CN114377367A - Badminton training action evaluation system based on machine vision - Google Patents
Badminton training action evaluation system based on machine vision Download PDFInfo
- Publication number
- CN114377367A CN114377367A CN202210045755.8A CN202210045755A CN114377367A CN 114377367 A CN114377367 A CN 114377367A CN 202210045755 A CN202210045755 A CN 202210045755A CN 114377367 A CN114377367 A CN 114377367A
- Authority
- CN
- China
- Prior art keywords
- badminton
- training action
- training
- parameters
- motion
- 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
- 238000012549 training Methods 0.000 title claims abstract description 102
- 230000009471 action Effects 0.000 title claims abstract description 90
- 238000011156 evaluation Methods 0.000 title claims abstract description 28
- 230000004927 fusion Effects 0.000 claims abstract description 14
- 238000012800 visualization Methods 0.000 claims description 7
- 239000011159 matrix material Substances 0.000 claims description 6
- 238000012937 correction Methods 0.000 claims description 3
- 238000003062 neural network model Methods 0.000 claims description 3
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000000034 method Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
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
- A63B69/0017—Training appliances or apparatus for special sports for badminton
-
- 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
- A63B71/0619—Displays, user interfaces and indicating devices, specially adapted for sport equipment, e.g. display mounted on treadmills
Landscapes
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Physical Education & Sports Medicine (AREA)
- Engineering & Computer Science (AREA)
- Human Computer Interaction (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The invention relates to the field of badminton training, in particular to a badminton training action evaluation system based on machine vision, which comprises: the binocular vision sensing module is used for directionally acquiring badminton training action videos; the infrared light curtain group is used for acquiring badminton motion trail parameters and badminton racket motion trail parameters; the feature fusion module is used for realizing fusion of badminton training action videos, badminton motion track parameters and badminton racket motion track parameters to obtain training action enhancement feature sets; and the training action evaluation module is used for realizing evaluation of the badminton training action based on the training action enhanced feature set. The invention realizes the automatic judgment and guidance of the badminton training action and has high precision.
Description
Technical Field
The invention relates to the field of badminton training, in particular to a badminton training action evaluation system based on machine vision.
Background
Shuttlecocks are a very popular sport. In the training process of the badminton, training of various actions such as serving, catching and pushing needs to be performed. The traditional badminton training guidance mode is that the badminton is evaluated and corrected under supervision and guidance of a coach, a professional is required to guide practice in a specific environment, personal experience factors are generally carried in an evaluation result, and meanwhile, due to the limitation of human observation, the situation that the evaluation result is incomplete easily exists, and the situation that training actions are not standard or the training progress is stopped can be caused to a certain extent.
Disclosure of Invention
In order to solve the problems, the invention provides a badminton training action evaluation system based on machine vision, which realizes automatic judgment and guidance of badminton training actions and has high accuracy.
In order to achieve the purpose, the invention adopts the technical scheme that:
a machine vision-based badminton training motion assessment system, comprising:
the binocular vision sensing module is used for directionally acquiring badminton training action videos;
the infrared light curtain group is used for acquiring badminton motion trail parameters and badminton racket motion trail parameters;
the feature fusion module is used for realizing fusion of badminton training action videos, badminton motion track parameters and badminton racket motion track parameters to obtain training action enhancement feature sets;
and the training action evaluation module is used for realizing evaluation of the badminton training action based on the training action enhanced feature set.
Furthermore, the badminton training action video needs to cover the badminton motion track, the badminton racket motion track and the human body posture motion track.
Furthermore, the badminton motion trail parameters, the badminton racket motion trail parameters and the human body posture motion trail parameters all comprise motion angle parameters and motion direction parameters.
Furthermore, the feature fusion module firstly calls a video frame taking script, obtains a badminton training action image at intervals of a certain number of frames, obtains human body depth information and skeleton information carried in the badminton training action image through kinect depth sensor data, eliminates jitter and noise interference of the obtained skeleton information, obtains angle rotation movement SO3 matrix information of all skeleton pairs, and then connects the angle rotation movement SO3 matrix information with corresponding badminton motion trajectory parameters and badminton racket motion trajectory parameters in series to form a training action enhancement feature set.
Further, the training action evaluation module realizes evaluation of the badminton training action according to the training action enhancement feature set based on the wireless deep neural network model.
Further, still include:
and the training action visualization module is used for completing the fusion of the badminton training action video and badminton motion trail parameters, badminton racket motion trail parameters and human posture motion trail parameters, and acquiring a badminton training action image set carrying the badminton motion trail parameters, the badminton racket motion trail parameters and the human posture motion trail parameters, so that the visualization of each badminton training action parameter is realized.
Further, still include:
the training action correcting module is used for generating corresponding training action guide opinions based on the evaluation result of the badminton training action;
and the training result summarizing module is used for summarizing training data according to seasons monthly, is convenient for a trainer to inquire the exercise condition, and mainly comprises the times of each action training, a matching value and action correction guidance suggestions.
