CN111773651A - Badminton training monitoring and evaluating system and method based on big data - Google Patents
Badminton training monitoring and evaluating system and method based on big data Download PDFInfo
- Publication number
- CN111773651A CN111773651A CN202010639259.6A CN202010639259A CN111773651A CN 111773651 A CN111773651 A CN 111773651A CN 202010639259 A CN202010639259 A CN 202010639259A CN 111773651 A CN111773651 A CN 111773651A
- Authority
- CN
- China
- Prior art keywords
- badminton
- training
- module
- data
- action
- 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
- 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
- A63B71/0622—Visual, audio or audio-visual systems for entertaining, instructing or motivating the user
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items
- G06V20/42—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items of sport video content
-
- 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
- G06V40/23—Recognition of whole body movements, e.g. for sport training
-
- A—HUMAN NECESSITIES
- A63—SPORTS; GAMES; AMUSEMENTS
- A63B—APPARATUS FOR PHYSICAL TRAINING, GYMNASTICS, SWIMMING, CLIMBING, OR FENCING; BALL GAMES; TRAINING EQUIPMENT
- A63B2230/00—Measuring physiological parameters of the user
- A63B2230/20—Measuring physiological parameters of the user blood composition characteristics
-
- A—HUMAN NECESSITIES
- A63—SPORTS; GAMES; AMUSEMENTS
- A63B—APPARATUS FOR PHYSICAL TRAINING, GYMNASTICS, SWIMMING, CLIMBING, OR FENCING; BALL GAMES; TRAINING EQUIPMENT
- A63B2230/00—Measuring physiological parameters of the user
- A63B2230/70—Measuring physiological parameters of the user body fat
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- Software Systems (AREA)
- Computational Linguistics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Psychiatry (AREA)
- Social Psychology (AREA)
- Physical Education & Sports Medicine (AREA)
- Image Analysis (AREA)
Abstract
The invention belongs to the technical field of badminton training monitoring evaluation, and discloses a badminton training monitoring evaluation system and method based on big data, wherein the badminton training monitoring evaluation system based on the big data comprises: the training video collection module, the physiological index collection module, the main control module, the action recognition module, the action analysis module, the training scheme editing module, the training result statistics module, the training quality evaluation module, the cloud service module and the display module. The badminton training score is counted through a training score counting module and a counting program; and data classification is carried out by using an association rule mining algorithm. According to the badminton training action recognition method, the action recognition module does not need to calculate all characteristic data at the same time, the type judgment frequency can be automatically adjusted, the calculation amount is effectively reduced, and the real-time performance of the badminton training action recognition method is guaranteed; meanwhile, accurate motion analysis data are obtained through the motion analysis module, and the badminton training quality is improved.
Description
Technical Field
The invention belongs to the technical field of badminton training monitoring evaluation, and particularly relates to a badminton training monitoring evaluation system and method based on big data.
Background
At present, the badminton is a sport which can be carried out indoors and outdoors. According to the number of people participating, the method can be divided into single-beat and double-beat, and the emerging 3 beats 3. The badminton racket consists of a racket face, a racket rod, a racket handle and a racket frame and a racket rod joint. The length of a racket is no more than 680 mm, wherein the length of a racket handle and a racket rod is no more than 41 cm, the length of a racket frame is 28 cm, and the width of the racket frame is 23 cm. However, the existing badminton training monitoring and evaluating technology based on big data has a large operation amount for motion recognition, and training motions cannot be recognized in real time; meanwhile, the existing badminton training monitoring and evaluating technology based on big data cannot accurately analyze badminton movement.
Through the above analysis, the problems and defects of the prior art are as follows: the existing badminton training monitoring and evaluating technology based on big data has large operation amount for recognizing actions and can not recognize training actions in real time; meanwhile, the existing badminton training monitoring and evaluating technology based on big data cannot accurately analyze badminton movement.
Disclosure of Invention
Aiming at the problems in the prior art, the invention provides a badminton training monitoring and evaluating system and method based on big data.
The invention is realized in such a way that a badminton training monitoring and evaluating method based on big data comprises the following steps:
the method comprises the following steps that firstly, a training video acquisition module acquires a badminton training video through a camera, and a physiological index acquisition module acquires physiological data of proteins, body fat percentage, vitamins, amino acids, trace elements, hormones and the like of badminton training athletes through medical equipment;
step two, according to the badminton training video and the physiological data of badminton training athletes collected in the step one, the main control module respectively controls each module of the training video collection module, the physiological index collection module, the action recognition module, the action analysis module, the training scheme editing module, the training result counting module, the training quality evaluation module, the cloud service module and the display module to work normally;
step three, the main control module controls the action recognition module to recognize badminton training actions according to the collected videos through a recognition program, the action analysis module analyzes the badminton training actions through an analysis program, and the training scheme editing module compiles a badminton training scheme through an editing program;
fourthly, badminton training is carried out according to the badminton training scheme, the main control module controls the training result counting module to count the badminton training results through a counting program, and meanwhile, the training quality evaluation module is controlled to evaluate the badminton training quality through an evaluation program;
fifthly, in the process, the main control module controls the display module to collect badminton training videos, physiological indexes, action recognition results, action analysis results, training schemes, training result statistics results and training quality evaluation results through the display, and the cloud service module collects large data resources through the cloud server to perform cloud processing on badminton training data;
the action recognition module recognition method comprises the following steps:
(1) collecting motion data of badminton actors through camera equipment; calculating first characteristic data representing the motion state of the badminton player according to the motion data, and judging whether the badminton player is in a static state or a motion state according to the first characteristic data;
(2) responding to the situation that the badminton player is in the sports action state, calculating second characteristic data representing the sports action type of the badminton player according to the sports action data, and judging the sports action type of the badminton player according to the second characteristic data;
(3) according to the determined motion action type, calculating third characteristic data representing motion actions according to the motion action data, and judging the motion actions of the badminton player according to the third characteristic data;
the action analysis module analysis method comprises the following steps:
1) acquiring badminton motion state data I of a target object through motion capture equipment, and performing normal normalization pretreatment on the badminton motion state data I to obtain badminton motion state data II;
2) determining badminton training actions corresponding to the badminton motion state data II, and calling reference actions of the badminton training actions from a reference action library;
3) determining the similarity between the badminton motion state data II and the badminton motion state data III of the reference action; and analyzing the badminton training action of the target object according to the similarity to obtain analysis data.
Further, the judging whether the badminton player is in a static state or a moving state according to the first characteristic data comprises:
(1.1) calculating the maximum value of the one-time actual combined acceleration at a preset first time interval, comparing the maximum value of the actual combined acceleration with a first preset value, and recording the times of exceeding the first preset value;
(1.2) calculating whether the times exceeding the first preset value exceeds a second preset value in a preset second time period, if so, judging that the badminton player is in a motion state, and if not, judging that the badminton player is in a static state, wherein the second time period comprises a plurality of first time periods.
Further, the judging the motion type of the badminton player according to the second characteristic data comprises:
setting a first detection frequency, detecting the motion state of the badminton player for multiple times according to the first detection frequency, respectively calculating second characteristic data corresponding to the motion state of each time, and judging the motion type of the badminton player according to the second characteristic data;
responding to the consistency of the multiple judgment results, outputting the motion action type determined by the multiple judgment, and switching to a second detection frequency to detect the motion action state of the badminton player for multiple times;
responding to the dispersion of the multiple judgment results, and continuing to maintain the first detection frequency;
wherein the first detection frequency is greater than the second detection frequency.
Further, the switching to the second detection frequency for detecting the motion state of the badminton player for a plurality of times comprises the following steps:
respectively calculating second characteristic data corresponding to the motion action state of each time, and judging the motion action type of the badminton player according to the second characteristic data;
responding to the consistency of the multiple judgment results, outputting the motion action type determined by the multiple judgment, and continuously keeping the second detection frequency;
and switching to the first detection frequency in response to the dispersion of the multiple judgment results.
Further, before the reference action of the badminton training action is called, the method further comprises the following steps:
collecting a plurality of groups of historical badminton motion state data in a historical time period and historical badminton training actions corresponding to each group of historical badminton motion state data in the plurality of groups of historical badminton motion state data;
training the collected historical badminton training actions corresponding to each group of historical badminton motion state data in the multiple groups of historical badminton motion state data and the multiple groups of historical badminton motion state data to obtain reference actions corresponding to each group of badminton motion state data in the multiple groups of historical badminton motion state data;
and storing the reference action corresponding to each group of badminton motion state data in the plurality of groups of historical badminton motion state data to obtain the reference action library.
Further, before determining the similarity between the badminton motion state data II and the badminton motion state data III of the reference action, the method further comprises the following steps: and carrying out coordinate conversion on the badminton motion state data II by utilizing a Principal Component Analysis (PCA).
Further, the coordinate conversion of the badminton motion state data II by utilizing a Principal Component Analysis (PCA) method comprises the following steps:
determining each group of badminton motion state data in the badminton motion state data II to perform track centralization processing;
generating a data matrix corresponding to the badminton motion state data according to the badminton motion state data obtained by track centralization processing;
generating a covariance matrix according to the data matrix, and obtaining an eigenvector and an eigenvalue of the covariance matrix;
generating an intermediate matrix according to the eigenvector of the covariance matrix;
and obtaining the badminton motion state data II after the coordinate conversion according to the intermediate matrix.
Further, in the training video acquisition module acquires the badminton training video through the camera, the process of denoising images in the video is as follows:
acquiring badminton training videos by a training video acquisition module camera, extracting image fragments, and identifying and judging images containing noise;
in a badminton training image containing noise, determining a circular neighborhood with a pixel as a central point,
determining pixel values in a circular neighborhood and sequencing the pixel values; selecting an intermediate pixel value as a correction pixel value according to the ordering of the pixels;
and continuously utilizing the correction pixel values in the circular neighborhood to carry out smoothing processing on the pixels in the correction neighborhood.
Another object of the present invention is to provide a big data-based badminton training monitoring and evaluating system for implementing the big data-based badminton training monitoring and evaluating method, the big data-based badminton training monitoring and evaluating system comprising:
the training system comprises a training video acquisition module, a physiological index acquisition module, a main control module, an action recognition module, an action analysis module, a training scheme editing module, a training result counting module, a training quality evaluation module, a cloud service module and a display module;
the training video acquisition module is connected with the main control module and is used for acquiring a badminton training video through the camera; meanwhile, a training video acquisition module camera is used for acquiring a badminton training video, extracting image fragments and identifying and judging images containing noise; determining a circular neighborhood with pixels as central points in a badminton training image containing noise, determining pixel values in the circular neighborhood, and sequencing; selecting an intermediate pixel value as a correction pixel value according to the ordering of the pixels; continuously utilizing the correction pixel values in the circular neighborhood to carry out smoothing treatment on the pixels in the correction neighborhood;
the physiological index acquisition module is connected with the main control module and is used for acquiring physiological data of proteins, body fat percentage, vitamins, amino acids, trace elements, hormones and the like of badminton training athletes through medical equipment;
the main control module is connected with the training video acquisition module, the physiological index acquisition module, the action recognition module, the action analysis module, the training scheme editing module, the training result counting module, the training quality evaluation module, the cloud service module and the display module and is used for controlling each module to normally work through the host;
the cloud service module is connected with the main control module and is used for carrying out cloud processing on the badminton training data by centralizing big data resources through the cloud server; and the display module is connected with the main control module and is used for acquiring badminton training videos, physiological indexes, action recognition results, action analysis results, training schemes, training result statistical results and training quality evaluation results through a display.
Further, badminton training monitoring and evaluating system based on big data still includes:
the motion recognition module is connected with the main control module and used for recognizing badminton training motions according to the collected videos through a recognition program; collecting motion data of badminton actors through camera equipment; calculating first characteristic data representing the motion state of the badminton player according to the motion data, and judging whether the badminton player is in a static state or a motion state according to the first characteristic data; responding to the situation that the badminton player is in the sports action state, calculating second characteristic data representing the sports action type of the badminton player according to the sports action data, and judging the sports action type of the badminton player according to the second characteristic data; according to the determined motion action type, calculating third characteristic data representing motion actions according to the motion action data, and judging the motion actions of the badminton player according to the third characteristic data;
the action analysis module is connected with the main control module and is used for analyzing the badminton training action through an analysis program; acquiring badminton motion state data I of a target object through motion capture equipment, and performing normal normalization pretreatment on the badminton motion state data I to obtain badminton motion state data II; determining badminton training actions corresponding to the badminton motion state data II, and calling reference actions of the badminton training actions from a reference action library; determining the similarity between the badminton motion state data II and the badminton motion state data III of the reference action; analyzing the badminton training action of the target object according to the similarity to obtain analysis data;
the training scheme editing module is connected with the main control module, and is used for compiling a badminton training scheme through an editing program according to the data obtained by the identification and analysis of the action identification module and the action analysis module;
the training score counting module is connected with the main control module and is used for counting the training scores of the shuttlecocks through a counting program; mining all class association rules meeting the specified support degree and confidence degree from the training data set by using an association rule mining algorithm; selecting a group of high-quality rules from the mined class association rules by using a heuristic method for classification;
and the training quality evaluation module is connected with the main control module and used for evaluating the training quality of the badminton through an evaluation program according to the badminton training scores classified and counted by the training score counting module.
By combining all the technical schemes, the invention has the advantages and positive effects that: the badminton training video is acquired through the training video acquisition module and the camera; meanwhile, images containing noise are subjected to smoothing processing, so that the accuracy of the whole badminton training monitoring evaluation is improved; the physiological index acquisition module is connected with the main control module and is used for acquiring physiological data of proteins, body fat percentage, vitamins, amino acids, trace elements, hormones and the like of badminton training athletes through medical equipment; the cloud service module is connected with the main control module and is used for carrying out cloud processing on the badminton training data by centralizing big data resources through the cloud server; the display module is connected with the main control module and is used for acquiring badminton training videos, physiological indexes, action recognition results, action analysis results, training schemes, training result statistical results and training quality evaluation results through a display; the motion recognition module is used for recognizing badminton training motions according to the collected video through a recognition program; the motion analysis module analyzes the badminton training motion through an analysis program; the training scheme editing module is used for compiling a badminton training scheme through an editing program; the training result counting module counts the training results of the shuttlecocks through a counting program; and the training quality evaluation module is used for evaluating the training quality of the badminton through an evaluation program. According to the badminton training action recognition method, the action recognition module does not need to calculate all characteristic data at the same time, the type judgment frequency can be automatically adjusted, the calculation amount is effectively reduced, and the real-time performance of the badminton training action recognition method is guaranteed; meanwhile, badminton motion state data I of the target object are collected through the motion analysis module, and normal normalization pretreatment is carried out on the badminton motion state data I to obtain badminton motion state data II; then determining badminton training actions corresponding to the badminton motion state data II, and calling reference actions of the badminton training actions from a reference action library; determining the similarity between the badminton motion state data II and the badminton motion state data III of the reference action; and analyzing the badminton training action of the target object according to the similarity to obtain accurate action analysis data, and improving the badminton training quality.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed to be used in the embodiments of the present application will be briefly described below, and it is obvious that the drawings described below are only some embodiments of the present application, and it is obvious for those skilled in the art that other drawings can be obtained from the drawings without creative efforts.
