| CN109101911B (en) * | 2018-07-31 | 2021-03-05 | 浙江大学 | Visual analysis method for football match formation change and personnel flow |
| CN109483540A (en) * | 2018-11-21 | 2019-03-19 | 南京邮电大学 | Anthropomorphic robot based on Gauss punishment is layered the optimization method for Optimized model of playing football |
| CN109330431A (en) * | 2018-12-04 | 2019-02-15 | 余姚市腾翔电子科技有限公司 | Automate ceramic bathtub |
| CN109567846A (en) * | 2018-12-05 | 2019-04-05 | 宁波耀通管阀科技有限公司 | Reaction type tomoscan platform |
| CN109731304A (en) * | 2018-12-06 | 2019-05-10 | 浙江大学 | A kind of rhythmic gymnastics individual clubs instrument difficulty space utilization detection method |
| CN109847292A (en) * | 2019-01-18 | 2019-06-07 | 昆明理工大学 | A kind of tennis Shou Qiu robot with visual identity function |
| CN110135308A (en) * | 2019-04-30 | 2019-08-16 | 天津工业大学 | A kind of direct free kick type identification method based on video analysis |
| 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 |
| 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 |
| CN111901516A (en) * | 2019-12-30 | 2020-11-06 | 蒋梅 | Switch control system of half-field capturing mechanism |
| CN111228777A (en) * | 2020-02-27 | 2020-06-05 | 东北石油大学 | Intelligent basketball referee processing method and device |
| CN111275021A (en) * | 2020-03-17 | 2020-06-12 | 淮安信息职业技术学院 | Automatic football offside line scribing method based on computer vision |
| US11935298B2 (en) | 2020-06-05 | 2024-03-19 | Stats Llc | System and method for predicting formation in sports |
| CN112528785A (en) * | 2020-11-30 | 2021-03-19 | 联想(北京)有限公司 | Information processing method and device |
| CN113082680A (en) * | 2021-04-09 | 2021-07-09 | 谢弘毅 | Automatic judgment system for ball out of bound of ball game based on machine vision |
| CN113476815A (en) * | 2021-05-17 | 2021-10-08 | 张昌昊 | Intelligent sports auxiliary training method and system based on E-ink |
| CN113780181A (en) * | 2021-09-13 | 2021-12-10 | 浙江大学 | Football match offside judgment method and device based on unmanned aerial vehicle and electronic equipment |
| CN113780181B (en) * | 2021-09-13 | 2023-11-14 | 浙江大学 | Football match offside judging method and device based on unmanned aerial vehicle and electronic equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN102819749B (en) | 2016-08-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102819749A (en) | Automatic identification system and method for offside of football based on video analysis | |
| JP7289080B2 (en) | Ball game video analysis device and ball game video analysis method | |
| Chen et al. | Play type recognition in real-world football video | |
| CN109101911B (en) | Visual analysis method for football match formation change and personnel flow | |
| JP6488295B2 (en) | Video processing method and video processing apparatus | |
| Santhosh et al. | An Automated Player Detection and Tracking in Basketball Game. | |
| Fu et al. | Screen-strategy analysis in broadcast basketball video using player tracking | |
| Weeratunga et al. | Application of computer vision and vector space model for tactical movement classification in badminton | |
| US20230377336A1 (en) | Method of operating server providing sports video-based platform service | |
| Yamamoto et al. | Multiple players tracking and identification using group detection and player number recognition in sports video | |
| He et al. | Notice of violation of ieee publication principles: study on sports volleyball tracking technology based on image processing and 3D space matching | |
| Karungaru et al. | Ground sports strategy formulation and assistance technology develpoment: player data acquisition from drone videos | |
| Liu et al. | Detecting and matching related objects with one proposal multiple predictions | |
| Hashimoto et al. | A system for automatic judgment of offsides in soccer games | |
| Muthuraman et al. | Vision based dynamic offside line marker for soccer games | |
| Chauhan et al. | Cricket activity detection using computer vision | |
| Gomez¹ et al. | Semi-automatic tracking of beach volleyball players | |
| Hsu et al. | 2D Histogram-based player localization in broadcast volleyball videos | |
| CN113876311B (en) | Non-contact type multi-player heart rate efficient extraction device capable of adaptively selecting | |
| Xia et al. | Advanced Volleyball Stats for All Levels: Automatic Setting Tactic Detection and Classification with a Single Camera | |
| Ivasic-Kos et al. | Active player detection in handball videos using optical flow and STIPs based measures | |
| US20180211397A1 (en) | Object extraction from video images system and method | |
| Siratanita et al. | A method of saliency-based football-offside detection using six cameras | |
| Ruiz-del-Solar et al. | An automated refereeing and analysis tool for the Four-Legged League | |
| Kurano et al. | Ball trajectory extraction in team sports videos by focusing on ball holder candidates for a play search and 3D virtual display system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20160803 Termination date: 20170723 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |