CN116271757A - Auxiliary system and method for basketball practice based on AI technology - Google Patents
Auxiliary system and method for basketball practice based on AI technology Download PDFInfo
- Publication number
- CN116271757A CN116271757A CN202310223139.1A CN202310223139A CN116271757A CN 116271757 A CN116271757 A CN 116271757A CN 202310223139 A CN202310223139 A CN 202310223139A CN 116271757 A CN116271757 A CN 116271757A
- Authority
- CN
- China
- Prior art keywords
- data
- athlete
- basketball
- dimensional
- rendering model
- 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
Images
Classifications
-
- A—HUMAN NECESSITIES
- A63—SPORTS; GAMES; AMUSEMENTS
- A63B—APPARATUS FOR PHYSICAL TRAINING, GYMNASTICS, SWIMMING, CLIMBING, OR FENCING; BALL GAMES; TRAINING EQUIPMENT
- A63B69/00—Training appliances or apparatus for special sports
- A63B69/0071—Training appliances or apparatus for special sports for basketball
-
- A—HUMAN NECESSITIES
- A63—SPORTS; GAMES; AMUSEMENTS
- A63B—APPARATUS FOR PHYSICAL TRAINING, GYMNASTICS, SWIMMING, CLIMBING, OR FENCING; BALL GAMES; TRAINING EQUIPMENT
- A63B24/00—Electric or electronic controls for exercising apparatus of preceding groups; Controlling or monitoring of exercises, sportive games, training or athletic performances
-
- A—HUMAN NECESSITIES
- A63—SPORTS; GAMES; AMUSEMENTS
- A63B—APPARATUS FOR PHYSICAL TRAINING, GYMNASTICS, SWIMMING, CLIMBING, OR FENCING; BALL GAMES; TRAINING EQUIPMENT
- A63B71/00—Games or sports accessories not covered in groups A63B1/00 - A63B69/00
- A63B71/06—Indicating or scoring devices for games or players, or for other sports activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T13/00—Animation
- G06T13/20—3D [Three Dimensional] animation
- G06T13/40—3D [Three Dimensional] animation of characters, e.g. humans, animals or virtual beings
-
- A—HUMAN NECESSITIES
- A63—SPORTS; GAMES; AMUSEMENTS
- A63B—APPARATUS FOR PHYSICAL TRAINING, GYMNASTICS, SWIMMING, CLIMBING, OR FENCING; BALL GAMES; TRAINING EQUIPMENT
- A63B2243/00—Specific ball sports not provided for in A63B2102/00 - A63B2102/38
- A63B2243/0037—Basketball
-
- A—HUMAN NECESSITIES
- A63—SPORTS; GAMES; AMUSEMENTS
- A63B—APPARATUS FOR PHYSICAL TRAINING, GYMNASTICS, SWIMMING, CLIMBING, OR FENCING; BALL GAMES; TRAINING EQUIPMENT
- A63B24/00—Electric or electronic controls for exercising apparatus of preceding groups; Controlling or monitoring of exercises, sportive games, training or athletic performances
- A63B24/0003—Analysing the course of a movement or motion sequences during an exercise or trainings sequence, e.g. swing for golf or tennis
- A63B24/0006—Computerised comparison for qualitative assessment of motion sequences or the course of a movement
Abstract
The invention discloses an auxiliary system and method for basketball practice based on an AI technology, comprising an AI data acquisition part, a display inquiry terminal and an analysis processing part arranged at the background; the AI data acquisition part acquires athlete face information and motion video data; the AI recognition processing server is used for analyzing and processing the sports video data to generate athlete three-dimensional skeleton data; the virtual simulation server is used for modeling venues and roles, binding athlete three-dimensional skeleton data and the roles and generating a rendering model for inquiry; the field display screen is used for displaying the query rendering model; binding athlete three-dimensional skeleton data and virtual character modeling to generate a rendering model for inquiry; the athlete can review the self training action from the three-dimensional angle, so that the repeated teaching intensity of a coach is reduced; athletes can visually check the training conditions, find action defects, take targeted measures and improve the training efficiency.
Description
Technical Field
The invention relates to the technical field of basketball auxiliary exercise equipment, in particular to an auxiliary system and an auxiliary method for basketball exercise based on an AI technology.
Background
The basketball exercise training is mainly to train the operation skills of the basketball by simulating the specific action mode, the athlete needs to frequently simulate, observe and correct the actions, the current basketball teaching is mostly to learn the technology about basketball by observing the demonstration actions of a coach, the coach can consume a great deal of physical strength after multiple exercise training demonstration, the accuracy of the teaching actions can be reduced, the basketball training effect of the student is influenced, meanwhile, the athlete cannot review the moving image of the athlete in real time through the display device, visually see the acting points, the jump heights, the jump angles of the feet, the instant explosive force during ball control, whether the limb actions in the ball control movement process are kept as technical actions and the like, further know the action defects of the athlete, compare with the standard actions, find the difference of the actions, and the coach cannot grasp the training progress of the basketball athlete in an image.
Patent literature with document number CN110052002A discloses a basketball shooting training auxiliary system, including controller, wireless signal receiving element, backboard, bracelet and first camera, install the basket above the backboard, be provided with inclination sensor, acceleration sensor and wireless signal transmission unit in the bracelet, acceleration sensor and inclination sensor and wireless signal transmission unit circuit connection, wireless signal transmission unit is connected with the controller, the face of backboard is made by the printing opacity material, the back of backboard is provided with a horizontal LED lamp area and a vertical LED lamp area.
The basketball shooting training auxiliary system can be used for rapidly cultivating shooting handfeel of a player and improving shooting accuracy. But the athlete cannot review the self-training action in a three-dimensional angle; training progress analysis reports and athlete personal action analysis reports cannot be automatically generated to conduct targeted training.
Patent document CN111724414a discloses a basketball motion analysis method based on 3D gesture estimation, and discloses a basketball training auxiliary system method based on gesture estimation and motion recognition pair analysis.
The basketball game and training video are analyzed by the basketball game system, a coach discovers weaknesses in the game through the analysis result of the basketball game system, the competitive level is improved, the game is prepared in advance in a targeted mode, teammates and game strategies are arranged according to the characteristics of opponents, the analysis result is fed back to athletes, and the athletes are helped to reduce the risk of injury. The system adopts a multi-view three-dimensional gesture detection method, acquires 3D gesture and position information of a player on a court through a plurality of video cameras containing depth information, recognizes the action of the player and tracks the track of the player, finally predicts and analyzes the action of the player, constructs a player movement gesture and track model, and recognizes the movement gesture on a competition field.
But has the following problems that 1, focusing on tracking of the track of a player, predicting and analyzing the action of the player, the method is suitable for basketball tactic teaching and has weak applicability to basketball training; 2. the three-dimensional dynamic output without the image is realized, and the athlete cannot review the self training action at the three-dimensional angle without the image; 3. progress analysis report of unassisted basketball training.
Disclosure of Invention
In view of the above problems, the present invention aims to provide an auxiliary system and method for basketball practice based on AI technology, which assists a trainer in reducing repeated teaching intensity; the athlete can be helped to review the self training action in a three-dimensional angle, the action defect is searched, the targeted measures are taken, and the training efficiency is improved.
The aim of the invention can be achieved by the following technical scheme: an auxiliary system for basketball practice based on an AI technology comprises an AI data acquisition part arranged on an entity basketball court, a display query terminal and an analysis processing part arranged on a background;
the AI data acquisition part comprises face recognition acquisition equipment and motion video acquisition equipment and is used for acquiring athlete face information and motion video data;
the analysis processing part comprises an AI identification processing server, a virtual simulation server and a data storage server;
the display inquiry terminal comprises a field display screen;
the AI recognition processing server is used for analyzing and processing the sports video data to generate athlete three-dimensional skeleton data;
the virtual simulation server is used for modeling venues and roles, binding athlete three-dimensional skeleton data and the roles and generating a rendering model for inquiry;
the venue display screen is configured to display a query rendering model.
An auxiliary method for basketball practice based on AI technology comprises the following steps:
s1, modeling basketball stadium and player roles by a virtual simulation server, and binding a digital simulation basketball court and a real basketball court;
s2, collecting athlete information by the face recognition acquisition equipment, and establishing an athlete training file;
s3, the sports video acquisition equipment acquires sports videos of athletes and transmits the sports videos to the AI recognition processing server;
s4, the AI recognition processing server recognizes and analyzes the sports video to generate athlete three-dimensional skeleton data;
s5, binding the athlete three-dimensional skeleton data and role modeling by the virtual simulation server, generating rendering model data, and transmitting the rendering model data to the data storage server and the display query terminal;
and S6, displaying the query dynamic rendering model by the display query terminal.
Further: in the step S4, the AI identification processing server identifies and analyzes the sports video to generate three-dimensional skeleton data of the athlete, and the method comprises the following steps:
s41, establishing a data set;
s42, extracting two-dimensional skeleton data, and comparing the data sets to obtain two-dimensional posture coordinates of the athlete;
s43, converting the two-dimensional gesture coordinates into three-dimensional gesture coordinates to obtain three-dimensional skeleton data.
A method for assisting basketball practice based on AI technology as claimed in claim 3, wherein: the step of extracting two-dimensional skeleton data in S42 includes the steps of:
s421, normalizing the input image, establishing a detection frame, and detecting the position of a human body in the detection frame;
s422, inputting the normalized image into a gesture estimation module, generating a gesture estimation suggestion, and comparing the gesture estimation suggestion with the actual gesture of the data set to generate a gesture estimation result;
s423, assigning a value to the attitude estimation result to generate two-dimensional skeleton data.
Further: in the step S5, the virtual simulation server realizes binding of the athlete three-dimensional skeleton data and role modeling, generates rendering model data, and transmits the rendering model data to the display query terminal, and includes the following steps:
s51, modeling a venue, and constructing a virtual basketball court;
s52, modeling roles, constructing virtual characters, determining key skeleton points of the virtual characters, and placing the motion trail of the key skeleton points on the constructed virtual characters;
s53, binding athlete three-dimensional skeleton data and virtual character key skeleton points;
s54, rendering the skeleton and the skin of the virtual character to form a rendering model; and obtaining the player rendering model animation.
Further: in S54, the skeleton and the skin of the avatar are rendered, wherein the face information data collected by the face recognition collection device is used for rendering the face skin of the avatar.
Further: and S5, the virtual simulation platform server also generates a training progress analysis report and an athlete personal action analysis report.
Further: the display inquiry terminal also comprises a mobile handheld terminal, wherein the handheld terminal is used for inquiring the rendering model animation, the training progress analysis report and the athlete personal action analysis report.
The invention has the beneficial effects that:
1. binding athlete three-dimensional skeleton data and virtual character modeling to generate a rendering model for inquiry; the athlete can review the self training action in a three-dimensional angle, compare the standard action, find the action to be insufficient, and reduce the repeated teaching intensity of a coach; the athlete can visually check the conditions of the acting points, the jump heights and the jump angles of the feet in training, find the defects of limb action coordination in ball control sports, find action defects, take targeted measures and improve training efficiency.
2. By generating the training progress analysis report and the athlete personal action analysis report, a coach is helped to master the training condition and the training progress of the athlete, and the training progress is received by targeted training, so that the pertinence of basketball training is improved, and the training efficiency is improved.
3. Through removing handheld terminal, supplementary coach teaching, the training condition of looking over the sportsman in a flexible way, look over motion progress and motion report, also make things convenient for the sportsman to look over the rendering model animation.
4. The facial information data acquired by adopting the facial recognition acquisition equipment is rendered on the facial skin of the virtual character, so that the facial features of the virtual character correspond to the athlete, and the athlete can feel the training process more vividly and intuitively when watching and playing back, can view the actions of the athlete at three-dimensional angles, and can restore the actions more truly.
