CN110222977A - One kind movement sport methods of marking based on computer vision and device - Google Patents
One kind movement sport methods of marking based on computer vision and device Download PDFInfo
- Publication number
- CN110222977A CN110222977A CN201910480123.2A CN201910480123A CN110222977A CN 110222977 A CN110222977 A CN 110222977A CN 201910480123 A CN201910480123 A CN 201910480123A CN 110222977 A CN110222977 A CN 110222977A
- Authority
- CN
- China
- Prior art keywords
- movement
- scoring
- video recording
- maximum
- deep learning
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/20—Movements or behaviour, e.g. gesture recognition
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Human Resources & Organizations (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Artificial Intelligence (AREA)
- Marketing (AREA)
- Tourism & Hospitality (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Life Sciences & Earth Sciences (AREA)
- Game Theory and Decision Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Business, Economics & Management (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Psychiatry (AREA)
- Social Psychology (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Image Analysis (AREA)
Abstract
One kind movement sport methods of marking based on computer vision and device, affiliated athletics grade information systems technology field.The present invention scores to movement sport using 3D video recording reconstruct and deep learning algorithm, overcome mankind referee's scoring often existing carelessness or injustice, it can accomplish transparent fair and just, and save judge's human resources, realize sports officiating automation, intelligent.
Description
Technical field
The present invention relates to the information systems technology fields of athletics grade.
Background technique
In sports tournament, is scored using mankind referee according to judge's rule, often there is carelessness or unjust
Just.The present invention propose it is a kind of using 3D record a video reconstruct and deep learning algorithm computer vision according to judge rule cut out
Sentence the method and apparatus of scoring, can accomplish it is fair and just, and save judge human resources, realize sports officiating automation,
It is intelligent.
Summary of the invention
The present invention is by installing three or more cameras being suitably distributed in athletic training or competition area, to fortune
The movement of mobilization is recorded a video, and camera is connected in computer system, and system was run by using former data
Trained deep learning algorithm movement to sportsman and its terminus and can execute defect and identify and according to judge
Rule and standards of grading score.The 3D to form player motion the video recording of three different directions can also be reconstructed
Video recording, so as to accurately calculate each movement commencing height, rise hop distance, rotating in air angle (spin hoop gyrally number or
Person's flip horizontal circle number), trunk upright degree and arm exhibition levelness, trunk deviate vertical axis angle maximum value and average value and
Arm exhibition deviates trunnion axis angle maximum value and average value etc. and judges various indexs involved in regular standards of grading or related refer to
Then mark carries out skill score according to the regular standards of grading of judge；Some of them index needs that deep learning algorithm is combined to carry out
It calculates, for example rotating in air angle, can use deep learning algorithm identification some characteristic point of athletes ' body, it is for example right
Shoulder, rotation calculate aerial rotation in conjunction with the angle of body Initial Azimuth and last landing orientation by the number of a certain feature orientations
Turn total angle.It, can also be by acting with the fusion degree of music and by previous match art scoring for artistic score
Deep learning artistic scoring is carried out to athletic type's grace degree and fluent movements degree and grace degree etc..If using a variety of
Automatic scoring method scores, and the weight of various methods of marking can be adjusted, and optimize, and eventually forms most suitable
When automatic scoring mode.
In one embodiment of the present invention, technical movements are identified by deep learning algorithm, deep learning algorithm
It can identify the start, end of each movement and the disadvantage in action executing process or the tumble of deduction of points item and unbalanced landing etc.