FIG. 1 is a block diagram of a big data-based badminton training monitoring and evaluation system according to an embodiment of the present invention.
FIG. 2 is a flow chart of a big data-based badminton training monitoring and evaluation method provided by the embodiment of the invention.
Fig. 3 is a flowchart of an identification method of an action identification module according to an embodiment of the present invention.
Fig. 4 is a flowchart of a method for determining whether the badminton player is in a stationary state or a moving state according to the first characteristic data.
Fig. 5 is a flowchart of an action parsing module parsing method according to an embodiment of the present invention.
In fig. 2: 1. a training video acquisition module; 2. a physiological index acquisition module; 3. a main control module; 4. an action recognition module; 5. an action analysis module; 6. a training scheme editing module; 7. a training result statistic module; 8. a training quality evaluation module; 9. a cloud service module; 10. and a display module.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is further described in detail with reference to the following embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
Aiming at the problems in the prior art, the invention provides a badminton training monitoring and evaluating system and method based on big data, and the invention is described in detail below with reference to the accompanying drawings.
As shown in fig. 1, the badminton training monitoring and evaluating system based on big data provided by the embodiment of the present invention includes: the training video collection system comprises a training video collection module 1, a physiological index collection module 2, a main control module 3, an action recognition module 4, an action analysis module 5, a training scheme editing module 6, a training result counting module 7, a training quality evaluation module 8, a cloud service module 9 and a display module 10.
The training video acquisition module 1 is connected with the main control module 3 and is used for acquiring a badminton training video through a camera;
the physiological index acquisition module 2 is connected with the main control module 3 and is used for acquiring physiological data of proteins, body fat percentage, vitamins, amino acids, trace elements, hormones and the like of badminton training athletes through medical equipment;
the main control module 3 is connected with the training video acquisition module 1, the physiological index acquisition module 2, the action recognition module 4, the action analysis module 5, the training scheme editing module 6, the training result counting module 7, the training quality evaluation module 8, the cloud service module 9 and the display module 10, and is used for controlling each module to normally work through a host;
the motion recognition module 4 is connected with the main control module 3 and used for recognizing badminton training motions according to the collected videos through a recognition program;
the action analysis module 5 is connected with the main control module 3 and is used for analyzing the badminton training action through an analysis program;
the training scheme editing module 6 is connected with the main control module 3 and used for compiling a badminton training scheme through an editing program;
the training result counting module 7 is connected with the main control module 3 and is used for counting the training results of the badminton through a counting program; mining all class association rules meeting the specified support degree and confidence degree from the training data set by using an association rule mining algorithm; selecting a group of high-quality rules from the mined class association rules by using a heuristic method for classification;
the training quality evaluation module 8 is connected with the main control module 3 and used for evaluating the training quality of the badminton through an evaluation program;
the cloud service module 9 is connected with the main control module 3 and is used for carrying out cloud processing on the badminton training data by centralizing big data resources through a cloud server;
and the display module 10 is connected with the main control module 3 and is used for acquiring badminton training videos, physiological indexes, action recognition results, action analysis results, training schemes, training result statistical results and training quality evaluation results through a display.
As shown in fig. 1, the badminton training monitoring and evaluating method based on big data provided by the invention comprises the following steps:
s101: the training video acquisition module acquires a badminton training video through a camera, and the physiological index acquisition module acquires physiological data of proteins, body fat percentage, vitamins, amino acids, trace elements, hormones and the like of badminton training athletes through medical equipment;
s102: according to the badminton training video and the physiological data of badminton training athletes, which are acquired in the first step, the main control module respectively controls the training video acquisition module, the physiological index acquisition module, the action recognition module, the action analysis module, the training scheme editing module, the training result counting module, the training quality evaluation module, the cloud service module and the display module to work normally;
s103: the main control module controls the action recognition module to recognize badminton training actions according to the collected video through a recognition program, the action analysis module analyzes the badminton training actions through an analysis program, and the training scheme editing module compiles a badminton training scheme through an editing program;
s104: badminton training is carried out according to a badminton training scheme, the main control module controls the training result counting module to count the badminton training results through a counting program, and meanwhile, the training quality evaluation module is controlled to evaluate the badminton training quality through an evaluation program;
s105: in the process, the main control module controls the display module to collect badminton training videos, physiological indexes, action recognition results, action analysis results, training schemes, training result statistical results and training quality evaluation results through the display, and the cloud service module collects big data resources through the cloud server to conduct cloud processing on badminton training data.
As shown in fig. 3, the method for identifying the action identifying module 4 provided by the present invention is as follows:
s201: collecting motion data of badminton actors through camera equipment; calculating first characteristic data representing the motion state of the badminton player according to the motion data, and judging whether the badminton player is in a static state or a motion state according to the first characteristic data;
s202: responding to the situation that the badminton player is in the sports action state, calculating second characteristic data representing the sports action type of the badminton player according to the sports action data, and judging the sports action type of the badminton player according to the second characteristic data;
s203: and according to the determined motion action type, calculating third characteristic data representing motion actions according to the motion action data, and judging the motion actions of the badminton player according to the third characteristic data.