Drawings
FIG. 1 is a schematic diagram of an auxiliary system for practicing basketball based on AI technology;
FIG. 2 is a flow chart of generating two-dimensional skeleton data by adopting an RMPE algorithm;
FIG. 3 is a flow chart of generating three-dimensional skeleton data using video Pose3D in accordance with the present invention;
FIG. 4 is a flowchart of the binding of athlete three-dimensional skeletal data with virtual character key skeletal points in accordance with the present invention.
100. An AI data acquisition unit; 110. face recognition acquisition equipment; 120. a motion video acquisition device;
200. displaying the query terminal; 210. a venue display screen;
300. an analysis processing unit; 310. an AI identification processing server; 320. a virtual simulation server; 330. and a data storage server.
Detailed Description
Embodiments of the present invention are described in detail below, examples of which are illustrated in the accompanying drawings, wherein like or similar symbols indicate like or similar elements or elements having like or similar functions throughout. The embodiments described below by referring to the drawings are exemplary only for explaining the present invention and are not to be construed as limiting the present invention.
As shown in fig. 1 to 4, the present invention discloses an auxiliary system for basketball practice based on AI technology, which comprises an auxiliary system for basketball practice based on AI technology, and is characterized in that: the basketball court comprises an AI data acquisition part 100 arranged on an entity basketball court, a display inquiry terminal 200 and an analysis processing part 300 arranged on a background; the AI data collection section 100 includes a face recognition collection device 110 and a sports video collection device 120 for collecting athlete face information and sports video data; the analysis processing section 300 includes an AI recognition processing server 310, a virtual simulation server 320, and a data storage server 330; the AI recognition processing server 310 is used for analyzing and processing the sports video data to generate athlete three-dimensional skeleton data; the virtual simulation server 320 is used for modeling venues and roles, binding athlete three-dimensional skeleton data and the roles and generating a rendering model for inquiry; the venue display screen 210 is used to display the query rendering model.
An auxiliary method for basketball practice based on AI technology comprises the following steps:
s1, modeling basketball stadium and player roles by a virtual simulation server 320, and binding a digital simulation basketball court and a real basketball court;
s2, the face recognition acquisition equipment 110 collects athlete information and builds an athlete training file;
s3, the sports video acquisition device 120 acquires sports videos of athletes and transmits the sports videos to the AI recognition processing server 310;
s4, the AI recognition processing server 310 recognizes and analyzes the sports video to generate athlete three-dimensional skeleton data;
s5, the virtual simulation server 320 realizes the binding of the athlete three-dimensional skeleton data and the role modeling, generates rendering model data, and transmits the rendering model data to the display query terminal 200;
s6, the display query terminal 200 displays the query dynamic rendering model.
The facial recognition collection device 110 is used to collect facial images of players, authenticate player information, and invoke database player information files, which include various items of data such as player name, birthday, height weight, pre-training action analysis report, etc., so that authenticated players and coaches can view player training data, complete basic information collection and comparative analysis of players.
The sports video collecting device 120 collects sports videos of the basketball court of the entity and transmits the sports videos to the AI identification processing server 310 in real time, the sports video collecting device 120 adopts a high-definition camera, such as a Haikang Wei view (DS-2 CD5A24 EFWD-IZS) camera, the resolution of the collected videos meets the high-definition requirement, high-definition video collection can be performed, motions, running distances and position videos of players can be collected and recorded in a multi-dimensional mode, the AI identification processing server 310 can conveniently analyze the motions, speeds, angles and other information of the players, accurate three-dimensional skeleton information is established, and one or more cameras can be adopted.
The AI-recognition processing server 310 is disposed in the background and is connected to the motion video capture device, the face recognition capture device 110, the virtual simulation server 320, and the storage server by using a wired network communication, a wireless network communication, or a 5G communication module.
The AI identification processing server 310 first creates a data set, including basketball training standard video, that includes single-person, multi-person basic training actions, such as: shooting, loading, in-situ dribbling, running dribbling, buckling, dribbling, and the like, wherein the dribbling breaks through, defends, and the like.
The AI recognition processing server 310 analyzes and processes the collected video, extracts two-dimensional skeleton data of the athlete by adopting a two-dimensional posture estimation algorithm, and the adopted two-dimensional posture estimation algorithm can be OpenPose, RMPE and other algorithms.