Can be formed the 3D of player motion by recording a video or reconstructing Deng, skill score and recorded a video, accurately calculate each movement commencing height,
It plays hop distance, rotating in air angle (spin hoop gyrally number or flip horizontal circle number), trunk upright degree and arm and opens up levelness, body
The dry angle maximum value for deviateing vertical axis and average value and arm exhibition deviate trunnion axis angle maximum value and average value and movement
Various indexs or index of correlation involved in regular standards of grading are judged with music degrees of fusion etc., are then commented according to judge's rule
Minute mark standard carries out skill score, and wherein technology deduction of points is carried out the knowledge fallen with items of deducting points such as unbalanced landings by deep learning algorithm
Not, and standard of deducting point is pressed, deducted points.Some of them index needs that deep learning algorithm is combined to be calculated, for example in the air
Angle is rotated, can use deep learning algorithm identification some characteristic point of athletes ' body, for example right shoulder, rotation pass through a certain
The number of feature orientations calculates rotating in air total angle in conjunction with the angle of body Initial Azimuth and last landing orientation.Art or
Person performs (presentation) scoring, by defined weight (for example 25%, if act do not have to match music if be 0%) by moving
Make to be calculated with the degrees of fusion of music, artistic or the score of performance remaining weight (for example 75%) by from calculate with
Relevant various indexs such as trunk upright degree is scored in artistic performance and arm exhibition levelness, trunk deviate vertical axis angle it is maximum
Value and the exhibition of average value and arm deviate trunnion axis angle maximum value and average value etc. and carry out scoring knot by regular standards of grading are judged
Close by previous competition data train come deep learning algorithm to the fluency of movement and grace degree etc. carry out identify be classified comment
Point.
In another embodiment of the invention, skill score and art or performance scoring before utilizing all by competing
The trained deep learning algorithm of big data carries out identification rank scores.Points-scoring system includes one and collects previous match video recording money
The big data database of material, scoring data and result of the match, can use the database and is trained to deep learning algorithm, from
And algorithm can identify various movements, the terminus of movement, movement execute defect, the graceful degree of movement and fluency etc. and
It acts the quality grading executed and executes defect system and the movement of sportsman is commented automatically to form a set of scoring algorithm
Point.
In another embodiment of the invention, it includes that identification is each that technical movements, which carry out identification by deep learning algorithm,
The terminus of son movement is recorded a video by the 3D that video recording reconstruct forms player motion, so as to accurately calculate rising for each movement
Jump degree, hop distance, rotating in air angle (spin hoop gyrally number or flip horizontal circle number) and immersion angle degree etc. judge
Then various indexs or index of correlation involved in regular standards of grading carry out skill score according to the regular standards of grading of judge,
Wherein technology deduction of points is by training the deep learning algorithm come progress immersion angle degree and spray size by big data of competing before
The identification of equal execution deduction of points item, and standard of deducting point is pressed, it deducts points.Some of them index needs that deep learning algorithm is combined to carry out
It calculates, for example rotating in air angle, can use deep learning algorithm identification some characteristic point of athletes ' body, it is for example right
Shoulder, rotation calculate aerial rotation in conjunction with the angle of body Initial Azimuth and last landing orientation by the number of a certain feature orientations
Turn total angle.The score of performance (presentation) can record a video from the 3D of reconstruct accurately calculates body trunk deviation vertical axis
Angle and/or arm exhibition deviate maximum value and average value of the angle of horizontal axis etc. and judge involved in regular standards of grading
Various indexs or index of correlation take certain weight to carry out calculating scoring, compete in conjunction with before by the regulation of judge's rule
Big data trains the deep learning algorithm carry out type body grace degree come and the performance scorings such as fluency and grace degree are equipped with centainly
Weight, to obtain performance (presentation) point.
In another embodiment of the invention, for pair event, in addition to the scoring that is acted for respective sport it
Outside, score also for the harmony of two human actions, can by video recording 3D reconstruct it is accurate calculate two people's take-off times it is poor,
The indexs such as jump degree is poor, operation poor, the actuation time difference of figure, by judge the certain weight of regular standards of grading imparting to harmony into
Row scoring；Deep learning can also be carried out by the big data for duets' Video Document before utilize deep learning
Algorithm scores to harmony.For group project, other than the scoring for respectively acting, video recording 3D weight can be passed through
Structure accurately calculates poor proprietary poor, the maximum commencing height of maximum take-off time, maximum operation figure difference or/and maximum actuation side
The indexs such as potential difference, maximum actuation time difference score to harmony by the certain weight of regular standards of grading imparting is judged；It can also
To carry out deep learning using deep learning algorithm to coordination by the big data for the match Video Document of group project before
Property scores.