As shown in fig. 4, the determining whether the badminton player is in a stationary state or a moving state according to the first characteristic data provided by the present invention includes:
s301: calculating the maximum value of the actual combined acceleration once every a preset first time period, comparing the maximum value of the actual combined acceleration with a first preset value, and recording the times of exceeding the first preset value;
s302: and calculating whether the times of exceeding the first preset value exceeds a second preset value in a preset second time period, if so, determining that the badminton player is in a motion state, and if not, determining that the badminton player is in a static state, wherein the second time period comprises a plurality of first time periods.
The invention provides a method for judging the sports action type of a badminton player according to the second characteristic data, which comprises the following steps:
setting a first detection frequency, detecting the motion state of the badminton player for multiple times according to the first detection frequency, respectively calculating second characteristic data corresponding to the motion state of each time, and judging the motion type of the badminton player according to the second characteristic data;
responding to the consistency of the multiple judgment results, outputting the motion action type determined by the multiple judgment, and switching to a second detection frequency to detect the motion action state of the badminton player for multiple times;
responding to the dispersion of the multiple judgment results, and continuing to maintain the first detection frequency;
wherein the first detection frequency is greater than the second detection frequency.
The invention provides a method for detecting the motion state of a badminton player by switching to a second detection frequency for multiple times, which comprises the following steps:
respectively calculating second characteristic data corresponding to the motion action state of each time, and judging the motion action type of the badminton player according to the second characteristic data;
responding to the consistency of the multiple judgment results, outputting the motion action type determined by the multiple judgment, and continuously keeping the second detection frequency;
and switching to the first detection frequency in response to the dispersion of the multiple judgment results.
As shown in fig. 5, the analysis method of the motion analysis module 5 according to the present invention is as follows:
s401: acquiring badminton motion state data I of a target object through motion capture equipment, and performing normal normalization pretreatment on the badminton motion state data I to obtain badminton motion state data II;
s402: determining badminton training actions corresponding to the badminton motion state data II, and calling reference actions of the badminton training actions from a reference action library;
s403: determining the similarity between the badminton motion state data II and the badminton motion state data III of the reference action; and analyzing the badminton training action of the target object according to the similarity to obtain analysis data.
Before the reference action of the badminton training action is called, the invention also comprises the following steps:
collecting a plurality of groups of historical badminton motion state data in a historical time period and historical badminton training actions corresponding to each group of historical badminton motion state data in the plurality of groups of historical badminton motion state data;
training the collected historical badminton training actions corresponding to each group of historical badminton motion state data in the multiple groups of historical badminton motion state data and the multiple groups of historical badminton motion state data to obtain reference actions corresponding to each group of badminton motion state data in the multiple groups of historical badminton motion state data;
and storing the reference action corresponding to each group of badminton motion state data in the plurality of groups of historical badminton motion state data to obtain the reference action library.
Before determining the similarity between the badminton motion state data II and the badminton motion state data III of the reference action, the method further comprises the following steps: and carrying out coordinate conversion on the badminton motion state data II by utilizing a Principal Component Analysis (PCA).
The coordinate conversion of the badminton motion state data II by utilizing the Principal Component Analysis (PCA) provided by the invention comprises the following steps:
determining each group of badminton motion state data in the badminton motion state data II to perform track centralization processing;
generating a data matrix corresponding to the badminton motion state data according to the badminton motion state data obtained by track centralization processing;
generating a covariance matrix according to the data matrix, and obtaining an eigenvector and an eigenvalue of the covariance matrix;
generating an intermediate matrix according to the eigenvector of the covariance matrix;
and obtaining the badminton motion state data II after the coordinate conversion according to the intermediate matrix.
In the embodiment of the invention, the training video acquisition module acquires the badminton training video through the camera, and the process of denoising the image in the video comprises the following steps:
acquiring badminton training videos by a training video acquisition module camera, extracting image fragments, and identifying and judging images containing noise;
in a badminton training image containing noise, determining a circular neighborhood with a pixel as a central point,
determining pixel values in a circular neighborhood and sequencing the pixel values; selecting an intermediate pixel value as a correction pixel value according to the ordering of the pixels;
and continuously utilizing the correction pixel values in the circular neighborhood to carry out smoothing processing on the pixels in the correction neighborhood.
The working principle of the invention is as follows: the training video acquisition module 1 acquires a badminton training video through a camera, and the physiological index acquisition module 2 acquires physiological data of proteins, body fat percentage, vitamins, amino acids, trace elements, hormones and the like of badminton training athletes through medical equipment; according to the badminton training video and the physiological data of badminton training athletes collected in the first step, the main control module 3 controls each module to work normally respectively;
the main control module 3 controls the action recognition module 4 to recognize badminton training actions according to the collected video through a recognition program, the action analysis module 5 analyzes the badminton training actions through an analysis program, and the training scheme editing module 6 compiles a badminton training scheme through an editing program; badminton training is carried out according to a badminton training scheme, the main control module 3 controls a training result counting module to count badminton training results through a counting program, and simultaneously controls a training quality evaluation module 8 to evaluate the badminton training quality through an evaluation program; in the process, the main control module 3 controls the display module to collect badminton training videos, physiological indexes, action recognition results, action analysis results, training schemes, training result statistics results and training quality assessment results through the display, and the cloud service module 9 collects large data resources through the cloud server to perform cloud processing on badminton training data.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention, and the scope of the present invention is not limited thereto, and any modification, equivalent replacement, and improvement made by those skilled in the art within the technical scope of the present invention disclosed herein, which is within the spirit and principle of the present invention, should be covered by the present invention.