Taking RMPE algorithm as an example, as shown in fig. 2, the input image is normalized by YOLOv3 algorithm, the image size is divided into several grids, a detection frame is established, and the position of the human body in the detection frame is detected.
Then inputting the human body frame into a symmetry STN+SPPE module, wherein the RMPE algorithm uses a symmetrical STN and parallel SPPE, the SPPE trains a single image, the training STN moves the human body to the center of an extraction area through the parallel SPPE, and further accurate posture estimation is carried out through the SPPE, so that posture suggestions are automatically generated; and comparing the posture estimation proposal with the actual posture of the data set to generate a posture estimation result.
And adopting a PoseNMS module to assign a value to the attitude estimation result to generate two-dimensional skeleton data.
The YOLOv3 algorithm, the symmetry stn+sppe module and the pounms module in RMPE algorithm and RMPE algorithm are all in the prior art, and can be queried through the open literature.
The two-dimensional skeleton data are converted into 3D skeleton gesture data, a video Pose3D algorithm can be used, as shown in fig. 3, the video Pose3D algorithm uses a full-product network to perform time-domain convolution cloud processing on the key point sequence of the input two-dimensional skeleton data, and three-dimensional skeleton data are obtained.
Both the videoPose3D algorithm and the full product network are the prior art and can be queried through open literature.
The three-dimensional skeletal data corresponds to various parts of the athlete, such as: the three-dimensional skeleton data and key skeleton points of the virtual character are bound, so that the virtual character and the athlete are bound.
The virtual character can be constructed by adopting Posestudio software, the specific functions of the skeleton structure, some joints and the like of the virtual character can be effectively fixed, then a virtual basketball sport stadium is constructed by adopting Maya software, a virtual character model generated by Posestudio software is imported, and the technical actions of the virtual character are virtually simulated. The motion tracks of the key bones are placed on the constructed virtual figures, and the training process of the virtual athlete is controlled by controlling the motion tracks of the key bones, so that the technical characteristics of the basketball athlete can be mastered conveniently.
The virtual basketball venue is constructed by Maya software, the primary work is to restore the building with the maximum possibility according to the proportional size of the venue, various invisible surfaces existing in the model are reduced, and whether the virtual character model can accurately perform three-dimensional animation display is an assessment standard for judging whether the venue model is constructed well or not.
As shown in fig. 4, model construction is performed on a basketball player's task skeleton and skin by Maya software, a smooth virtual character model is obtained by means of UV texture mapping, simplified model surface number, merging organization and the like, three-dimensional skeleton data and virtual character key skeleton points are bound, and binding of the virtual character and the player is achieved.
And processing contents such as characters, environment, sound effects and the like at the later stage by using Mava software to obtain the three-dimensional animation of basketball training of the athlete.
When the Maya software is adopted to model and render basketball roles, the face information data acquired by the face recognition acquisition equipment 110 is adopted to render the face skins of the virtual characters, so that the facial features of the virtual characters correspond to athletes, the athletes can visually feel the training process of the athletes more vividly when watching and playing back the basketball roles, the athletes can view the actions of the athletes at three-dimensional angles, and the action can be restored more truly.
Further, the display query terminal 200 further includes a mobile handheld terminal, and the handheld terminal 220 is connected to the data storage server 330 through a network, and the handheld terminal 220 can be used for querying rendering model animation, training progress analysis report, athlete personal action analysis report, and is convenient to use.
The handheld terminal 220 can be used as exercise auxiliary equipment, and can be a mobile phone, a tablet computer or other portable electronic terminal equipment, and the handheld terminal 220 can assist a coach to master the situation of an athlete, can check exercise progress and exercise reports, and is convenient for the athlete to check rendering model animation.
Further, through the data analysis of the virtual simulation platform server, the main distinguishing points of the athlete movement time, the bouncing height, the movement angle and the standard movement can be obtained, and a movement report is generated for the athlete and a coach to check and analyze.