Realize that the present invention to the device of method for acting sport and scoring, including several is connected to using computer vision
The camera of computer system, operation camera shooting 3D reconstruct and stroking technique index is accurately calculated or/and by greatly count
Sport action recognition is carried out according to analysis and deep learning and carries out the computer of the deep learning algorithm of technology or/and performance scoring
System and the big data database for collecting match Video data data, score data data and result of the match in the past.
Above-mentioned technical proposal includes best-of-breed technology scheme of the invention, but the present invention also includes following innovation of the present invention simultaneously
The various mutation of the above-mentioned technical proposal of thought, for example, system three or more cameras can be set in competition area
Different orientation；3D reconstruct is imaged in system and the function of being accurately calculated to stroking technique index can have or not have
Have, if not provided, with regard to purely carrying out identification and rank scores to movement with the algorithm of deep learning；Match Video data money in the past
The big data database of material can collect the Video Document data competed before more as far as possible, score data data and match knot
Fruit；The system can be for a variety of sports, for example figure skating, on ice skill, gymnastics, diving, synchronized swimming, spring
The points-scoring system of bed (trampoline) etc. is also possible to a single item sports and for example dives or figure skating
Points-scoring system；Computer information system in above-mentioned technical proposal can be cloud computing system A/S (App/Server system),
It is also possible to B/S system (Browser/Server system), is also possible to C/S system (Client/Server system) etc..
Based on the movement sport methods of marking of computer vision, mankind referee's scoring often existing carelessness is overcome
Or it is injustice, it can accomplish transparent fair and just, and save judge's human resources, realize sports officiating automation, intelligence
Energyization.
Specific embodiment
The present invention is further elaborated below with reference to two embodiments.
Embodiment one: the computer vision points-scoring system of diving.In diving, technical movements are known in advance, can be with
Each height is acted using deep learning algorithm and its terminus identifies, as long as setting three or more camera is connected to
Computer vision points-scoring system is recorded a video by the 3D of technical movements and is reconstructed, and can accurately calculate the commencing height of each movement, rise
Hop distance, rotating in air angle (spin hoop gyrally number or flip horizontal circle number), trunk upright degree and arm open up levelness, trunk
The angle maximum value and average value of deviation vertical axis and arm exhibition deviate trunnion axis angle maximum value and average value and immersion angle
Degree etc. judges various indexs or index of correlation involved in regular standards of grading, is then utilized according to the regular standards of grading of judge
These indexs carry out skill score, and some of them index needs that deep learning algorithm is combined to be calculated, for example rotating in air
Angle can use deep learning algorithm identification some characteristic point of athletes ' body, and for example right shoulder, rotation pass through a certain feature
The number in orientation calculates rotating in air total angle in conjunction with the angle of body Initial Azimuth and last landing orientation；Technology deduction of points by
By big data of competing before train come deep learning algorithm carry out immersion angle degree, spray size and movement and execute defect etc.
The identification of deduction of points item, and standard of deducting point is pressed, it deducts points.It is accurate that the score of performance (presentation) can record a video from the 3D of reconstruct
It calculates such as trunk upright degree and arm exhibition levelness, the angle maximum value of trunk deviation vertical axis and average value and arm exhibition deviates
Various indexs or index of correlation involved in trunnion axis angle maximum value and average value etc. judge's rule, then by judge's rule
Standards of grading take respective weights to carry out calculating scoring, in conjunction with by big data of competing before train come deep learning algorithm
Carry out type body grace degree and performance grace degree etc. carry out identification rank scores and are equipped with the weight of standards of grading defined, to obtain
The score of performance.