Claims (10)
1. A badminton training monitoring and evaluating method based on big data is characterized by comprising the following steps:
the method comprises the following steps that firstly, a training video acquisition module acquires a badminton training video through a camera, and a physiological index acquisition module acquires physiological data of proteins, body fat percentage, vitamins, amino acids, trace elements, hormones and the like of badminton training athletes through medical equipment;
step two, according to the badminton training video and the physiological data of badminton training athletes collected in the step one, the main control module respectively controls each module of the training video collection module, the physiological index collection module, the action recognition module, the action analysis module, the training scheme editing module, the training result counting module, the training quality evaluation module, the cloud service module and the display module to work normally;
step three, the main control module controls the action recognition module to recognize badminton training actions according to the collected videos through a recognition program, the action analysis module analyzes the badminton training actions through an analysis program, and the training scheme editing module compiles a badminton training scheme through an editing program;
fourthly, badminton training is carried out according to the badminton training scheme, the main control module controls the training result counting module to count the badminton training results through a counting program, and meanwhile, the training quality evaluation module is controlled to evaluate the badminton training quality through an evaluation program;
fifthly, in the process, the main control module controls the display module to collect badminton training videos, physiological indexes, action recognition results, action analysis results, training schemes, training result statistics results and training quality evaluation results through the display, and the cloud service module collects large data resources through the cloud server to perform cloud processing on badminton training data;
the action recognition module recognition method comprises the following steps:
(1) collecting motion data of badminton actors through camera equipment; calculating first characteristic data representing the motion state of the badminton player according to the motion data, and judging whether the badminton player is in a static state or a motion state according to the first characteristic data;
(2) responding to the situation that the badminton player is in the sports action state, calculating second characteristic data representing the sports action type of the badminton player according to the sports action data, and judging the sports action type of the badminton player according to the second characteristic data;
(3) according to the determined motion action type, calculating third characteristic data representing motion actions according to the motion action data, and judging the motion actions of the badminton player according to the third characteristic data;
the action analysis module analysis method comprises the following steps:
1) acquiring badminton motion state data I of a target object through motion capture equipment, and performing normal normalization pretreatment on the badminton motion state data I to obtain badminton motion state data II;
2) determining badminton training actions corresponding to the badminton motion state data II, and calling reference actions of the badminton training actions from a reference action library;
3) determining the similarity between the badminton motion state data II and the badminton motion state data III of the reference action; and analyzing the badminton training action of the target object according to the similarity to obtain analysis data.
2. The big data based badminton training monitoring and evaluation method of claim 1, wherein the determining whether the badminton player is in a static state or a sports state according to the first characteristic data comprises:
(1.1) calculating the maximum value of the one-time actual combined acceleration at a preset first time interval, comparing the maximum value of the actual combined acceleration with a first preset value, and recording the times of exceeding the first preset value;
(1.2) calculating whether the times exceeding the first preset value exceeds a second preset value in a preset second time period, if so, judging that the badminton player is in a motion state, and if not, judging that the badminton player is in a static state, wherein the second time period comprises a plurality of first time periods.
3. The big data based badminton training monitoring and evaluation method of claim 1, wherein the judging the type of the badminton player's sports motion according to the second feature data comprises:
setting a first detection frequency, detecting the motion state of the badminton player for multiple times according to the first detection frequency, respectively calculating second characteristic data corresponding to the motion state of each time, and judging the motion type of the badminton player according to the second characteristic data;
responding to the consistency of the multiple judgment results, outputting the motion action type determined by the multiple judgment, and switching to a second detection frequency to detect the motion action state of the badminton player for multiple times;
responding to the dispersion of the multiple judgment results, and continuing to maintain the first detection frequency;
wherein the first detection frequency is greater than the second detection frequency.
4. The big data based badminton training monitoring and evaluation method according to claim 1, wherein the switching to the second detection frequency for detecting the badminton player's sports action state a plurality of times comprises:
respectively calculating second characteristic data corresponding to the motion action state of each time, and judging the motion action type of the badminton player according to the second characteristic data;
responding to the consistency of the multiple judgment results, outputting the motion action type determined by the multiple judgment, and continuously keeping the second detection frequency;
and switching to the first detection frequency in response to the dispersion of the multiple judgment results.
5. The big data based badminton training monitoring evaluation method according to claim 1, wherein before the reference action of the badminton training action is called, the method further comprises the following steps:
collecting a plurality of groups of historical badminton motion state data in a historical time period and historical badminton training actions corresponding to each group of historical badminton motion state data in the plurality of groups of historical badminton motion state data;
training the collected historical badminton training actions corresponding to each group of historical badminton motion state data in the multiple groups of historical badminton motion state data and the multiple groups of historical badminton motion state data to obtain reference actions corresponding to each group of badminton motion state data in the multiple groups of historical badminton motion state data;
and storing the reference action corresponding to each group of badminton motion state data in the plurality of groups of historical badminton motion state data to obtain the reference action library.