The sport report includes various aspects such as a training progress analysis report and an athlete personal action analysis report. The following is illustrated with a training schedule report:
basketball training subjects were 5.8mx5 return runs and full-field 3/4 accelerated runs, and 15 athletes in basketball training were speed tested on day 9 of 2022, day 1 of 2022, day 11 of 2022, and day 1 of 2022, respectively, and the results are shown in table 1.
TABLE 1 speed training test results
As can be seen from the exercise report in Table 1, the average time of 5.8mX5 times of retracing running and the average time of 3/4 accelerating running of the athletes before 9 months and 1 day are respectively 11.2s and 4.52s, and the overall time is longer; the basketball training progress conditions can be mastered by athletes and coaches, and the pertinence of basketball training is improved more, and training measures are adopted.
The foregoing is only a preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art, who is within the scope of the present invention, should make equivalent substitutions or modifications according to the technical scheme of the present invention and the inventive concept thereof, and should be covered by the scope of the present invention.
Claims (8)
1. An auxiliary system of basketball exercise based on AI technique, its characterized in that: the basketball court comprises an AI data acquisition part (100) arranged on an entity basketball court, a display inquiry terminal (200) and an analysis processing part (300) arranged on the background;
the AI data acquisition part (100) comprises a face recognition acquisition device (110) and a motion video acquisition device (120) which are used for acquiring athlete face information and motion video data;
the analysis processing unit (300) includes an AI identification processing server (310), a virtual simulation server (320), and a data storage server (330);
the display query terminal (200) includes a venue display screen (210);
the AI recognition processing server (310) is used for analyzing and processing the sports video data to generate athlete three-dimensional skeleton data;
the virtual simulation server (320) is used for modeling venues and roles, binding athlete three-dimensional skeleton data and the roles and generating a rendering model for inquiry;
the venue display screen (210) is for displaying a query rendering model.
2. An auxiliary method for basketball practice based on AI technology is characterized in that: the method comprises the following steps:
s1, modeling basketball venues and player roles by a virtual simulation server (320), and binding a digital simulation basketball court and a real basketball court;
s2, collecting athlete information by the face recognition acquisition equipment (110), and establishing an athlete training file;
s3, the sports video acquisition equipment (120) acquires sports videos of athletes and transmits the sports videos to the AI recognition processing server (310);
s4, an AI recognition processing server (310) recognizes and analyzes the sports video to generate athlete three-dimensional skeleton data;
s5, binding the athlete three-dimensional skeleton data and role modeling is achieved by the virtual simulation server (320), rendering model data are generated, and the rendering model data are transmitted to the data storage server (330) and the display query terminal (200);
and S6, displaying the query dynamic rendering model by the display query terminal (200).
3. The auxiliary method for basketball practice based on AI technology of claim 2, wherein: in the step S4, the AI-recognition processing server (310) recognizes and analyzes the sports video to generate three-dimensional skeleton data of the athlete, and the method comprises the following steps:
s41, establishing a data set;
s42, extracting two-dimensional skeleton data, and comparing the data sets to obtain two-dimensional posture coordinates of the athlete;
s43, converting the two-dimensional gesture coordinates into three-dimensional gesture coordinates to obtain three-dimensional skeleton data.
4. A method for assisting basketball practice based on AI technology as claimed in claim 3, wherein: the step of extracting two-dimensional skeleton data in S42 includes the steps of:
s421, normalizing the input image, establishing a detection frame, and detecting the position of a human body in the detection frame;
s422, inputting the normalized image into a gesture estimation module, generating a gesture estimation suggestion, and comparing the gesture estimation suggestion with the actual gesture of the data set to generate a gesture estimation result;
s423, assigning a value to the attitude estimation result to generate two-dimensional skeleton data.
5. The auxiliary method for basketball practice based on AI technology of claim 2, wherein: in the step S5, the virtual simulation server (320) implements binding of the athlete three-dimensional skeleton data and character modeling, generates rendering model data, and transmits the rendering model data to the display query terminal (200), and includes the following steps:
s51, modeling a venue, and constructing a virtual basketball court;
s52, modeling roles, constructing virtual characters, determining key skeleton points of the virtual characters, and placing the motion trail of the key skeleton points on the constructed virtual characters;
s53, binding athlete three-dimensional skeleton data and virtual character key skeleton points;
s54, rendering the skeleton and the skin of the virtual character to form a rendering model; and obtaining the player rendering model animation.