Embodiment two: the computer vision points-scoring system of figure skating.Technical movements and its terminus are calculated by deep learning
Method is identified that skill score is recorded a video by the 3D that video recording reconstruct forms player motion, so as to accurately calculate each movement
Commencing height, play hop distance, rotating in air angle (spin hoop gyrally number), ice face rotation speed and rotating cycle etc. judge
Then various indexs or index of correlation involved in regular standards of grading carry out skill score according to the regular standards of grading of judge,
Some of them index needs that deep learning algorithm is combined to be calculated, and for example rotating in air angle, can use deep learning
Algorithm identifies some characteristic point of athletes ' body, for example right shoulder, and rotation is risen by the number of a certain feature orientations in conjunction with body
The angle in beginning orientation and last landing orientation, calculates rotating in air total angle；Technology deduction of points is fallen by deep learning algorithm
With the identification of the deduction of points item such as unbalanced landing, and standard of deducting point is pressed, deducted points.Art or performance (presentation) are commented
Point, it is inclined that degrees of fusion, trunk upright degree and the arm of the accurate calculating action that can record a video from the 3D of reconstruct and music open up levelness, trunk
Angle maximum value and average value and arm exhibition from vertical axis deviate trunnion axis angle maximum value and average value etc. judge's rule
Then various indexs or index of correlation involved in standards of grading take regulation weight to carry out calculating and comment by the regular standards of grading of judge
Point, in conjunction with training the deep learning algorithm come to type body grace degree by big data of competing before and perform grace degree and stream
Smooth degree etc. carries out identification rank scores and is equipped with weight as defined in standards of grading, to obtain the score of performance.
Computer system in the present invention can use in various general or dedicated calculating environment or configuration.It is suitable
Include, but are not limited to individual calculus for the well known computing system of information system of the present invention, environment and/or the example of configuration
Machine, server computer, smart phone, mobile phone, tablet computer, portable or laptop devices, multicomputer system, based on micro-
The system of processor, set-top box, programmable consumer electronic device, network PC, minicomputer, mainframe computer etc. and packet
Include the information system (including cloud computing system, A/S system, B/S system and C/S system), wired of any of the above system or equipment
Or/and wireless and wired+Radio Network System and distributed computing environment etc..
Above-described embodiment is available to those of ordinary skill in the art to realize the embodiment of the present invention.The common skill in this field
Art personnel can make various modifications or variation, therefore this to above-described embodiment in the case where following innovative idea of the present invention
The protection scope of invention is not limited by above-described embodiment, and should meet inventive features that claims are mentioned most
On a large scale.
Claims (10)
1. a kind of method to be scored using computer vision movement sport, comprising:
It records a video to the movement of sportsman；
Defect is executed to the terminus of each movement and movement by deep learning algorithm to identify；
The various various indexs and index of correlation for judging regular standards of grading are calculated from recording a video or reconstructing 3D video recording；
For Score index such as rotating in air angle, the performance smoothness that can not be directly calculated from video recording or reconstruct 3D video recording
Degree and grace degree can carry out calculating in conjunction with deep learning algorithm or carry out identification evaluation using deep learning algorithm；
It is scored using various indexs obtained above and index of correlation according to standards of grading, it is scarce to executing according to standards of grading
It is trapped into capable deduction of points.
2. methods of marking as described in claim 1, it is characterised in that when performance needs to be equipped with music, wanted according to right
It asks the relevant index of the various and artistic performance calculated in 1 point such as to act and deviates vertical axis with music degrees of fusion, trunk
Maximum value and average value and the arm exhibition of angle deviate the maximum value and average value etc. of trunnion axis angle, in conjunction with passing through deep learning
Algorithm does identification classification by weight progress artistic performance scoring as defined in judge's rule with grace degree to the fluency that movement executes.
3. methods of marking as described in claim 1, it is characterised in that for pair event, in addition to what is acted for respective sport
It except scoring, scores also for the harmony of two human actions, video recording or 3D video recording two people's take-offs of accurate calculating can be passed through
The indexs such as time difference, poor, operation poor, the actuation time difference of figure of commencing height, assign certain weight by regular standards of grading are judged
It scores harmony.