6. The big data based badminton training monitoring and evaluation method according to claim 1, wherein before determining the similarity between the badminton motion state data two and the badminton motion state data three of the reference action, the method further comprises the following steps: and carrying out coordinate conversion on the badminton motion state data II by utilizing a Principal Component Analysis (PCA).
7. The big data based badminton training monitoring and evaluation method of claim 1, wherein the coordinate transformation of the badminton motion state data two by using Principal Component Analysis (PCA) comprises the following steps:
determining each group of badminton motion state data in the badminton motion state data II to perform track centralization processing;
generating a data matrix corresponding to the badminton motion state data according to the badminton motion state data obtained by track centralization processing;
generating a covariance matrix according to the data matrix, and obtaining an eigenvector and an eigenvalue of the covariance matrix;
generating an intermediate matrix according to the eigenvector of the covariance matrix;
and obtaining the badminton motion state data II after the coordinate conversion according to the intermediate matrix.
8. The badminton training monitoring and evaluation method based on big data as claimed in claim 1, wherein the training video acquisition module acquires badminton training videos through a camera, and the process of denoising images in the videos comprises:
acquiring badminton training videos by a training video acquisition module camera, extracting image fragments, and identifying and judging images containing noise;
in a badminton training image containing noise, determining a circular neighborhood with a pixel as a central point,
determining pixel values in a circular neighborhood and sequencing the pixel values; selecting an intermediate pixel value as a correction pixel value according to the ordering of the pixels;
and continuously utilizing the correction pixel values in the circular neighborhood to carry out smoothing processing on the pixels in the correction neighborhood.
9. A big-data based badminton training monitoring and evaluation system implementing the big-data based badminton training monitoring and evaluation method according to claims 1-8, wherein the big-data based badminton training monitoring and evaluation system comprises:
the training system comprises a training video acquisition module, a physiological index acquisition module, a main control module, an action recognition module, an action analysis module, a training scheme editing module, a training result counting module, a training quality evaluation module, a cloud service module and a display module;
the training video acquisition module is connected with the main control module and is used for acquiring a badminton training video through the camera; meanwhile, a training video acquisition module camera is used for acquiring a badminton training video, extracting image fragments and identifying and judging images containing noise; determining a circular neighborhood with pixels as central points in a badminton training image containing noise, determining pixel values in the circular neighborhood, and sequencing; selecting an intermediate pixel value as a correction pixel value according to the ordering of the pixels; continuously utilizing the correction pixel values in the circular neighborhood to carry out smoothing treatment on the pixels in the correction neighborhood;
the physiological index acquisition module is connected with the main control module and is used for acquiring physiological data of proteins, body fat percentage, vitamins, amino acids, trace elements, hormones and the like of badminton training athletes through medical equipment;
the main control module is connected with the training video acquisition module, the physiological index acquisition module, the action recognition module, the action analysis module, the training scheme editing module, the training result counting module, the training quality evaluation module, the cloud service module and the display module and is used for controlling each module to normally work through the host;
the cloud service module is connected with the main control module and is used for carrying out cloud processing on the badminton training data by centralizing big data resources through the cloud server; and the display module is connected with the main control module and is used for acquiring badminton training videos, physiological indexes, action recognition results, action analysis results, training schemes, training result statistical results and training quality evaluation results through a display.
10. The big data based badminton training monitoring and evaluation system of claim 9, wherein the big data based badminton training monitoring and evaluation system further comprises:
the motion recognition module is connected with the main control module and used for recognizing badminton training motions according to the collected videos through a recognition program; collecting motion data of badminton actors through camera equipment; calculating first characteristic data representing the motion state of the badminton player according to the motion data, and judging whether the badminton player is in a static state or a motion state according to the first characteristic data; responding to the situation that the badminton player is in the sports action state, calculating second characteristic data representing the sports action type of the badminton player according to the sports action data, and judging the sports action type of the badminton player according to the second characteristic data; according to the determined motion action type, calculating third characteristic data representing motion actions according to the motion action data, and judging the motion actions of the badminton player according to the third characteristic data;
the action analysis module is connected with the main control module and is used for analyzing the badminton training action through an analysis program; acquiring badminton motion state data I of a target object through motion capture equipment, and performing normal normalization pretreatment on the badminton motion state data I to obtain badminton motion state data II; determining badminton training actions corresponding to the badminton motion state data II, and calling reference actions of the badminton training actions from a reference action library; determining the similarity between the badminton motion state data II and the badminton motion state data III of the reference action; analyzing the badminton training action of the target object according to the similarity to obtain analysis data;