6. The AI-technology-based basketball practice assistance method of claim 5 wherein: in S54, the skeleton and the skin of the avatar are rendered, wherein the face of the avatar is rendered by using the face information data acquired by the face recognition acquisition device (110).
7. The auxiliary method for basketball practice based on AI technology of claim 2, wherein: and S5, the virtual simulation platform server also generates a training progress analysis report and an athlete personal action analysis report.
8. The intelligent playground training method based on the AI technology as set forth in claim 2, wherein: the display query terminal (200) further includes a mobile handheld terminal, the handheld terminal (220) for querying rendering model animations, training progress analysis reports, and athlete personal action analysis reports.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310223139.1A CN116271757A (en) | 2023-03-09 | 2023-03-09 | Auxiliary system and method for basketball practice based on AI technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310223139.1A CN116271757A (en) | 2023-03-09 | 2023-03-09 | Auxiliary system and method for basketball practice based on AI technology |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116271757A true CN116271757A (en) | 2023-06-23 |
Family
ID=86782904
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310223139.1A Pending CN116271757A (en) | 2023-03-09 | 2023-03-09 | Auxiliary system and method for basketball practice based on AI technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116271757A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117475514A (en) * | 2023-11-10 | 2024-01-30 | 广州市微锋科技有限公司 | Shooting training system and method based on image analysis |
-
2023
- 2023-03-09 CN CN202310223139.1A patent/CN116271757A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117475514A (en) * | 2023-11-10 | 2024-01-30 | 广州市微锋科技有限公司 | Shooting training system and method based on image analysis |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109191588B (en) | Motion teaching method, motion teaching device, storage medium and electronic equipment | |
| CN108734104B (en) | Body-building action error correction method and system based on deep learning image recognition | |
| KR100772497B1 (en) | Golf clinic system and application method thereof | |
| US11113988B2 (en) | Apparatus for writing motion script, apparatus for self-teaching of motion and method for using the same | |
| CN110739040A (en) | rehabilitation evaluation and training system for upper and lower limbs | |
| TWI537767B (en) | System and method of multi-user coaching inside a tunable motion-sensing range | |
| CN104766503A (en) | cardiopulmonary resuscitation teaching system and method | |
| CN107220608B (en) | Basketball action model reconstruction and defense guidance system and method | |
| CN109815930B (en) | Method for evaluating action simulation fitting degree | |
| CN107930048B (en) | Space somatosensory recognition motion analysis system and motion analysis method | |
| KR20220028654A (en) | Apparatus and method for providing taekwondo movement coaching service using mirror dispaly | |
| KR101555863B1 (en) | Device and method for taekwondo poomsae readout and education | |
| JP2020174910A (en) | Exercise support system | |
| CN113409651B (en) | Live broadcast body building method, system, electronic equipment and storage medium | |
| CN116271757A (en) | Auxiliary system and method for basketball practice based on AI technology | |
| Yang et al. | Research on face recognition sports intelligence training platform based on artificial intelligence | |
| Ma et al. | Development of the Interactive Rehabilitation Game System for Children with Autism Based on Game Psychology | |
| CN112966370B (en) | Design method of human body lower limb muscle training system based on Kinect | |
| CN114093032A (en) | Human body action evaluation method based on action state information | |
| CN112933581A (en) | Sports action scoring method and device based on virtual reality technology | |
| CN114832349B (en) | Yuanzhou swimming teaching auxiliary system and use method thereof | |
| KR20170140756A (en) | Appratus for writing motion-script, appratus for self-learning montion and method for using the same | |
| CN110223748A (en) | A kind of processing method of internet of things data, device and Internet of things system | |
| Wei et al. | Sports motion analysis based on mobile sensing technology | |
| Kahtan et al. | Motion analysis-based application for enhancing physical education |
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 |