4. methods of marking as described in claim 1, it is characterised in that for group project, in addition to the scoring for respectively acting
Except, it can accurately calculate that proprietary maximum take-off time poor, maximum commencing height is poor, maximum fortune by video recording or 3D video recording
The indexs such as row figure difference or/and maximum actuation gun parallax, maximum actuation time difference assign certain power by regular standards of grading are judged
It scores again harmony.
5. methods of marking as described in claim 1, it is characterised in that different direction install 3 or more cameras for
The movement of sportsman is recorded a video so as to the 3D image of reconstitution movement person's movement.
6. realizing a kind of scoring apparatus of method to score using computer vision movement sport, including it is mounted on match
3 or more cameras of place different direction, these cameras are connected to a computer information system, the information system
It big data database with a previous match video recording and scoring data and result of the match and runs and realizes claim 1
The program of the methods of marking.
7. scoring apparatus as claimed in claim 6, it is characterised in that when performance needs to be equipped with music, wanted according to right
It asks the relevant index of the various and artistic performance calculated in 1 point such as to act and deviates vertical axis with music degrees of fusion, trunk
Maximum value and average value and the arm exhibition of angle deviate the maximum value and average value etc. of trunnion axis angle, in conjunction with passing through deep learning
Algorithm does identification classification by weight progress artistic performance scoring as defined in judge's rule with grace degree to the fluency that movement executes.
8. scoring apparatus as claimed in claim 6, it is characterised in that for pair event, in addition to what is acted for respective sport
It except scoring, scores also for the harmony of two human actions, video recording or 3D video recording two people's take-offs of accurate calculating can be passed through
The indexs such as time difference, poor, operation poor, the actuation time difference of figure of commencing height, assign certain weight by regular standards of grading are judged
It scores harmony.
9. scoring apparatus as claimed in claim 6, it is characterised in that for group project, in addition to the scoring for respectively acting
Except, it can accurately calculate that proprietary maximum take-off time poor, maximum commencing height is poor, maximum fortune by video recording or 3D video recording
The indexs such as row figure difference or/and maximum actuation gun parallax, maximum actuation time difference assign certain power by regular standards of grading are judged
It scores again harmony.
10. scoring apparatus as claimed in claim 6, it is characterised in that the computer information system of the device includes one previous
The big data database of code, the database include Video Document, scoring data and the result of the match competed in the past, can
To carry out learning training to previous competition data using deep learning algorithm, held so as to the terminus of identification maneuver, movement
Graceful degree and fluency of capable defect, movement execution etc..
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910480123.2A CN110222977A (en) | 2019-06-03 | 2019-06-03 | One kind movement sport methods of marking based on computer vision and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910480123.2A CN110222977A (en) | 2019-06-03 | 2019-06-03 | One kind movement sport methods of marking based on computer vision and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110222977A true CN110222977A (en) | 2019-09-10 |
Family
ID=67819249
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910480123.2A Pending CN110222977A (en) | 2019-06-03 | 2019-06-03 | One kind movement sport methods of marking based on computer vision and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110222977A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111282245A (en) * | 2020-01-17 | 2020-06-16 | 浙江金耐斯体育用品有限公司 | AI recognition sports track data analysis method and system |
| CN111784121A (en) * | 2020-06-12 | 2020-10-16 | 清华大学 | Action quality evaluation method based on uncertainty score distribution learning |
| CN111915643A (en) * | 2020-05-20 | 2020-11-10 | 北京理工大学 | System and method for detecting water outlet height of swimmer based on ZED vision |