the training scheme editing module is connected with the main control module, and is used for compiling a badminton training scheme through an editing program according to the data obtained by the identification and analysis of the action identification module and the action analysis module;
the training score counting module is connected with the main control module and is used for counting the training scores of the shuttlecocks through a counting program; mining all class association rules meeting the specified support degree and confidence degree from the training data set by using an association rule mining algorithm; selecting a group of high-quality rules from the mined class association rules by using a heuristic method for classification;
and the training quality evaluation module is connected with the main control module and used for evaluating the training quality of the badminton through an evaluation program according to the badminton training scores classified and counted by the training score counting module.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010639259.6A CN111773651A (en) | 2020-07-06 | 2020-07-06 | Badminton training monitoring and evaluating system and method based on big data |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010639259.6A CN111773651A (en) | 2020-07-06 | 2020-07-06 | Badminton training monitoring and evaluating system and method based on big data |
Publications (1)
Publication Number | Publication Date |
---|---|
CN111773651A true CN111773651A (en) | 2020-10-16 |
Family
ID=72759581
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010639259.6A Pending CN111773651A (en) | 2020-07-06 | 2020-07-06 | Badminton training monitoring and evaluating system and method based on big data |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111773651A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113095248A (en) * | 2021-04-19 | 2021-07-09 | 中国石油大学(华东) | Technical action correction method for badminton |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105205832A (en) * | 2015-08-31 | 2015-12-30 | 清华大学深圳研究生院 | Moving object detection method |
CN107050803A (en) * | 2017-03-19 | 2017-08-18 | 西安理工大学 | A kind of shuttlecock training supervision assessment system |
CN109344758A (en) * | 2018-09-25 | 2019-02-15 | 厦门大学 | Based on the face identification method for improving local binary patterns |
CN109753868A (en) * | 2018-11-14 | 2019-05-14 | 深圳卡路里科技有限公司 | Appraisal procedure and device, the Intelligent bracelet of athletic performance |
CN109847308A (en) * | 2019-02-14 | 2019-06-07 | 山西大同大学 | A kind of athletic training system based on big data |
CN111288986A (en) * | 2019-12-31 | 2020-06-16 | 中科彭州智慧产业创新中心有限公司 | Motion recognition method and motion recognition device |
-
2020
- 2020-07-06 CN CN202010639259.6A patent/CN111773651A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105205832A (en) * | 2015-08-31 | 2015-12-30 | 清华大学深圳研究生院 | Moving object detection method |
CN107050803A (en) * | 2017-03-19 | 2017-08-18 | 西安理工大学 | A kind of shuttlecock training supervision assessment system |
CN109344758A (en) * | 2018-09-25 | 2019-02-15 | 厦门大学 | Based on the face identification method for improving local binary patterns |
CN109753868A (en) * | 2018-11-14 | 2019-05-14 | 深圳卡路里科技有限公司 | Appraisal procedure and device, the Intelligent bracelet of athletic performance |
CN109847308A (en) * | 2019-02-14 | 2019-06-07 | 山西大同大学 | A kind of athletic training system based on big data |
CN111288986A (en) * | 2019-12-31 | 2020-06-16 | 中科彭州智慧产业创新中心有限公司 | Motion recognition method and motion recognition device |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113095248A (en) * | 2021-04-19 | 2021-07-09 | 中国石油大学(华东) | Technical action correction method for badminton |
CN113095248B (en) * | 2021-04-19 | 2022-10-25 | 中国石油大学(华东) | Technical action correcting method for badminton |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108810620B (en) | Method, device, equipment and storage medium for identifying key time points in video | |
CN108256433B (en) | Motion attitude assessment method and system | |
US8634638B2 (en) | Real-time action detection and classification | |
CN109508648A (en) | A kind of face snap method and apparatus | |
Hammam et al. | Real-time multiple spatiotemporal action localization and prediction approach using deep learning | |
CN117133057A (en) | Physical exercise counting and illegal action distinguishing method based on human body gesture recognition | |
CN115331314A (en) | Exercise effect evaluation method and system based on APP screening function | |
CN109460724B (en) | Object detection-based separation method and system for ball-stopping event | |
CN111773651A (en) | Badminton training monitoring and evaluating system and method based on big data | |
CN114566249A (en) | Human motion safety risk assessment and analysis system | |
CN113177476A (en) | Identification method, system and test method for heel key points of standing long jump | |
JPWO2004012150A1 (en) | Image recognition apparatus and image recognition program | |
CN108388883A (en) | A kind of video demographic method based on HOG+SVM | |
CN114264239B (en) | Motion platform laser calibration system | |
CN113537168B (en) | Basketball goal detection method and system for rebroadcasting and court monitoring scene | |
CN110969133B (en) | Intelligent data acquisition method for table tennis game video | |
CN115482569A (en) | Target passenger flow statistical method, electronic device and computer readable storage medium | |
CN114783057A (en) | Gait information acquisition method and related device | |
CN110490064B (en) | Sports video data processing method and device, computer equipment and computer storage medium | |
KR102055146B1 (en) | Method for checking out sports motion using event-based vision sensor and apparatus for the same | |
CN111476118A (en) | Animal behavior automatic identification method and device | |
CN112990159B (en) | Video interesting segment intercepting method, electronic equipment and storage medium | |
CN117333947B (en) | Badminton action analysis method and system | |
CN113762228B (en) | Oral instrument disinfection and sterilization operation monitoring method and device | |
CN117809376A (en) | Motion action recognition and evaluation method and system |
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 |
Application publication date: 20201016 |
|
RJ01 | Rejection of invention patent application after publication |