The invention has the following characteristics and advantages:
1) the badminton training action is automatically judged and guided based on the training action enhancement feature set integrated with the badminton training action video, the badminton motion track parameters and the badminton racket motion track parameters, and the accuracy of the action evaluation result is greatly improved.
2) The visualization of each badminton training action parameter is realized based on the badminton training action image set carrying the badminton motion trail parameters, the badminton racket motion trail parameters and the human body posture motion trail parameters, so that the positions of the distinguishing points between each action and the standard actions can be conveniently and clearly known, and a targeted reference suggestion is provided for subsequent training.
Drawings
Fig. 1 is a badminton training action evaluation system based on machine vision according to an embodiment of the present invention.
Detailed Description
In order to make the objects and advantages of the present invention clearer, the following detailed description is further made with reference to examples. It should be understood that the specific examples described herein are intended to be illustrative only and are not intended to be limiting.
As shown in fig. 1, an embodiment of the present invention provides a badminton training action evaluation system based on machine vision, including:
the binocular vision sensing module is used for directionally acquiring badminton training action videos;
the infrared light curtain group is used for acquiring badminton motion trail parameters and badminton racket motion trail parameters;
the feature fusion module is used for realizing fusion of badminton training action videos, badminton motion track parameters and badminton racket motion track parameters to obtain training action enhancement feature sets; specifically, the feature fusion module calls a video frame taking script to obtain a badminton training action image at regular intervals, obtains human body depth information and skeleton information carried in the badminton training action image through kinect depth sensor data, eliminates jitter and noise interference of the obtained skeleton information, obtains angle rotation movement SO3 matrix information of all skeleton pairs, and then connects the angle rotation movement SO3 matrix information with corresponding badminton motion trajectory parameters and badminton racket motion trajectory parameters in series to form a training action enhancement feature set.
The training action evaluation module is used for realizing evaluation of badminton training actions according to the training action enhancement feature set based on the wireless deep neural network model;
and the training action visualization module is used for completing the fusion of the badminton training action video and badminton motion trail parameters, badminton racket motion trail parameters and human posture motion trail parameters, and acquiring a badminton training action image set carrying the badminton motion trail parameters, the badminton racket motion trail parameters and the human posture motion trail parameters, so that the visualization of each badminton training action parameter is realized.
The training action correcting module is used for generating corresponding training action guide opinions based on the evaluation result of the badminton training action;
and the training result summarizing module is used for summarizing training data according to seasons monthly, is convenient for a trainer to inquire the exercise condition, and mainly comprises the times of each action training, a matching value and action correction guidance suggestions.
In this embodiment, badminton training action video needs to cover badminton motion trail, badminton racket motion trail and human gesture motion trail, badminton motion trail parameter, badminton racket motion trail parameter, human gesture motion trail parameter all include motion angle parameter and direction of motion parameter, and wherein, badminton motion trail parameter needs to include the starting point coordinate information, peak coordinate information and the coordinate information of landing point of badminton, and badminton racket motion trail parameter needs to include the starting point coordinate information (with badminton row top central point as monitoring point), terminal point coordinate information when the racket waves.
The foregoing is only a preferred embodiment of the present invention, and it should be noted that those skilled in the art can make various improvements and modifications without departing from the principle of the present invention, and these improvements and modifications should also be construed as the protection scope of the present invention.
Claims (7)
1. A badminton training action evaluation system based on machine vision is characterized by comprising:
the binocular vision sensing module is used for directionally acquiring badminton training action videos;
the infrared light curtain group is used for acquiring badminton motion trail parameters and badminton racket motion trail parameters;
the feature fusion module is used for realizing fusion of badminton training action videos, badminton motion track parameters and badminton racket motion track parameters to obtain training action enhancement feature sets;
and the training action evaluation module is used for realizing evaluation of the badminton training action based on the training action enhanced feature set.
2. The machine vision-based badminton training motion assessment system according to claim 1, wherein the badminton training motion video is required to cover badminton motion trail, badminton racket motion trail and human body posture motion trail.
3. The machine vision-based badminton training motion assessment system according to claim 1, wherein the badminton motion trail parameters, the badminton racket motion trail parameters and the human body posture motion trail parameters comprise motion angle parameters and motion direction parameters.
4. The badminton training action evaluation system based on machine vision of claim 1, wherein the feature fusion module firstly calls a video frame taking script to obtain a badminton training action image at regular frame intervals, obtains human body depth information and skeleton information carried in the badminton training action image through kinect depth sensor data, eliminates shaking and noise interference of the obtained skeleton information, obtains angular rotation movement SO3 matrix information of all skeleton pairs, and then connects the angular rotation movement SO3 matrix information with corresponding badminton motion trajectory parameters and badminton racket motion trajectory parameters in series to form a training action enhancement feature set.
5. The machine vision-based badminton training action evaluation system of claim 1, wherein the training action evaluation module implements evaluation of badminton training action according to a training action enhancement feature set based on a wireless deep neural network model.