| CN114722230A (en) * | 2022-03-30 | 2022-07-08 | 蔡戴朋 | Auxiliary judgment system using angle big data matching |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101470898A (en) * | 2007-12-26 | 2009-07-01 | 中国科学院自动化研究所 | Automatic analysis method for synchronization of two-person synchronized diving |
| CN107909060A (en) * | 2017-12-05 | 2018-04-13 | 前海健匠智能科技（深圳）有限公司 | Gymnasium body-building action identification method and device based on deep learning |
| CN109045664A (en) * | 2018-09-05 | 2018-12-21 | 山东大学 | Diving scoring method, server and system based on deep learning |
| CN109829442A (en) * | 2019-02-22 | 2019-05-31 | 焦点科技股份有限公司 | A kind of method and system of the human action scoring based on camera |
-
2019
- 2019-06-03 CN CN201910480123.2A patent/CN110222977A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101470898A (en) * | 2007-12-26 | 2009-07-01 | 中国科学院自动化研究所 | Automatic analysis method for synchronization of two-person synchronized diving |
| CN107909060A (en) * | 2017-12-05 | 2018-04-13 | 前海健匠智能科技（深圳）有限公司 | Gymnasium body-building action identification method and device based on deep learning |
| CN109045664A (en) * | 2018-09-05 | 2018-12-21 | 山东大学 | Diving scoring method, server and system based on deep learning |
| CN109829442A (en) * | 2019-02-22 | 2019-05-31 | 焦点科技股份有限公司 | A kind of method and system of the human action scoring based on camera |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111282245A (en) * | 2020-01-17 | 2020-06-16 | 浙江金耐斯体育用品有限公司 | AI recognition sports track data analysis method and system |
| CN111915643A (en) * | 2020-05-20 | 2020-11-10 | 北京理工大学 | System and method for detecting water outlet height of swimmer based on ZED vision |
| CN111915643B (en) * | 2020-05-20 | 2023-10-10 | 北京理工大学 | System and method for detecting water outlet height of swimmer based on ZED vision |
| CN111784121A (en) * | 2020-06-12 | 2020-10-16 | 清华大学 | Action quality evaluation method based on uncertainty score distribution learning |
| CN111784121B (en) * | 2020-06-12 | 2022-08-09 | 清华大学 | Action quality evaluation method based on uncertainty score distribution learning |
| CN114722230A (en) * | 2022-03-30 | 2022-07-08 | 蔡戴朋 | Auxiliary judgment system using angle big data matching |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Li et al. | Application of artificial intelligence in basketball sport | |
| CN110222977A (en) | One kind movement sport methods of marking based on computer vision and device | |
| CN101964047B (en) | Multiple trace point-based human body action recognition method | |
| CN106066990A (en) | For the method and apparatus that the frame in the motion video of people is associated with event | |
| US11565166B2 (en) | Golf game implementation using ball tracking and scoring system | |
| CN105080111A (en) | Sport ball motion monitoring methods and systems | |
| US11620858B2 (en) | Object fitting using quantitative biomechanical-based analysis | |
| KR100907704B1 (en) | Golfer's posture correction system using artificial caddy and golfer's posture correction method using it | |
| US20240082683A1 (en) | Kinematic analysis of user form | |
| CN105999677A (en) | Portable golf simulation system capable of being networked and simulation method | |
| WO2022251671A1 (en) | 3d avatar generation and robotic limbs using biomechanical analysis | |
| US20240042281A1 (en) | User experience platform for connected fitness systems | |
| CN115475373B (en) | Display method and device of motion data, storage medium and electronic device | |
| Peng et al. | Accurate recognition of volleyball motion based on fusion of MEMS inertial measurement unit and video analytic | |
| CN116246347A (en) | Standard judging method and scoring device for basic motor skills of human body | |
| Malawski et al. | Automatic analysis of techniques and body motion patterns in sport | |
| Blank | Smart Racket–Instrumented Racket as Real-time Feedback Device for Table Tennis | |
| Malik et al. | Badminton Action Analysis Using LSTM | |
| CN114241603B (en) | Shuttlecock action recognition and level grade evaluation method and system based on wearable equipment | |
| Link | Wearables in Sports: From Experimental Validation to Deep Learning Applications | |
| US20230302325A1 (en) | Systems and methods for measuring and analyzing the motion of a swing and matching the motion of a swing to optimized swing equipment | |
| Colombo | Goalkeeper’s Performances Assessed with Action Cameras Based Mocap System | |
| Yan et al. | A Generic Framework for Sport-specific Movement Recognition | |
| Kilpeläinen | Perception tools and their usage in sports | |
| Marsland | Macro-kinematic performance analysis in cross-country skiing competition using micro-sensors |
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 |