6. The machine vision-based badminton training motion assessment system according to claim 1, further comprising:
and the training action visualization module is used for completing the fusion of the badminton training action video and badminton motion trail parameters, badminton racket motion trail parameters and human posture motion trail parameters, and acquiring a badminton training action image set carrying the badminton motion trail parameters, the badminton racket motion trail parameters and the human posture motion trail parameters, so that the visualization of each badminton training action parameter is realized.
7. The machine vision-based badminton training motion assessment system according to claim 1, further comprising:
the training action correcting module is used for generating corresponding training action guide opinions based on the evaluation result of the badminton training action;
and the training result summarizing module is used for summarizing training data according to seasons monthly, so that a trainer can conveniently inquire the exercise condition and the exercise condition comprises the times of each action training, the matching value and the action correction guidance suggestion.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210045755.8A CN114377367A (en) | 2022-01-16 | 2022-01-16 | Badminton training action evaluation system based on machine vision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210045755.8A CN114377367A (en) | 2022-01-16 | 2022-01-16 | Badminton training action evaluation system based on machine vision |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114377367A true CN114377367A (en) | 2022-04-22 |
Family
ID=81202559
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210045755.8A Pending CN114377367A (en) | 2022-01-16 | 2022-01-16 | Badminton training action evaluation system based on machine vision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114377367A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110354481A (en) * | 2019-07-30 | 2019-10-22 | 天水师范学院 | A kind of athletic training analysis system based on digital field and high-speed image |
| CN110433471A (en) * | 2019-08-13 | 2019-11-12 | 宋雅伟 | A kind of badminton track monitoring analysis system and method |
| US20210178244A1 (en) * | 2019-12-13 | 2021-06-17 | Rapsodo Pte. Ltd. | Kinematic analysis of user form |
| CN113384861A (en) * | 2021-05-20 | 2021-09-14 | 上海奥视达智能科技有限公司 | Table tennis training device, table tennis training method, and computer-readable storage medium |
| CN113476815A (en) * | 2021-05-17 | 2021-10-08 | 张昌昊 | Intelligent sports auxiliary training method and system based on E-ink |
-
2022
- 2022-01-16 CN CN202210045755.8A patent/CN114377367A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110354481A (en) * | 2019-07-30 | 2019-10-22 | 天水师范学院 | A kind of athletic training analysis system based on digital field and high-speed image |
| CN110433471A (en) * | 2019-08-13 | 2019-11-12 | 宋雅伟 | A kind of badminton track monitoring analysis system and method |
| US20210178244A1 (en) * | 2019-12-13 | 2021-06-17 | Rapsodo Pte. Ltd. | Kinematic analysis of user form |
| CN113476815A (en) * | 2021-05-17 | 2021-10-08 | 张昌昊 | Intelligent sports auxiliary training method and system based on E-ink |
| CN113384861A (en) * | 2021-05-20 | 2021-09-14 | 上海奥视达智能科技有限公司 | Table tennis training device, table tennis training method, and computer-readable storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| AU2017331639B2 (en) | A system and method to analyze and improve sports performance using monitoring devices | |
| US8781610B2 (en) | Method of ball game motion recognition, apparatus for the same, and motion assisting device | |
| CN109260672B (en) | Motion data analysis method and device, wearable device and storage medium | |
| US20190246981A1 (en) | Limb movement gesture judgment method and device | |
| CN111444890A (en) | Sports data analysis system and method based on machine learning | |
| WO2017103270A1 (en) | Method and device for analysis of movement of a piece of sports equipment | |
| CN107803010B (en) | Table tennis training system | |
| US20160296795A1 (en) | Apparatus and method for analyzing golf motion | |
| US20210170580A1 (en) | Action imitation method and robot and computer readable medium using the same | |
| CN111259716A (en) | Human body running posture identification and analysis method and device based on computer vision | |
| CN101836237A (en) | Be used to select the method and system of watching configuration of rendered figure | |
| CN111184994B (en) | Batting training method, terminal equipment and storage medium | |
| CN108905182B (en) | Intelligent glasses and billiard shooting positioning and aiming method | |
| KR101972526B1 (en) | golf swing correcting system | |
| CN110929595A (en) | System and method for training or entertainment with or without ball based on artificial intelligence | |
| KR20100033205A (en) | System suppporting golf practice and method therefor | |
| CN107106900A (en) | Detection means, detecting system, motion analysis system, recording medium and analysis method | |
| CN114377367A (en) | Badminton training action evaluation system based on machine vision | |
| CN109464798B (en) | Sensory data driven snooker auxiliary exercise method | |
| US20230285832A1 (en) | Automatic ball machine apparatus utilizing player identification and player tracking | |
| Maeda et al. | Sport skill classification using time series motion picture data | |
| Dhinesh et al. | Tennis serve correction using a performance improvement platform | |
| CN112802051B (en) | Fitting method and system of basketball shooting curve based on neural network | |
| CN112494915A (en) | Badminton robot and system and control method thereof | |
| Okuno et al. | Body posture and face orientation estimation by convolutional network with heterogeneous learning |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20220422 |